{"meta":{"query_hash":"466ddf5883b4","filters":{"venue":"Canadian Journal of Program Evaluation"},"cohort_total":892,"direct_labels_cover":52,"predictions_cover":892,"exported":892,"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/466ddf5883b4","api":"https://metacan.xera.ac/api/v1/cohort?venue=Canadian+Journal+of+Program+Evaluation"},"results":[{"id":"W112258392","doi":"","title":"Stakeholder Involvement in Educational Evaluation: Quebec's Commission de'evaluation de l'enseignement collegial.","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Higher Education Governance and Development","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commission; Stakeholder; Political science; Evaluation methods; Program evaluation; Public administration; Public relations; Law; Engineering","score_opus":0.13929226367768574,"score_gpt":0.40257777450394205,"score_spread":0.2632855108262563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W112258392","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012598033,0.0635734,0.005842249,0.8040739,0.0073930495,0.0025944659,0.002464648,0.00038217986,0.10107809],"genre_scores_gemma":[0.4151773,0.038995598,0.040945545,0.2698019,0.0019926946,0.004173266,0.003245379,0.0006389808,0.22502935],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.8886996,0.029748498,0.0072665913,0.0033082196,0.061343424,0.009633724],"domain_scores_gemma":[0.7293022,0.070242375,0.008105378,0.007877293,0.14784697,0.03662569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1276046,0.0011553487,0.0016121346,0.004426989,0.010873118,0.01331157,0.0057070055,0.016354581,0.0048920424],"category_scores_gemma":[0.13763516,0.0010957208,0.0015102782,0.0062818155,0.009149655,0.003763195,0.0068110595,0.010302848,0.0007081028],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024464412,0.00024046363,0.009766517,0.0011901866,0.000096447,0.00033322533,0.0049034306,0.0011797905,0.0008016173,0.06268187,0.78488535,0.13367653],"study_design_scores_gemma":[0.00016697655,0.00010587915,0.05549825,0.0052706487,0.00014692632,0.00011903803,0.0039262474,0.0012463264,0.0008660391,0.007082825,0.9253521,0.00021873739],"about_ca_topic_score_codex":0.97177863,"about_ca_topic_score_gemma":0.9823386,"teacher_disagreement_score":0.8747927,"about_ca_system_score_codex":0.12520729,"about_ca_system_score_gemma":0.54233634,"threshold_uncertainty_score":0.9084467},"labels":[],"label_agreement":null},{"id":"W121847069","doi":"10.3138/cjpe.23.006","title":"Drawing on Indigenous Ways of Knowing: Reflections from a Community Evaluator","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Participatory Visual Research Methods","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Formative assessment; Participatory action research; Sociology; Community-based participatory research; Native American studies; Agency (philosophy); Citizen journalism; Population; Native american; Public relations; Community studies; Traditional knowledge; Gender studies; Pedagogy; Social science; Political science; Anthropology; Law","score_opus":0.9067708680690213,"score_gpt":0.6786730021568608,"score_spread":0.22809786591216052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W121847069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8502344,0.0018965611,0.013263549,0.09415109,0.001642765,0.0011563824,0.00005205215,0.00019087846,0.03741227],"genre_scores_gemma":[0.97352165,0.0008300224,0.004366198,0.010572344,0.00023802592,0.0004997874,0.000022295468,0.00018989065,0.009759858],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.86238414,0.11525046,0.0021667443,0.0031107706,0.0073400466,0.009747947],"domain_scores_gemma":[0.88600194,0.076103434,0.003499508,0.0037810314,0.018420687,0.012193382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09045326,0.0012377984,0.0016219853,0.0028619543,0.04701534,0.01649854,0.0049128807,0.008041365,0.0028466985],"category_scores_gemma":[0.114348054,0.0012541136,0.0011986169,0.0017026893,0.04449991,0.01031654,0.019829577,0.020735603,0.0005220534],"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":[0.00001337547,0.000078844685,0.00031707995,0.000040864157,0.0000044538347,0.0005104507,0.9945597,0.000034455235,0.00015877184,0.0011930323,0.0007990119,0.0022897916],"study_design_scores_gemma":[0.00000764096,0.00009162478,0.00017992564,0.00009998891,0.00000858126,0.0003013452,0.98282754,0.00015415062,0.0002472032,0.00097008096,0.015083916,0.000027958908],"about_ca_topic_score_codex":0.026166257,"about_ca_topic_score_gemma":0.030545829,"teacher_disagreement_score":0.09045326,"about_ca_system_score_codex":0.013282622,"about_ca_system_score_gemma":0.021030813,"threshold_uncertainty_score":0.47836828},"labels":[],"label_agreement":null},{"id":"W14092155","doi":"10.3138/cjpe.018.003","title":"Balancing Ethical Principles in Evaluation: A Case Study","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Neglect; Engineering ethics; Politics; Indigenous; Ethical decision; Ethical issues; Ethical code; Political science; Public relations; Psychology; Sociology; Law; Engineering","score_opus":0.5803079388152322,"score_gpt":0.5911604505217036,"score_spread":0.01085251170647139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W14092155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8208747,0.005744351,0.031679824,0.055754878,0.0005532083,0.0030703298,0.00007800375,0.000057873673,0.08218686],"genre_scores_gemma":[0.96920043,0.0030512745,0.017378768,0.0038353053,0.00013623407,0.0013056998,0.000022381519,0.000039767554,0.005030126],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8369499,0.14548455,0.0027997086,0.0012402833,0.008023588,0.005501984],"domain_scores_gemma":[0.8371333,0.14058648,0.004823931,0.0028669597,0.008402903,0.006186506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11244857,0.0008658094,0.0008751741,0.0028032628,0.027943853,0.010314052,0.0033571685,0.010416303,0.0034508428],"category_scores_gemma":[0.1186845,0.00090081175,0.0012162444,0.0035243095,0.017895458,0.0069683017,0.010920525,0.011303336,0.00045481746],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004008676,0.0043811183,0.0176652,0.0014467691,0.000083249055,0.078609005,0.67390543,0.0026286195,0.00083398964,0.10920621,0.014477211,0.09636242],"study_design_scores_gemma":[0.00019131406,0.0010499719,0.0053563556,0.0031170135,0.00008888822,0.031026749,0.8289547,0.0041061905,0.001999617,0.028397487,0.09556248,0.00014922889],"about_ca_topic_score_codex":0.008071973,"about_ca_topic_score_gemma":0.020628002,"teacher_disagreement_score":0.11244857,"about_ca_system_score_codex":0.01661272,"about_ca_system_score_gemma":0.015144812,"threshold_uncertainty_score":0.594692},"labels":[],"label_agreement":null},{"id":"W1443241397","doi":"10.3138/cjpe.30.1.41","title":"Assessing the Value of Inductive and Deductive Outcome Measures in Community-Based Programs: Lessons from the City Kidz Evaluation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Homelessness and Social Issues","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Community Based Research; University of Waterloo","funders":"","keywords":"Consistency (knowledge bases); Value (mathematics); Internal consistency; Deductive method; Outcome (game theory); Inductive method; Deductive reasoning; Inductive reasoning; Computer science; Psychology; Management science; Sociology; Economics; Psychometrics; Mathematics education; Artificial intelligence; Social science","score_opus":0.6544069422406532,"score_gpt":0.5881462375898072,"score_spread":0.06626070465084599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1443241397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.590765,0.011742467,0.23719504,0.036556967,0.0012925069,0.04055713,0.0008253664,0.0005393322,0.08052625],"genre_scores_gemma":[0.7968527,0.0017354762,0.17742333,0.0020277288,0.0001473112,0.020524457,0.0001607603,0.00008820219,0.001040008],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.28538695,0.65297514,0.016983166,0.0023780612,0.039979137,0.0022975188],"domain_scores_gemma":[0.12838574,0.78250045,0.015430105,0.0128655685,0.05914951,0.0016687512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.56488043,0.0009992342,0.0016351864,0.0061596087,0.0040897224,0.0071456507,0.0037131996,0.0017178409,0.0020511271],"category_scores_gemma":[0.65438616,0.0009057792,0.0019079953,0.0061806147,0.0089895185,0.007133955,0.009032879,0.003667146,0.0003033844],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00320696,0.003522519,0.0900423,0.01051814,0.0013692621,0.00020900289,0.10582708,0.0043588225,0.0007411634,0.06293807,0.0062364885,0.71103024],"study_design_scores_gemma":[0.0068312245,0.03651917,0.3076713,0.059964772,0.0043814583,0.00077589275,0.23546046,0.060798053,0.017035216,0.15125622,0.11786837,0.0014379496],"about_ca_topic_score_codex":0.010764924,"about_ca_topic_score_gemma":0.018478671,"teacher_disagreement_score":0.56488043,"about_ca_system_score_codex":0.018754033,"about_ca_system_score_gemma":0.026418148,"threshold_uncertainty_score":0.53657997},"labels":[],"label_agreement":null},{"id":"W1481182936","doi":"10.3138/cjpe.30.1.103","title":"S. E. Efron &amp; R. Ravid. (2013). <i>Action Research in Education: A Practical Guide.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Teacher Education and Leadership Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Action (physics); Psychology; Sociology; Media studies; Physics","score_opus":0.8382456137066764,"score_gpt":0.6507650594239581,"score_spread":0.18748055428271826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1481182936","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015248455,0.3484938,0.056324765,0.33081922,0.032583747,0.0010426217,0.0055117463,0.0032844443,0.22041479],"genre_scores_gemma":[0.027672272,0.31038007,0.11769633,0.070047386,0.005320532,0.0018337017,0.0021922688,0.0018916371,0.46296576],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976635,0.0008508588,0.0002729808,0.0001384792,0.0009726059,0.00010165858],"domain_scores_gemma":[0.9827167,0.008912057,0.0007547813,0.00063880236,0.006037905,0.0009398804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008857848,0.001528101,0.0008313563,0.005927368,0.002785867,0.0041354625,0.0027532529,0.0043077245,0.046397272],"category_scores_gemma":[0.022199742,0.0012074386,0.00058812957,0.0036057266,0.0025407064,0.0058111097,0.0022961819,0.005140289,0.04054947],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012988117,0.00002505983,0.00021564588,0.00028097283,0.0000032677992,0.000050330676,0.00047898391,0.000038623377,0.00008869802,0.0031978465,0.81372863,0.1818789],"study_design_scores_gemma":[0.0000112330645,0.00002344047,0.0012618297,0.001984959,0.0000097029015,0.00019898576,0.00091090286,0.00008848856,0.0003197951,0.0068156584,0.9883549,0.000020124886],"about_ca_topic_score_codex":0.029472062,"about_ca_topic_score_gemma":0.09815914,"teacher_disagreement_score":0.046397272,"about_ca_system_score_codex":0.0023217218,"about_ca_system_score_gemma":0.008901513,"threshold_uncertainty_score":0.15521431},"labels":[],"label_agreement":null},{"id":"W1490602178","doi":"10.3138/cjpe.0028.005","title":"A Professional Grounding and History of the Development and Formal Use of Evaluator Competencies","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Viewpoints; Credentialing; Engineering ethics; Value (mathematics); Professional association; Field (mathematics); Foundation (evidence); Professional development; Psychology; Political science; Sociology; Pedagogy; Public relations; Engineering; Computer science; Social science; Law","score_opus":0.39851549563026134,"score_gpt":0.4680725057001939,"score_spread":0.06955701006993253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490602178","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029790353,0.35613677,0.04838993,0.2634225,0.009983225,0.0002134647,0.00029081132,0.00025910695,0.29151398],"genre_scores_gemma":[0.6628987,0.19036634,0.038807046,0.03368633,0.0063521424,0.00036985046,0.00026863962,0.0004917656,0.06675916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9823982,0.008765443,0.0013595787,0.0017321168,0.0047727,0.00097197137],"domain_scores_gemma":[0.90590364,0.0635317,0.0037780064,0.005517366,0.018295767,0.0029734636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034841787,0.00038868087,0.0004695023,0.0066638826,0.0044959523,0.010196981,0.0014906512,0.003329294,0.005558582],"category_scores_gemma":[0.044829924,0.00055401423,0.00035306747,0.004432496,0.020618586,0.008838331,0.005377891,0.0076348293,0.0007908993],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006180116,0.00009406816,0.0030802947,0.0010935104,0.000012309462,0.0001878199,0.0148007665,0.00033292288,0.00050459045,0.52145344,0.032794055,0.42558447],"study_design_scores_gemma":[0.000009665611,0.00008827356,0.006317279,0.0047120065,0.000011817609,0.0005055464,0.0052277097,0.0005125223,0.001570483,0.05422748,0.9267505,0.00006675527],"about_ca_topic_score_codex":0.019356485,"about_ca_topic_score_gemma":0.021960905,"teacher_disagreement_score":0.034841787,"about_ca_system_score_codex":0.018185021,"about_ca_system_score_gemma":0.022514258,"threshold_uncertainty_score":0.18426323},"labels":[],"label_agreement":null},{"id":"W1493255413","doi":"10.3138/cjpe.027.003","title":"Capturing the Complexity of Evaluations of Health Promotion Interventions: A Scoping Review","year":2012,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Lloydminster Hospital; University of Calgary","funders":"","keywords":"Psychological intervention; Perspective (graphical); Promotion (chess); Grey literature; Health promotion; Management science; Psychology; Applied psychology; Computer science; MEDLINE; Medicine; Public health; Nursing; Political science; Engineering; Artificial intelligence","score_opus":0.9727255468434597,"score_gpt":0.7916901593614977,"score_spread":0.18103538748196202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493255413","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021664474,0.8879426,0.048908733,0.009747835,0.0014073576,0.01962988,0.0010717901,0.00013745273,0.00948988],"genre_scores_gemma":[0.2338677,0.5744503,0.14948894,0.0035081229,0.000578216,0.035890885,0.0012767209,0.0000896451,0.00084947277],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.6193001,0.252163,0.07159695,0.0051159984,0.050239112,0.0015848039],"domain_scores_gemma":[0.26970792,0.6151707,0.041263677,0.015418152,0.05728308,0.0011565087],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.32814425,0.002069994,0.0072532436,0.02118894,0.0021959038,0.010471111,0.0031534738,0.0027899514,0.0019880203],"category_scores_gemma":[0.59623456,0.002361517,0.006069713,0.021134507,0.0031766575,0.01003801,0.0042791734,0.0028236278,0.000271761],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041120258,0.00022174223,0.0072784983,0.46892545,0.0113006495,0.0001418584,0.0052953186,0.002130482,0.0007876255,0.008621112,0.0041911397,0.4906949],"study_design_scores_gemma":[0.00030847354,0.00074942276,0.011440522,0.9145831,0.020570993,0.00021796512,0.0041428637,0.0021982922,0.00159371,0.010395952,0.033613708,0.00018497613],"about_ca_topic_score_codex":0.011184769,"about_ca_topic_score_gemma":0.03301184,"teacher_disagreement_score":0.67185575,"about_ca_system_score_codex":0.013906963,"about_ca_system_score_gemma":0.057181578,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":["metaepi_broad"],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W1494699756","doi":"","title":"ARTICLE 6: METAEVALUATION: EVALUATING THE EVALUATION OF THE PARIS DECLARATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Strengths and weaknesses; Evaluation methods; Quality (philosophy); Commission; Political science; Psychology; Computer science; Engineering; Law; Social psychology; Reliability engineering","score_opus":0.7038098888130093,"score_gpt":0.5979079630601261,"score_spread":0.10590192575288326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494699756","genre_codex":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03144242,0.46256903,0.2784951,0.08942761,0.021749314,0.06797106,0.0076004504,0.0031399091,0.037605014],"genre_scores_gemma":[0.24197856,0.066455066,0.58225757,0.014241671,0.0034329777,0.085695066,0.0016048633,0.00085518503,0.0034790353],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.17042376,0.73646015,0.04595796,0.0059269415,0.04020789,0.0010234115],"domain_scores_gemma":[0.15905368,0.7364784,0.04135232,0.029189417,0.03179759,0.0021286444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5713279,0.0049280445,0.010484718,0.017471258,0.0036053858,0.015654234,0.005437723,0.009600978,0.008759044],"category_scores_gemma":[0.77562594,0.0032541642,0.020096874,0.016203282,0.008753151,0.00957015,0.008727165,0.0072310385,0.00083270995],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012106144,0.0005478312,0.009364876,0.27433214,0.21404037,0.00058059674,0.007033931,0.010509302,0.0015800215,0.06513683,0.046886224,0.3578818],"study_design_scores_gemma":[0.013757173,0.0060108984,0.0151098315,0.34382328,0.2537829,0.0007425805,0.0027126991,0.01596102,0.009964218,0.13888662,0.1977423,0.0015065578],"about_ca_topic_score_codex":0.005048352,"about_ca_topic_score_gemma":0.008902544,"teacher_disagreement_score":0.42867208,"about_ca_system_score_codex":0.021519661,"about_ca_system_score_gemma":0.031106675,"threshold_uncertainty_score":0.52862906},"labels":[],"label_agreement":null},{"id":"W1496927098","doi":"","title":"Barbier, J. C., & Hawkins, P. (Eds.). (2012). Evaluation Cultures: Sense-making in Complex Times","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sense (electronics); Psychology; Chemistry; Physical chemistry","score_opus":0.32864005862634,"score_gpt":0.529181536959155,"score_spread":0.20054147833281505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496927098","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055823284,0.8743861,0.019115929,0.06174097,0.00306663,0.00013077632,0.000499922,0.00033769963,0.035139613],"genre_scores_gemma":[0.063404776,0.89488375,0.028765043,0.0020442952,0.0010305058,0.00021443712,0.0002882665,0.00016165845,0.009207306],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99510765,0.0020728046,0.000499163,0.00029166444,0.0017675174,0.0002611697],"domain_scores_gemma":[0.9805917,0.012714108,0.0015449191,0.00065070164,0.0031862303,0.0013124236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0150059,0.0019053048,0.0017105589,0.007900195,0.0046154484,0.015623461,0.0025497358,0.0033832656,0.009149927],"category_scores_gemma":[0.017330205,0.0018163319,0.00081554166,0.011165873,0.0072760815,0.014714462,0.0035179148,0.0060178516,0.004856509],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012908553,0.00006219321,0.0028136692,0.003216825,0.000054696106,0.00013225299,0.017590743,0.0005422814,0.00037539334,0.027282218,0.14174901,0.8060515],"study_design_scores_gemma":[0.00006640356,0.00022416121,0.02374898,0.015868774,0.00034914134,0.0015618039,0.050639857,0.0013693301,0.001937113,0.10879932,0.795166,0.00026917],"about_ca_topic_score_codex":0.05907148,"about_ca_topic_score_gemma":0.10492222,"teacher_disagreement_score":0.05907148,"about_ca_system_score_codex":0.007318256,"about_ca_system_score_gemma":0.013773442,"threshold_uncertainty_score":0.1174553},"labels":[],"label_agreement":null},{"id":"W1506594705","doi":"10.3138/cjpe.0028.003","title":"Introduction to Professionalizing Evaluation: A Global Perspective on Evaluator Competencies","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Psychology; Sociology; Pedagogy; Knowledge management; Computer science; Artificial intelligence","score_opus":0.26065355762357273,"score_gpt":0.5437613801430642,"score_spread":0.28310782251949146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506594705","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013265157,0.032854185,0.0136555545,0.8981491,0.0052384017,0.000060439226,0.00005026276,0.00006830482,0.04859725],"genre_scores_gemma":[0.15692967,0.05459129,0.022089146,0.720001,0.017781474,0.00048346937,0.000115560324,0.00035492395,0.027653502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9208054,0.055322368,0.0042533246,0.0055687237,0.01102724,0.00302298],"domain_scores_gemma":[0.8188778,0.14790791,0.0033724406,0.005558377,0.019496405,0.0047870902],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.084219135,0.000869831,0.001180931,0.004101699,0.009869692,0.020883089,0.0031414127,0.019366087,0.006710461],"category_scores_gemma":[0.07189128,0.0005853496,0.0011785682,0.003934548,0.08236835,0.030499203,0.0106954025,0.025545644,0.001947882],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028348762,0.000029803232,0.0008769906,0.00070628326,0.000008342576,0.00019557752,0.030609509,0.00023091899,0.00015221516,0.741648,0.17959507,0.04591892],"study_design_scores_gemma":[0.000010594913,0.000050884886,0.0012685,0.0038746882,0.000008335384,0.0005122477,0.01764558,0.0003039926,0.00014204893,0.21954216,0.75658864,0.000052266398],"about_ca_topic_score_codex":0.01263326,"about_ca_topic_score_gemma":0.011574313,"teacher_disagreement_score":0.91578084,"about_ca_system_score_codex":0.020147663,"about_ca_system_score_gemma":0.019419806,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1514004023","doi":"10.3138/cjpe.025.006","title":"An Alternative to the Traditional Literature Review","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Disk formatting; Process (computing); Information needs; Work (physics); Computer science; Process management; Outcome (game theory); Risk analysis (engineering); Knowledge management; Management science; Business; World Wide Web; Engineering; Economics","score_opus":0.4147867432021777,"score_gpt":0.5561090360664662,"score_spread":0.14132229286428855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514004023","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00979962,0.13688192,0.3089663,0.0971644,0.02001719,0.009576142,0.0088966,0.0010832879,0.40761456],"genre_scores_gemma":[0.24779804,0.11851404,0.48330495,0.040734,0.0060671195,0.022163318,0.0047167395,0.0005555865,0.07614626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.952675,0.029657343,0.003988022,0.002708797,0.010396276,0.00057446293],"domain_scores_gemma":[0.9036934,0.05729915,0.0057812403,0.010073335,0.02180198,0.0013507903],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.038186103,0.0012884537,0.0025911778,0.026649984,0.0026351332,0.010266116,0.004224962,0.0034766954,0.049048364],"category_scores_gemma":[0.08315364,0.0006175499,0.0021418494,0.030891227,0.0035485632,0.013616083,0.006403317,0.0021499884,0.0073524117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034209897,0.00020131435,0.0011205864,0.03714572,0.00074952416,0.00076695654,0.0031956783,0.00036637532,0.00073048513,0.5095965,0.091868535,0.35391617],"study_design_scores_gemma":[0.00034559704,0.00024353604,0.0015764034,0.024120726,0.00085308275,0.0012369185,0.0054461616,0.001282349,0.00067787815,0.14135335,0.8227708,0.00009316466],"about_ca_topic_score_codex":0.0027028455,"about_ca_topic_score_gemma":0.0064012245,"teacher_disagreement_score":0.9618139,"about_ca_system_score_codex":0.005499097,"about_ca_system_score_gemma":0.013297097,"threshold_uncertainty_score":0.20194983},"labels":[],"label_agreement":null},{"id":"W1517551366","doi":"10.3138/cjpe.028.005","title":"Learning Circles for Advanced Professional Development in Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Public Health Agency of Canada; Health Canada","funders":"","keywords":"Professional development; Context (archaeology); Process (computing); Quality (philosophy); Psychology; Professional learning community; Collaborative learning; Knowledge management; Medical education; Pedagogy; Computer science; Medicine","score_opus":0.36610878492078347,"score_gpt":0.5580433458244787,"score_spread":0.1919345609036952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517551366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35078752,0.007339277,0.25570792,0.09687124,0.0010542201,0.013368799,0.00015732931,0.0019314804,0.2727822],"genre_scores_gemma":[0.8786912,0.00052127865,0.111828156,0.0018038151,0.000091090296,0.0043826546,0.000028325987,0.00007189444,0.002581591],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6583835,0.31459385,0.00399549,0.0029558435,0.01653305,0.0035383715],"domain_scores_gemma":[0.5752622,0.33776665,0.017597103,0.026644522,0.022960614,0.019768994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21163383,0.00062950206,0.00069281895,0.002013539,0.0067012953,0.011459394,0.0028021792,0.00271124,0.010836057],"category_scores_gemma":[0.21080898,0.0006412037,0.00057458924,0.001557393,0.009910975,0.008270128,0.015191167,0.0037077,0.0010882206],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012935344,0.0044777533,0.00940463,0.0027417182,0.000081183534,0.00016424035,0.04261436,0.003563838,0.0012924777,0.24330322,0.020324223,0.6707388],"study_design_scores_gemma":[0.006738246,0.011381026,0.043086007,0.011693601,0.0003613483,0.00094245584,0.06677875,0.049323466,0.015377829,0.29376388,0.49983317,0.0007203281],"about_ca_topic_score_codex":0.0061842767,"about_ca_topic_score_gemma":0.009608576,"teacher_disagreement_score":0.21163383,"about_ca_system_score_codex":0.017535752,"about_ca_system_score_gemma":0.038067732,"threshold_uncertainty_score":0.97219586},"labels":[],"label_agreement":null},{"id":"W1547906511","doi":"10.3138/cjpe.0028.008","title":"Evaluator Competencies: The South African Government Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Presidency; Context (archaeology); Institution; Process (computing); Political science; Computer science; Geography","score_opus":0.27171115503889426,"score_gpt":0.4784742502509596,"score_spread":0.20676309521206532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1547906511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87380975,0.0028451013,0.000998009,0.049687177,0.0002468698,0.0001252343,0.00004045376,0.000030817333,0.07221656],"genre_scores_gemma":[0.98187476,0.0025916174,0.0005944578,0.0026688974,0.00003244051,0.00007613026,0.000017601085,0.000028908631,0.012115247],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9904891,0.006269469,0.00024102567,0.0002160095,0.00072688004,0.0020575174],"domain_scores_gemma":[0.99193186,0.0038834827,0.0006954226,0.000283168,0.0010123088,0.0021937848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013616986,0.0003211474,0.000301503,0.0010555424,0.01895323,0.0047489777,0.0007622692,0.0017797016,0.009964157],"category_scores_gemma":[0.011655433,0.00055221224,0.0002019832,0.0018225288,0.0062027383,0.004599222,0.0073277997,0.005201592,0.00087682594],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008332057,0.00023881411,0.010410773,0.00021836767,0.000007835911,0.0021229084,0.9183166,0.00010779419,0.00086091715,0.026760532,0.008845406,0.032026667],"study_design_scores_gemma":[0.00001909982,0.00014800488,0.011284564,0.0006369855,0.000009015518,0.0012943863,0.77059764,0.00020030829,0.0009974265,0.0024946092,0.21229023,0.00002769839],"about_ca_topic_score_codex":0.021526625,"about_ca_topic_score_gemma":0.045824546,"teacher_disagreement_score":0.021526625,"about_ca_system_score_codex":0.0076942015,"about_ca_system_score_gemma":0.021859499,"threshold_uncertainty_score":0.07201433},"labels":[],"label_agreement":null},{"id":"W1557237650","doi":"10.3138/cjpe.30.1.79","title":"Toward an Evaluation Framework for Community-Based FASD Prevention Programs","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Prenatal Substance Exposure Effects","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"British Columbia Centre of Excellence for Women's Health; University of Victoria","funders":"","keywords":"Formative assessment; Perspective (graphical); Product (mathematics); Psychology; Program evaluation; Knowledge management; Computer science; Medical education; Medicine; Mathematics education; Artificial intelligence; Political science","score_opus":0.3497687767764537,"score_gpt":0.4455843861144736,"score_spread":0.09581560933801991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1557237650","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016357526,0.0066558607,0.82679,0.05692998,0.0007158474,0.022520702,0.0011189565,0.0013768665,0.0675343],"genre_scores_gemma":[0.10606415,0.0010834036,0.8792715,0.0011819568,0.000050923372,0.0109177595,0.00036006758,0.00010697073,0.00096324354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.69077444,0.25714606,0.01836556,0.006179855,0.022770489,0.0047636],"domain_scores_gemma":[0.77306557,0.13416986,0.011520547,0.009461152,0.06582013,0.005962751],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3096955,0.002945286,0.0032687772,0.02699978,0.010787681,0.026621785,0.007485971,0.0055762962,0.0038654632],"category_scores_gemma":[0.166632,0.0019155272,0.004120893,0.01295439,0.018052064,0.015945828,0.015241928,0.0076872394,0.0006738318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017684029,0.00079222955,0.005830292,0.006364896,0.00029830573,0.00030264253,0.027390815,0.013390049,0.00064934266,0.78088844,0.013999883,0.14991632],"study_design_scores_gemma":[0.0008302791,0.0009922835,0.009097352,0.03266026,0.0008094743,0.00040228726,0.06786975,0.04642578,0.0032396724,0.67235243,0.16493613,0.00038432854],"about_ca_topic_score_codex":0.06059222,"about_ca_topic_score_gemma":0.0622338,"teacher_disagreement_score":0.3096955,"about_ca_system_score_codex":0.06774554,"about_ca_system_score_gemma":0.10861775,"threshold_uncertainty_score":0.85126835},"labels":[],"label_agreement":null},{"id":"W1558175818","doi":"10.3138/cjpe.028.002","title":"The Reciprocal Relationship between Implementation Theory and Program Theory in Assisting Program Design and Decision-Making","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reciprocal; Management science; Program Design Language; Interpretation (philosophy); Computer science; Decision theory; Focus (optics); Development theory; Theory of change; Epistemology; Sociology; Software engineering; Mathematics; Engineering; Economics; Programming language","score_opus":0.3607936961203019,"score_gpt":0.5650848166150938,"score_spread":0.20429112049479192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558175818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0811191,0.006751296,0.6834691,0.0678099,0.00056488457,0.0016048348,0.00010273723,0.0003338488,0.15824431],"genre_scores_gemma":[0.7510026,0.00257691,0.24079655,0.0025926814,0.00010388998,0.001363567,0.000046793317,0.000068297304,0.001448787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8199651,0.15787454,0.0028735714,0.0018621124,0.015598147,0.0018265331],"domain_scores_gemma":[0.5861359,0.37888893,0.0072342507,0.008033902,0.01724327,0.0024636313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.116573736,0.0009010406,0.0011596892,0.005737048,0.0028090884,0.012908249,0.0022426983,0.0030014464,0.005064511],"category_scores_gemma":[0.14457485,0.0008878934,0.0009687994,0.0031427778,0.018164268,0.009758868,0.0069069806,0.005376157,0.0005258805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013857741,0.0007052161,0.009061383,0.0033088312,0.0001694712,0.0001404178,0.011083708,0.01151277,0.00059601094,0.7448067,0.0029911506,0.21548578],"study_design_scores_gemma":[0.000191787,0.0009187857,0.0067368015,0.008489477,0.0002576826,0.00026685887,0.013526285,0.03708657,0.003260371,0.89500767,0.034120865,0.00013689102],"about_ca_topic_score_codex":0.0026449831,"about_ca_topic_score_gemma":0.004170395,"teacher_disagreement_score":0.116573736,"about_ca_system_score_codex":0.010992551,"about_ca_system_score_gemma":0.02323632,"threshold_uncertainty_score":0.61650825},"labels":[],"label_agreement":null},{"id":"W1559496221","doi":"10.3138/cjpe.28.005","title":"Neutral Assessment of the National Research Council Canada Evaluation Function","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique; National Research Council Canada","funders":"","keywords":"Treasury; Function (biology); Government (linguistics); Research council; Public administration; Political science; Public relations; Accounting; Business; Law","score_opus":0.7595030484590533,"score_gpt":0.59285100163704,"score_spread":0.1666520468220133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1559496221","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25931278,0.003755733,0.18415695,0.019677365,0.0014935505,0.010831801,0.003766039,0.0025313292,0.5144744],"genre_scores_gemma":[0.8452289,0.0006551847,0.1192299,0.0022032694,0.00007427444,0.0031488403,0.0019063653,0.00033652104,0.027216803],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.80604476,0.070196114,0.010487909,0.004759947,0.09992687,0.008584402],"domain_scores_gemma":[0.5214064,0.030684393,0.0071477783,0.009581304,0.42279094,0.008389266],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21257748,0.0011551017,0.0011212747,0.0068652215,0.007067619,0.011989709,0.0039907615,0.0016336542,0.00413858],"category_scores_gemma":[0.22441871,0.0006354731,0.0013762036,0.004113114,0.004764839,0.0035291037,0.0057955687,0.0027523441,0.0014447647],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023251728,0.0011088377,0.10598376,0.0014993965,0.00035742848,0.00023104588,0.009951727,0.016956504,0.005345717,0.1758569,0.16636442,0.51401913],"study_design_scores_gemma":[0.00095154974,0.0033104096,0.35257885,0.0034537376,0.0006151008,0.0003980318,0.014248211,0.084497675,0.02380743,0.042425826,0.472331,0.001382146],"about_ca_topic_score_codex":0.7164484,"about_ca_topic_score_gemma":0.6857876,"teacher_disagreement_score":0.90056485,"about_ca_system_score_codex":0.09943515,"about_ca_system_score_gemma":0.22042163,"threshold_uncertainty_score":0.97103214},"labels":[],"label_agreement":null},{"id":"W1570565511","doi":"10.3138/cjpe.27.007","title":"Funnell, S. C., and Rogers, P. J. (2011). <i>Purposeful Program Theory.</i> San Francisco, CA: Jossey-Bass. 550 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bass (fish); Psychology; Fishery; Biology","score_opus":0.24747467403425955,"score_gpt":0.4667965692241588,"score_spread":0.21932189518989925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570565511","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005617342,0.5294295,0.11679885,0.108836524,0.0064565064,0.00080850115,0.004026212,0.0015637745,0.22646289],"genre_scores_gemma":[0.12537281,0.59304637,0.11973713,0.009708374,0.0015057194,0.0016448884,0.0028350942,0.0011900563,0.14495954],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964573,0.001103118,0.00046453474,0.00018766573,0.0016701177,0.00011721074],"domain_scores_gemma":[0.9659185,0.022387695,0.002084519,0.0010074358,0.00795178,0.00065011135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01217067,0.0011574229,0.00083887024,0.005505025,0.0026321197,0.0066238246,0.0022469372,0.002659363,0.02674139],"category_scores_gemma":[0.04092499,0.0012965229,0.0008566427,0.006239775,0.0041281614,0.011028441,0.0018012476,0.0042776866,0.012122647],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000106505184,0.000110256035,0.003933466,0.0020096109,0.000047647187,0.0001229635,0.0022291266,0.0005264684,0.00035405837,0.049575172,0.35715,0.5838347],"study_design_scores_gemma":[0.00007716641,0.00015388524,0.014457015,0.008926075,0.00025453934,0.0005934126,0.003155869,0.00072743394,0.0021491684,0.11312045,0.8562163,0.0001686804],"about_ca_topic_score_codex":0.022567656,"about_ca_topic_score_gemma":0.050575487,"teacher_disagreement_score":0.02674139,"about_ca_system_score_codex":0.0029867839,"about_ca_system_score_gemma":0.005799691,"threshold_uncertainty_score":0.08945882},"labels":[],"label_agreement":null},{"id":"W1588229591","doi":"10.3138/cjpe.30.1.105","title":"Sharon Brisolara, Denise Seigart, &amp; Saumitra SenGupta (Eds.). (2014). <i>Feminist Evaluation and Research: Theory and Practice.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sociology; Theology; Philosophy","score_opus":0.6285746015045411,"score_gpt":0.6044724397125063,"score_spread":0.024102161792034837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588229591","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057842984,0.84678364,0.0058961054,0.07046028,0.010201532,0.00004996585,0.00060404936,0.00038672876,0.065039285],"genre_scores_gemma":[0.0060431194,0.89755106,0.004672585,0.0041358653,0.002837927,0.00004776978,0.0003980961,0.000203078,0.084110625],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898463,0.00020066257,0.000064890875,0.00011522577,0.0005809726,0.000053521166],"domain_scores_gemma":[0.9962054,0.0018861424,0.00024973665,0.00008456732,0.0012727844,0.00030138818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025846998,0.0015289758,0.00089455215,0.0028763344,0.0011318248,0.0038264515,0.0012210946,0.0019054825,0.03099762],"category_scores_gemma":[0.0042991554,0.0008977118,0.00039664702,0.0033622188,0.0011386458,0.006317956,0.0012384646,0.002692065,0.030081438],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028526754,0.000013035139,0.00022755041,0.0007470129,0.0000072225357,0.00003494144,0.00043472555,0.00011187426,0.000090975074,0.003040082,0.7514194,0.24384464],"study_design_scores_gemma":[0.000008565039,0.000014676235,0.0011326876,0.0016713414,0.000021318798,0.00020861295,0.000833495,0.00014527784,0.00030531434,0.004218669,0.9914169,0.000023242503],"about_ca_topic_score_codex":0.027200537,"about_ca_topic_score_gemma":0.08359456,"teacher_disagreement_score":0.03099762,"about_ca_system_score_codex":0.0020145022,"about_ca_system_score_gemma":0.005985766,"threshold_uncertainty_score":0.10369742},"labels":[],"label_agreement":null},{"id":"W1591702131","doi":"10.3138/cjpe.28.002","title":"To Case Study or Not to Case Study: Our Experience with the Canadian Government’s Evaluation Practices and the Use of Case Studies as an Evaluation Methodology for First Nations Programs","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Case study research; Work (physics); Public relations; Comparative case; Value (mathematics); Political science; Psychology; Business; Marketing; Engineering","score_opus":0.8529623701720311,"score_gpt":0.6548419671908232,"score_spread":0.19812040298120792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1591702131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5494615,0.016301218,0.06595605,0.11535546,0.0015316132,0.004103851,0.00024211072,0.00050333276,0.24654487],"genre_scores_gemma":[0.9374199,0.004912679,0.03037633,0.008161482,0.00009973215,0.00077971723,0.00009255217,0.0002010104,0.017956683],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.88782936,0.081553765,0.0026635753,0.002706123,0.015742838,0.00950432],"domain_scores_gemma":[0.89200264,0.057184696,0.0034972283,0.0045241015,0.02813373,0.014657607],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07766068,0.00092331826,0.00063439447,0.0029143419,0.047701396,0.009990354,0.0053807055,0.0036509184,0.0044055325],"category_scores_gemma":[0.07836291,0.00066621136,0.00081976294,0.006192482,0.022776056,0.0040029786,0.01076728,0.006151505,0.0005032816],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012564645,0.00059104484,0.010885436,0.0010593623,0.000058514725,0.006788886,0.7646674,0.0021733055,0.001360433,0.03673419,0.03582669,0.13972902],"study_design_scores_gemma":[0.00002836653,0.00017739195,0.00828259,0.0011916289,0.00003853803,0.0021701276,0.6119417,0.001833656,0.0013925601,0.007160468,0.3656259,0.00015705747],"about_ca_topic_score_codex":0.8062072,"about_ca_topic_score_gemma":0.90092486,"teacher_disagreement_score":0.9223393,"about_ca_system_score_codex":0.10244412,"about_ca_system_score_gemma":0.14134398,"threshold_uncertainty_score":0.74328756},"labels":[],"label_agreement":null},{"id":"W1594257894","doi":"10.3138/cjpe.23.003","title":"Reframing Evaluation: Defining an Indigenous Evaluation Framework","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognitive reframing; Indigenous; Traditional knowledge; Focus group; Common ground; Sociology; Public relations; Political science; Engineering ethics; Psychology; Engineering; Social psychology; Anthropology; Ecology","score_opus":0.396733003676957,"score_gpt":0.552227878522765,"score_spread":0.15549487484580798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594257894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031988014,0.011764554,0.62352955,0.10995308,0.0013227167,0.0074473387,0.00012161145,0.00045718145,0.21341595],"genre_scores_gemma":[0.55880135,0.0029527845,0.42238414,0.0063040513,0.00031891972,0.004826165,0.00007735299,0.0001222876,0.0042129555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5482283,0.3949724,0.015385639,0.0063284524,0.029711423,0.0053736693],"domain_scores_gemma":[0.7037707,0.20326525,0.009856616,0.011203183,0.06604079,0.0058635054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.37477827,0.0015570794,0.0019699389,0.010791549,0.013884839,0.02329494,0.006419277,0.0056357994,0.0017571904],"category_scores_gemma":[0.1820413,0.0009820202,0.0016356193,0.0052103074,0.05415861,0.01864165,0.019191833,0.009775716,0.0003761933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006387779,0.00019967076,0.002282284,0.002049425,0.00012185555,0.00026917356,0.109421805,0.0025309497,0.000559381,0.78931844,0.005334386,0.08784875],"study_design_scores_gemma":[0.00011546696,0.000394034,0.0035153257,0.011286922,0.00028306476,0.000423618,0.1280249,0.011120956,0.0018801942,0.6758608,0.16682668,0.00026796458],"about_ca_topic_score_codex":0.025290063,"about_ca_topic_score_gemma":0.027506456,"teacher_disagreement_score":0.37477827,"about_ca_system_score_codex":0.042801093,"about_ca_system_score_gemma":0.07545284,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["sts"],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W1594443358","doi":"10.3138/cjpe.027.002","title":"Research on Evaluation: A Needs Assessment","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Psychology; Survey research; Engineering ethics; Management science; Sociology; Applied psychology; Engineering","score_opus":0.7833440326357193,"score_gpt":0.6849524617018541,"score_spread":0.09839157093386519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594443358","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06721896,0.13609578,0.019948833,0.71868944,0.0026601462,0.0032799183,0.00030028808,0.00016815551,0.05163841],"genre_scores_gemma":[0.8117876,0.09199062,0.05104283,0.03611031,0.0024367122,0.0042473837,0.0002991828,0.000060971477,0.0020243858],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.81705475,0.1347093,0.015420535,0.002018375,0.027607309,0.0031896816],"domain_scores_gemma":[0.3551454,0.5328668,0.0132859275,0.008982779,0.07583314,0.0138860475],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24241006,0.00057825405,0.002133234,0.014215154,0.007725369,0.016891388,0.002232369,0.008007633,0.0045708255],"category_scores_gemma":[0.31488642,0.0009542456,0.0007612598,0.010349292,0.013851313,0.023124574,0.0068872864,0.006038045,0.0007703134],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024763733,0.0014948479,0.024733184,0.038949136,0.00009910335,0.0005446845,0.061027158,0.0011437669,0.0010480706,0.15712397,0.035321373,0.678267],"study_design_scores_gemma":[0.00019021542,0.0022181906,0.02728864,0.1558491,0.00016998644,0.0018261239,0.35981002,0.004048598,0.0015616626,0.1329394,0.31383786,0.00026021505],"about_ca_topic_score_codex":0.002836159,"about_ca_topic_score_gemma":0.003263121,"teacher_disagreement_score":0.9845385,"about_ca_system_score_codex":0.015461476,"about_ca_system_score_gemma":0.045248006,"threshold_uncertainty_score":0.93424326},"labels":[],"label_agreement":null},{"id":"W1594828522","doi":"","title":"The key functions of collaborative logic modeling: Insights from the British Columbia Early Childhood Dental Programs","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Documentation; General partnership; Logic model; Government (linguistics); Key (lock); Early childhood; Computer science; Knowledge management; Public relations; Political science; Process management; Psychology; Public administration; Business; Programming language; Developmental psychology","score_opus":0.20652292156545762,"score_gpt":0.41826608559438194,"score_spread":0.21174316402892432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594828522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68922555,0.0009094466,0.041890237,0.03923155,0.000033522065,0.0005702719,0.0002689132,0.00014558516,0.2277249],"genre_scores_gemma":[0.97606397,0.00036638803,0.019280046,0.0005871387,0.0000063346088,0.00012327051,0.00007755439,0.00003871591,0.0034567227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9790189,0.016563017,0.00035719946,0.0004888954,0.0020583945,0.0015134972],"domain_scores_gemma":[0.940872,0.049093954,0.0015613963,0.0014872196,0.0052116206,0.0017737092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016874861,0.0004971291,0.00043733986,0.0021177782,0.008177461,0.01111069,0.0022792544,0.0015703727,0.0028421406],"category_scores_gemma":[0.037879236,0.0005058224,0.0004610012,0.0031364232,0.008801291,0.0045668636,0.00394302,0.0029034489,0.00024618473],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003367959,0.000976778,0.052012417,0.0005050268,0.00008483986,0.0028825146,0.26420993,0.048343826,0.0012262568,0.48586372,0.010034046,0.13352391],"study_design_scores_gemma":[0.00020915898,0.0002639598,0.025758095,0.0009784899,0.00013686717,0.0006141365,0.48396522,0.16431426,0.0020343917,0.23552316,0.08599208,0.00021018808],"about_ca_topic_score_codex":0.6844086,"about_ca_topic_score_gemma":0.7605874,"teacher_disagreement_score":0.3155914,"about_ca_system_score_codex":0.040262587,"about_ca_system_score_gemma":0.056529988,"threshold_uncertainty_score":0.6349},"labels":[],"label_agreement":null},{"id":"W1596745603","doi":"10.3138/cjpe.027.005","title":"Bamberger, Michael, Rugh, Jim, and Mabry, Linda. (2012). <i>Real World Evaluation: Working Under Budget, Time, Data, and Political Constraints</i> (2nd ed.). Thousand Oaks, CA: Sage. 666 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Politics; Economic history; Media studies; Gerontology; Sociology; Political science; History; Medicine; Law","score_opus":0.18890778587147808,"score_gpt":0.45984872552332184,"score_spread":0.27094093965184374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1596745603","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002410316,0.6479089,0.025669744,0.2134866,0.010453095,0.00042331358,0.0062024416,0.0014994593,0.091946095],"genre_scores_gemma":[0.057461295,0.70897454,0.071439154,0.03268608,0.0046501686,0.00086064066,0.0038760665,0.000991276,0.11906086],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762243,0.00067187217,0.00026004572,0.00012147194,0.0012070304,0.00011718598],"domain_scores_gemma":[0.97573143,0.014197152,0.0014978879,0.00044223192,0.0072066085,0.0009246187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009872148,0.0010122943,0.0006556845,0.004558061,0.0025826269,0.006007561,0.0017385812,0.0022239804,0.030783048],"category_scores_gemma":[0.036562823,0.0008782323,0.0005546813,0.0055004847,0.0019177884,0.009078618,0.0016013628,0.005295353,0.020058474],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042094223,0.000017042608,0.00083037623,0.00059148535,0.000013507604,0.000035598798,0.00047799505,0.00013036607,0.00013801467,0.003796642,0.80772495,0.18620189],"study_design_scores_gemma":[0.000049921542,0.00006207743,0.010179359,0.0051856316,0.00013391167,0.000246751,0.0013689635,0.0002870612,0.0008758517,0.02570034,0.9558352,0.000074884665],"about_ca_topic_score_codex":0.04252802,"about_ca_topic_score_gemma":0.12655964,"teacher_disagreement_score":0.04252802,"about_ca_system_score_codex":0.0036403735,"about_ca_system_score_gemma":0.008279593,"threshold_uncertainty_score":0.1029796},"labels":[],"label_agreement":null},{"id":"W16024769","doi":"10.3138/cjpe.0019.004","title":"A Comprehensive Evaluation Framework for Mental Health Consumer/Survivor Organizations: Values, Conceptualization, Design, and Action","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre for Addiction and Mental Health; Centre for Community Based Research; Wilfrid Laurier University","funders":"","keywords":"Conceptualization; Mental health; Action (physics); Citizen journalism; Participatory action research; Psychology; Qualitative research; Sociology; Public relations; Applied psychology; Psychotherapist; Computer science; Political science; Social science","score_opus":0.5141511402610605,"score_gpt":0.5389048974662233,"score_spread":0.02475375720516282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W16024769","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04041373,0.008773272,0.6725537,0.115634635,0.00055987766,0.06259889,0.0006992171,0.0008010976,0.09796552],"genre_scores_gemma":[0.19008796,0.0013896103,0.7677603,0.002441212,0.000039408224,0.036538344,0.00020491905,0.000063938656,0.0014743427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.49600518,0.455218,0.015912123,0.005189844,0.022189487,0.005485406],"domain_scores_gemma":[0.7787466,0.15575685,0.008287966,0.008514452,0.039183818,0.009510273],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.40135118,0.0033806635,0.0032180946,0.014394995,0.018751966,0.023385094,0.006596418,0.0074341623,0.0031108416],"category_scores_gemma":[0.1713603,0.0020269589,0.002752618,0.007985566,0.034051593,0.017053572,0.014862407,0.0074426397,0.000518175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001826977,0.001164262,0.007090252,0.005873534,0.00024390819,0.0005703641,0.11583851,0.009348157,0.0010101801,0.7064399,0.013129254,0.13910897],"study_design_scores_gemma":[0.0012342402,0.0019001861,0.007141151,0.03318919,0.00060609856,0.0006355852,0.24532744,0.03230987,0.003252007,0.49556088,0.17837192,0.0004714632],"about_ca_topic_score_codex":0.056177977,"about_ca_topic_score_gemma":0.07809232,"teacher_disagreement_score":0.40135118,"about_ca_system_score_codex":0.09201389,"about_ca_system_score_gemma":0.19567923,"threshold_uncertainty_score":0.7382406},"labels":[],"label_agreement":null},{"id":"W1606698357","doi":"","title":"Fetterman, D. M. (2013). Empowerment Evaluation in the Digital Villages: Hewlett Packard’s $15 Million Race Towards Social Justice. Stanford, CA: Stanford University Press. 154 pages","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Innovative Approaches in Technology and Social Development","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empowerment; Race (biology); Social justice; Sociology; Economic Justice; Media studies; Political science; Gender studies; Criminology; Law","score_opus":0.0646681345517927,"score_gpt":0.2858982040530056,"score_spread":0.22123006950121288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1606698357","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055916677,0.32747218,0.024723504,0.3965321,0.011006651,0.00063270255,0.0016950975,0.0009529683,0.23139317],"genre_scores_gemma":[0.24957696,0.37498415,0.06194556,0.059736744,0.003931616,0.0017890164,0.0013356743,0.00083880627,0.2458616],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974872,0.0010025512,0.000178343,0.00013173158,0.0010678801,0.00013218539],"domain_scores_gemma":[0.980078,0.012310369,0.0006631238,0.0003887656,0.005478379,0.0010813895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013575693,0.00073348894,0.00044494667,0.0027496598,0.005119256,0.0055218837,0.001438095,0.0031674076,0.037989777],"category_scores_gemma":[0.026543539,0.0007394574,0.00034943924,0.0020401059,0.003991973,0.011551554,0.0024628816,0.0057013505,0.008418377],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006795739,0.000045080727,0.0009405815,0.00039848246,0.000010377618,0.00003929499,0.0014607327,0.00008724004,0.00019598036,0.0157984,0.63150436,0.34945145],"study_design_scores_gemma":[0.000080389415,0.00013048452,0.012340209,0.003823466,0.00006412854,0.00014145656,0.004350057,0.00023601121,0.0010882296,0.04667266,0.931008,0.00006503915],"about_ca_topic_score_codex":0.02775068,"about_ca_topic_score_gemma":0.08922008,"teacher_disagreement_score":0.037989777,"about_ca_system_score_codex":0.0032167702,"about_ca_system_score_gemma":0.006694192,"threshold_uncertainty_score":0.12708843},"labels":[],"label_agreement":null},{"id":"W1611881142","doi":"10.3138/cjpe.30.1.64","title":"Exploring the Leadership Dimension of Developmental Evaluation: The Evaluator as a Servant-Leader","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Servant leadership; Situational ethics; Leadership development; Situated; Psychology; Servant; Dimension (graph theory); Adaptation (eye); Applied psychology; Knowledge management; Computer science; Public relations; Social psychology; Leadership style; Political science; Artificial intelligence; Software engineering","score_opus":0.8742798159456303,"score_gpt":0.541068240408882,"score_spread":0.3332115755367483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1611881142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33539322,0.0058650626,0.13056494,0.27229133,0.001207993,0.00067541515,0.000051264455,0.0003055495,0.2536452],"genre_scores_gemma":[0.9757711,0.0008162172,0.015981907,0.0039418167,0.00008164768,0.00021074542,0.000010561103,0.000047891157,0.0031379424],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8512181,0.1386002,0.0013399682,0.0013729971,0.004375815,0.0030928962],"domain_scores_gemma":[0.8916349,0.072683774,0.004659233,0.0034162565,0.012797603,0.014808255],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09869299,0.000385627,0.00046907554,0.0021627932,0.013521535,0.020966118,0.001889866,0.0024761327,0.0037038834],"category_scores_gemma":[0.07525007,0.00054450874,0.00046655757,0.0012473994,0.025598936,0.011298765,0.012624188,0.0060906736,0.0005106893],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015569,0.00047900432,0.030077782,0.00059189036,0.000043378182,0.0013824614,0.529067,0.00057218154,0.00083829294,0.2990719,0.015845949,0.12187449],"study_design_scores_gemma":[0.00009608668,0.00039226422,0.013465013,0.002388697,0.00008051314,0.0011141994,0.71867335,0.004431225,0.001789827,0.11257089,0.1448618,0.00013616343],"about_ca_topic_score_codex":0.00808459,"about_ca_topic_score_gemma":0.027844276,"teacher_disagreement_score":0.901307,"about_ca_system_score_codex":0.01239606,"about_ca_system_score_gemma":0.03367232,"threshold_uncertainty_score":0.52194464},"labels":[],"label_agreement":null},{"id":"W1658636278","doi":"10.3138/cjpe.0028.004","title":"Introduction à la professionnalisation de l’évaluation : perspective globale sur les compétences des évaluateurs","year":2014,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.2965364943297302,"score_gpt":0.4989688669957872,"score_spread":0.20243237266605696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1658636278","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016462162,0.1132872,0.044625852,0.3014244,0.0036774394,0.00015831008,0.0001939319,0.00024326322,0.5199273],"genre_scores_gemma":[0.7399707,0.07546149,0.027180374,0.04427952,0.005179618,0.00052905176,0.00024709143,0.0005831403,0.10656904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9640377,0.023584248,0.0016190438,0.0034887036,0.0053541125,0.0019161784],"domain_scores_gemma":[0.9396957,0.040797316,0.0029231356,0.003084208,0.011020343,0.002479221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.038494896,0.00090922357,0.0010964323,0.004968785,0.005074961,0.022620628,0.0017783764,0.006058601,0.01195717],"category_scores_gemma":[0.04473219,0.00050635496,0.0009240272,0.0049590417,0.03441042,0.019905733,0.008013847,0.008232523,0.0027645403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005532993,0.000024750618,0.0016661831,0.00086351536,0.000019009016,0.00013221124,0.026611328,0.00037914191,0.0002297922,0.86704695,0.02810628,0.074865565],"study_design_scores_gemma":[0.000018621513,0.000095023475,0.0059329956,0.0037982885,0.000029344405,0.00040201336,0.027122464,0.00068636687,0.00043494278,0.32542062,0.6359882,0.000071055365],"about_ca_topic_score_codex":0.014555476,"about_ca_topic_score_gemma":0.010817193,"teacher_disagreement_score":0.038494896,"about_ca_system_score_codex":0.01637695,"about_ca_system_score_gemma":0.0147055825,"threshold_uncertainty_score":0.20358294},"labels":[],"label_agreement":null},{"id":"W166307397","doi":"10.3138/cjpe.24.001","title":"Building an Evaluative Culture: The Key to Effective Evaluation and Results Management","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Rogers Communications (Canada)","funders":"","keywords":"Key (lock); Organizational culture; Knowledge management; Order (exchange); Empirical research; Business; Sociology; Computer science; Public relations; Psychology; Process management; Epistemology; Political science; Computer security","score_opus":0.0790348188226643,"score_gpt":0.42865230901452656,"score_spread":0.3496174901918623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W166307397","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03677788,0.0096928375,0.2567933,0.56401414,0.0038847052,0.0020042588,0.000093151015,0.001225976,0.12551384],"genre_scores_gemma":[0.6578277,0.0061558695,0.27895245,0.044456318,0.0026320254,0.002602261,0.000112992115,0.0006898282,0.006570551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.5287412,0.34252617,0.02534611,0.012912712,0.08188657,0.008587223],"domain_scores_gemma":[0.33778307,0.37038115,0.049174745,0.06458131,0.12967785,0.048401855],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.40834442,0.0012649985,0.002784829,0.008436148,0.021806622,0.04972962,0.0040286877,0.007805128,0.0035347051],"category_scores_gemma":[0.3721286,0.001959202,0.0013061421,0.0050808587,0.06008661,0.025640426,0.025297692,0.024113176,0.001933962],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017381483,0.0013303095,0.01348296,0.0024026376,0.00041994936,0.00037383125,0.10379955,0.001979186,0.0024874688,0.43391293,0.060926624,0.37871072],"study_design_scores_gemma":[0.00021921132,0.0008037887,0.02065365,0.013346213,0.00026195156,0.0007544166,0.10339164,0.00357049,0.004384517,0.5706697,0.28113478,0.00080962403],"about_ca_topic_score_codex":0.005350514,"about_ca_topic_score_gemma":0.0036514525,"teacher_disagreement_score":0.40834442,"about_ca_system_score_codex":0.020148143,"about_ca_system_score_gemma":0.0875332,"threshold_uncertainty_score":0.72961664},"labels":[],"label_agreement":null},{"id":"W1663638353","doi":"10.3138/cjpe.30.1.108","title":"Robert K. Yin. (2014). <i>Case Study Research Design and Methods (5th ed.).</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":406,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Philosophy; Sociology","score_opus":0.6829255352418476,"score_gpt":0.6779845172067633,"score_spread":0.004941018035084288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1663638353","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023077582,0.45942312,0.18616702,0.21117736,0.013714995,0.00212161,0.0035866678,0.002850197,0.11865129],"genre_scores_gemma":[0.036027774,0.48628387,0.38065842,0.021509852,0.002991993,0.006189463,0.0021862953,0.0014274429,0.06272488],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9892762,0.0057811975,0.0011555782,0.00054115034,0.003009275,0.00023662817],"domain_scores_gemma":[0.93489313,0.043149583,0.0028365059,0.0016024362,0.016329294,0.0011891455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029780999,0.0020180868,0.0010484587,0.0074548903,0.0036532418,0.0044056126,0.0022447777,0.002689517,0.021928502],"category_scores_gemma":[0.051778894,0.0021152082,0.0008713582,0.0069928532,0.005416553,0.009186066,0.0026537953,0.0080712475,0.013445316],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004991242,0.0000457421,0.000866619,0.0028822701,0.000027701264,0.00015036254,0.003055526,0.00025436239,0.00038004754,0.024326619,0.64880043,0.31916043],"study_design_scores_gemma":[0.0000472024,0.0000692937,0.0038432656,0.01115862,0.0001005593,0.00037296524,0.004105941,0.00028571076,0.0011113511,0.043599322,0.9351793,0.00012651079],"about_ca_topic_score_codex":0.033308215,"about_ca_topic_score_gemma":0.06936149,"teacher_disagreement_score":0.033308215,"about_ca_system_score_codex":0.0051035746,"about_ca_system_score_gemma":0.014387028,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1666893058","doi":"","title":"M&E Competencies in Support of the AIDS Response: A Sector-Specific Example","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Human immunodeficiency virus (HIV); Context (archaeology); Political science; Humanities; Medicine; Nursing; Family medicine; Geography","score_opus":0.41677236886577906,"score_gpt":0.4821539888231361,"score_spread":0.06538161995735703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1666893058","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3741866,0.0132770445,0.015115064,0.082447864,0.00097261096,0.0009688237,0.00054830697,0.00024998302,0.5122337],"genre_scores_gemma":[0.9342816,0.008653745,0.01740009,0.005023424,0.00023120201,0.0001913795,0.00034391292,0.00004064633,0.033833995],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99650216,0.0020912483,0.000099133045,0.000068494264,0.0003456679,0.00089325896],"domain_scores_gemma":[0.995761,0.0018040538,0.00020092604,0.00014325177,0.001162869,0.0009279126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036846744,0.0003305729,0.00015059441,0.0014458968,0.0024498363,0.0021834176,0.00063763227,0.0020689385,0.010054362],"category_scores_gemma":[0.005926101,0.00012875408,0.00040127253,0.001789441,0.0008844946,0.001811296,0.0030695582,0.0012436422,0.0022883585],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044957336,0.0020723492,0.049862042,0.002775954,0.000022592358,0.010945573,0.049575128,0.003283043,0.0027647389,0.07676711,0.08214247,0.71933943],"study_design_scores_gemma":[0.00015549341,0.0010036591,0.07197418,0.0031137427,0.000038614085,0.008859538,0.10012804,0.0038659426,0.0034823625,0.0121919,0.79510814,0.000078403464],"about_ca_topic_score_codex":0.009223521,"about_ca_topic_score_gemma":0.019423813,"teacher_disagreement_score":0.010054362,"about_ca_system_score_codex":0.002921917,"about_ca_system_score_gemma":0.0071300953,"threshold_uncertainty_score":0.03363514},"labels":[],"label_agreement":null},{"id":"W1688463168","doi":"10.3138/cjpe.30.1.99","title":"McDavid, J. C., Huse, I., &amp; Hawthorn, L. R. L. (2013). <i>Program Evaluation and Performance Measurement: An Introduction to Practice (2nd ed.).</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"SAGE; Psychology; Sociology; Library science; Computer science; Physics; Nuclear physics","score_opus":0.4454211636939176,"score_gpt":0.5224499535137422,"score_spread":0.07702878981982464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1688463168","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016036499,0.5353429,0.04528494,0.27117884,0.008362984,0.000579508,0.004218323,0.0012058286,0.13222294],"genre_scores_gemma":[0.06419586,0.61813796,0.17391244,0.048491184,0.0032623147,0.0009856205,0.002404238,0.0008869946,0.08772333],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951007,0.0015247545,0.0005114204,0.0002527382,0.0024917214,0.00011878407],"domain_scores_gemma":[0.97775567,0.012560959,0.0014055886,0.0006261017,0.0070767575,0.00057492184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008237403,0.0010618086,0.0007487965,0.011112153,0.0029913837,0.0043116715,0.0032827116,0.003256807,0.024203442],"category_scores_gemma":[0.03661192,0.0011658119,0.00060868886,0.010661233,0.0033705716,0.0047835824,0.001983641,0.0044481475,0.009957988],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023070874,0.00002784928,0.001104878,0.0009369631,0.000020067619,0.00006544566,0.0006735678,0.00017520081,0.00016641917,0.009004076,0.72444177,0.2633606],"study_design_scores_gemma":[0.000014612477,0.000025842968,0.0044806306,0.0030470982,0.000030451183,0.0003392389,0.00082632585,0.00024364631,0.00048716224,0.017566767,0.9728967,0.00004157082],"about_ca_topic_score_codex":0.06489155,"about_ca_topic_score_gemma":0.21677068,"teacher_disagreement_score":0.06489155,"about_ca_system_score_codex":0.006666859,"about_ca_system_score_gemma":0.008356311,"threshold_uncertainty_score":0.12902766},"labels":[],"label_agreement":null},{"id":"W1696578794","doi":"","title":"Mot du rédacteur en chef 27(1)","year":2012,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.1863010128882506,"score_gpt":0.482610622353628,"score_spread":0.29630960946537743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1696578794","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04036438,0.021002991,0.0054374738,0.16301817,0.052950297,0.0012653082,0.008367321,0.0031969983,0.704397],"genre_scores_gemma":[0.10851105,0.012158298,0.008944416,0.03250293,0.006995646,0.0010688017,0.0044120043,0.0015338479,0.823873],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99110293,0.0023716134,0.00049522024,0.0005866344,0.0037856335,0.001657952],"domain_scores_gemma":[0.9868188,0.0017296023,0.0006525394,0.00045637556,0.0061256895,0.0042170906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063427878,0.00097128924,0.0010821641,0.0033942615,0.0046214787,0.004966577,0.0014129519,0.0042787166,0.25698537],"category_scores_gemma":[0.024816548,0.00051894784,0.0016878744,0.0019314582,0.0011467525,0.0023677927,0.003190317,0.004957225,0.059123136],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002226043,0.00031671172,0.008154109,0.00036104015,0.00003923036,0.0011075768,0.0007172842,0.0001972556,0.0004505049,0.0074160895,0.7418054,0.23921224],"study_design_scores_gemma":[0.00007908523,0.00008030138,0.0105045745,0.0006913008,0.000023032548,0.00111223,0.00082887604,0.00016120727,0.00044299482,0.0007439831,0.9852911,0.000041259515],"about_ca_topic_score_codex":0.107141785,"about_ca_topic_score_gemma":0.11706935,"teacher_disagreement_score":0.25698537,"about_ca_system_score_codex":0.010111632,"about_ca_system_score_gemma":0.02157449,"threshold_uncertainty_score":0.8597017},"labels":[],"label_agreement":null},{"id":"W1700780107","doi":"10.3138/cjpe.0028.006","title":"Evaluator Competencies: The Canadian Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Engineering ethics; Context (archaeology); Political science; Psychology; Sociology; Public relations; Management; Engineering; History; Law","score_opus":0.36189769178651315,"score_gpt":0.5260247839748239,"score_spread":0.16412709218831073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1700780107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5571717,0.022441959,0.004428066,0.13666335,0.0019882298,0.00069111417,0.0009905116,0.00022244905,0.2754026],"genre_scores_gemma":[0.9361299,0.015363916,0.0029125488,0.008009801,0.00009291663,0.0001484022,0.00028403947,0.00013340026,0.036924973],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9761244,0.0075358427,0.00064217846,0.0012741366,0.00957144,0.0048520314],"domain_scores_gemma":[0.95620984,0.007029003,0.0010196059,0.00093783607,0.02114486,0.013658825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027174778,0.00038706965,0.0005748736,0.0017414263,0.021101013,0.008371206,0.002396625,0.0021037022,0.0075084167],"category_scores_gemma":[0.028296394,0.0005523502,0.00032602556,0.004428464,0.007495877,0.0032078198,0.0060754,0.0046033105,0.0005766884],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00043743863,0.0008879087,0.05447154,0.0011668324,0.000056168796,0.0018485541,0.46469575,0.0007458357,0.0012608683,0.0696774,0.15492022,0.24983153],"study_design_scores_gemma":[0.000058310845,0.00028898008,0.046649028,0.0011725675,0.000034332963,0.00066041294,0.19773318,0.00044095097,0.0009628132,0.0016397744,0.7502143,0.00014531953],"about_ca_topic_score_codex":0.97525966,"about_ca_topic_score_gemma":0.99153674,"teacher_disagreement_score":0.85912573,"about_ca_system_score_codex":0.1408743,"about_ca_system_score_gemma":0.3809314,"threshold_uncertainty_score":0.996464},"labels":[],"label_agreement":null},{"id":"W1701527280","doi":"","title":"King, J. A., & Stevahn, L. (2013). Interactive Evaluation Practice: Mastering the Interpersonal Dynamics of Program Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dynamics (music); Interpersonal communication; Psychology; Interpersonal relationship; Applied psychology; Social psychology; Pedagogy","score_opus":0.29701047840383554,"score_gpt":0.5445591158437647,"score_spread":0.24754863743992916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1701527280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09694147,0.033472512,0.36313307,0.21653534,0.0018120178,0.0022114583,0.0005624311,0.0022393514,0.28309226],"genre_scores_gemma":[0.61863655,0.025232768,0.31949267,0.009344232,0.00031038257,0.0014088998,0.00013671383,0.00052134745,0.024916425],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9835752,0.009790978,0.0009084467,0.00073993596,0.0045271986,0.00045825104],"domain_scores_gemma":[0.8232448,0.14759724,0.006037416,0.0044246526,0.014774477,0.003921468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053286184,0.0005317549,0.000503155,0.003065981,0.005913883,0.009296433,0.0019692988,0.00209814,0.008380437],"category_scores_gemma":[0.13299456,0.0009884137,0.00050325476,0.0015395698,0.007157463,0.01139706,0.0061515984,0.0064342143,0.002219435],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023469672,0.00024536168,0.013060741,0.0016012925,0.00009591043,0.00027727787,0.06559618,0.0012099607,0.0026187815,0.040691443,0.09409461,0.78027385],"study_design_scores_gemma":[0.0002721012,0.0009262179,0.06833031,0.008296078,0.0005576077,0.0019939544,0.063765,0.00712639,0.011697052,0.24180852,0.594713,0.0005137158],"about_ca_topic_score_codex":0.016401801,"about_ca_topic_score_gemma":0.05409766,"teacher_disagreement_score":0.053286184,"about_ca_system_score_codex":0.0049320585,"about_ca_system_score_gemma":0.01194457,"threshold_uncertainty_score":0.2818076},"labels":[],"label_agreement":null},{"id":"W1720965121","doi":"10.3138/cjpe.28.001","title":"Measuring Organizational Evaluation Capacity in the Canadian Federal Government","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Saint Paul University; Carleton University; École Nationale d'Administration Publique","funders":"","keywords":"Government (linguistics); Identification (biology); Organization development; Business; Evaluation methods; Organizational effectiveness; Organizational learning; Organizational identification; Public relations; Process management; Organizational commitment; Knowledge management; Political science; Computer science; Engineering","score_opus":0.5879919298116747,"score_gpt":0.4514966114809471,"score_spread":0.1364953183307276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1720965121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91430336,0.0006416833,0.003038117,0.002429314,0.00006201737,0.0010497549,0.0018793716,0.00016495593,0.07643141],"genre_scores_gemma":[0.9919992,0.00017398753,0.0042240787,0.000120585595,0.000006196973,0.00026152722,0.000606374,0.000014471533,0.002593557],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98366654,0.0036179335,0.00076662865,0.00077087275,0.008598268,0.0025797903],"domain_scores_gemma":[0.9362344,0.006344948,0.003457631,0.0016948284,0.046591315,0.0056767827],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015467183,0.00034807425,0.00035509892,0.006664886,0.00700048,0.0037466004,0.0018851705,0.00053592736,0.002939616],"category_scores_gemma":[0.031026652,0.00034334254,0.00041068622,0.0056055454,0.00272967,0.0012178418,0.0030442178,0.0009840993,0.00026094838],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034488464,0.0007316595,0.7102209,0.00048374315,0.00016803975,0.00013507396,0.026367174,0.0065323296,0.0017854564,0.027221506,0.032976992,0.19303216],"study_design_scores_gemma":[0.000031341337,0.00014139594,0.92827606,0.00030545573,0.00004808122,0.000032526186,0.0206303,0.0054714037,0.002029125,0.0011696073,0.041751757,0.00011296162],"about_ca_topic_score_codex":0.97564405,"about_ca_topic_score_gemma":0.98268867,"teacher_disagreement_score":0.98453283,"about_ca_system_score_codex":0.13086712,"about_ca_system_score_gemma":0.18191469,"threshold_uncertainty_score":0.9495119},"labels":[],"label_agreement":null},{"id":"W1723825527","doi":"","title":"Contributing Factors to the Continued Blurring of Research and Evaluation: Strategies for Moving Forward","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Confusion; Terminology; Political science; Humanities; Psychology; Philosophy","score_opus":0.5525192653748852,"score_gpt":0.6023241883787067,"score_spread":0.049804923003821555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1723825527","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043024924,0.06292876,0.078639224,0.83884704,0.005426715,0.0011543921,0.00003864468,0.0002829884,0.008379709],"genre_scores_gemma":[0.38330922,0.050080102,0.34718075,0.19280694,0.009232167,0.010496233,0.00011888238,0.000705749,0.00606995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.16594806,0.6847111,0.051663015,0.021722429,0.06643029,0.009525091],"domain_scores_gemma":[0.086583875,0.7525179,0.028696219,0.048223365,0.07636725,0.007611472],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7990208,0.0052348697,0.011447754,0.024413258,0.022738464,0.06038363,0.013857965,0.03566354,0.006693371],"category_scores_gemma":[0.7652836,0.005199498,0.0050829803,0.019572366,0.11652152,0.09793044,0.05185396,0.054256704,0.0019271014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055049814,0.00030069452,0.002886198,0.007947933,0.00035190693,0.0005311118,0.046826888,0.0013920498,0.00047999778,0.7281467,0.019826386,0.19075967],"study_design_scores_gemma":[0.0004944239,0.0004876644,0.002297022,0.023511281,0.0002722717,0.00067227415,0.052457538,0.0043094126,0.0012554735,0.77585673,0.13774389,0.00064193585],"about_ca_topic_score_codex":0.021155044,"about_ca_topic_score_gemma":0.01524084,"teacher_disagreement_score":0.20097917,"about_ca_system_score_codex":0.08065927,"about_ca_system_score_gemma":0.13574971,"threshold_uncertainty_score":0.5852267},"labels":[],"label_agreement":null},{"id":"W1724770786","doi":"10.3138/cjpe.30.1.23","title":"Reflexivity in Evaluating an Aboriginal Women Heart Health Promotion Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"B.C. Women's Hospital & Health Centre","funders":"","keywords":"Reflexivity; Context (archaeology); Process (computing); Promotion (chess); Rework; Sociology; Power (physics); Psychology; Computer science; Political science; Social science","score_opus":0.6574517143601347,"score_gpt":0.6690681666853625,"score_spread":0.011616452325227788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1724770786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78647166,0.003365293,0.064083844,0.017253647,0.00049596623,0.008133194,0.00009858638,0.00015472305,0.119943105],"genre_scores_gemma":[0.9685761,0.0008366716,0.024337552,0.00092485157,0.00005340258,0.0019275469,0.00002271517,0.000032891527,0.0032882371],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7496751,0.22530273,0.0046165967,0.0021653057,0.01524181,0.002998424],"domain_scores_gemma":[0.8040201,0.15729344,0.0102189705,0.0050222045,0.020515496,0.0029297224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.20589434,0.0006899626,0.00077982707,0.0020092041,0.0055258516,0.008900992,0.0018279221,0.0017890553,0.002808868],"category_scores_gemma":[0.19691712,0.0004014049,0.00063867687,0.0012373232,0.010343415,0.0036842243,0.00869823,0.0029613697,0.00032165818],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001068667,0.0011756974,0.011541307,0.0040757516,0.00022582842,0.0006860013,0.71428674,0.0022140117,0.0049313866,0.045415435,0.0024544545,0.21192466],"study_design_scores_gemma":[0.000532796,0.0062835827,0.029505415,0.0115070725,0.0006891054,0.00073583797,0.78533715,0.0073464634,0.029595068,0.050799698,0.07734101,0.00032674885],"about_ca_topic_score_codex":0.005701237,"about_ca_topic_score_gemma":0.008608016,"teacher_disagreement_score":0.99429876,"about_ca_system_score_codex":0.009931855,"about_ca_system_score_gemma":0.023208046,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1727891101","doi":"","title":"S. N. Hesse-Biber. (2010). Mixed Methods Research: Merging Theory with Practice. New York, NY: Guildford. 242 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Sociology; Information retrieval; Computer science","score_opus":0.7558464177977277,"score_gpt":0.634052245019063,"score_spread":0.12179417277866467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1727891101","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014740154,0.7606975,0.12938261,0.054262873,0.020143216,0.0010814128,0.0037530407,0.0017259977,0.02747945],"genre_scores_gemma":[0.024752712,0.6689291,0.25268468,0.0098171085,0.0062359925,0.0031021978,0.0031486817,0.0014354367,0.029893989],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9809153,0.011225936,0.0026567494,0.0007300214,0.004289662,0.00018244765],"domain_scores_gemma":[0.7737542,0.1812876,0.006942024,0.005122178,0.031060794,0.001833106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04755094,0.00397031,0.002785002,0.011047127,0.0035555896,0.0052776053,0.0035388195,0.006582662,0.03893921],"category_scores_gemma":[0.12280375,0.0049210275,0.0018780563,0.012937414,0.005035605,0.00958888,0.0030451412,0.008673529,0.025595153],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018967611,0.00009176539,0.0010699437,0.0057844226,0.00012728339,0.00017606381,0.0017989242,0.0006453811,0.0005218579,0.009100213,0.37610266,0.6043918],"study_design_scores_gemma":[0.00038993324,0.00045541336,0.01356593,0.0405952,0.00080183457,0.0020078323,0.0025663099,0.003611783,0.0036291464,0.068758115,0.863067,0.0005515852],"about_ca_topic_score_codex":0.018764371,"about_ca_topic_score_gemma":0.04796703,"teacher_disagreement_score":0.04755094,"about_ca_system_score_codex":0.0033404357,"about_ca_system_score_gemma":0.009588631,"threshold_uncertainty_score":0.25147635},"labels":[],"label_agreement":null},{"id":"W1728339452","doi":"10.3138/cjpe.27.002","title":"Assessing the Value for Money of Active Labour Market Programming for Persons with Disabilities","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Canadian Policy and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Employment and Social Development Canada; University of Manitoba","funders":"","keywords":"Value for money; Directive; Treasury; Value (mathematics); Actuarial science; Market value; Economics; Business; Computer science; Accounting; Public economics; Political science; Law","score_opus":0.12424518924406619,"score_gpt":0.42395986741004366,"score_spread":0.29971467816597747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1728339452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68573457,0.005188821,0.006756915,0.055392846,0.00047273166,0.0026964275,0.0015962463,0.00008591232,0.24207564],"genre_scores_gemma":[0.99115694,0.0011373903,0.003055602,0.00095331576,0.000059468468,0.0004353232,0.00014959056,0.000011268586,0.0030411957],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.93654025,0.041320775,0.0019074677,0.0006683034,0.014584119,0.0049791047],"domain_scores_gemma":[0.85341007,0.07178458,0.01061206,0.0028948192,0.051653408,0.009645137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.057066884,0.00054252514,0.0007070279,0.005201874,0.0058695828,0.007933189,0.0018660876,0.0015932893,0.0052499585],"category_scores_gemma":[0.13523562,0.0002965508,0.00074035214,0.0037597944,0.0043042325,0.0036744897,0.005851062,0.0028228208,0.00029874637],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018587005,0.0020306534,0.21604618,0.0025101013,0.00063989026,0.00040619652,0.028499559,0.0068994793,0.00088033895,0.10372812,0.04169667,0.5948041],"study_design_scores_gemma":[0.000714478,0.00635706,0.56770015,0.020287588,0.0015193535,0.00038141047,0.1570478,0.017248388,0.009045524,0.04862047,0.17045179,0.00062593713],"about_ca_topic_score_codex":0.28175506,"about_ca_topic_score_gemma":0.49701977,"teacher_disagreement_score":0.7182449,"about_ca_system_score_codex":0.053518742,"about_ca_system_score_gemma":0.08655579,"threshold_uncertainty_score":0.56023014},"labels":[],"label_agreement":null},{"id":"W1731692312","doi":"10.3138/cjpe.023.010","title":"Professional Identity of Evaluators in Israel","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diversity (politics); Identity (music); Context (archaeology); Public relations; Professional association; Professional development; Political science; Publication; Sociology; Pedagogy; Law; Geography","score_opus":0.5165946088532868,"score_gpt":0.591396369755435,"score_spread":0.07480176090214818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1731692312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9571668,0.0006840633,0.00087915664,0.0062732245,0.00011165722,0.00006794179,0.00003492984,0.000014325146,0.034767788],"genre_scores_gemma":[0.99542266,0.00018745818,0.00020776322,0.0005258305,0.000016873619,0.000020988284,0.000019248659,0.00000478244,0.0035944104],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9856323,0.008137435,0.0005007606,0.0005894137,0.0028015603,0.002338483],"domain_scores_gemma":[0.96820754,0.009739166,0.0049208445,0.0008990191,0.009176189,0.0070573534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015070469,0.0001562424,0.00028812973,0.0023234808,0.008035114,0.005249747,0.0007030684,0.001033756,0.0059767845],"category_scores_gemma":[0.025819467,0.00018387887,0.00014233301,0.00093338935,0.003896364,0.0014350434,0.003827597,0.0012245768,0.0005263697],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043098125,0.000650708,0.43918902,0.00023424067,0.000029837842,0.000932157,0.4100115,0.00024804333,0.0015959156,0.022350674,0.014287985,0.110038914],"study_design_scores_gemma":[0.00004916076,0.00031609728,0.1684697,0.00065317855,0.000023095457,0.001063389,0.72046477,0.0012376145,0.001330363,0.0057465048,0.10054803,0.00009816266],"about_ca_topic_score_codex":0.01328284,"about_ca_topic_score_gemma":0.011891087,"teacher_disagreement_score":0.015070469,"about_ca_system_score_codex":0.0070167114,"about_ca_system_score_gemma":0.010031166,"threshold_uncertainty_score":0.079701185},"labels":[],"label_agreement":null},{"id":"W1746443872","doi":"","title":"Rubin, Herbert J. et Rubin, Irene S. (2011). Qualitative interviewing: The art of hearing data (3e éd.). Thousand Oaks, CA: Sage, 360 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Research in Social Sciences","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"SAGE; Interview; Art; Psychology; Sociology; Anthropology; Physics","score_opus":0.4452409145155379,"score_gpt":0.5406676830756556,"score_spread":0.09542676856011773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1746443872","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009126436,0.56102616,0.19857672,0.16277002,0.005074639,0.0037734793,0.0075570126,0.0015841718,0.050511446],"genre_scores_gemma":[0.12546268,0.49536347,0.3054038,0.019093918,0.0013098331,0.014798314,0.0035304385,0.0014231589,0.033614382],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97260374,0.018146517,0.0028200457,0.0013159784,0.0046479,0.00046577485],"domain_scores_gemma":[0.73787206,0.22077341,0.0074547655,0.007927241,0.024305243,0.0016671605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.092374586,0.0010814489,0.0014286042,0.007229046,0.005883244,0.0042532478,0.0028051948,0.0035873877,0.011070729],"category_scores_gemma":[0.20694631,0.0033083414,0.0009836602,0.008355537,0.0057730004,0.009586797,0.003017909,0.009664314,0.004299847],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013591102,0.000060928196,0.0023351978,0.0077986005,0.00012853641,0.00014992387,0.020124214,0.00035355828,0.00090425933,0.022465331,0.3926066,0.552937],"study_design_scores_gemma":[0.0001760246,0.00019534735,0.018449552,0.029257612,0.0004909665,0.0008805605,0.025342058,0.0006014076,0.0034372155,0.09495451,0.82588863,0.00032607472],"about_ca_topic_score_codex":0.023235042,"about_ca_topic_score_gemma":0.047687285,"teacher_disagreement_score":0.092374586,"about_ca_system_score_codex":0.0037751677,"about_ca_system_score_gemma":0.0092423605,"threshold_uncertainty_score":0.48852932},"labels":[],"label_agreement":null},{"id":"W1746934302","doi":"10.3138/cjpe.0028.012","title":"Evaluator Competencies and Professionalizing the Field: Where Are We Now?","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Professionalization; Globe; Narrative; Field (mathematics); Core competency; Happening; Engineering ethics; Sociology; Epistemology; Pedagogy; Psychology; Management; Engineering; Social science; Linguistics; History; Philosophy","score_opus":0.27667815328718687,"score_gpt":0.51874720227499,"score_spread":0.24206904898780318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1746934302","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13273193,0.010069275,0.036060143,0.65911734,0.0013377384,0.00023449193,0.000043745837,0.00013212457,0.16027324],"genre_scores_gemma":[0.95972544,0.0044664713,0.01088798,0.015589567,0.00016244702,0.00016282717,0.00002146282,0.00005593641,0.008927858],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91874695,0.0641097,0.0014535341,0.001729842,0.008856626,0.0051034433],"domain_scores_gemma":[0.89544225,0.071803115,0.0052871406,0.002248426,0.01613219,0.009086858],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.069949426,0.00035031085,0.00053389504,0.002394117,0.015049399,0.015568249,0.0017264195,0.0040948177,0.005688509],"category_scores_gemma":[0.09058418,0.0003569851,0.00035123847,0.0013773895,0.027085546,0.016864574,0.00983663,0.0096924715,0.00068914803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011023114,0.00021835158,0.016052898,0.00076080963,0.000017996335,0.000840094,0.41133967,0.00043081038,0.00077110843,0.40901792,0.027449135,0.13299097],"study_design_scores_gemma":[0.00003333057,0.00015346779,0.0085536465,0.004259522,0.000022386714,0.00088333985,0.5875081,0.0011526782,0.002219229,0.093020126,0.30205855,0.00013559873],"about_ca_topic_score_codex":0.02247965,"about_ca_topic_score_gemma":0.025146797,"teacher_disagreement_score":0.93005055,"about_ca_system_score_codex":0.018507244,"about_ca_system_score_gemma":0.057305705,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W1747638654","doi":"","title":"Edmonds, W. A., & Kennedy, T. D. (2012). An Applied Reference Guide to Research Designs: Quantitative, Qualitative, and Mixed Methods","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Research Methods and Applications","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Qualitative research; Sociology; Psychology; Social science","score_opus":0.7265469170618565,"score_gpt":0.7150760736578025,"score_spread":0.01147084340405402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1747638654","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077098627,0.08975742,0.72933626,0.06135076,0.007095174,0.03495749,0.007637031,0.0028137257,0.059342314],"genre_scores_gemma":[0.017235318,0.042908527,0.90152186,0.003449559,0.00033179743,0.024719624,0.0011424894,0.00037976896,0.008310972],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8706227,0.085004635,0.019140055,0.0024783546,0.022055075,0.00069917465],"domain_scores_gemma":[0.5725207,0.30355322,0.012513213,0.018080141,0.090691335,0.0026413857],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22325471,0.0019604445,0.0022523017,0.0129326405,0.008001825,0.007182004,0.004772105,0.003251692,0.008819225],"category_scores_gemma":[0.27674198,0.004314549,0.0022610333,0.012387727,0.0070401793,0.008677274,0.0037127924,0.012371514,0.005108567],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029719595,0.00035675778,0.0032671858,0.016935192,0.00030477054,0.0002474659,0.025871418,0.0008235478,0.0038351126,0.04173332,0.25394344,0.65238464],"study_design_scores_gemma":[0.00033778188,0.0007671376,0.015055922,0.046534374,0.00081042026,0.00062499667,0.013618746,0.0015640236,0.007230403,0.075424865,0.8374128,0.00061856647],"about_ca_topic_score_codex":0.028263776,"about_ca_topic_score_gemma":0.06794136,"teacher_disagreement_score":0.22325471,"about_ca_system_score_codex":0.010707246,"about_ca_system_score_gemma":0.03461111,"threshold_uncertainty_score":0.95786524},"labels":[],"label_agreement":null},{"id":"W1752506239","doi":"10.3138/cjpe.29.3.21","title":"Professional Standards for Evaluators: The Development of an Action Plan for the Canadian Evaluation Society","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Action plan; Plan (archaeology); Action (physics); Professional association; Professional standards; Political science; Public relations; Professional development; Medical education; Engineering ethics; Management; Medicine; Engineering; Geography","score_opus":0.710120940519769,"score_gpt":0.6227491034315585,"score_spread":0.0873718370882105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1752506239","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014175293,0.0035570476,0.1721112,0.6701478,0.005939875,0.03408552,0.0006910029,0.0018350317,0.0974572],"genre_scores_gemma":[0.11696151,0.002859354,0.7911143,0.03298633,0.000752738,0.018502101,0.0012178172,0.00048288243,0.03512299],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7225121,0.111921884,0.032732736,0.008431472,0.10291794,0.021483835],"domain_scores_gemma":[0.50268865,0.057601962,0.013999379,0.012796768,0.3511493,0.06176392],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4402716,0.0024166014,0.0021393418,0.016570022,0.031603783,0.023283763,0.011698103,0.019885546,0.005626345],"category_scores_gemma":[0.3117352,0.0027615905,0.0026655304,0.007023881,0.014432346,0.011561456,0.017922169,0.02340722,0.0024810028],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00014050707,0.0013615952,0.011140733,0.001644623,0.000097678254,0.001214815,0.028615093,0.008119894,0.0025000544,0.24614955,0.42951995,0.26949552],"study_design_scores_gemma":[0.00028960523,0.00041431116,0.013786475,0.0069951396,0.000121358025,0.0004805766,0.035659496,0.012608164,0.0023500482,0.08233109,0.8441203,0.0008433617],"about_ca_topic_score_codex":0.4442008,"about_ca_topic_score_gemma":0.5037598,"teacher_disagreement_score":0.8588215,"about_ca_system_score_codex":0.1411785,"about_ca_system_score_gemma":0.61956847,"threshold_uncertainty_score":0.9961112},"labels":[],"label_agreement":null},{"id":"W1754618883","doi":"10.3138/cjpe.31.3.vi","title":"Un mot du rédacteur","year":2017,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Philosophy; Sociology","score_opus":0.5024763693194022,"score_gpt":0.5371872597063074,"score_spread":0.034710890386905224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1754618883","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010162579,0.013225393,0.015372435,0.24289264,0.027544104,0.00022133274,0.00082563964,0.00065145013,0.6891045],"genre_scores_gemma":[0.15057893,0.013554029,0.0200461,0.059939373,0.0097231865,0.0004084148,0.0011179668,0.0009664786,0.74366564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884282,0.004155043,0.0005265702,0.0014559674,0.004540806,0.0008934341],"domain_scores_gemma":[0.9746884,0.0062989234,0.001379552,0.0034555814,0.011597112,0.0025803745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008526459,0.0010082115,0.0006468223,0.0024920662,0.0054607764,0.0110069765,0.002034304,0.00449026,0.06666301],"category_scores_gemma":[0.031135522,0.0004757858,0.00070055155,0.0019669638,0.0052490993,0.010550325,0.0069091986,0.006351317,0.020297961],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121290854,0.000074528914,0.0023809313,0.000655284,0.000018863206,0.00038717728,0.008507319,0.00021916801,0.001275987,0.3840048,0.36548525,0.23686936],"study_design_scores_gemma":[0.000009969271,0.00003810352,0.0012385341,0.00055415434,0.0000088248735,0.0003451813,0.0034779485,0.00014667923,0.0007221051,0.023027245,0.9704056,0.000025724761],"about_ca_topic_score_codex":0.009215246,"about_ca_topic_score_gemma":0.011815436,"teacher_disagreement_score":0.06666301,"about_ca_system_score_codex":0.0075564333,"about_ca_system_score_gemma":0.013999038,"threshold_uncertainty_score":0.22301},"labels":[],"label_agreement":null},{"id":"W1758177958","doi":"10.3138/cjpe.29.3.86","title":"View from the Credentialing Board: Where We've Been and Where We're Going","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Northwest Territories; Barrie Urology Group","funders":"","keywords":"Credentialing; On board; Editorial board; Psychology; Engineering ethics; Medical education; Management; Computer science; Library science; Engineering; Medicine","score_opus":0.4342804105770348,"score_gpt":0.5121123250234277,"score_spread":0.07783191444639292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1758177958","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07170432,0.007813272,0.0069778664,0.8355242,0.0058252905,0.000066621855,0.000073426956,0.00009330282,0.07192166],"genre_scores_gemma":[0.9139628,0.005953522,0.0027057142,0.052865516,0.0009767137,0.000065812994,0.0000595032,0.00010539387,0.023305014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96631205,0.022103315,0.00066091307,0.0011096305,0.006154413,0.0036597294],"domain_scores_gemma":[0.94870263,0.01984015,0.003019486,0.00083699904,0.013575054,0.014025728],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026918475,0.00029835355,0.00047222426,0.0015514038,0.021310441,0.022741016,0.0017757119,0.0063124737,0.009158526],"category_scores_gemma":[0.07494007,0.0003570593,0.0003834643,0.001672266,0.01579057,0.013147633,0.0067191278,0.01832179,0.0009815473],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017131933,0.00020978508,0.012239319,0.0005267311,0.000023618946,0.0022591024,0.30484575,0.0005200055,0.0011435611,0.20109582,0.32549265,0.15147227],"study_design_scores_gemma":[0.00001696064,0.000060537197,0.0041306866,0.0012481721,0.000016574526,0.00048263796,0.40284362,0.0003269531,0.0006302811,0.016141495,0.5739928,0.00010921018],"about_ca_topic_score_codex":0.06173345,"about_ca_topic_score_gemma":0.071804784,"teacher_disagreement_score":0.9794242,"about_ca_system_score_codex":0.020575823,"about_ca_system_score_gemma":0.03856653,"threshold_uncertainty_score":0.14928871},"labels":[],"label_agreement":null},{"id":"W1766534752","doi":"","title":"Bold, C. (2012). Using Narrative in Research. London: Sage Publications Ltd. 200 pages","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Digital Storytelling and Education","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Narrative; Psychology; Art; Literature; Physics","score_opus":0.5369190052135998,"score_gpt":0.5587508773866938,"score_spread":0.021831872173094014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1766534752","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042308713,0.6608771,0.03493245,0.11591068,0.009408565,0.0007996006,0.0045481143,0.0010316247,0.16826102],"genre_scores_gemma":[0.08815398,0.6764584,0.08313839,0.013641715,0.001989975,0.0018391911,0.0031466815,0.00089722755,0.13073447],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959847,0.0017937478,0.0005068514,0.00017780573,0.0014177965,0.000119211916],"domain_scores_gemma":[0.9612732,0.02662825,0.001695596,0.0012128365,0.0076983445,0.0014918058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013210267,0.00082644855,0.0006635421,0.0053623496,0.0044467053,0.0076412084,0.001492023,0.0021789053,0.026341837],"category_scores_gemma":[0.03335027,0.001130172,0.00051173306,0.0048618126,0.0049244286,0.01082148,0.0027890457,0.0046361918,0.01081601],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008134026,0.00003674785,0.0011322142,0.003186359,0.000021085658,0.00015638187,0.011453209,0.0001418065,0.0006560569,0.02220155,0.58732766,0.3736056],"study_design_scores_gemma":[0.000018177234,0.00004823725,0.004271178,0.0096567245,0.0000384626,0.00041172895,0.012855303,0.00010225626,0.0006308106,0.031126617,0.9407864,0.000054137963],"about_ca_topic_score_codex":0.023940599,"about_ca_topic_score_gemma":0.064767905,"teacher_disagreement_score":0.026341837,"about_ca_system_score_codex":0.0030119182,"about_ca_system_score_gemma":0.009276367,"threshold_uncertainty_score":0.08812219},"labels":[],"label_agreement":null},{"id":"W1767493202","doi":"","title":"The 5 Cs for innovating in evaluation: Lessons from the field","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Excellence; Courage; Coaching; Humanities; Political science; Sociology; Management; Art; Economics","score_opus":0.5293170350997406,"score_gpt":0.5948341961710625,"score_spread":0.06551716107132188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1767493202","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011450686,0.052589934,0.07976538,0.7159052,0.004684874,0.00078324915,0.000084413776,0.00033380376,0.13440254],"genre_scores_gemma":[0.5554774,0.06102008,0.25556687,0.092682526,0.0042288983,0.0026629504,0.00015222872,0.00068880356,0.027520237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.84899646,0.11486975,0.005320712,0.0052025905,0.019800391,0.0058100563],"domain_scores_gemma":[0.7347842,0.19532247,0.0044332803,0.017357754,0.02895039,0.019151898],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17177688,0.0013209607,0.001508871,0.0066332626,0.012116996,0.026067652,0.0050308285,0.011878867,0.007939601],"category_scores_gemma":[0.120643765,0.0011026022,0.002210341,0.0044953185,0.077727206,0.024281835,0.019665167,0.017543525,0.001449881],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011658084,0.00021100021,0.0033675013,0.001670106,0.00006137394,0.00037292423,0.018234847,0.0012302035,0.00025166242,0.7355946,0.035272427,0.20361677],"study_design_scores_gemma":[0.00015403215,0.00023867263,0.004105805,0.0060842396,0.000053143725,0.00050195196,0.020590749,0.0028288125,0.00074618397,0.61391544,0.3505907,0.0001903021],"about_ca_topic_score_codex":0.06128724,"about_ca_topic_score_gemma":0.07917738,"teacher_disagreement_score":0.8282231,"about_ca_system_score_codex":0.05567558,"about_ca_system_score_gemma":0.12891887,"threshold_uncertainty_score":0.9084538},"labels":[],"label_agreement":null},{"id":"W1769680758","doi":"10.3138/cjpe.29.3.70","title":"Launching the Credentialed Evaluator (CE) Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Credentialing; Credibility; Process (computing); Stakeholder; Corporate governance; Politics; Political science; Public relations; Business; Engineering ethics; Public administration; Process management; Management; Engineering management; Law; Computer science; Engineering; Economics","score_opus":0.6094119450625466,"score_gpt":0.5671337020641761,"score_spread":0.04227824299837046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769680758","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07783029,0.0019248136,0.18011239,0.2720184,0.0077676144,0.01133818,0.00061256386,0.00289837,0.4454974],"genre_scores_gemma":[0.6240654,0.001215156,0.19584182,0.03228668,0.0009940565,0.003721082,0.00059137936,0.00071132754,0.14057308],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92499924,0.03990038,0.002768872,0.003022543,0.021907317,0.0074017146],"domain_scores_gemma":[0.80165523,0.03498592,0.0054776003,0.015390557,0.10587055,0.036620162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13149898,0.000490199,0.00054052914,0.0020882525,0.010227274,0.008753784,0.003591133,0.0029936244,0.01698925],"category_scores_gemma":[0.13267255,0.0004542421,0.00055922806,0.0009973025,0.0064186654,0.00453439,0.008561601,0.005893633,0.0037364673],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035021713,0.0012423145,0.015019411,0.00065231795,0.000040205716,0.00035111135,0.015274529,0.0017421816,0.002944021,0.11190782,0.34103945,0.5094364],"study_design_scores_gemma":[0.00018285247,0.00046554994,0.012689645,0.0009776552,0.000024415602,0.0001915994,0.00974568,0.0029500523,0.0042680767,0.021912863,0.94641423,0.00017724917],"about_ca_topic_score_codex":0.12828825,"about_ca_topic_score_gemma":0.22944479,"teacher_disagreement_score":0.9696437,"about_ca_system_score_codex":0.030356284,"about_ca_system_score_gemma":0.15302773,"threshold_uncertainty_score":0.69544137},"labels":[],"label_agreement":null},{"id":"W1769901993","doi":"10.3138/cjpe.29.3.33","title":"A Made-in-Canada Credential: Developing an Evaluation Professional Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credential; Context (archaeology); Public relations; Political science; Process (computing); Service (business); Credentialing; Sociology; Business; Law; Marketing; Geography; Computer science","score_opus":0.6273699174603828,"score_gpt":0.566949663297369,"score_spread":0.06042025416301389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769901993","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07961618,0.0033563501,0.18876052,0.38560024,0.0076488364,0.005264607,0.0005903177,0.0010069156,0.3281561],"genre_scores_gemma":[0.6231597,0.0016716989,0.26460937,0.022722758,0.0003394873,0.001461197,0.0004062864,0.0003475082,0.08528207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9289115,0.029905304,0.0040446483,0.0029417991,0.02719827,0.0069984165],"domain_scores_gemma":[0.88072926,0.017012928,0.0028671157,0.004883267,0.06566792,0.028839523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07909906,0.00054501294,0.0006330841,0.003957856,0.028821012,0.023976145,0.0037216377,0.0060484246,0.0061594187],"category_scores_gemma":[0.09960065,0.0007329146,0.00055876555,0.0027175313,0.021485249,0.007522305,0.013003032,0.009398586,0.0016661992],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011217682,0.00032134695,0.011398854,0.00047248392,0.000022575752,0.000818499,0.058035433,0.001784192,0.0015756907,0.54061997,0.18370771,0.20113106],"study_design_scores_gemma":[0.0000444678,0.00011118789,0.005701636,0.0014146629,0.000024286768,0.0003264412,0.039568592,0.003368593,0.0021957732,0.03769574,0.9093225,0.00022610412],"about_ca_topic_score_codex":0.64133954,"about_ca_topic_score_gemma":0.8198354,"teacher_disagreement_score":0.88221014,"about_ca_system_score_codex":0.11778988,"about_ca_system_score_gemma":0.40991592,"threshold_uncertainty_score":0.8546294},"labels":[],"label_agreement":null},{"id":"W1773568500","doi":"10.3138/cjpe.0028.007","title":"Evaluator Competencies: The Aotearoa New Zealand Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Credentialing; Underpinning; Pedagogy; Set (abstract data type); Engineering ethics; Cultural competence; Sociology; Psychology; Medical education; Engineering; Computer science; Medicine; Gender studies","score_opus":0.27326673436579285,"score_gpt":0.4978504535242318,"score_spread":0.22458371915843894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1773568500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81441903,0.0034053605,0.0022664198,0.05767208,0.0007281904,0.00088764436,0.00018655571,0.00006431926,0.120370455],"genre_scores_gemma":[0.9260659,0.0057114013,0.0058558495,0.0068453173,0.000110581735,0.00063379935,0.0001280816,0.00012014357,0.054528907],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9900857,0.0043047983,0.00044184012,0.00062969176,0.002871167,0.001666763],"domain_scores_gemma":[0.97889555,0.0042581395,0.0012046574,0.000918322,0.005644283,0.009079137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02505977,0.00031601515,0.0004793534,0.0008065654,0.008559217,0.0045201443,0.0011018914,0.0016401941,0.0069710044],"category_scores_gemma":[0.022307059,0.0005403452,0.00036217048,0.0013066013,0.0059808604,0.0037425978,0.007409636,0.004522505,0.0005019557],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008128946,0.0024793728,0.06485031,0.0012805609,0.00007002919,0.005088117,0.6245288,0.00063081714,0.0044827745,0.025179023,0.056024347,0.21457294],"study_design_scores_gemma":[0.00017733857,0.001252332,0.09953109,0.0017278348,0.000051316892,0.0020859602,0.33324662,0.00062683184,0.0012925585,0.0032243994,0.556626,0.0001576566],"about_ca_topic_score_codex":0.407992,"about_ca_topic_score_gemma":0.766743,"teacher_disagreement_score":0.407992,"about_ca_system_score_codex":0.021825299,"about_ca_system_score_gemma":0.07818974,"threshold_uncertainty_score":0.8112345},"labels":[],"label_agreement":null},{"id":"W1776761859","doi":"","title":"Aldrick, J. O., & Rodriguez, H. M. (2013). Building SPSS Graphs to Understand Data","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics","score_opus":0.17716966082276855,"score_gpt":0.3747928407452575,"score_spread":0.19762317992248893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1776761859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029821035,0.006272926,0.89860153,0.01813833,0.0011543304,0.0010737039,0.010232938,0.009591249,0.025113925],"genre_scores_gemma":[0.0920774,0.0053452174,0.8872561,0.0013760369,0.00028894606,0.00071727706,0.004282008,0.0016769789,0.006980143],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99608624,0.0016123381,0.00042022744,0.00037016603,0.0014227673,0.000088204404],"domain_scores_gemma":[0.83774835,0.13615213,0.0051652323,0.006454943,0.013453463,0.0010258786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01373376,0.00093805214,0.00060520583,0.0075917267,0.0015991194,0.004672045,0.0012674067,0.00075346266,0.011227095],"category_scores_gemma":[0.13772383,0.0009809827,0.0010926547,0.0053244773,0.001982964,0.0053108297,0.0015162887,0.0037008775,0.0037938573],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040015197,0.00017895151,0.028647635,0.002122909,0.00032235673,0.00029435457,0.0068491567,0.0043155192,0.0048797163,0.056459364,0.16855507,0.72697484],"study_design_scores_gemma":[0.00025414443,0.0004478267,0.057548434,0.0026890214,0.001248708,0.0009845557,0.0074616186,0.03327293,0.012170333,0.36286736,0.5206197,0.00043536726],"about_ca_topic_score_codex":0.010637416,"about_ca_topic_score_gemma":0.023753526,"teacher_disagreement_score":0.01373376,"about_ca_system_score_codex":0.0010911818,"about_ca_system_score_gemma":0.0033978783,"threshold_uncertainty_score":0.072631955},"labels":[],"label_agreement":null},{"id":"W1782129283","doi":"","title":"ARTICLE 5: DISSEMINATION AND EARLY USE OF THE PARIS DECLARATION EVALUATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Champion; Declaration; Transparency (behavior); Stakeholder; Corporate governance; Politics; Stakeholder engagement; Public relations; Political science; Evaluation methods; Process management; Business; Management science; Engineering; Law","score_opus":0.4613107564983002,"score_gpt":0.5371820478652425,"score_spread":0.07587129136694226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1782129283","genre_codex":"other","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027617028,0.0053425585,0.20337304,0.18857095,0.020609198,0.11091623,0.008616119,0.0046718363,0.4302831],"genre_scores_gemma":[0.3855363,0.0034833823,0.25422266,0.04197252,0.0028401387,0.1969312,0.0041352813,0.002115181,0.10876333],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.39431658,0.46706507,0.0379694,0.0092420485,0.08178119,0.009625676],"domain_scores_gemma":[0.2712191,0.45666862,0.014787382,0.09910736,0.14846985,0.009747606],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.52277935,0.0011049544,0.0015895338,0.009023038,0.0065883356,0.019773187,0.0038510696,0.0063241827,0.027866561],"category_scores_gemma":[0.70893776,0.001736277,0.0015507378,0.005831158,0.011018043,0.009962135,0.014114736,0.008255595,0.005677739],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080109347,0.00046172828,0.0026875797,0.005197686,0.00014474367,0.00048022723,0.07725885,0.001392056,0.0015992345,0.17747888,0.3432836,0.38921437],"study_design_scores_gemma":[0.0004066849,0.00041902822,0.006263347,0.009828952,0.000070561735,0.00010903965,0.01647762,0.0011335913,0.0039003326,0.033465162,0.92763346,0.000292187],"about_ca_topic_score_codex":0.013465184,"about_ca_topic_score_gemma":0.013739316,"teacher_disagreement_score":0.52277935,"about_ca_system_score_codex":0.028209245,"about_ca_system_score_gemma":0.1018779,"threshold_uncertainty_score":0.58849806},"labels":[],"label_agreement":null},{"id":"W1782687918","doi":"10.3138/cjpe.027.001","title":"L’évaluateur éthiquement engagé: sur le sens et la pertinence d’un nouveau référentiel","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Meaning (existential); Commit; Neutrality; Subject (documents); Sociology; Epistemology; Psychology; Social psychology; Philosophy; Library science","score_opus":0.32017871900978256,"score_gpt":0.4955612199298118,"score_spread":0.17538250092002922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1782687918","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24846151,0.016802201,0.12499471,0.14936428,0.0022551033,0.0003883398,0.00008416253,0.0002517841,0.45739794],"genre_scores_gemma":[0.9771706,0.0013644884,0.009196215,0.0028486683,0.00022377212,0.00022094605,0.000018551245,0.0000716056,0.00888516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.83487296,0.1267893,0.0030034448,0.0037604421,0.028893901,0.0026799487],"domain_scores_gemma":[0.8262708,0.11849468,0.011718093,0.0071323747,0.03223363,0.004150433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09235724,0.00063959573,0.0007005589,0.0038134288,0.009251542,0.020653231,0.00208896,0.0058409744,0.005186912],"category_scores_gemma":[0.19924481,0.00049792655,0.0005805267,0.0024675452,0.027454881,0.012555398,0.009754921,0.0061220755,0.0007159035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028050758,0.00015912863,0.009232936,0.00057342526,0.00009183189,0.00064617075,0.13105834,0.0007400691,0.0015015176,0.75237054,0.007896001,0.095449485],"study_design_scores_gemma":[0.00019417796,0.00056104374,0.022416957,0.0054285135,0.00021271475,0.001588085,0.194404,0.0043164073,0.009192783,0.33835554,0.42306674,0.00026304793],"about_ca_topic_score_codex":0.012969678,"about_ca_topic_score_gemma":0.011325116,"teacher_disagreement_score":0.09235724,"about_ca_system_score_codex":0.0138099175,"about_ca_system_score_gemma":0.016879711,"threshold_uncertainty_score":0.4884376},"labels":[],"label_agreement":null},{"id":"W1788049718","doi":"10.3138/cjpe.29.3.54","title":"The Development and Initial Validation of Competencies and Descriptors for Canadian Evaluation Practice","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Barrie Urology Group","funders":"","keywords":"Psychology; Medical education; Computer science; Medicine","score_opus":0.5926820838299982,"score_gpt":0.5503943550828988,"score_spread":0.04228772874709941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1788049718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6403252,0.0033701966,0.15561184,0.02165411,0.0011488715,0.02328437,0.0030504984,0.0007760565,0.15077877],"genre_scores_gemma":[0.72334296,0.0015617866,0.2565323,0.00071304885,0.0000327281,0.0076220986,0.0021616055,0.00015116805,0.00788219],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.94477475,0.027074726,0.0050019985,0.0016857685,0.018489456,0.0029733244],"domain_scores_gemma":[0.8274106,0.031284716,0.0052284026,0.00840042,0.12154295,0.006132863],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09585789,0.0006448261,0.00061624753,0.0060374727,0.008010888,0.0058606747,0.0027948963,0.0009252451,0.0019131928],"category_scores_gemma":[0.15840276,0.0005146367,0.0007657913,0.0052374154,0.0041568475,0.0030818882,0.0065061185,0.0029719593,0.00043121944],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031177117,0.0009550885,0.090164654,0.0023604007,0.000063115964,0.0004313498,0.09642905,0.0036139318,0.006215713,0.06746478,0.02868323,0.703307],"study_design_scores_gemma":[0.00026292572,0.001176092,0.35496426,0.009158081,0.00018347788,0.0006637329,0.1910714,0.016963126,0.021776823,0.018803453,0.38452974,0.00044693574],"about_ca_topic_score_codex":0.63418305,"about_ca_topic_score_gemma":0.7605325,"teacher_disagreement_score":0.91959906,"about_ca_system_score_codex":0.08040093,"about_ca_system_score_gemma":0.22695234,"threshold_uncertainty_score":0.7359426},"labels":[],"label_agreement":null},{"id":"W1790388803","doi":"","title":"Hurteau, M., Houle, S., & Guillemette, F. (Éds.). (2012). L’évaluation de programme axée sur le jugement crédible. Québec, QC : Presses de l’Université du Québec, 200 pages","year":2013,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Physics; Mathematical physics; Economics; Accounting","score_opus":0.1689980442060935,"score_gpt":0.37409090493899916,"score_spread":0.20509286073290567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1790388803","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018843682,0.9572105,0.0052482695,0.013087183,0.0014952247,0.00008659847,0.0010560685,0.00016120708,0.019770535],"genre_scores_gemma":[0.021652434,0.9436602,0.010342465,0.00058982236,0.0005064151,0.00007030659,0.0008516307,0.000095049356,0.022231732],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961343,0.0007421609,0.00021897223,0.00018821275,0.0024622704,0.0002541574],"domain_scores_gemma":[0.9903729,0.0041682078,0.0006186475,0.0002457546,0.003927981,0.00066645344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008784156,0.0022781054,0.0019681137,0.009485516,0.0023889348,0.0075911344,0.002758227,0.002346509,0.024664609],"category_scores_gemma":[0.009142931,0.0014886389,0.0011986975,0.012438707,0.0030772022,0.0038978504,0.0012808345,0.0032081858,0.008002286],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011065465,0.00006697771,0.0040335855,0.004313645,0.000113929884,0.00010180325,0.0015527161,0.0013598423,0.0004941022,0.0055362983,0.2661968,0.7161197],"study_design_scores_gemma":[0.00005046378,0.00013455942,0.029645849,0.011078298,0.00030978004,0.00051804725,0.0024856133,0.0013800319,0.0015545969,0.0067194845,0.9459822,0.00014116049],"about_ca_topic_score_codex":0.74218154,"about_ca_topic_score_gemma":0.8409395,"teacher_disagreement_score":0.74218154,"about_ca_system_score_codex":0.026636332,"about_ca_system_score_gemma":0.04088175,"threshold_uncertainty_score":0.5186736},"labels":[],"label_agreement":null},{"id":"W1793639688","doi":"","title":"Ryan, K. E., & Cousins, J. B. (Eds.). (2009). The Sage International Handbook of Educational Evaluation. Thousand Oaks, CA: Sage. 608 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Sociology; Library science; Psychology; Computer science; Physics","score_opus":0.17227601125528205,"score_gpt":0.4771476743022029,"score_spread":0.3048716630469208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1793639688","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016572651,0.9258606,0.013852219,0.013252471,0.003614041,0.00017459237,0.0023605195,0.0007740554,0.038454212],"genre_scores_gemma":[0.0074897553,0.9446622,0.01721857,0.00081804575,0.0008129695,0.00016016276,0.0011506825,0.00022028576,0.027467374],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736387,0.000560743,0.00039376062,0.00017982497,0.0013939711,0.00010780823],"domain_scores_gemma":[0.9903717,0.0048852297,0.00088533125,0.00039977304,0.0029700832,0.00048785142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006072469,0.002081115,0.0017833725,0.0048185457,0.0012855618,0.004193573,0.001822502,0.0018146788,0.026218195],"category_scores_gemma":[0.012013767,0.0018568442,0.0012064489,0.004977124,0.0016241211,0.0053409203,0.0012908513,0.003787438,0.029767418],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077148106,0.000059868114,0.0011330692,0.002356275,0.000041009596,0.00008099807,0.0006468698,0.00038197057,0.00039114826,0.0018948999,0.34167162,0.65126514],"study_design_scores_gemma":[0.00003993134,0.00017563725,0.009114374,0.009238119,0.00018709009,0.0013508025,0.0011992868,0.00030756675,0.0012306992,0.010261327,0.9667705,0.00012459594],"about_ca_topic_score_codex":0.023160195,"about_ca_topic_score_gemma":0.049668513,"teacher_disagreement_score":0.026218195,"about_ca_system_score_codex":0.0016525106,"about_ca_system_score_gemma":0.0065376265,"threshold_uncertainty_score":0.08770865},"labels":[],"label_agreement":null},{"id":"W1800600860","doi":"","title":"Remarques introductives de l'éditeur","year":2012,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Reproductive Health and Technologies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.14617695522208848,"score_gpt":0.4382814795352628,"score_spread":0.29210452431317435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1800600860","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008756293,0.018795768,0.0016693176,0.102924116,0.8693681,0.000041380066,0.00023599483,0.00026736618,0.005822356],"genre_scores_gemma":[0.01405648,0.020217735,0.002807668,0.106578514,0.7941374,0.0003441239,0.00039895627,0.00039617068,0.061062958],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99455535,0.0017185839,0.0009209305,0.00070269976,0.0017255843,0.00037680485],"domain_scores_gemma":[0.9687982,0.013479489,0.0025243363,0.0014654106,0.012086151,0.0016463929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049635735,0.001536937,0.0011981694,0.0028508569,0.0017898269,0.0035733907,0.0019459021,0.0044968575,0.01520175],"category_scores_gemma":[0.0389902,0.00050052814,0.0011912289,0.00095568324,0.0016913627,0.0022617015,0.0021123015,0.005869878,0.0067143943],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007573402,0.000028696992,0.0004195765,0.0006071409,0.000031295804,0.0006208416,0.00015869498,0.000083419196,0.00031923733,0.0018869818,0.9553923,0.040376157],"study_design_scores_gemma":[0.000021284957,0.000038534286,0.0012667453,0.0003929948,0.00002614377,0.0013075008,0.000071963244,0.00013327009,0.00032058987,0.00052026106,0.99587655,0.000024154995],"about_ca_topic_score_codex":0.006821867,"about_ca_topic_score_gemma":0.008224647,"teacher_disagreement_score":0.01520175,"about_ca_system_score_codex":0.002757014,"about_ca_system_score_gemma":0.0028041694,"threshold_uncertainty_score":0.05085492},"labels":[],"label_agreement":null},{"id":"W1826075361","doi":"10.3138/cjpe.22.007","title":"Participatory Impact Pathways Analysis: A Practical Application of Program Theory in Research-for-Development","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Logic model; Citizen journalism; Food security; Computer science; Poverty; Narrative; Theory of change; Management science; Knowledge management; Process management; Sociology; Business; Engineering; Economics; Economic growth; Social science","score_opus":0.815960147008348,"score_gpt":0.6979548155552535,"score_spread":0.11800533145309444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1826075361","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009603402,0.00012563184,0.9651693,0.0031456675,0.00006421066,0.0017389795,0.00034409686,0.0003303292,0.019478373],"genre_scores_gemma":[0.16202195,0.00018851968,0.8325685,0.00014128577,0.00001499952,0.002919939,0.00022580998,0.00007640878,0.0018425725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95645326,0.038123462,0.0009957644,0.001366571,0.0024573095,0.0006035994],"domain_scores_gemma":[0.925275,0.061666597,0.0023027016,0.005291001,0.004701562,0.0007631269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054440565,0.0014133105,0.0009123429,0.0076001524,0.0057928897,0.0081824865,0.002828105,0.0020424265,0.013523038],"category_scores_gemma":[0.07623443,0.0008961734,0.001643293,0.008722563,0.008116969,0.012006003,0.0077963704,0.0026444194,0.0008681473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009988418,0.00019928001,0.0029698014,0.00088785856,0.000109909386,0.0004323146,0.0193293,0.025159553,0.0004455977,0.7879646,0.003943196,0.15845865],"study_design_scores_gemma":[0.000087321016,0.00012219572,0.00056796405,0.0006397751,0.00006245517,0.00022947382,0.01450076,0.055770207,0.0009986577,0.8849876,0.041978464,0.00005514315],"about_ca_topic_score_codex":0.00625913,"about_ca_topic_score_gemma":0.0070403153,"teacher_disagreement_score":0.054440565,"about_ca_system_score_codex":0.008496668,"about_ca_system_score_gemma":0.015018697,"threshold_uncertainty_score":0.28791273},"labels":[],"label_agreement":null},{"id":"W1836020270","doi":"","title":"ARTICLE 2: PREPARING, GOVERNING AND MANAGING THE PARIS DECLARATION EVALUATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credibility; Declaration; Stakeholder; Corporate governance; Joint (building); Process management; Stakeholder engagement; Quality (philosophy); Business; Public relations; Political science; Environmental resource management; Economics; Engineering; Law","score_opus":0.37383956162570414,"score_gpt":0.523925339424259,"score_spread":0.15008577779855486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1836020270","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06429817,0.004162093,0.12859733,0.11487432,0.007820316,0.029575098,0.0015346695,0.0027559702,0.64638203],"genre_scores_gemma":[0.42637864,0.0029151805,0.2535019,0.01824799,0.0019543758,0.015698815,0.0016929253,0.0015499782,0.27806023],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8717411,0.074409515,0.0071267383,0.0047641173,0.032296095,0.00966236],"domain_scores_gemma":[0.86963356,0.05012761,0.006437728,0.008299097,0.05456323,0.010938789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13529487,0.0007694616,0.0006048417,0.0052247383,0.011265043,0.025154244,0.0029679462,0.004597332,0.014082324],"category_scores_gemma":[0.1381194,0.0008591937,0.0006986607,0.003286252,0.009395425,0.007107518,0.0068075927,0.0057117646,0.0042020623],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019936779,0.0003863756,0.0075204843,0.0008744123,0.00006329324,0.0011534942,0.04975866,0.005724998,0.002297523,0.23147018,0.3922868,0.3082644],"study_design_scores_gemma":[0.00007177012,0.00016689871,0.00681316,0.0012686871,0.000031788597,0.00017510078,0.021777298,0.0014134897,0.0032258618,0.020504372,0.9442981,0.00025346485],"about_ca_topic_score_codex":0.056934524,"about_ca_topic_score_gemma":0.091273695,"teacher_disagreement_score":0.13529487,"about_ca_system_score_codex":0.045251403,"about_ca_system_score_gemma":0.122708485,"threshold_uncertainty_score":0.7155162},"labels":[],"label_agreement":null},{"id":"W183745815","doi":"10.3138/cjpe.0023.006","title":"Participatory Evaluation as Seen in a Vygotskian Framework","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interview; Categorization; Psychology; Citizen journalism; Participatory evaluation; Coding (social sciences); Medical education; Pedagogy; Applied psychology; Computer science; Sociology; Medicine","score_opus":0.567309139198488,"score_gpt":0.6135182252392328,"score_spread":0.04620908604074481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W183745815","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088965625,0.0029750399,0.6038945,0.029786926,0.00027936205,0.0044391383,0.00010730229,0.00020281984,0.26934934],"genre_scores_gemma":[0.8633994,0.00042958785,0.1296843,0.00068535004,0.000046817466,0.0029395842,0.000029141518,0.00003777841,0.0027480226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6540979,0.30948108,0.0068262736,0.00694591,0.017787913,0.0048608375],"domain_scores_gemma":[0.8629884,0.09978261,0.008966747,0.008466688,0.016216477,0.003579053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16111016,0.0013803185,0.0014151353,0.009543944,0.0138736395,0.017901342,0.0036451553,0.00357075,0.0028369776],"category_scores_gemma":[0.088980414,0.0010945814,0.0012801412,0.0053198575,0.07171173,0.0139137525,0.013534754,0.004582234,0.00029750087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046231562,0.00006229591,0.0013362692,0.00038598073,0.000047621477,0.00018328427,0.04369849,0.0024139492,0.0002878013,0.93430966,0.0007628554,0.016465502],"study_design_scores_gemma":[0.00011085106,0.00015201318,0.0014177451,0.0011858958,0.000046229212,0.00021892799,0.031699527,0.010525544,0.0006211898,0.9107194,0.043216176,0.00008642612],"about_ca_topic_score_codex":0.010864205,"about_ca_topic_score_gemma":0.009754018,"teacher_disagreement_score":0.16111016,"about_ca_system_score_codex":0.03071565,"about_ca_system_score_gemma":0.037339725,"threshold_uncertainty_score":0.8520422},"labels":[],"label_agreement":null},{"id":"W1841863553","doi":"","title":"ARTICLE 3: THE PARIS DECLARATION EVALUATION PROCESS AND METHODS","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Process (computing); Engineering ethics; Corporate governance; Process management; Perspective (graphical); Quality (philosophy); Management science; Political science; Computer science; Business; Engineering; Epistemology; Law","score_opus":0.516238008344546,"score_gpt":0.625758530785327,"score_spread":0.10952052244078092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1841863553","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018616492,0.0032259903,0.30290613,0.022728382,0.004414922,0.30606058,0.009207603,0.0016127836,0.3312271],"genre_scores_gemma":[0.07456951,0.0012552039,0.36492804,0.009042697,0.00072023744,0.46168166,0.003467372,0.000882631,0.08345266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.76147383,0.16794562,0.01958707,0.010731098,0.033166025,0.0070963716],"domain_scores_gemma":[0.8373322,0.08039025,0.0062169507,0.021802599,0.04950298,0.0047550015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21125619,0.0014124628,0.0012849487,0.008915477,0.0079875635,0.014033629,0.0040261517,0.005629785,0.039840125],"category_scores_gemma":[0.18358745,0.0018178187,0.0015909675,0.0062695337,0.010006091,0.0045866254,0.007607619,0.006319597,0.00983768],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00099103,0.00069615076,0.0037754788,0.0034381389,0.00007490263,0.0006961325,0.04615064,0.0036089006,0.0025562765,0.49616715,0.15868172,0.28316346],"study_design_scores_gemma":[0.00029784875,0.00023808594,0.0033330482,0.0036573869,0.00003056639,0.00012628849,0.0070167235,0.0013806052,0.0029431514,0.031350918,0.949466,0.00015936053],"about_ca_topic_score_codex":0.014408849,"about_ca_topic_score_gemma":0.020149633,"teacher_disagreement_score":0.21125619,"about_ca_system_score_codex":0.023361325,"about_ca_system_score_gemma":0.07817187,"threshold_uncertainty_score":0.97266155},"labels":[],"label_agreement":null},{"id":"W1842305377","doi":"","title":"ARTICLE 4: RESULTS OF THE PARIS DECLARATION EVALUATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"International Development and Aid","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Variety (cybernetics); Aid effectiveness; Relevance (law); Development aid; Developing country; Political science; Economic growth; Public relations; Business; Public administration; Computer science; Economics; Law","score_opus":0.18664274145437315,"score_gpt":0.4224035792042196,"score_spread":0.23576083774984646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1842305377","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39256313,0.008568179,0.016650274,0.016437616,0.002140197,0.050376453,0.063842595,0.0013488343,0.44807267],"genre_scores_gemma":[0.8085284,0.0035731054,0.033079024,0.0050946483,0.00044094896,0.053009555,0.020530604,0.00088988343,0.074853845],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7147913,0.21408193,0.014740918,0.005595632,0.045234274,0.005555847],"domain_scores_gemma":[0.5660306,0.28149933,0.014474049,0.013121482,0.12136547,0.0035090342],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20181246,0.0016588302,0.0023765485,0.01401182,0.003881828,0.011722571,0.0023182936,0.0029432662,0.032897267],"category_scores_gemma":[0.37040663,0.0009832728,0.002859634,0.010666174,0.0034173783,0.0059864786,0.0062943827,0.0022181387,0.005736102],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01873562,0.004068832,0.061097432,0.01757512,0.0028160815,0.00070407806,0.09550633,0.008257182,0.0017499895,0.026177345,0.15152493,0.611787],"study_design_scores_gemma":[0.0028248045,0.008707925,0.21924967,0.017880248,0.004037869,0.0003203813,0.14471827,0.004182314,0.01796653,0.017446373,0.5616815,0.0009841832],"about_ca_topic_score_codex":0.017929288,"about_ca_topic_score_gemma":0.014123092,"teacher_disagreement_score":0.20181246,"about_ca_system_score_codex":0.024252366,"about_ca_system_score_gemma":0.022025948,"threshold_uncertainty_score":0.98430735},"labels":[],"label_agreement":null},{"id":"W1845568876","doi":"10.3138/cjpe.028.003","title":"Using the Results of Economic Evaluations of Public Health Interventions: Challenges and Proposals","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Hôpital Charles-Le Moyne; Université de Sherbrooke; Université du Québec en Outaouais","funders":"","keywords":"Transferability; Psychological intervention; Public health interventions; Context (archaeology); Recession; Public health; Public economics; Economic evaluation; Quality (philosophy); Health care; Business; Public relations; Economics; Political science; Economic growth; Medicine; Nursing; Microeconomics","score_opus":0.7999877621921118,"score_gpt":0.5466317301386421,"score_spread":0.2533560320534697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1845568876","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015210284,0.03948534,0.19389708,0.6873309,0.0061737215,0.0014552893,0.0007368264,0.00026323632,0.055447306],"genre_scores_gemma":[0.71891034,0.01889527,0.19656001,0.05078139,0.006762688,0.0046243155,0.0003207657,0.0002997588,0.0028455164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.1385007,0.79674,0.018868934,0.0058695218,0.037764113,0.0022566547],"domain_scores_gemma":[0.050269514,0.8608325,0.0213696,0.03191538,0.03439286,0.0012201383],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.7600146,0.003975792,0.009055817,0.014510389,0.0042517637,0.038796928,0.0108923,0.01804391,0.0047378438],"category_scores_gemma":[0.86927515,0.0020095464,0.007012815,0.011667309,0.05166567,0.04930441,0.015895445,0.01846639,0.0009126937],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011110386,0.00039267933,0.0068951417,0.004229325,0.0022574249,0.0002729564,0.0037231725,0.011196009,0.00014243144,0.8107819,0.014452672,0.1445453],"study_design_scores_gemma":[0.00059137435,0.000401386,0.0015722889,0.013219813,0.0007887183,0.00014501126,0.002743227,0.0128124645,0.00087708316,0.94189644,0.02466281,0.0002894352],"about_ca_topic_score_codex":0.005793632,"about_ca_topic_score_gemma":0.0026694504,"teacher_disagreement_score":0.7600146,"about_ca_system_score_codex":0.016284456,"about_ca_system_score_gemma":0.028857347,"threshold_uncertainty_score":0.2959448},"labels":[],"label_agreement":null},{"id":"W1865612267","doi":"10.3138/cjpe.30.1.1","title":"From New Public Management to New Political Governance: Implications for Evaluation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bureaucracy; Public administration; Politics; Corporate governance; Institution; Context (archaeology); Political science; New public management; Public service; Democracy; Power (physics); Public management; Public relations; Economics; Public sector; Management; Law","score_opus":0.627667754868374,"score_gpt":0.5924472023472562,"score_spread":0.035220552521117776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1865612267","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013221022,0.02423316,0.025207622,0.84643203,0.0015307867,0.0005108633,0.00018834764,0.00011045155,0.08856562],"genre_scores_gemma":[0.9040061,0.010433951,0.028408146,0.05015198,0.0019892114,0.0012034995,0.000093011105,0.000082931416,0.0036310994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76236254,0.20777202,0.005922934,0.0034698022,0.01545994,0.005012767],"domain_scores_gemma":[0.3828835,0.5139675,0.014001489,0.013901461,0.05791227,0.017333727],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22009215,0.00085848174,0.0020982418,0.0051627746,0.009052132,0.029843837,0.004411399,0.007185534,0.013881078],"category_scores_gemma":[0.45212457,0.000506424,0.0009961278,0.006713599,0.05195165,0.032532357,0.010483689,0.009991826,0.0005924202],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002912541,0.00023434886,0.0069262492,0.0015067478,0.000053558564,0.00021368374,0.006108064,0.0016678988,0.00007431524,0.838269,0.026351603,0.11830342],"study_design_scores_gemma":[0.00016208149,0.00014383554,0.005118966,0.006967688,0.000086251915,0.0001326381,0.024100663,0.004333544,0.0003679164,0.8894744,0.06900509,0.0001068739],"about_ca_topic_score_codex":0.06002547,"about_ca_topic_score_gemma":0.062499866,"teacher_disagreement_score":0.22009215,"about_ca_system_score_codex":0.052256547,"about_ca_system_score_gemma":0.0799727,"threshold_uncertainty_score":0.9617652},"labels":[],"label_agreement":null},{"id":"W1874375828","doi":"10.3138/cjpe.29.3.x","title":"Introduction à la professionnalisation de l’évaluation au Canada","year":2015,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.34891936041679567,"score_gpt":0.5163978479684853,"score_spread":0.16747848755168965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1874375828","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021272855,0.06980778,0.025388991,0.34533104,0.008468244,0.0006425577,0.0020215071,0.0007734975,0.52629346],"genre_scores_gemma":[0.42039376,0.071833275,0.038522817,0.059107006,0.0031176286,0.0006186501,0.0013441639,0.0007373781,0.40432537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9693224,0.005007011,0.0012343263,0.002638843,0.017806632,0.0039907936],"domain_scores_gemma":[0.9480308,0.0062426683,0.0014745052,0.0015191826,0.037221454,0.0055114394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015055627,0.0006015971,0.00062583503,0.0051141223,0.011269187,0.015261536,0.0023237064,0.0040806374,0.022148054],"category_scores_gemma":[0.029305652,0.0006260453,0.0007196513,0.008130171,0.013004415,0.003037942,0.004153383,0.0060137114,0.002297268],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000118258184,0.000105317115,0.006733636,0.0014003344,0.00003529552,0.00038678525,0.010034367,0.0011940607,0.0014509021,0.41491398,0.29331183,0.27031532],"study_design_scores_gemma":[0.000013530372,0.000025881907,0.014204708,0.0016898197,0.000014322779,0.00013425916,0.00320021,0.0004790668,0.0004416393,0.008888154,0.9708407,0.00006760194],"about_ca_topic_score_codex":0.96441555,"about_ca_topic_score_gemma":0.97220224,"teacher_disagreement_score":0.8305526,"about_ca_system_score_codex":0.1694474,"about_ca_system_score_gemma":0.3081291,"threshold_uncertainty_score":0.9633233},"labels":[],"label_agreement":null},{"id":"W18830643","doi":"10.3138/cjpe.026.001","title":"Advancing Empirical Scholarship to Further Develop Evaluation Theory and Practice","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Grounded theory; Context (archaeology); Development theory; Field (mathematics); Empirical research; Contingency; Epistemology; Sociology; Intersection (aeronautics); Contingency theory; Management science; Engineering ethics; Qualitative research; Knowledge management; Computer science; Social science; Political science; Economics","score_opus":0.580695406400756,"score_gpt":0.5966934622915074,"score_spread":0.015998055890751428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W18830643","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01891878,0.024307808,0.38868153,0.36142734,0.0024945945,0.0009004703,0.00018856044,0.00034568907,0.20273525],"genre_scores_gemma":[0.5642834,0.026516518,0.37481955,0.021359654,0.0019905951,0.0016603383,0.0003586346,0.00020114104,0.008810181],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94005287,0.045216117,0.0032145784,0.0017727836,0.008369938,0.0013736556],"domain_scores_gemma":[0.67903644,0.2508772,0.0072430717,0.021487964,0.036868814,0.004486474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.099656515,0.0010291542,0.0012835219,0.009681543,0.0040868837,0.015034238,0.0034408122,0.0058081793,0.010018516],"category_scores_gemma":[0.17081341,0.0006412046,0.0009025412,0.0052150125,0.02590112,0.02371424,0.00838335,0.010055544,0.001766211],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012068872,0.0002844561,0.0015586365,0.0006785861,0.000021071744,0.000054084703,0.002817515,0.0014060993,0.00013058208,0.92635626,0.0068172263,0.05986344],"study_design_scores_gemma":[0.000042493833,0.000056507863,0.0012878443,0.0058557526,0.000019271964,0.000060908864,0.007437041,0.0053051007,0.0005385125,0.90943354,0.069933616,0.00002937895],"about_ca_topic_score_codex":0.005630156,"about_ca_topic_score_gemma":0.00628848,"teacher_disagreement_score":0.9003435,"about_ca_system_score_codex":0.015778843,"about_ca_system_score_gemma":0.038587928,"threshold_uncertainty_score":0.52704036},"labels":[],"label_agreement":null},{"id":"W1888577351","doi":"10.3138/cjpe.27.004","title":"L’étude des mécanismes de changement, une avenue de recherche prometteuse pour optimiser les programmes de traitement destinés aux jeunes en difficulté : enjeux conceptuels et méthodologiques","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychiatric care and mental health services","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Psychology; Humanities; Philosophy","score_opus":0.5651908111891591,"score_gpt":0.5439940381536859,"score_spread":0.021196773035473293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888577351","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47271892,0.016474493,0.37722892,0.026547318,0.0007949226,0.026080504,0.0018672845,0.00052102626,0.07776666],"genre_scores_gemma":[0.7151044,0.003055514,0.25342673,0.0013047208,0.000093633644,0.019804724,0.0003681777,0.00009775556,0.0067444067],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9196695,0.06677242,0.0032892374,0.0041902456,0.004935878,0.0011426804],"domain_scores_gemma":[0.8974824,0.08061331,0.0075396686,0.0062905275,0.0068789916,0.0011950788],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07377857,0.0008831078,0.0012103871,0.0040720613,0.0033839762,0.0091163935,0.0031531996,0.0023508195,0.01046236],"category_scores_gemma":[0.085833475,0.00089838094,0.0020957522,0.0040249797,0.0072191595,0.008300394,0.0035464293,0.0026271634,0.00077343243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012088311,0.0011560385,0.06299291,0.008573035,0.00049832097,0.00047293806,0.11844609,0.0017590049,0.0030803473,0.35889706,0.003459073,0.43945637],"study_design_scores_gemma":[0.0019653582,0.0037313984,0.1586317,0.019281035,0.0023915328,0.0016387672,0.23641391,0.038693175,0.015455386,0.33903047,0.18224154,0.0005257462],"about_ca_topic_score_codex":0.012266156,"about_ca_topic_score_gemma":0.01811858,"teacher_disagreement_score":0.92622143,"about_ca_system_score_codex":0.012101914,"about_ca_system_score_gemma":0.01793473,"threshold_uncertainty_score":0.39018303},"labels":[],"label_agreement":null},{"id":"W1891772057","doi":"","title":"ARTICLE 1: THE PARIS DECLARATION ON AID EFFECTIVENESS: HISTORY AND SIGNIFICANCE","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Context (archaeology); Relevance (law); Harmonization; Diversity (politics); Accountability; Political science; Public administration; Law; History","score_opus":0.39254754268677033,"score_gpt":0.488255545621587,"score_spread":0.09570800293481668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1891772057","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055935723,0.046345714,0.015929911,0.27181888,0.01157577,0.00031115246,0.001261009,0.0003482352,0.64681566],"genre_scores_gemma":[0.41667902,0.039235905,0.034222163,0.12661865,0.013151478,0.0014555589,0.0018532457,0.0008337856,0.36595026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.93746907,0.029472658,0.002740012,0.003004391,0.024166081,0.0031477793],"domain_scores_gemma":[0.9534226,0.027821401,0.003557193,0.0031598664,0.010500869,0.0015379909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031007176,0.0011704686,0.00073348894,0.0037327893,0.0073456974,0.02729588,0.0024636583,0.010730024,0.01204792],"category_scores_gemma":[0.06047377,0.0005888509,0.00067512796,0.0043881433,0.025954736,0.008273659,0.009163031,0.009871202,0.0033299176],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032324122,0.00002388155,0.00043503856,0.00027883504,0.000010575606,0.00008744059,0.0034260438,0.00052699115,0.000085592306,0.77037096,0.17574507,0.04897727],"study_design_scores_gemma":[0.000008337739,0.000023080545,0.00065705884,0.0007792902,0.0000076059973,0.00008949205,0.001275353,0.00009699653,0.00035411204,0.03907253,0.95758235,0.000053861633],"about_ca_topic_score_codex":0.028452734,"about_ca_topic_score_gemma":0.02078819,"teacher_disagreement_score":0.031007176,"about_ca_system_score_codex":0.018837519,"about_ca_system_score_gemma":0.035048943,"threshold_uncertainty_score":0.16398352},"labels":[],"label_agreement":null},{"id":"W193071","doi":"10.3138/cjpe.17.006","title":"Developing an Evaluation Habit of Mind","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Habit; Accountability; Sustainability; Psychology; Political science; Sociology; Social psychology; Law","score_opus":0.6840143153944287,"score_gpt":0.5727226976961833,"score_spread":0.11129161769824536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W193071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1029025,0.0015636327,0.49963441,0.17051417,0.0020474363,0.00083705684,0.000068154106,0.0018592334,0.22057346],"genre_scores_gemma":[0.8385572,0.00046804285,0.12851834,0.01685193,0.00031569807,0.0007509436,0.000057680903,0.00038364212,0.014096638],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.94772106,0.036532238,0.0015945793,0.0037405866,0.008647246,0.0017642828],"domain_scores_gemma":[0.87137103,0.065353096,0.0063982,0.019093698,0.028607871,0.009176132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07910418,0.0004474728,0.00046601062,0.0024753897,0.0041765464,0.012123853,0.0019801247,0.003948609,0.00470713],"category_scores_gemma":[0.10786017,0.0006595159,0.0006228182,0.0010068867,0.028252194,0.016979404,0.015146924,0.0088588195,0.0013866937],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009413223,0.0004272937,0.019179236,0.0003211434,0.00006116434,0.00036066354,0.06946992,0.001112925,0.0032416675,0.6965797,0.028398296,0.18075386],"study_design_scores_gemma":[0.00005996494,0.00038616988,0.0060322164,0.00133722,0.00004012364,0.0007600681,0.032567944,0.00704607,0.0056684995,0.54759425,0.39834508,0.00016226737],"about_ca_topic_score_codex":0.0019534288,"about_ca_topic_score_gemma":0.002230284,"teacher_disagreement_score":0.07910418,"about_ca_system_score_codex":0.0075482773,"about_ca_system_score_gemma":0.014908393,"threshold_uncertainty_score":0.4183479},"labels":[],"label_agreement":null},{"id":"W1951995802","doi":"10.3138/cjpe.027.004","title":"Propositions théoriques et pratiques pour l’évaluation de programmes en négligence","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec en Outaouais","funders":"Université de Montréal; Université du Québec en Outaouais; Université du Québec à Montréal","keywords":"Neglect; Fidelity; Valuation (finance); Psychological intervention; Psychology; Variety (cybernetics); Intervention (counseling); Sustainability; Program evaluation; Social psychology; Computer science; Political science; Business","score_opus":0.3343002875915336,"score_gpt":0.5692418239309505,"score_spread":0.2349415363394169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951995802","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034307126,0.025344126,0.58905977,0.19976859,0.0022554696,0.006415056,0.0006303947,0.00036703836,0.14185244],"genre_scores_gemma":[0.57526326,0.008240607,0.38580248,0.009842915,0.00064337975,0.015393944,0.00026439098,0.000083713705,0.004465325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7750989,0.18767257,0.007509149,0.0051965863,0.021507738,0.0030150458],"domain_scores_gemma":[0.3811152,0.57740283,0.01073628,0.007195103,0.021906875,0.0016436748],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23509444,0.003819591,0.0032904875,0.011585157,0.0048403125,0.019828143,0.0073103937,0.013171157,0.014273297],"category_scores_gemma":[0.31650677,0.0018296046,0.0050687343,0.0064485576,0.037025876,0.022622636,0.0059061255,0.0094645135,0.0011065644],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017471184,0.00029749257,0.0010807343,0.0020379839,0.00028136958,0.00014899467,0.0033064776,0.0067274156,0.0000989919,0.96461326,0.0020097266,0.019222815],"study_design_scores_gemma":[0.0004197279,0.00034204798,0.00085754297,0.005712874,0.00030417243,0.00012651383,0.004489484,0.021352787,0.00058411376,0.9533779,0.012345634,0.000087115026],"about_ca_topic_score_codex":0.015042699,"about_ca_topic_score_gemma":0.009476488,"teacher_disagreement_score":0.23509444,"about_ca_system_score_codex":0.031124199,"about_ca_system_score_gemma":0.026350204,"threshold_uncertainty_score":0.9432647},"labels":[],"label_agreement":null},{"id":"W195248577","doi":"","title":"Toward Sustainability of Human Services: Assessing Community Self-Determination and Self-Reliance.","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Community Health and Development","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sustainability; Dependency (UML); Accountability; Negotiation; Self reliance; Process (computing); Knowledge management; Process management; Relevance (law); Human resources; Self-determination; Environmental resource management; Business; Psychology; Computer science; Political science; Social psychology; Ecology; Economics","score_opus":0.1816843573803989,"score_gpt":0.5047644280535238,"score_spread":0.32308007067312494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W195248577","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9718478,0.00043255574,0.007151707,0.0009836453,0.000030037749,0.0007284684,0.0001934092,0.000054450655,0.018577982],"genre_scores_gemma":[0.9925155,0.00018638933,0.0063145384,0.0000720214,0.000004314115,0.00030755793,0.00012464446,0.000004910494,0.0004701754],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98961544,0.004977218,0.0007755754,0.00025778078,0.0038676208,0.00050646055],"domain_scores_gemma":[0.96793973,0.009214448,0.007964978,0.0014057312,0.009646718,0.0038284375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023332724,0.00032260007,0.000342585,0.00450749,0.0019724728,0.0025731898,0.0007051965,0.00066968385,0.0008014277],"category_scores_gemma":[0.04982127,0.00028691097,0.00069572625,0.0025097474,0.0024552962,0.002607226,0.0045505096,0.0011739475,0.00013274718],"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":[0.000060802024,0.00043449455,0.8450902,0.00028115077,0.00013466971,0.00007768573,0.024760852,0.0010514975,0.00038354468,0.004299884,0.0012668611,0.1221584],"study_design_scores_gemma":[0.0000157788,0.00078595045,0.9007883,0.00047337892,0.000085951186,0.00030722746,0.0707775,0.00578529,0.0014289679,0.009919619,0.009531392,0.00010062981],"about_ca_topic_score_codex":0.01092496,"about_ca_topic_score_gemma":0.02446597,"teacher_disagreement_score":0.023332724,"about_ca_system_score_codex":0.0042465525,"about_ca_system_score_gemma":0.008029996,"threshold_uncertainty_score":0.123396754},"labels":[],"label_agreement":null},{"id":"W1960015609","doi":"","title":"ARTICLE 7: LESSONS LEARNED AND THE CONTRIBUTIONS OF THE PARIS DECLARATION EVALUATION TO EVALUATION THEORY AND PRACTICE","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; General partnership; Stakeholder; Declaration of independence; Political science; Engineering ethics; Management; Public relations; Sociology; Engineering; Law; Economics","score_opus":0.4814292938080387,"score_gpt":0.5829727740956275,"score_spread":0.1015434802875888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960015609","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009754366,0.01768113,0.052966725,0.7968332,0.005877384,0.00038378776,0.00006647486,0.0003535209,0.116083406],"genre_scores_gemma":[0.7311483,0.020489402,0.09697567,0.11082451,0.003256051,0.0017256299,0.0001789975,0.0007132953,0.034688123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.5891609,0.35479483,0.0077073346,0.005246841,0.03643289,0.006657146],"domain_scores_gemma":[0.64193755,0.2759812,0.006638362,0.018264547,0.047406346,0.009772036],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2608644,0.0011022121,0.0010080712,0.0048757205,0.012463244,0.035262734,0.0058817435,0.009818867,0.0051238653],"category_scores_gemma":[0.28042197,0.0011899547,0.0012820868,0.0040090955,0.05968234,0.023293812,0.014963824,0.02137984,0.0012917215],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007207346,0.00016446928,0.001778779,0.0008952659,0.000045379755,0.00041157572,0.048885413,0.0018351804,0.00012707649,0.6811452,0.10792817,0.15671131],"study_design_scores_gemma":[0.00006107652,0.0001275918,0.0021104794,0.008573023,0.000031794232,0.0003783293,0.06383291,0.002125555,0.0009484065,0.3116655,0.6099091,0.00023625341],"about_ca_topic_score_codex":0.023261737,"about_ca_topic_score_gemma":0.023391424,"teacher_disagreement_score":0.2608644,"about_ca_system_score_codex":0.049722347,"about_ca_system_score_gemma":0.069443226,"threshold_uncertainty_score":0.9114858},"labels":[],"label_agreement":null},{"id":"W1968516213","doi":"10.3138/cjpe.29.2.67","title":"Positive Thinking Approaches to Evaluation and Program Perspectives","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Value (mathematics); Nothing; Management science; Yield (engineering); Psychology; Sociology; Computer science; Epistemology; Economics; Artificial intelligence; Philosophy","score_opus":0.5279838688003321,"score_gpt":0.5159939137242172,"score_spread":0.011989955076114889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968516213","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033227038,0.012367793,0.3876245,0.05632688,0.0014285494,0.00079217646,0.00010589978,0.0002323455,0.5078948],"genre_scores_gemma":[0.8396615,0.0064736065,0.13712594,0.0051062866,0.00069233426,0.0014938099,0.000056800833,0.00011606337,0.009273636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89519393,0.0882131,0.001894604,0.001533064,0.012003043,0.0011622409],"domain_scores_gemma":[0.87870866,0.095393375,0.0044291504,0.0026019847,0.016731838,0.0021349604],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.055787537,0.0014297297,0.00067633606,0.0063516265,0.0025038992,0.011690442,0.0020554673,0.002256376,0.0046387604],"category_scores_gemma":[0.04516389,0.000405202,0.0006879491,0.0030869336,0.021786852,0.0069290344,0.0048894617,0.0047163004,0.0004888915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005646988,0.00012469958,0.00083134166,0.0007046306,0.00003525531,0.00006443002,0.0057980022,0.0011029795,0.00017701137,0.9461059,0.0022538279,0.0427455],"study_design_scores_gemma":[0.00011655359,0.0001823889,0.0009389387,0.0023375077,0.00009069847,0.00015551917,0.00760585,0.0038278992,0.0015527264,0.9264856,0.056663904,0.00004248731],"about_ca_topic_score_codex":0.0022064869,"about_ca_topic_score_gemma":0.002390631,"teacher_disagreement_score":0.94421244,"about_ca_system_score_codex":0.014175431,"about_ca_system_score_gemma":0.011150274,"threshold_uncertainty_score":0.2950362},"labels":[],"label_agreement":null},{"id":"W1973373172","doi":"10.3138/cjpe.29.1.118","title":"Evaluating Humanitarian Action in Real Time: Recent Practices, Challenges, and Innovations","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Accountability; Bridge (graph theory); Action (physics); Process management; Business; Computer science; Risk analysis (engineering); Political science; Sociology; Law","score_opus":0.7423398199910727,"score_gpt":0.610782611392342,"score_spread":0.13155720859873066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973373172","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07921702,0.4096492,0.10899512,0.31018785,0.0032601105,0.0010570603,0.00063993636,0.00063221465,0.08636147],"genre_scores_gemma":[0.6845369,0.17776048,0.120116204,0.0108258175,0.0017893878,0.0010315423,0.00035309306,0.00030946534,0.0032771686],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8655325,0.0955029,0.008168658,0.007871283,0.020872857,0.002051767],"domain_scores_gemma":[0.57724047,0.3009056,0.011169597,0.016102297,0.089107886,0.0054741586],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22516614,0.0010602818,0.0015368053,0.0056500845,0.0025065467,0.017681032,0.005872633,0.0042265775,0.0035333266],"category_scores_gemma":[0.21258889,0.00076305337,0.00079713436,0.0072587323,0.017718995,0.014531987,0.006398514,0.005650577,0.0006254647],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021122834,0.00036481395,0.00996774,0.0072819665,0.00013417158,0.00008576645,0.015860269,0.0035040565,0.0009033624,0.06478885,0.009562334,0.8873355],"study_design_scores_gemma":[0.00022354002,0.0018021837,0.044635378,0.06398495,0.00037174788,0.00090408686,0.10580448,0.0148990685,0.008651769,0.16835043,0.5894899,0.00088245],"about_ca_topic_score_codex":0.038606234,"about_ca_topic_score_gemma":0.040923912,"teacher_disagreement_score":0.9793124,"about_ca_system_score_codex":0.020687565,"about_ca_system_score_gemma":0.030010238,"threshold_uncertainty_score":0.9555081},"labels":[],"label_agreement":null},{"id":"W197622962","doi":"10.3138/cjpe.16.006","title":"Softly, Softly Catch the Monkey: Innovative Approaches to Measure Socially Sensitive and Complex Issues in Evaluation Research","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Respondent; Reliability (semiconductor); Measure (data warehouse); Psychology; Government (linguistics); Focus (optics); Research design; Management science; Knowledge management; Computer science; Data science; Applied psychology; Sociology; Engineering; Political science; Social science; Data mining","score_opus":0.8765369178333454,"score_gpt":0.6071075175501194,"score_spread":0.26942940028322604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W197622962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03343506,0.0018217539,0.9149211,0.023046287,0.00043678813,0.0055765132,0.000065107,0.00030991767,0.020387486],"genre_scores_gemma":[0.23935577,0.0008830964,0.74114305,0.0023751622,0.00016217872,0.014927765,0.000031525407,0.00011129565,0.001010117],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.42926434,0.5067607,0.015612863,0.005836499,0.040627945,0.0018976865],"domain_scores_gemma":[0.3243181,0.57275754,0.027969617,0.041264206,0.031120446,0.0025700317],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37520546,0.002095821,0.0020695964,0.01255402,0.007656565,0.017666372,0.0038017537,0.0043889224,0.0038706705],"category_scores_gemma":[0.47038847,0.0018801849,0.0024983042,0.009013824,0.038148027,0.024125954,0.019243963,0.009382343,0.00066061306],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025131047,0.0008660225,0.012171636,0.0050677885,0.00058632815,0.00023404259,0.09756332,0.003311527,0.0025126473,0.35001925,0.006083333,0.52133274],"study_design_scores_gemma":[0.00049798016,0.0015423592,0.016579181,0.011232451,0.0007827072,0.0007969544,0.064365014,0.021816857,0.00805583,0.81516737,0.058418036,0.000745245],"about_ca_topic_score_codex":0.0015130033,"about_ca_topic_score_gemma":0.0045442325,"teacher_disagreement_score":0.62479454,"about_ca_system_score_codex":0.011199819,"about_ca_system_score_gemma":0.015296863,"threshold_uncertainty_score":0.7704829},"labels":[],"label_agreement":null},{"id":"W1979608959","doi":"10.3138/cjpe.29.2.139","title":"Spaulding, D. T. (2014). <i>Program evaluation in practice: Core concepts and examples for discussion and analysis</i> (2nd ed.).","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Core (optical fiber); Psychology; Mathematics education; Computer science","score_opus":0.2714138296030427,"score_gpt":0.5558037051431876,"score_spread":0.28438987554014483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979608959","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000164343,0.9239352,0.005950736,0.054325983,0.0041565048,0.00008015353,0.00021053113,0.00010133901,0.0110751465],"genre_scores_gemma":[0.006031297,0.9517374,0.013321505,0.015606026,0.00231885,0.00029089046,0.00023226136,0.0001223251,0.010339354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926912,0.0024621342,0.000945996,0.00039298402,0.003305474,0.0002022403],"domain_scores_gemma":[0.9631821,0.022029674,0.0019655528,0.0006514729,0.011124733,0.0010464084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018065495,0.0011783706,0.0011555761,0.006024815,0.0019277453,0.004019276,0.0024822154,0.005029096,0.010248041],"category_scores_gemma":[0.037605233,0.0009854002,0.0010104111,0.008307139,0.0037030776,0.007695567,0.0023177036,0.0073853126,0.007441012],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043432414,0.000018109882,0.00044919897,0.0039766203,0.000026468728,0.00007211618,0.0010569306,0.00020700102,0.00017256568,0.01196882,0.5962199,0.3857888],"study_design_scores_gemma":[0.000030650815,0.00007876341,0.0028813374,0.015827775,0.00007633372,0.00044953736,0.0007650466,0.00016880746,0.0005197318,0.023900943,0.9552452,0.00005585195],"about_ca_topic_score_codex":0.031648602,"about_ca_topic_score_gemma":0.058825154,"teacher_disagreement_score":0.031648602,"about_ca_system_score_codex":0.0058909515,"about_ca_system_score_gemma":0.016505273,"threshold_uncertainty_score":0.09554064},"labels":[],"label_agreement":null},{"id":"W1992090873","doi":"10.3138/cjpe.29.2.87","title":"The Utility of a Realist Evaluation Approach in Implementing and Evaluating Health Equity Policy","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Equity (law); Program evaluation; Public economics; Health policy; Program Design Language; Management science; Political science; Economics; Business; Economic growth; Public administration; Computer science; Health care","score_opus":0.6286769634684284,"score_gpt":0.6421045718362257,"score_spread":0.013427608367797328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992090873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050952435,0.010390025,0.7322032,0.06465534,0.0013466614,0.009933674,0.00033176556,0.0003701483,0.12981679],"genre_scores_gemma":[0.60956156,0.002215636,0.37483475,0.003916697,0.0002876163,0.007153122,0.000064514665,0.00008425187,0.0018818757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.38678676,0.5806772,0.0072533297,0.004384159,0.018857364,0.0020411832],"domain_scores_gemma":[0.3751899,0.5694263,0.015005752,0.014549373,0.023558978,0.002269646],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.37300056,0.0018533557,0.0028406316,0.0071444428,0.004275055,0.016333101,0.0037784884,0.0044758082,0.006227457],"category_scores_gemma":[0.41240168,0.0011059837,0.0018811603,0.0036373672,0.01624967,0.011772972,0.009119702,0.0068967543,0.00047428405],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013168248,0.0015886729,0.0114158215,0.008507739,0.001804088,0.00029511304,0.010505495,0.0669147,0.00059727207,0.62926006,0.006627094,0.26116714],"study_design_scores_gemma":[0.001801492,0.0032468985,0.007200122,0.01066285,0.0007197712,0.00027300618,0.009817599,0.11525274,0.0030891402,0.80321264,0.044338766,0.00038505546],"about_ca_topic_score_codex":0.007522498,"about_ca_topic_score_gemma":0.011880244,"teacher_disagreement_score":0.37300056,"about_ca_system_score_codex":0.025431296,"about_ca_system_score_gemma":0.034781013,"threshold_uncertainty_score":0.77320194},"labels":[],"label_agreement":null},{"id":"W1998312778","doi":"10.3138/cjpe.29.1.87","title":"Toward a Definition of Evaluation Within the Canadian Context: Who Knew This Would Be So Difficult?","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada; Canadian Evaluation Society; University of Alberta","funders":"","keywords":"Scope (computer science); Presentation (obstetrics); Context (archaeology); Process (computing); Public relations; Psychology; Sociology; Computer science; Social psychology; Political science; History; Medicine","score_opus":0.40214964057962616,"score_gpt":0.47723035797279373,"score_spread":0.07508071739316757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998312778","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04345281,0.06469052,0.13015288,0.57821447,0.0040851603,0.0023129238,0.000420769,0.00035310246,0.17631733],"genre_scores_gemma":[0.8156778,0.018982332,0.1260065,0.030397303,0.0005241781,0.0015110091,0.00023600007,0.00032811143,0.006336661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8164898,0.101824485,0.010631408,0.007875972,0.04918565,0.013992646],"domain_scores_gemma":[0.7626232,0.06398183,0.007450372,0.005568599,0.14517605,0.015199918],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16551514,0.0013073487,0.0024590786,0.014829357,0.037112202,0.0365443,0.0073173973,0.0066731973,0.0020433753],"category_scores_gemma":[0.16151349,0.0010150219,0.0013399662,0.01449276,0.0729346,0.017485784,0.016663047,0.016301813,0.0003716185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000116891184,0.00011805878,0.010594108,0.0030315581,0.00010922277,0.00046395246,0.1770221,0.0017652274,0.0011907322,0.63557136,0.033505533,0.13651133],"study_design_scores_gemma":[0.00009118948,0.00016221298,0.01969785,0.022299398,0.0003025282,0.00054636935,0.32550147,0.003810392,0.0018556896,0.19336951,0.4317728,0.0005906197],"about_ca_topic_score_codex":0.93756104,"about_ca_topic_score_gemma":0.9489504,"teacher_disagreement_score":0.8344849,"about_ca_system_score_codex":0.27071652,"about_ca_system_score_gemma":0.5470752,"threshold_uncertainty_score":0.8753382},"labels":[],"label_agreement":null},{"id":"W2004772372","doi":"10.3138/cjpe.29.2.145","title":"Pawson, R. (2013). <i>The science of evaluation: A realist manifesto.</i>","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; University of Toronto","funders":"","keywords":"Manifesto; Philosophy; Epistemology; Sociology; Psychology; Political science; Law","score_opus":0.31751238103500456,"score_gpt":0.5079111319318299,"score_spread":0.19039875089682534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004772372","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013567056,0.15975255,0.04747781,0.57776874,0.017241498,0.00017226613,0.002433115,0.00066348194,0.19313385],"genre_scores_gemma":[0.22066833,0.32600397,0.063751675,0.21179967,0.015711254,0.0009156793,0.0032391145,0.002018556,0.1558917],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985872,0.0049268827,0.0017758483,0.00082231394,0.006183996,0.00041896533],"domain_scores_gemma":[0.91080976,0.057704385,0.0044348314,0.0036746764,0.02135377,0.0020225751],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02779282,0.00090307626,0.00074036245,0.004805044,0.003985282,0.014770515,0.0022399055,0.0055457763,0.013026939],"category_scores_gemma":[0.07128429,0.00082427746,0.00061794784,0.008597617,0.011741496,0.015092051,0.0049254214,0.01576214,0.008478205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005770868,0.000018009145,0.000514319,0.0008851188,0.000036635232,0.00004812231,0.0011938226,0.00027458963,0.00023624212,0.3425532,0.5814877,0.07269453],"study_design_scores_gemma":[0.000022428883,0.000024557614,0.0013737215,0.0023533136,0.000066594985,0.00013634229,0.0008518148,0.000204437,0.0006574573,0.14852044,0.8457279,0.000060961393],"about_ca_topic_score_codex":0.027156381,"about_ca_topic_score_gemma":0.037109967,"teacher_disagreement_score":0.9722072,"about_ca_system_score_codex":0.005902717,"about_ca_system_score_gemma":0.021485278,"threshold_uncertainty_score":0.14698428},"labels":[],"label_agreement":null},{"id":"W2014034431","doi":"10.3138/cjpe.29.2.21","title":"Les défis de l’évaluation d'un programme d'intervention en contexte carcéral","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Centre Jeunesse de Quebec","funders":"","keywords":"Prison; Valuation (finance); Government (linguistics); Psychology; Intervention (counseling); Public relations; Welfare economics; Political science; Business; Sociology; Applied psychology; Criminology; Economics; Finance; Psychiatry","score_opus":0.29812468333778513,"score_gpt":0.5076521920618863,"score_spread":0.20952750872410114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014034431","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13565181,0.116132915,0.13820773,0.26572728,0.004585685,0.016351769,0.0037433913,0.0006238284,0.31897566],"genre_scores_gemma":[0.8645035,0.011866756,0.08169501,0.017842315,0.00052862085,0.013850117,0.0006342011,0.0001230819,0.008956412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.53870165,0.33630782,0.03243435,0.00806415,0.079731576,0.0047604465],"domain_scores_gemma":[0.6220814,0.29083693,0.019163815,0.008007532,0.054807827,0.005102465],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38668382,0.0030399386,0.0034202733,0.0071063205,0.005614587,0.022715148,0.005211323,0.0074444152,0.0039261826],"category_scores_gemma":[0.35730544,0.001224726,0.0026441403,0.0053965426,0.015980748,0.008563033,0.005262507,0.008493889,0.00066777476],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006490717,0.0014809308,0.03882112,0.030568605,0.0025987255,0.00052419025,0.024691546,0.012595274,0.00178477,0.44977987,0.050378487,0.38028577],"study_design_scores_gemma":[0.005333978,0.007864516,0.09691164,0.12492556,0.003783706,0.0011595179,0.023488306,0.031174932,0.013409887,0.23093642,0.4603339,0.0006775648],"about_ca_topic_score_codex":0.10367241,"about_ca_topic_score_gemma":0.073851064,"teacher_disagreement_score":0.38668382,"about_ca_system_score_codex":0.058028556,"about_ca_system_score_gemma":0.057306953,"threshold_uncertainty_score":0.75632805},"labels":[],"label_agreement":null},{"id":"W2015255563","doi":"10.3138/cjpe.29.1.1","title":"Evaluating the Identity of Program Recipients Using an Identity Exploration Instrument","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Adult and Continuing Education Topics","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"NOSM University","funders":"","keywords":"Identity (music); Identification (biology); Strengths and weaknesses; Psychology; Process (computing); Social psychology; Computer science","score_opus":0.39109846619272415,"score_gpt":0.523373435742151,"score_spread":0.13227496954942686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015255563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98726815,0.000051323324,0.0042354953,0.00024491505,0.00002899038,0.0012389747,0.00007455638,0.000036975616,0.0068205805],"genre_scores_gemma":[0.9890609,0.00009513999,0.007264164,0.00006610265,0.000011001946,0.001846661,0.00010391783,0.000009078074,0.0015430431],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9856235,0.010184143,0.0008200195,0.00028713283,0.002259886,0.00082528294],"domain_scores_gemma":[0.9706315,0.014131494,0.004246684,0.0016217922,0.0073966486,0.0019718893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029433807,0.000338133,0.00044537123,0.0020481786,0.0025917927,0.0022123526,0.0006604805,0.00053651386,0.0032246215],"category_scores_gemma":[0.03765057,0.00017123994,0.00065979036,0.00078542193,0.0013136124,0.00157157,0.0038316264,0.0012598868,0.00051337405],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00211267,0.01079599,0.36331475,0.0006374994,0.00011648754,0.00019817447,0.08685165,0.00088559696,0.0024918534,0.005124905,0.002927166,0.5245431],"study_design_scores_gemma":[0.0005382798,0.019967921,0.71339417,0.0011187801,0.0003196547,0.0004535856,0.19913948,0.009625196,0.027501555,0.007188292,0.020467328,0.00028571772],"about_ca_topic_score_codex":0.0010113067,"about_ca_topic_score_gemma":0.0010934679,"teacher_disagreement_score":0.029433807,"about_ca_system_score_codex":0.0017487628,"about_ca_system_score_gemma":0.0049631703,"threshold_uncertainty_score":0.15566266},"labels":[],"label_agreement":null},{"id":"W2022560527","doi":"10.3138/cjpe.29.2.104","title":"Appreciative Inquiry and Evaluation – Getting to What Works","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Appreciative Inquiry and Organizational Change","field":"Business, Management and Accounting","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Appreciative inquiry; Cognitive reframing; Criticism; Set (abstract data type); Process (computing); Generative grammar; Epistemology; Psychology; Sociology; Computer science; Artificial intelligence; Social psychology; Political science; Pedagogy; Philosophy; Law","score_opus":0.12120690213551288,"score_gpt":0.3404921344939218,"score_spread":0.2192852323584089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022560527","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03932407,0.07542998,0.086677335,0.4819693,0.0044789333,0.0011557303,0.000083103536,0.00050693535,0.3103747],"genre_scores_gemma":[0.85714936,0.029187018,0.071530245,0.025896456,0.001210684,0.0012752189,0.00007297662,0.00035699413,0.013320898],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8300437,0.14659669,0.0032307983,0.0021193821,0.014964341,0.0030451813],"domain_scores_gemma":[0.80030286,0.15591995,0.006381869,0.010685805,0.019522727,0.0071868645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.113575324,0.00066482835,0.0011901424,0.0042330725,0.0072805393,0.02289135,0.0021491824,0.005318601,0.0055015073],"category_scores_gemma":[0.15359588,0.0004277566,0.00074504886,0.0032510755,0.049498644,0.018235052,0.0091132885,0.006324602,0.0008729471],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016651143,0.00033990282,0.0029290353,0.0030093184,0.00009064663,0.00022443154,0.10454744,0.00067419,0.00052299624,0.42547846,0.027806176,0.43421084],"study_design_scores_gemma":[0.00010811395,0.0003066369,0.0031678532,0.016623868,0.000085938394,0.00030858128,0.15309738,0.0015146608,0.0021772564,0.52435493,0.29811123,0.00014355358],"about_ca_topic_score_codex":0.009275065,"about_ca_topic_score_gemma":0.0074579283,"teacher_disagreement_score":0.113575324,"about_ca_system_score_codex":0.017709902,"about_ca_system_score_gemma":0.027045337,"threshold_uncertainty_score":0.6006509},"labels":[],"label_agreement":null},{"id":"W2034750899","doi":"10.3138/cjpe.29.2.1","title":"Time to Evaluate Diabetes and Guide Health Research and Policy Innovation: The Diabetes Evaluation Framework (DEFINE)","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Diabetes mellitus; Knowledge translation; Knowledge management; Value (mathematics); Process management; Medicine; Diabetes management; Risk analysis (engineering); Business; Management science; Computer science; Type 2 diabetes; Engineering","score_opus":0.7356164747435894,"score_gpt":0.7041031224283412,"score_spread":0.03151335231524821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034750899","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050680353,0.033853963,0.3335768,0.5702356,0.004135591,0.018085057,0.0013770659,0.00063707953,0.033030853],"genre_scores_gemma":[0.04904319,0.012122327,0.8851428,0.033466477,0.0007790388,0.017120706,0.00061295525,0.00014450334,0.0015680194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.52809715,0.40346846,0.033337623,0.0053778277,0.022453694,0.007265103],"domain_scores_gemma":[0.4907649,0.3824559,0.022531422,0.013361921,0.06633992,0.02454597],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.51560384,0.0031372628,0.006593703,0.013998505,0.008370204,0.026660485,0.008339807,0.013528457,0.006113882],"category_scores_gemma":[0.3982639,0.0028258585,0.005257462,0.008124498,0.017573366,0.020935956,0.020310847,0.01964933,0.001787228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003676092,0.0006643896,0.0053159385,0.018554097,0.0006330156,0.00034151901,0.014839216,0.007891613,0.0005196151,0.5005043,0.09459273,0.35577595],"study_design_scores_gemma":[0.0011540641,0.001057999,0.0051843612,0.094407566,0.0009345093,0.00040426475,0.023832913,0.0075998125,0.0012131807,0.516048,0.3476325,0.00053082564],"about_ca_topic_score_codex":0.024210297,"about_ca_topic_score_gemma":0.03881234,"teacher_disagreement_score":0.9757897,"about_ca_system_score_codex":0.03614781,"about_ca_system_score_gemma":0.18985276,"threshold_uncertainty_score":0.5973468},"labels":[],"label_agreement":null},{"id":"W2043777716","doi":"10.3138/cjpe.29.1.36","title":"Supporting Knowledge Translation Through Evaluation: Evaluator as Knowledge Broker","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McMaster University; Queen's University","funders":"","keywords":"Knowledge translation; Context (archaeology); Knowledge management; Computer science; History","score_opus":0.4946854783565933,"score_gpt":0.5959329823406669,"score_spread":0.10124750398407362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043777716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.245385,0.0029961504,0.51786274,0.050268948,0.001185859,0.013543684,0.00025985527,0.0028512273,0.16564666],"genre_scores_gemma":[0.7825405,0.0008122145,0.20467478,0.001929347,0.000206484,0.0038062374,0.0001347103,0.0002297484,0.0056660795],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.5438042,0.4126205,0.01206977,0.006616288,0.019326694,0.005562517],"domain_scores_gemma":[0.5103707,0.37025943,0.024402566,0.03401584,0.047931865,0.013019586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28600067,0.0010444506,0.0017793712,0.004360806,0.0065712305,0.017639142,0.0029521903,0.0033169389,0.010022684],"category_scores_gemma":[0.3300284,0.00097015296,0.000917877,0.003659431,0.0065132114,0.018802641,0.014755771,0.0032563538,0.002548755],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002140456,0.0037979498,0.0276984,0.0036981686,0.00026422547,0.0017173612,0.13722304,0.0040320153,0.0076329997,0.04863327,0.018715901,0.7444463],"study_design_scores_gemma":[0.0035510845,0.008277378,0.03100457,0.017233444,0.0013971602,0.002193218,0.25442693,0.09716104,0.039754722,0.14559473,0.3983962,0.0010095454],"about_ca_topic_score_codex":0.0030671603,"about_ca_topic_score_gemma":0.0030354979,"teacher_disagreement_score":0.28600067,"about_ca_system_score_codex":0.009213918,"about_ca_system_score_gemma":0.03893637,"threshold_uncertainty_score":0.8804883},"labels":[],"label_agreement":null},{"id":"W204379101","doi":"10.3138/cjpe.16.003","title":"Do Distinct Servqual Dimensions Emerge From Mystery Shopping Data? A Test of Convergent Validity","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Customer Service Quality and Loyalty","field":"Business, Management and Accounting","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SERVQUAL; Service quality; Marketing; Empathy; Reliability (semiconductor); Convergent validity; Service (business); Test (biology); Perception; Quality (philosophy); Customer satisfaction; Psychology; Business; Computer science; Social psychology","score_opus":0.275098266428428,"score_gpt":0.3667225047697671,"score_spread":0.09162423834133909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W204379101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9888364,0.000068223875,0.003707079,0.00019938385,0.000027584922,0.0003480876,0.00044466642,0.000017360499,0.0063511613],"genre_scores_gemma":[0.99590045,0.00002616874,0.0026972226,0.0000817157,0.000008600698,0.00040356893,0.00060693617,0.00001221951,0.00026318748],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.978226,0.007427528,0.0027651845,0.0017645189,0.008939104,0.00087767874],"domain_scores_gemma":[0.88258976,0.057595007,0.015126417,0.016392637,0.026301008,0.0019950739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029897373,0.000396115,0.00061516603,0.0031370465,0.0010865922,0.0021241393,0.0010696837,0.0008974523,0.0022315579],"category_scores_gemma":[0.11272199,0.00045317275,0.0009494174,0.0027626322,0.0028594,0.0026244097,0.003611592,0.0011550577,0.0005229942],"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":[0.00035335103,0.00031572275,0.9557796,0.000097425036,0.00021269197,0.00004650276,0.008541648,0.0005388319,0.00075691025,0.0023583418,0.00043748255,0.030561449],"study_design_scores_gemma":[0.00006010771,0.0004253859,0.97902244,0.00012176787,0.000053205982,0.00011406656,0.00789658,0.005397013,0.0010945352,0.0038631503,0.0019038165,0.000047865684],"about_ca_topic_score_codex":0.0027314345,"about_ca_topic_score_gemma":0.003460816,"teacher_disagreement_score":0.029897373,"about_ca_system_score_codex":0.0012956928,"about_ca_system_score_gemma":0.001572731,"threshold_uncertainty_score":0.15811431},"labels":[],"label_agreement":null},{"id":"W205902208","doi":"10.3138/cjpe.17.003","title":"The Inclusion of Stakeholders in Evaluation: Benefits and Drawbacks","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stakeholder; Inclusion (mineral); Foundation (evidence); Process (computing); Empirical research; Evaluation methods; Business; Process management; Management science; Knowledge management; Psychology; Computer science; Public relations; Political science; Economics; Social psychology; Engineering","score_opus":0.5130399514960976,"score_gpt":0.5057613927462337,"score_spread":0.007278558749863939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W205902208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.319269,0.04211194,0.2662507,0.19376118,0.0015419901,0.0031530194,0.00022384721,0.00062883797,0.17305946],"genre_scores_gemma":[0.92608035,0.0029934333,0.061456565,0.005196373,0.0004664328,0.0010034536,0.000042647305,0.0000837696,0.0026770353],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.44485053,0.46138856,0.016381301,0.0048009334,0.06961619,0.0029624861],"domain_scores_gemma":[0.32437545,0.57279176,0.016076516,0.02438193,0.058632176,0.0037422322],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2961636,0.0012795152,0.0015989967,0.0030859988,0.0046506007,0.011597521,0.0027695785,0.0058318577,0.0032742568],"category_scores_gemma":[0.36571115,0.0009990371,0.0017464843,0.0033343562,0.00900353,0.01604059,0.012956744,0.005371577,0.0011298825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029464012,0.0011253401,0.056521658,0.009004898,0.0006079179,0.0006884284,0.018100047,0.004945605,0.003916105,0.12140104,0.010375275,0.77036726],"study_design_scores_gemma":[0.0014498554,0.005956932,0.09320729,0.052117124,0.0034864575,0.008284329,0.07135799,0.06755213,0.034235872,0.45245144,0.20885123,0.0010493961],"about_ca_topic_score_codex":0.002859823,"about_ca_topic_score_gemma":0.0039798613,"teacher_disagreement_score":0.70383644,"about_ca_system_score_codex":0.005136479,"about_ca_system_score_gemma":0.010389182,"threshold_uncertainty_score":0.8679556},"labels":[],"label_agreement":null},{"id":"W2071368667","doi":"10.3138/cjpe.29.2.128","title":"Pertinence de la recension réaliste des écrits pour l'analyse des évaluations de programmes complexes : l'exemple du suivi dans la communauté en santé mentale","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Relevance (law); Sociology; Humanities; Philosophy; Political science","score_opus":0.17300183107063663,"score_gpt":0.4822728331215107,"score_spread":0.3092710020508741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071368667","genre_codex":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030917224,0.7099984,0.088750534,0.13092178,0.008393915,0.0060532438,0.0014352355,0.0002795635,0.023250075],"genre_scores_gemma":[0.6593482,0.15237729,0.15189251,0.01450859,0.004394987,0.013803951,0.000793258,0.00028778682,0.0025934433],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.21073379,0.60964555,0.091101766,0.010230274,0.0763507,0.001937988],"domain_scores_gemma":[0.062542535,0.80582017,0.037723932,0.025754292,0.06680344,0.0013556068],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7032954,0.0022217194,0.0101396255,0.021693168,0.004235101,0.028260585,0.005445108,0.0074090958,0.0035615615],"category_scores_gemma":[0.85464853,0.0021002016,0.0067486996,0.018376026,0.0117534315,0.023480058,0.010298264,0.0088224765,0.00046482164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00265358,0.0002750657,0.022890871,0.26914507,0.020431822,0.00052539236,0.033266224,0.003103604,0.0022334743,0.11606353,0.017378658,0.51203275],"study_design_scores_gemma":[0.0016813447,0.0028059862,0.041353177,0.5314767,0.031234946,0.0020276613,0.01735292,0.014365974,0.0073121716,0.16232133,0.1871973,0.00087050337],"about_ca_topic_score_codex":0.012403704,"about_ca_topic_score_gemma":0.020193478,"teacher_disagreement_score":0.9720585,"about_ca_system_score_codex":0.027941503,"about_ca_system_score_gemma":0.04853296,"threshold_uncertainty_score":0.3658896},"labels":[],"label_agreement":null},{"id":"W2081701430","doi":"10.3138/cjpe.29.1.62","title":"Assessing the Quality of Aboriginal Program Evaluations","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Treasury; Popularity; Quality (philosophy); Context (archaeology); Government (linguistics); Program evaluation; Strengths and weaknesses; Corporate governance; Replicate; Business; Political science; Public administration; Psychology; Finance; Geography; Statistics","score_opus":0.5441703005540053,"score_gpt":0.6713453947850856,"score_spread":0.1271750942310803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081701430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5100587,0.26152545,0.14679846,0.01704636,0.002019162,0.016176797,0.017529054,0.0006176547,0.028228393],"genre_scores_gemma":[0.9473459,0.008280066,0.038607277,0.00059424073,0.00015340057,0.0028719713,0.0016409014,0.00006315855,0.00044299205],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.43960133,0.41152018,0.07419215,0.008228734,0.06446396,0.0019936971],"domain_scores_gemma":[0.15041165,0.62325513,0.07561405,0.03555488,0.11309614,0.0020682563],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5048721,0.0014761714,0.0041373204,0.017162515,0.0020406109,0.006047614,0.0032084968,0.0012559766,0.0020456724],"category_scores_gemma":[0.7597043,0.0012081825,0.0076625496,0.02121109,0.0043308996,0.0030789066,0.0044749836,0.001610303,0.00010070939],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005460544,0.0002303734,0.43553346,0.09497305,0.16559671,0.00020849016,0.010406988,0.0113388505,0.00069032813,0.011424673,0.0076184105,0.25651813],"study_design_scores_gemma":[0.0025601673,0.004591452,0.4858947,0.10997348,0.2720604,0.0006113741,0.010326589,0.025130406,0.0107287215,0.024888467,0.052492853,0.00074133376],"about_ca_topic_score_codex":0.0548638,"about_ca_topic_score_gemma":0.07341382,"teacher_disagreement_score":0.98390895,"about_ca_system_score_codex":0.016091041,"about_ca_system_score_gemma":0.02956002,"threshold_uncertainty_score":0.6105809},"labels":[],"label_agreement":null},{"id":"W2081929183","doi":"10.3138/cjpe.29.2.48","title":"Think Positively! And Make a Difference Through Evaluation","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Obligation; Punishment (psychology); Theme (computing); Accountability; Reinforcement; Psychology; Social psychology; Epistemology; Computer science; Political science; Law; Philosophy","score_opus":0.37937904172344933,"score_gpt":0.5354819516833826,"score_spread":0.1561029099599333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081929183","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037064403,0.008716696,0.080458,0.29141453,0.0045905667,0.0006888418,0.00014046054,0.00069291424,0.57623357],"genre_scores_gemma":[0.80286205,0.007259281,0.070279844,0.044943616,0.0016460269,0.000833829,0.00014847437,0.00049142574,0.07153548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96125907,0.026569922,0.00078268046,0.0006899685,0.009547712,0.0011507024],"domain_scores_gemma":[0.97114795,0.015871169,0.0019379013,0.0015851504,0.0065478627,0.0029100112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026379578,0.00045256683,0.0003908026,0.0013149651,0.0026970266,0.009383282,0.00083369645,0.0019420155,0.012678456],"category_scores_gemma":[0.053693403,0.0001709181,0.00041622223,0.0007835563,0.009306877,0.006349445,0.0054171695,0.00429757,0.002443589],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017917165,0.00047471118,0.0053023584,0.00074658485,0.00007113524,0.00022397439,0.016021905,0.0005447131,0.0012812155,0.26014063,0.17947732,0.5355364],"study_design_scores_gemma":[0.00012002224,0.00041590497,0.008344005,0.0032542506,0.000088146335,0.00049179466,0.018157551,0.0016695339,0.004294001,0.30520532,0.6578252,0.00013424622],"about_ca_topic_score_codex":0.0025021846,"about_ca_topic_score_gemma":0.004461356,"teacher_disagreement_score":0.026379578,"about_ca_system_score_codex":0.004041915,"about_ca_system_score_gemma":0.0072815497,"threshold_uncertainty_score":0.13951015},"labels":[],"label_agreement":null},{"id":"W2096736443","doi":"10.3138/cjpe.17.002","title":"The Temporal Logic Model Concept","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Complex Systems and Decision Making","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interim; Computer science; Documentation; Logic model; Temporal logic; Context (archaeology); Adaptation (eye); Accountability; Process (computing); Temporal logic of actions; Duration (music); Space (punctuation); Artificial intelligence; Programming language; Interval temporal logic; Sociology; Psychology; Political science; Social science; History; Law","score_opus":0.5968884418094136,"score_gpt":0.48887320881789953,"score_spread":0.10801523299151405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096736443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008271641,0.0010137706,0.8486045,0.008530144,0.0004995805,0.00017892559,0.00047700526,0.00036173654,0.13206269],"genre_scores_gemma":[0.5739535,0.0012767012,0.38957044,0.0025269368,0.00047341452,0.0008430986,0.00063668506,0.00019152627,0.030527595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99632555,0.0018051785,0.00020714135,0.00052342756,0.00086695794,0.00027174337],"domain_scores_gemma":[0.9964128,0.0019771226,0.00028279235,0.0004052448,0.00066905137,0.00025291392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043611396,0.0007670767,0.00038615818,0.0018100888,0.0013757115,0.005714958,0.002344748,0.0021831817,0.01736139],"category_scores_gemma":[0.0045757038,0.00036380175,0.00155696,0.0015848473,0.006448371,0.010486618,0.002382702,0.0032265333,0.0017577215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007575659,0.000008395612,0.000043690005,0.000018209439,0.0000034294887,0.000024640918,0.000096755684,0.0010022894,0.00005367616,0.995693,0.0006627414,0.0023854468],"study_design_scores_gemma":[0.000026978523,0.000025243051,0.00005540218,0.00008327083,0.000014050384,0.00012554346,0.00018429972,0.024914613,0.0004512289,0.92972887,0.044374604,0.00001587184],"about_ca_topic_score_codex":0.0050822813,"about_ca_topic_score_gemma":0.0027633484,"teacher_disagreement_score":0.01736139,"about_ca_system_score_codex":0.0054088803,"about_ca_system_score_gemma":0.0037948198,"threshold_uncertainty_score":0.05807966},"labels":[],"label_agreement":null},{"id":"W2113515522","doi":"10.3138/cjpe.016.001","title":"Addressing Attribution through Contribution Analysis: Using Performance Measures Sensibly","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":342,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Canada","funders":"","keywords":"Attribution; Accountability; Authorship attribution; Public relations; Administration (probate law); Psychology; Business; Political science; Social psychology; Computer science; Law; Artificial intelligence","score_opus":0.6796845234554371,"score_gpt":0.5702891541640307,"score_spread":0.10939536929140636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113515522","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09221153,0.0024257305,0.6746214,0.073979154,0.0023231767,0.0013734351,0.00029965973,0.001126257,0.15163967],"genre_scores_gemma":[0.8616789,0.00096396933,0.12944146,0.0019664718,0.0006381311,0.000983318,0.00010931748,0.00023766857,0.003980828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5601743,0.36616987,0.00970088,0.005340076,0.054548074,0.0040667523],"domain_scores_gemma":[0.38365763,0.45590827,0.04896079,0.04298695,0.06314822,0.005338111],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2501988,0.0023667894,0.0014657624,0.009304908,0.005556213,0.021944625,0.0040563834,0.004386266,0.0055424636],"category_scores_gemma":[0.5074871,0.0006854335,0.0012228453,0.008964634,0.016085077,0.028039984,0.013885073,0.009504279,0.0011425066],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005304755,0.0007259019,0.04637861,0.0018470956,0.00046230372,0.0002591189,0.035092894,0.004942377,0.0017746462,0.46061566,0.017620811,0.4297501],"study_design_scores_gemma":[0.00016646976,0.00091365795,0.02325374,0.0035608304,0.00038853384,0.00041741438,0.033372905,0.045193527,0.015555608,0.80254936,0.074191846,0.0004361568],"about_ca_topic_score_codex":0.0018711194,"about_ca_topic_score_gemma":0.0014415523,"teacher_disagreement_score":0.74980116,"about_ca_system_score_codex":0.007487682,"about_ca_system_score_gemma":0.011894471,"threshold_uncertainty_score":0.9246384},"labels":[],"label_agreement":null},{"id":"W2115776235","doi":"10.3138/cjpe.0023.004","title":"Evaluation Capacity Building in the Schools: Administrator-Led and Teacher-Led Perspectives","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Capacity building; Sustainability; Capacity development; Process (computing); Process management; Business; Knowledge management; Computer science; Political science; Environmental resource management; Environmental science","score_opus":0.3996361563938446,"score_gpt":0.5246982158041983,"score_spread":0.1250620594103537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115776235","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20631279,0.014836271,0.13977888,0.25621262,0.0009405166,0.0010021094,0.000094859344,0.00025319844,0.3805687],"genre_scores_gemma":[0.9842821,0.0013443906,0.007287067,0.0019704138,0.000099814344,0.00021379716,0.000011934911,0.000031604843,0.0047589475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.85881764,0.12278798,0.002088786,0.0020483728,0.0074142413,0.0068429573],"domain_scores_gemma":[0.90766597,0.069103055,0.0028513754,0.0021704535,0.010505226,0.0077039427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08030852,0.0006304934,0.0007336159,0.0046968763,0.010917285,0.023937969,0.00335233,0.005304297,0.0042674886],"category_scores_gemma":[0.044608302,0.0008165097,0.00070990814,0.0021693108,0.050920192,0.012504658,0.018927027,0.009807965,0.00032195242],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056279634,0.00030508862,0.0034651724,0.0005318354,0.00002888897,0.0005954774,0.18856013,0.0030968082,0.00039379267,0.7692883,0.0057323445,0.027945945],"study_design_scores_gemma":[0.000106905914,0.00020816093,0.0039957464,0.0021804138,0.000041600095,0.00051067275,0.44362208,0.008921295,0.0032201908,0.32346386,0.21356863,0.00016038946],"about_ca_topic_score_codex":0.019322168,"about_ca_topic_score_gemma":0.016837154,"teacher_disagreement_score":0.98067784,"about_ca_system_score_codex":0.036547028,"about_ca_system_score_gemma":0.049982563,"threshold_uncertainty_score":0.42471713},"labels":[],"label_agreement":null},{"id":"W2117862951","doi":"10.3138/cjpe.29.3.98","title":"The CES Professional Designations Program: Views from Members","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Global Health Workforce Issues","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; Health Canada","funders":"","keywords":"Credential; Credentialing; Professionalization; Psychology; Perception; Certification; Medical education; Public relations; Social psychology; Political science; Medicine; Law","score_opus":0.38827812049943927,"score_gpt":0.5566227842552148,"score_spread":0.16834466375577556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117862951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98252,0.00014173567,0.00036024043,0.0071744,0.00008679021,0.00007090079,0.0000980771,0.00001256961,0.009535341],"genre_scores_gemma":[0.9929986,0.00025870051,0.00025063023,0.0014695678,0.00006324137,0.00007123097,0.00007680765,0.000007636434,0.0048036613],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9946531,0.0028519237,0.00021334738,0.00016092193,0.0013776083,0.0007432026],"domain_scores_gemma":[0.9758707,0.006187236,0.002344712,0.00048692749,0.009087141,0.0060233725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011345262,0.00016852078,0.00015115143,0.00067670137,0.0027933244,0.0013706805,0.00038910462,0.00072805217,0.00392273],"category_scores_gemma":[0.020236157,0.0001619241,0.00016596218,0.00049409736,0.0012075894,0.00082433794,0.0017772838,0.0012054049,0.0003630842],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056645717,0.0010612324,0.553835,0.00034138633,0.000045385535,0.0009327177,0.25800318,0.00046115136,0.0047933883,0.0015019629,0.040881567,0.1375766],"study_design_scores_gemma":[0.000031896252,0.00076551596,0.37740293,0.00032955434,0.00002754542,0.00050150783,0.54029757,0.0007302298,0.0030867097,0.00024636035,0.07651883,0.00006135957],"about_ca_topic_score_codex":0.019040614,"about_ca_topic_score_gemma":0.02501604,"teacher_disagreement_score":0.019040614,"about_ca_system_score_codex":0.0028458205,"about_ca_system_score_gemma":0.0046560317,"threshold_uncertainty_score":0.06000024},"labels":[],"label_agreement":null},{"id":"W2131390173","doi":"10.3138/cjpe.29.2.142","title":"Cousins, J. B., &amp; Chouinard, J. A. (Eds.). (2012). <i>Participatory evaluation up close: An integration of research-based knowledge.</i>","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Participatory action research; Sociology; Psychology; Computer science; Anthropology; World Wide Web","score_opus":0.6397693202422317,"score_gpt":0.6152156273843152,"score_spread":0.02455369285791642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131390173","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023017518,0.9747999,0.003801208,0.011495027,0.0009747452,0.000055055963,0.0000998537,0.00005387233,0.0084900865],"genre_scores_gemma":[0.0050473046,0.98130655,0.0059317597,0.0013590817,0.00048985414,0.00009053055,0.000119846605,0.000043126718,0.0056118616],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99127215,0.0033349085,0.00074988365,0.0005978956,0.0037451354,0.00029999547],"domain_scores_gemma":[0.96311826,0.025351435,0.002342094,0.00076707976,0.0073871035,0.0010340167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015169417,0.0018356773,0.0018789289,0.010925671,0.0028273747,0.0071149077,0.0031236429,0.004120903,0.011968392],"category_scores_gemma":[0.025424201,0.0017120888,0.0013246237,0.014384606,0.0045738555,0.009525184,0.0024340684,0.0046186387,0.0069516944],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056742396,0.00005199105,0.0008640486,0.0066327774,0.000068346686,0.000113040245,0.0024425255,0.00032854656,0.00028913756,0.012099181,0.25333914,0.7237145],"study_design_scores_gemma":[0.000022625121,0.00008269961,0.0036144159,0.01368118,0.00016073041,0.00050007366,0.0017558255,0.00023918427,0.0006725817,0.016574875,0.9626134,0.00008235481],"about_ca_topic_score_codex":0.08353952,"about_ca_topic_score_gemma":0.16940965,"teacher_disagreement_score":0.08353952,"about_ca_system_score_codex":0.008552647,"about_ca_system_score_gemma":0.017033234,"threshold_uncertainty_score":0.16610652},"labels":[],"label_agreement":null},{"id":"W2135942607","doi":"10.3138/cjpe.025.002","title":"Evaluability Assessment of a National Driver Retraining Program: Are We Evaluating in the Right Lane?","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Older Adults Driving Studies","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Retraining; Stakeholder; Snapshot (computer storage); Psychology; Program evaluation; Medical education; Protocol (science); Evaluation methods; Applied psychology; Public relations; Political science; Computer science; Engineering; Medicine; Public administration","score_opus":0.3051666555782433,"score_gpt":0.5726167240872077,"score_spread":0.26745006850896436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135942607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96791625,0.00054835,0.0072581563,0.0028730375,0.00012693372,0.008800693,0.00023694153,0.000080915765,0.0121587],"genre_scores_gemma":[0.986299,0.00016314816,0.0071853097,0.0003655208,0.000029181809,0.005151966,0.000115276474,0.000013448457,0.0006772387],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.90040654,0.072913446,0.006170193,0.0020844778,0.015902389,0.002522945],"domain_scores_gemma":[0.8179604,0.08784852,0.019472731,0.0075022997,0.059734046,0.0074820016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14500466,0.00037119127,0.0008935614,0.0015858014,0.0024278238,0.0025257345,0.0015239852,0.000838501,0.0027740584],"category_scores_gemma":[0.24427703,0.0003122849,0.0010811419,0.0010819548,0.0010735502,0.0036715965,0.0025212045,0.0012867876,0.00023727847],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0074636657,0.014667412,0.26206425,0.0039218655,0.0007261795,0.00020123858,0.04975643,0.0015226306,0.0028251233,0.0019795739,0.0050972803,0.64977443],"study_design_scores_gemma":[0.0015574751,0.030271277,0.87178063,0.0030717843,0.00080239185,0.00012233,0.060798388,0.0044041416,0.008233391,0.0021648677,0.016604621,0.00018875551],"about_ca_topic_score_codex":0.007635739,"about_ca_topic_score_gemma":0.015746854,"teacher_disagreement_score":0.14500466,"about_ca_system_score_codex":0.007199815,"about_ca_system_score_gemma":0.01689088,"threshold_uncertainty_score":0.7668671},"labels":[],"label_agreement":null},{"id":"W2140061750","doi":"10.3138/cjpe.29.3.134","title":"From the Outside, Looking In with a Smile: A Summary and Discussion of CES's Credentialed Evaluator Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credentialing; Credential; Management; Action (physics); Political science; Context (archaeology); Humanities; Sociology; Public relations; Law; Art; Geography; Economics","score_opus":0.3069585015711737,"score_gpt":0.4904886684929546,"score_spread":0.18353016692178087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140061750","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032346357,0.0077312374,0.18795015,0.47462642,0.0076393434,0.0017534099,0.00038609523,0.00053265004,0.28703433],"genre_scores_gemma":[0.64393777,0.011793045,0.115129404,0.097012214,0.0018640978,0.0029340785,0.0003910366,0.0006108473,0.12632754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92816865,0.04332745,0.005874735,0.0031526564,0.015485868,0.003990602],"domain_scores_gemma":[0.92339724,0.035089746,0.0016102679,0.0030983542,0.03404859,0.002755749],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07141851,0.00082517695,0.0007197226,0.0029155891,0.009127923,0.013483775,0.004551374,0.0064552487,0.004332559],"category_scores_gemma":[0.08329367,0.0005507693,0.0013810568,0.0032707243,0.02069949,0.0068854825,0.0066753686,0.008604029,0.001001035],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007846945,0.00014722088,0.0033396746,0.00071907457,0.000027010403,0.0006884746,0.040824898,0.0023562014,0.00076206395,0.77771837,0.087891914,0.08544666],"study_design_scores_gemma":[0.000033496883,0.0001210884,0.002630156,0.0011385742,0.000033338012,0.0004087073,0.040530827,0.0022757698,0.002783496,0.03261437,0.91730857,0.00012170942],"about_ca_topic_score_codex":0.107236065,"about_ca_topic_score_gemma":0.12658024,"teacher_disagreement_score":0.9285815,"about_ca_system_score_codex":0.036489356,"about_ca_system_score_gemma":0.0551493,"threshold_uncertainty_score":0.3777017},"labels":[],"label_agreement":null},{"id":"W2142219519","doi":"","title":"System-Wide Program Assessment with Performance Indicators: Alberta's Performance Funding Mechanisms.","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Performance measurement; Business; Performance indicator; Process management; Political science; Accounting; Marketing","score_opus":0.14727823206226057,"score_gpt":0.4519045550663222,"score_spread":0.30462632300406167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142219519","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.258324,0.020973004,0.10532738,0.10975864,0.001468993,0.0059629693,0.011612848,0.004393119,0.4821791],"genre_scores_gemma":[0.8062851,0.0054396475,0.121643364,0.003288325,0.00020064745,0.0014279848,0.003784743,0.00020301071,0.05772708],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9772307,0.0067681517,0.0007193658,0.0006519128,0.012997814,0.0016320659],"domain_scores_gemma":[0.96782625,0.008172655,0.0021585226,0.0015252056,0.016145263,0.0041720388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027217736,0.00047415815,0.00025342684,0.005108429,0.002904363,0.005855848,0.0019703787,0.00076548994,0.002793314],"category_scores_gemma":[0.03817638,0.00031144996,0.00025227427,0.008611948,0.0020990036,0.001988692,0.003993807,0.0010814365,0.00039661472],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019558857,0.00021924339,0.08297482,0.0005816293,0.000058361315,0.000105786276,0.0035845106,0.0034247914,0.0011480906,0.06501631,0.07461308,0.7680778],"study_design_scores_gemma":[0.00020215065,0.000672861,0.44986734,0.001433272,0.0002574282,0.00024040966,0.008911724,0.010223008,0.0053314967,0.022458415,0.50014144,0.00026044532],"about_ca_topic_score_codex":0.7980783,"about_ca_topic_score_gemma":0.8868503,"teacher_disagreement_score":0.95808613,"about_ca_system_score_codex":0.041913882,"about_ca_system_score_gemma":0.14767462,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":true,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2150927259","doi":"10.3138/cjpe.27.003","title":"The Art of the Nudge: Five Practices for Developmental Evaluators","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Servant; Psychology; Adaptation (eye); Servant leadership; Energy (signal processing); Pedagogy; Applied psychology; Public relations; Social psychology; Political science; Computer science","score_opus":0.5020626007095538,"score_gpt":0.5787691116820812,"score_spread":0.07670651097252745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150927259","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032073993,0.011442889,0.39789593,0.48982066,0.0037996497,0.002405654,0.00009515625,0.0015391839,0.060926992],"genre_scores_gemma":[0.3642545,0.0022412855,0.60401887,0.018762602,0.00043041626,0.0041653276,0.000040345563,0.0005106954,0.005575996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5017094,0.4539477,0.011402382,0.008283056,0.020138131,0.0045194183],"domain_scores_gemma":[0.62679946,0.24358648,0.008638199,0.0584804,0.045157216,0.017338172],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.42979315,0.0022442567,0.0022390992,0.011687401,0.02569194,0.033311848,0.006971737,0.011799879,0.0036452473],"category_scores_gemma":[0.31278744,0.002380642,0.0014670576,0.0045808144,0.10885364,0.033894114,0.03753179,0.032042563,0.0012734107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017930203,0.00036884448,0.0059449114,0.0010880954,0.00008546364,0.0006239585,0.36831692,0.0006598383,0.0013372295,0.37654412,0.0361382,0.20871316],"study_design_scores_gemma":[0.00016888036,0.00033373592,0.001876555,0.0067341207,0.000072972776,0.0009883658,0.18565507,0.00279819,0.0016054171,0.42750728,0.37192452,0.0003348077],"about_ca_topic_score_codex":0.008023971,"about_ca_topic_score_gemma":0.016063184,"teacher_disagreement_score":0.42979315,"about_ca_system_score_codex":0.023287944,"about_ca_system_score_gemma":0.04327685,"threshold_uncertainty_score":0.7031666},"labels":[],"label_agreement":null},{"id":"W2158039605","doi":"10.3138/cjpe.0014.002","title":"Reflections on Empowerment Evaluation: Learning from Experience","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Community Health and Development","field":"Health Professions","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empowerment; Psychology; Program evaluation; Public relations; Participatory evaluation; Welfare; Focus group; Medical education; Sociology; Nursing; Social psychology; Medicine; Political science; Social science; Public administration","score_opus":0.45094206743730725,"score_gpt":0.5918598170060205,"score_spread":0.14091774956871328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158039605","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015602749,0.02527332,0.017339788,0.8735659,0.014991306,0.0003908525,0.00006206441,0.00012151692,0.05265247],"genre_scores_gemma":[0.4562035,0.06706527,0.044624705,0.3658684,0.011718126,0.0014278931,0.0001627063,0.0006871928,0.052242227],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.8558339,0.12616077,0.0021173374,0.00215602,0.009122779,0.0046091606],"domain_scores_gemma":[0.8356454,0.12509926,0.0020295405,0.004581474,0.021376345,0.011268023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11730232,0.0011212496,0.0008271403,0.001690165,0.0099367,0.015382355,0.0037471806,0.009529976,0.005912176],"category_scores_gemma":[0.1361493,0.0005896835,0.0013277978,0.0016254205,0.030152362,0.022055032,0.01632483,0.027426865,0.0014173554],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016385783,0.0009955446,0.0016147553,0.0013743698,0.000041957745,0.0017486303,0.26679534,0.0006693894,0.00055377197,0.1403197,0.33969286,0.24602987],"study_design_scores_gemma":[0.00006323935,0.0002541255,0.00056793995,0.0033952529,0.000015835507,0.00090871856,0.123847425,0.00032209756,0.0008150562,0.040657353,0.82906485,0.00008805843],"about_ca_topic_score_codex":0.007605924,"about_ca_topic_score_gemma":0.011665769,"teacher_disagreement_score":0.11730232,"about_ca_system_score_codex":0.016947597,"about_ca_system_score_gemma":0.018449973,"threshold_uncertainty_score":0.6203614},"labels":[],"label_agreement":null},{"id":"W2161163161","doi":"","title":"Knowlton, L.W. & Phillips, C.C. (2013). The Logic Model Guidebook: Better Strategies for Great Results (2nd Edition), Thousand Oaks, CA: Sage.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Physics; Nuclear physics","score_opus":0.10310341952547852,"score_gpt":0.3427688452820291,"score_spread":0.2396654257565506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161163161","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005660751,0.33946356,0.15097623,0.08083143,0.009777884,0.0005301615,0.011155773,0.0047136163,0.39689058],"genre_scores_gemma":[0.05898078,0.36912045,0.19659065,0.013844167,0.0024562213,0.0009349662,0.007444132,0.0025411283,0.3480875],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989085,0.00021651325,0.00013701407,0.000089727226,0.00059700356,0.000051120354],"domain_scores_gemma":[0.9882863,0.006330257,0.0005307983,0.000558498,0.0038845052,0.00040959258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004340908,0.0010675732,0.0006103852,0.004191337,0.0014820809,0.0041817175,0.0019672615,0.0018334368,0.0518028],"category_scores_gemma":[0.018079702,0.00094408006,0.00067257264,0.0028894423,0.0018132128,0.0078078387,0.0012444918,0.0039224136,0.030330503],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003748181,0.000046102705,0.0005495345,0.0007391749,0.000012752676,0.00007027383,0.00064136815,0.00016230026,0.0005166056,0.00933746,0.5875308,0.4003562],"study_design_scores_gemma":[0.000018516725,0.00006611487,0.0041848784,0.0020872182,0.000065235094,0.00043848276,0.00082766643,0.00029317365,0.0018753945,0.038712148,0.9513782,0.00005308089],"about_ca_topic_score_codex":0.017692124,"about_ca_topic_score_gemma":0.04569193,"teacher_disagreement_score":0.0518028,"about_ca_system_score_codex":0.0017320466,"about_ca_system_score_gemma":0.004696794,"threshold_uncertainty_score":0.17329764},"labels":[],"label_agreement":null},{"id":"W2163998785","doi":"10.3138/cjpe.0023.002","title":"Organizational Capacity To Do and Use Evaluation: Results of a Pan-Canadian Survey of Evaluators","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada; Atlantic Canada Opportunities Agency; University of Ottawa","funders":"","keywords":"Respondent; Psychology; Stakeholder; Knowledge management; Organizational learning; Context (archaeology); Descriptive statistics; Exploratory research; Social psychology; Applied psychology; Public relations; Sociology; Political science; Computer science; Social science; Geography","score_opus":0.44394440400345575,"score_gpt":0.5021568546325215,"score_spread":0.058212450629065715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163998785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942972,0.00033388752,0.00014785878,0.00034715713,0.000005852742,0.000103445665,0.0008640868,0.000011738961,0.0038887651],"genre_scores_gemma":[0.9976941,0.00041548896,0.00026125088,0.000094621595,0.000002430256,0.000046903133,0.0004300957,0.000007193946,0.0010479412],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9955382,0.00078346283,0.00036230424,0.00030164424,0.0020963354,0.00091808336],"domain_scores_gemma":[0.9695155,0.0041063456,0.003643461,0.0008197826,0.0184449,0.0034699799],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008102149,0.00026691778,0.0003081682,0.0027566063,0.0033724832,0.0018433628,0.0009595311,0.00036574827,0.0017807226],"category_scores_gemma":[0.01954207,0.00033025726,0.0003625996,0.0042704884,0.0014254086,0.00069970614,0.0017096879,0.0007356384,0.0002770408],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101462145,0.00009902543,0.94335693,0.00015865562,0.000028064616,0.00007688154,0.030811548,0.000100455916,0.00032411274,0.00020693264,0.0022428944,0.02249311],"study_design_scores_gemma":[0.0000040991804,0.000046591525,0.9728845,0.00006241631,0.000008596255,0.000025181147,0.023857193,0.0001454379,0.00011838019,0.000020887157,0.002806386,0.000020358058],"about_ca_topic_score_codex":0.9583757,"about_ca_topic_score_gemma":0.9743662,"teacher_disagreement_score":0.9918978,"about_ca_system_score_codex":0.015433948,"about_ca_system_score_gemma":0.027887633,"threshold_uncertainty_score":0.11198163},"labels":[],"label_agreement":null},{"id":"W2174546371","doi":"10.3138/cjpe.30.1.90","title":"Calculating Outcome Rates in Web Surveys","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Outcome (game theory); Tracking (education); Function (biology); Service (business); Quality (philosophy); Web survey; Computer science; World Wide Web; Psychology; Business; Marketing; Mathematics; Biology","score_opus":0.7320566072354909,"score_gpt":0.5853431466329448,"score_spread":0.1467134606025461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174546371","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09080559,0.003774432,0.85227084,0.0018919031,0.0011767085,0.01912111,0.0058281333,0.0015550975,0.023576202],"genre_scores_gemma":[0.31793836,0.002215033,0.60626805,0.0011248077,0.00047659886,0.061709695,0.0057538874,0.0005929825,0.0039205584],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3853714,0.50963193,0.048345666,0.008244805,0.046594612,0.0018116035],"domain_scores_gemma":[0.33826828,0.48709694,0.05989219,0.056616843,0.056729056,0.0013967162],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41989177,0.0015681179,0.0020650593,0.01474338,0.0010484502,0.0040284162,0.0033679039,0.0022099116,0.0039399257],"category_scores_gemma":[0.7124938,0.0012204127,0.003566113,0.011117026,0.0016483339,0.0055238814,0.004874631,0.0030728036,0.0025410496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001822879,0.0006236954,0.2800199,0.0070783193,0.0025303268,0.00017942165,0.0046692407,0.009140905,0.0006584952,0.041923515,0.018747024,0.63260627],"study_design_scores_gemma":[0.0016827965,0.0058211572,0.49455008,0.022655519,0.003465222,0.00241311,0.005497794,0.15842548,0.022049809,0.12558769,0.15714692,0.0007044575],"about_ca_topic_score_codex":0.0022941804,"about_ca_topic_score_gemma":0.0010669733,"teacher_disagreement_score":0.5801082,"about_ca_system_score_codex":0.003312873,"about_ca_system_score_gemma":0.0031439222,"threshold_uncertainty_score":0.71537673},"labels":[],"label_agreement":null},{"id":"W2177445649","doi":"10.3138/cjpe.0028.009","title":"The Emerging Field of Evaluation and the Growth of the Evaluation Profession: The Russian Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Institutionalisation; Field (mathematics); Political science; Capacity development; Private sector; Evaluation methods; Foundation (evidence); Engineering ethics; Environmental resource management; Engineering; Economics; Law","score_opus":0.20594391447379515,"score_gpt":0.5328023639531525,"score_spread":0.3268584494793574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177445649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4970524,0.08551641,0.014437443,0.13028792,0.0018633223,0.000083903215,0.00015569078,0.000120404125,0.2704825],"genre_scores_gemma":[0.97815335,0.012212785,0.0016454736,0.0012913481,0.00018467953,0.00001565533,0.000025490941,0.000030379604,0.0064407606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9888532,0.00730155,0.0006380966,0.000662278,0.0015806725,0.0009641659],"domain_scores_gemma":[0.9898887,0.0054482,0.0009674707,0.0006141761,0.0016917925,0.0013895652],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01593084,0.0001891113,0.00043778925,0.0016397124,0.0040908605,0.0062693674,0.0005167555,0.0013548383,0.002498366],"category_scores_gemma":[0.0069286996,0.00018779295,0.0003791152,0.0018075496,0.009449309,0.0037556097,0.004760897,0.0031953736,0.0005580468],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022300691,0.00042977778,0.031141143,0.0011441405,0.00003820952,0.0019149997,0.11119834,0.0013475864,0.0023399303,0.5700189,0.016323535,0.26388043],"study_design_scores_gemma":[0.000040744773,0.00044312555,0.058974683,0.003277535,0.000041428506,0.0030734017,0.11076149,0.002070068,0.0025580265,0.061607707,0.7570572,0.0000944919],"about_ca_topic_score_codex":0.007119925,"about_ca_topic_score_gemma":0.0052182763,"teacher_disagreement_score":0.98406917,"about_ca_system_score_codex":0.009166071,"about_ca_system_score_gemma":0.014157137,"threshold_uncertainty_score":0.084251404},"labels":[],"label_agreement":null},{"id":"W2179175560","doi":"10.3138/cjpe.0026.004","title":"L’évaluation des interventions complexes : quelle peut être la contribution des approches configurationnelles?","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Operationalization; Epistemology; Psychological intervention; Sociology; Valuation (finance); Psychology; Philosophy; Economics","score_opus":0.42523218998141776,"score_gpt":0.5299160107559208,"score_spread":0.104683820774503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179175560","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077484146,0.08317073,0.6002732,0.1128947,0.0024359263,0.0033834246,0.0002914057,0.0009872561,0.119079255],"genre_scores_gemma":[0.7125596,0.013016416,0.2639785,0.005279391,0.000720644,0.0022521866,0.00014049251,0.0002533814,0.0017993995],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.73382443,0.21279427,0.010146356,0.007088457,0.03405853,0.0020879335],"domain_scores_gemma":[0.6152456,0.31731814,0.016104896,0.023803344,0.024325442,0.0032026467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13731025,0.002239636,0.0030308894,0.0050529432,0.0031421771,0.016183242,0.0052039516,0.0056934897,0.012346108],"category_scores_gemma":[0.24187751,0.0012351397,0.003421712,0.004728082,0.017306216,0.017786803,0.007594235,0.007248884,0.0011922057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015969536,0.00079188496,0.005398371,0.012395022,0.0015221324,0.00021232267,0.00737848,0.023645055,0.0014568181,0.41094515,0.006722624,0.5279352],"study_design_scores_gemma":[0.0015753806,0.0025654242,0.008041162,0.03574196,0.0013483954,0.0010639052,0.007763007,0.046506945,0.0071669216,0.77866644,0.108987726,0.00057285],"about_ca_topic_score_codex":0.0053010224,"about_ca_topic_score_gemma":0.0049981684,"teacher_disagreement_score":0.13731025,"about_ca_system_score_codex":0.013535624,"about_ca_system_score_gemma":0.015926251,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2182857497","doi":"10.3138/cjpe.29.3.154","title":"A Point of No Return Finally Reached: The Journey Ahead","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Point (geometry); Mathematics; Economics; Econometrics; History; Geometry","score_opus":0.5769749004666175,"score_gpt":0.5455323490261877,"score_spread":0.031442551440429733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182857497","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006383251,0.009293725,0.004618915,0.9488504,0.004780214,0.000069051064,0.00013054693,0.000202969,0.025670942],"genre_scores_gemma":[0.62476116,0.03275753,0.03926841,0.20148975,0.0034688334,0.00054142525,0.00082958746,0.0012545573,0.09562873],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9584162,0.017985588,0.0012251304,0.001800383,0.01173649,0.008836241],"domain_scores_gemma":[0.90415597,0.01358562,0.0028018458,0.003018065,0.03289482,0.04354363],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.051344033,0.00078363396,0.0016920577,0.0020120065,0.021266678,0.029414348,0.0054388857,0.012553766,0.02456126],"category_scores_gemma":[0.09177009,0.00054321124,0.00142799,0.0018959806,0.0146309575,0.023550466,0.017370991,0.02417138,0.008298164],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033201586,0.0003488236,0.0058145006,0.00088922156,0.000062629886,0.0011791196,0.01672985,0.0007347158,0.00036054986,0.17300858,0.49021134,0.3103287],"study_design_scores_gemma":[0.00004437368,0.00032780267,0.0057639983,0.0063425363,0.00006675618,0.000998015,0.099373296,0.0011361677,0.0005996949,0.21204394,0.6730679,0.0002355119],"about_ca_topic_score_codex":0.0876167,"about_ca_topic_score_gemma":0.19683765,"teacher_disagreement_score":0.96641195,"about_ca_system_score_codex":0.033588056,"about_ca_system_score_gemma":0.15851727,"threshold_uncertainty_score":0.27153647},"labels":[],"label_agreement":null},{"id":"W2183451661","doi":"10.3138/cjpe.0021.007","title":"The Role of Culture and the Future of the Evaluation Function: Considerations and Key Questions","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Treasury Board of Canada Secretariat","funders":"","keywords":"Function (biology); Extension (predicate logic); Key (lock); Work (physics); Political science; Public relations; Administration (probate law); Sociology; Public administration; Computer science; Engineering; Law","score_opus":0.13572695358587547,"score_gpt":0.46709632153462205,"score_spread":0.3313693679487466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183451661","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008669186,0.06909935,0.004727026,0.8911448,0.0018712607,0.000039275503,0.00002979426,0.000028206165,0.024391077],"genre_scores_gemma":[0.82668793,0.08808627,0.010875368,0.065061994,0.002934637,0.00026077253,0.00004581292,0.00008291765,0.005964329],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9320333,0.046700727,0.0022264146,0.00175408,0.010652104,0.0066335103],"domain_scores_gemma":[0.8042049,0.1275642,0.0063791284,0.0037516325,0.044196058,0.013904135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09453895,0.0007441158,0.0019197024,0.0032657338,0.013223643,0.039629493,0.006655422,0.009024436,0.0032894786],"category_scores_gemma":[0.086857095,0.0005761143,0.00091426645,0.005204655,0.062448885,0.04166558,0.007487863,0.011085576,0.00044919577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007167263,0.000064741434,0.004194131,0.0013366351,0.000037618378,0.0002039702,0.02282851,0.00051120634,0.00013964812,0.8760219,0.022566613,0.07202337],"study_design_scores_gemma":[0.000028283348,0.00010657302,0.007320994,0.007909664,0.000054287437,0.00044058703,0.27171567,0.0029530728,0.0005085714,0.5504567,0.15830006,0.00020552776],"about_ca_topic_score_codex":0.1265264,"about_ca_topic_score_gemma":0.116819,"teacher_disagreement_score":0.1265264,"about_ca_system_score_codex":0.040787585,"about_ca_system_score_gemma":0.07495842,"threshold_uncertainty_score":0.49997574},"labels":[],"label_agreement":null},{"id":"W2184444384","doi":"10.3138/cjpe.19.007","title":"The Analysis of Focus Groups in Published Research Articles","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Focus Groups and Qualitative Methods","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Focus group; sort; Inter-rater reliability; Coding (social sciences); Focus (optics); Psychology; Computer science; Sociology; Applied psychology; Information retrieval; Social science; Developmental psychology","score_opus":0.39882849553213817,"score_gpt":0.5595611463391841,"score_spread":0.1607326508070459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184444384","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77924883,0.037534293,0.100344695,0.007323374,0.0039267926,0.014156173,0.0050632725,0.00056431687,0.05183832],"genre_scores_gemma":[0.8809252,0.018335916,0.06725807,0.0020312893,0.0014425911,0.021179276,0.0026763943,0.00035547995,0.005795806],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.7910122,0.13352998,0.020626578,0.0053284178,0.04665621,0.0028465276],"domain_scores_gemma":[0.19918922,0.7060473,0.02664297,0.009988546,0.05711108,0.0010208731],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15460995,0.0011983847,0.0018669065,0.052102458,0.0053211725,0.0073962654,0.0031368556,0.0024273505,0.006362868],"category_scores_gemma":[0.46140274,0.0011666535,0.0016177277,0.032389853,0.004650881,0.0075843083,0.005936365,0.0012917903,0.0011997283],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081362604,0.00026832407,0.028319517,0.030078655,0.00075292255,0.00200264,0.65807164,0.00043343444,0.0047604213,0.009635782,0.008815827,0.25604722],"study_design_scores_gemma":[0.00031871334,0.0011588072,0.09458847,0.04913208,0.0014324925,0.003004535,0.67345464,0.0020413133,0.018064331,0.017187262,0.13927552,0.00034183933],"about_ca_topic_score_codex":0.0017808225,"about_ca_topic_score_gemma":0.0019403804,"teacher_disagreement_score":0.8453901,"about_ca_system_score_codex":0.0077333935,"about_ca_system_score_gemma":0.0069218758,"threshold_uncertainty_score":0.81766534},"labels":[],"label_agreement":null},{"id":"W2185313922","doi":"10.3138/cjpe.29.3.1","title":"Building the Foundation for the CES Professional Designation Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Psychology; Archaeology; History","score_opus":0.6387757866045108,"score_gpt":0.6092163742699974,"score_spread":0.029559412334513424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185313922","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036957134,0.0017610537,0.10809966,0.65527636,0.0047473577,0.0019142273,0.00026228427,0.00067321735,0.19030873],"genre_scores_gemma":[0.6980892,0.001874836,0.16726826,0.04650839,0.0014056826,0.002746663,0.00043071623,0.00035351075,0.08132283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92927146,0.03461302,0.0030855578,0.003827611,0.020814283,0.00838802],"domain_scores_gemma":[0.77839786,0.051886316,0.005932121,0.01492758,0.11183548,0.037020605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13150595,0.00072765816,0.00055069424,0.004400374,0.011664016,0.012058738,0.0036559016,0.0063401354,0.011891703],"category_scores_gemma":[0.12538296,0.00076177396,0.000848301,0.002154319,0.01732673,0.0070357737,0.017871657,0.0109340325,0.0018260995],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009090327,0.00060105027,0.0050750007,0.00031889393,0.000020618814,0.00025679465,0.009462375,0.002709863,0.0006514044,0.7475447,0.101407334,0.13186106],"study_design_scores_gemma":[0.000110185705,0.00026847806,0.006828647,0.0015067002,0.000019037503,0.00012336024,0.01642804,0.0043560886,0.0020945019,0.12169948,0.8464427,0.00012277928],"about_ca_topic_score_codex":0.1473158,"about_ca_topic_score_gemma":0.16437735,"teacher_disagreement_score":0.1473158,"about_ca_system_score_codex":0.05875874,"about_ca_system_score_gemma":0.2808949,"threshold_uncertainty_score":0.69547826},"labels":[],"label_agreement":null},{"id":"W2185731738","doi":"10.3138/cjpe.19.001","title":"The Role of the Evaluator in a Political World","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Politics; Power (physics); Simplicity; Argument (complex analysis); Elite; Ambiguity; Servant; Sociology; Independence (probability theory); Fundamentalism; Environmental ethics; Law; Political science; Political economy; Epistemology; Philosophy","score_opus":0.22938257899034617,"score_gpt":0.5204448598505118,"score_spread":0.2910622808601656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185731738","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016136382,0.034804534,0.051390193,0.44197908,0.005098042,0.0001088389,0.000057678513,0.00020149106,0.4502237],"genre_scores_gemma":[0.86358607,0.01425931,0.018558614,0.04648434,0.0045477366,0.00035321762,0.0000509908,0.0005031586,0.051656604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8913752,0.092369564,0.0012492584,0.003496347,0.0081802355,0.003329415],"domain_scores_gemma":[0.9475804,0.037814025,0.001884446,0.002379418,0.0058730417,0.004468746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.058461428,0.0008056386,0.0010516278,0.0038614096,0.018343117,0.04147071,0.0018737743,0.0064550503,0.004218417],"category_scores_gemma":[0.05238507,0.00067932345,0.00042400783,0.0035864455,0.091330424,0.02313066,0.0076118317,0.012217469,0.0010638468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001827646,0.000018508055,0.00031429913,0.00006591958,0.000008860087,0.00007220335,0.018766118,0.00016424846,0.00008799622,0.95262295,0.016833909,0.011026742],"study_design_scores_gemma":[0.000032185664,0.000043848373,0.0005625318,0.00067968154,0.000012738148,0.00014525982,0.020770198,0.0007656987,0.00036833945,0.6220622,0.35450792,0.000049480503],"about_ca_topic_score_codex":0.006378277,"about_ca_topic_score_gemma":0.005940548,"teacher_disagreement_score":0.058461428,"about_ca_system_score_codex":0.013731429,"about_ca_system_score_gemma":0.0151489,"threshold_uncertainty_score":0.30917728},"labels":[],"label_agreement":null},{"id":"W2188387579","doi":"10.3138/cjpe.019.002","title":"Reporting on Outcomes: Setting Performance Expectations and Telling Performance Stories","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Canada","funders":"","keywords":"Outcome (game theory); Chart; Public relations; Actuarial science; Business; Psychology; Political science; Economics; Microeconomics; Statistics","score_opus":0.4090562215533984,"score_gpt":0.5347074822731473,"score_spread":0.12565126071974897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188387579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15195686,0.0017505758,0.5173674,0.14046383,0.001242352,0.0021437951,0.0022427894,0.003244074,0.17958823],"genre_scores_gemma":[0.79986703,0.0013026486,0.19018944,0.0021510979,0.00030091894,0.0013959422,0.00080929813,0.00026453758,0.0037191166],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8623679,0.10562748,0.009063789,0.0020352723,0.018603718,0.0023019195],"domain_scores_gemma":[0.5885613,0.2771844,0.048098873,0.024239596,0.053322285,0.008593654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13499267,0.0012009374,0.00052310363,0.0050444617,0.004015363,0.0168375,0.002463764,0.0027867202,0.00431065],"category_scores_gemma":[0.29031834,0.0006777737,0.000599569,0.0030353768,0.008964244,0.02110801,0.0076236776,0.0043365476,0.0010833229],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074540375,0.0005456429,0.042355616,0.0014216867,0.000102325364,0.00071806565,0.06965319,0.011282896,0.0015891334,0.3031508,0.065797664,0.50263757],"study_design_scores_gemma":[0.00023932804,0.0020273414,0.04055053,0.006001134,0.00024792607,0.00084908825,0.11194831,0.056916773,0.028248556,0.42621472,0.32573077,0.0010256037],"about_ca_topic_score_codex":0.0081196,"about_ca_topic_score_gemma":0.0051956316,"teacher_disagreement_score":0.13499267,"about_ca_system_score_codex":0.010593505,"about_ca_system_score_gemma":0.013618991,"threshold_uncertainty_score":0.71391803},"labels":[],"label_agreement":null},{"id":"W2188606052","doi":"10.3138/cjpe.0028.011","title":"A Good Start, but We Can Do Better","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Globe; Engineering ethics; Computer science; Psychology; Engineering management; Process management; Knowledge management; Risk analysis (engineering); Business; Management science; Engineering","score_opus":0.31888172658606007,"score_gpt":0.4975859348037114,"score_spread":0.17870420821765132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188606052","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038190137,0.010307518,0.0041821375,0.94109917,0.022295339,0.000080461,0.00026572385,0.00037084988,0.02101675],"genre_scores_gemma":[0.04210814,0.032080907,0.03500331,0.7614429,0.024988197,0.00034845984,0.0009500818,0.0015353349,0.10154272],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9723858,0.008907099,0.0018935058,0.0018408941,0.012279979,0.0026927239],"domain_scores_gemma":[0.8633866,0.03488118,0.004135776,0.010365559,0.071371675,0.015859146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045211907,0.0018181873,0.0022144313,0.003883231,0.008952899,0.017066702,0.0034904694,0.009884306,0.06824603],"category_scores_gemma":[0.14707194,0.00068074634,0.0019463819,0.0025296852,0.014048482,0.027976207,0.009232402,0.027000776,0.03194931],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005256478,0.00006573563,0.0009429418,0.0005491868,0.00004632354,0.00008161488,0.0011229505,0.00011952553,0.0001846663,0.030938327,0.8949285,0.07096759],"study_design_scores_gemma":[0.000028957269,0.00004794793,0.0009140583,0.002453103,0.000039353235,0.0001684201,0.0038510442,0.00018858325,0.00028178093,0.034889504,0.95703435,0.00010291064],"about_ca_topic_score_codex":0.11731861,"about_ca_topic_score_gemma":0.1522988,"teacher_disagreement_score":0.11731861,"about_ca_system_score_codex":0.014226317,"about_ca_system_score_gemma":0.041144487,"threshold_uncertainty_score":0.2391063},"labels":[],"label_agreement":null},{"id":"W2188824898","doi":"10.3138/cjpe.0020.004","title":"Two Decades of the <i>Canadian Journal of Program Evaluation</i> : A Content Analysis","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Milestone; Editorial board; Content analysis; Library science; Descriptive statistics; History; Sociology; Social science; Computer science; Statistics; Mathematics","score_opus":0.43548977213527457,"score_gpt":0.5284019432527968,"score_spread":0.0929121711175222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188824898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61453176,0.09237478,0.008656415,0.111188434,0.012008906,0.002413821,0.010853751,0.00033089585,0.14764127],"genre_scores_gemma":[0.8978544,0.042664662,0.016472926,0.008653469,0.0028699841,0.0019319396,0.004025506,0.00033060825,0.025196476],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97346956,0.003813983,0.0023108027,0.0010769329,0.01799537,0.0013333911],"domain_scores_gemma":[0.8028624,0.042025816,0.013643512,0.003764428,0.12926771,0.0084360875],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.032058302,0.00041317233,0.00088374113,0.027719649,0.008792662,0.014143109,0.0012790089,0.0009173305,0.004798028],"category_scores_gemma":[0.08794782,0.00053224474,0.0005249112,0.04212042,0.00437531,0.004185707,0.0029440385,0.0018067146,0.00045400098],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005482987,0.00039314374,0.14060943,0.0060674995,0.00028428782,0.0007959411,0.116852626,0.00025714238,0.0033138671,0.039634403,0.18665831,0.504585],"study_design_scores_gemma":[0.000040908697,0.00026615598,0.38518623,0.0075542945,0.00029289923,0.00044937345,0.10765623,0.0005783622,0.0024772317,0.003139964,0.49220163,0.0001568095],"about_ca_topic_score_codex":0.16940992,"about_ca_topic_score_gemma":0.30669677,"teacher_disagreement_score":0.9722803,"about_ca_system_score_codex":0.029470855,"about_ca_system_score_gemma":0.10486789,"threshold_uncertainty_score":0.33684772},"labels":[],"label_agreement":null},{"id":"W219521914","doi":"10.3138/cjpe.0025.010","title":"Successful or Not: It Depends on Your Frame of Reference","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Frame (networking); Point (geometry); Frame of reference; Key (lock); Psychology; Knowledge management; Computer science; Engineering ethics; Process management; Business; Computer security; Engineering","score_opus":0.7666920347927102,"score_gpt":0.5786637113913813,"score_spread":0.1880283234013289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W219521914","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034960885,0.01231939,0.11850689,0.50165886,0.03326332,0.0015197679,0.00089094386,0.0010228486,0.2958571],"genre_scores_gemma":[0.7406821,0.010892721,0.116340496,0.058447763,0.007515802,0.002365191,0.0008185278,0.002218305,0.06071917],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90711004,0.048931506,0.006922855,0.0041520363,0.029672945,0.0032106563],"domain_scores_gemma":[0.74525285,0.104936786,0.01595283,0.01968692,0.10659746,0.007573119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07751524,0.00083312317,0.0019173922,0.005111321,0.006465048,0.018421184,0.0028564485,0.00560486,0.011498692],"category_scores_gemma":[0.2983591,0.00052022014,0.0008776543,0.0030811776,0.011540664,0.015826374,0.005710733,0.0068359813,0.0067383708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053728087,0.00023675202,0.009681882,0.0020503402,0.00016325962,0.0006579049,0.084603034,0.00043706587,0.0030461003,0.26119813,0.28663555,0.35075268],"study_design_scores_gemma":[0.00011940642,0.00031488787,0.013780004,0.012062824,0.00028660477,0.00088214205,0.0699472,0.001927871,0.004067445,0.14890084,0.74725777,0.00045309658],"about_ca_topic_score_codex":0.010748865,"about_ca_topic_score_gemma":0.011926895,"teacher_disagreement_score":0.07751524,"about_ca_system_score_codex":0.00897011,"about_ca_system_score_gemma":0.010953878,"threshold_uncertainty_score":0.40994465},"labels":[],"label_agreement":null},{"id":"W220182117","doi":"10.3138/cjpe.17.001","title":"Improving Social Policy with National Data: A Comparison of Social Support for Students Among Canadian Provinces","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Socioeconomic status; Social support; Prosocial behavior; Psychology; Emotional support; Census; Immigration; Multilevel model; Survey data collection; Social psychology; Demography; Geography; Sociology","score_opus":0.23200503594318395,"score_gpt":0.5050164749738383,"score_spread":0.27301143903065433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W220182117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903217,0.0003908219,0.00016410566,0.00047061112,0.00001337022,0.00006524622,0.0048695155,0.000014123733,0.0036905396],"genre_scores_gemma":[0.99758124,0.000122035744,0.0001621068,0.000029262083,0.0000021698822,0.000023800298,0.0018156026,0.0000036525682,0.0002601434],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954,0.0009888208,0.00025170975,0.000368098,0.0016525084,0.0013389479],"domain_scores_gemma":[0.99146456,0.0011411234,0.0012492073,0.00045234445,0.0044576726,0.0012350729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004210203,0.00025478454,0.00049188663,0.002372104,0.0025750997,0.0018825738,0.0012699957,0.00029673494,0.0017322716],"category_scores_gemma":[0.020090204,0.00019225023,0.0006532494,0.008253027,0.00057923124,0.0005572604,0.0016534975,0.0005564552,0.000121366545],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001953273,0.00007413647,0.98520523,0.00005053547,0.0001065786,0.000025641266,0.0008240859,0.0005884429,0.000053804426,0.00025145424,0.0013785346,0.011246101],"study_design_scores_gemma":[0.000011354112,0.00002623071,0.9966131,0.000022552242,0.000028412405,0.000005784343,0.0016826731,0.0005901395,0.00005101188,0.000028057833,0.00093424134,0.00000641776],"about_ca_topic_score_codex":0.99251574,"about_ca_topic_score_gemma":0.9944061,"teacher_disagreement_score":0.036692284,"about_ca_system_score_codex":0.036692284,"about_ca_system_score_gemma":0.04344724,"threshold_uncertainty_score":0.26622242},"labels":[],"label_agreement":null},{"id":"W2228177330","doi":"10.3138/cjpe.026.003","title":"Addressing the Challenges Encountered During a Developmental Evaluation: Implications for Evaluation Practice","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Perspective (graphical); Evaluation methods; Program evaluation; Psychology; Government (linguistics); Engineering ethics; Knowledge management; Process management; Medical education; Management science; Political science; Computer science; Business; Medicine; Engineering; Public administration","score_opus":0.8348360624185777,"score_gpt":0.6002670065070299,"score_spread":0.23456905591154775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228177330","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07390438,0.037235156,0.24314478,0.56952155,0.0057161916,0.008224281,0.00012149917,0.0009719642,0.06116024],"genre_scores_gemma":[0.60077316,0.01031477,0.33830225,0.036888447,0.0013632464,0.006919856,0.00009313114,0.00045613202,0.0048890645],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.3440154,0.56161994,0.034342203,0.006122866,0.04696998,0.006929655],"domain_scores_gemma":[0.21898256,0.5851072,0.02464549,0.01603955,0.13751282,0.017712444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5843487,0.001249053,0.0023166663,0.0057309256,0.018313188,0.024543399,0.007070913,0.009229776,0.003182311],"category_scores_gemma":[0.64920163,0.001627154,0.0016185496,0.004000848,0.021490712,0.01917372,0.017914258,0.015674194,0.0011405259],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057904504,0.0014172887,0.019882783,0.007907379,0.00034953118,0.004056654,0.25405258,0.004468784,0.0017250944,0.07140253,0.05783278,0.57632554],"study_design_scores_gemma":[0.0006213227,0.0014253046,0.02059788,0.04320857,0.000326148,0.0055833464,0.3990986,0.010594317,0.0050006164,0.19125466,0.3212739,0.0010153585],"about_ca_topic_score_codex":0.014984707,"about_ca_topic_score_gemma":0.026538692,"teacher_disagreement_score":0.41565132,"about_ca_system_score_codex":0.03249208,"about_ca_system_score_gemma":0.09903822,"threshold_uncertainty_score":0.5125721},"labels":[],"label_agreement":null},{"id":"W223375945","doi":"10.3138/cjpe.15.003","title":"Evaluating Policy Outcomes: Federal Economic Development Programs in Atlantic Canada","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Canadian Policy and Governance","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Atlantic Canada Opportunities Agency","funders":"","keywords":"Agency (philosophy); Mandate; Unemployment; Revenue; Government (linguistics); Economics; Economic impact analysis; Business; Public economics; Economic growth; Finance; Political science; Sociology","score_opus":0.15684117218464694,"score_gpt":0.4095520808445661,"score_spread":0.2527109086599192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W223375945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92818534,0.0020318942,0.0021412773,0.008332919,0.00013481568,0.00477694,0.0044415626,0.00011231962,0.049843006],"genre_scores_gemma":[0.98859054,0.0006607578,0.0040367465,0.00055320485,0.000023330766,0.0018037604,0.0015250677,0.00001162728,0.002794994],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9649201,0.014567099,0.0010984566,0.0009870759,0.012118423,0.006308892],"domain_scores_gemma":[0.93480843,0.015967906,0.0053627184,0.001810968,0.033997726,0.008052266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039918397,0.00048414638,0.00062798115,0.0032747283,0.006841292,0.0040749903,0.002470258,0.00101126,0.0019841318],"category_scores_gemma":[0.057842903,0.00039196518,0.0005596581,0.008284136,0.0026595336,0.0014647334,0.0042232997,0.0023536552,0.00015855214],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.004754506,0.009377158,0.46527052,0.0022153351,0.0008308755,0.000341123,0.017862331,0.028872952,0.00075485854,0.04179696,0.044477943,0.38344535],"study_design_scores_gemma":[0.0014801179,0.0027057608,0.898669,0.0013864796,0.00053962774,0.000046223082,0.022508841,0.018713342,0.0034133897,0.004961378,0.04541152,0.00016433594],"about_ca_topic_score_codex":0.98126054,"about_ca_topic_score_gemma":0.985876,"teacher_disagreement_score":0.780005,"about_ca_system_score_codex":0.21999499,"about_ca_system_score_gemma":0.280499,"threshold_uncertainty_score":0.9046953},"labels":[],"label_agreement":null},{"id":"W2274124070","doi":"10.3138/cjpe.21.003","title":"Understanding Cultural Competence Through the Evaluation of “Breaking the Silence: A Project to Generate Critical Knowledge About Family Violence within Immigrant Communities”","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Salient; Silence; Cultural competence; Competence (human resources); Immigration; Psychology; Cultural knowledge; Social psychology; Sociology; Pedagogy; Political science","score_opus":0.6873320058970728,"score_gpt":0.5646945822728154,"score_spread":0.12263742362425734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274124070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9539906,0.00022699239,0.012350688,0.005015511,0.0001147242,0.003934534,0.000043338456,0.000089765796,0.024233803],"genre_scores_gemma":[0.9742011,0.00031698772,0.018732721,0.00063701294,0.00003110955,0.0022496032,0.00005043668,0.00003889246,0.0037421642],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95724154,0.03602541,0.00077236776,0.0007109419,0.0029851794,0.0022645027],"domain_scores_gemma":[0.9522458,0.028273687,0.0027381957,0.0017944045,0.00888409,0.0060638078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05262571,0.00075810886,0.00039069713,0.000937542,0.007409408,0.004409312,0.0020441213,0.0021482396,0.0028685823],"category_scores_gemma":[0.060078952,0.00041409166,0.00051257265,0.00040632475,0.006988666,0.001984585,0.008750511,0.0042409445,0.00032928513],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007937041,0.01014209,0.01008125,0.0012093267,0.000070647955,0.0011197202,0.6870671,0.002379032,0.006968067,0.010247876,0.007653749,0.26226747],"study_design_scores_gemma":[0.00077368435,0.012286165,0.017566977,0.0024551235,0.00017262044,0.00095853105,0.788912,0.006058317,0.046223395,0.013711272,0.11066458,0.00021737108],"about_ca_topic_score_codex":0.0050964733,"about_ca_topic_score_gemma":0.008369077,"teacher_disagreement_score":0.9949035,"about_ca_system_score_codex":0.0064427406,"about_ca_system_score_gemma":0.019724207,"threshold_uncertainty_score":0.27831465},"labels":[],"label_agreement":null},{"id":"W2274776964","doi":"10.3138/cjpe.022.003","title":"Developing a Tool to Measure Knowledge Exchange Outcomes","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"USable; Knowledge management; Measure (data warehouse); Process (computing); Computer science; Best practice; Reliability (semiconductor); Point (geometry); Process management; Business; World Wide Web; Data mining","score_opus":0.8485447477899826,"score_gpt":0.719432757191686,"score_spread":0.1291119905982966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274776964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6067127,0.0008142761,0.27601427,0.003594269,0.0007518466,0.028811209,0.00916543,0.003600551,0.070535414],"genre_scores_gemma":[0.53742445,0.00043910404,0.41537327,0.00042655924,0.000073751806,0.037319105,0.0049980697,0.00016809806,0.0037775943],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9584577,0.018849216,0.0075483886,0.0012684911,0.012740731,0.0011355163],"domain_scores_gemma":[0.83510286,0.1105197,0.01598569,0.004806349,0.031780362,0.0018050598],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05321929,0.00082627096,0.0011178864,0.011232824,0.0013002106,0.0034424656,0.0015900627,0.0012788646,0.005604278],"category_scores_gemma":[0.13023163,0.00047490225,0.0019383924,0.006879717,0.001044366,0.0051722582,0.0037472465,0.0019344102,0.0016312762],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057493616,0.002042865,0.19735372,0.0019416768,0.00032324728,0.00009049097,0.0065836436,0.0023408744,0.0017611622,0.010230386,0.012590192,0.7641668],"study_design_scores_gemma":[0.001105036,0.009350845,0.76236236,0.0048518255,0.0009598624,0.000656968,0.021514816,0.038451027,0.033287246,0.037299633,0.08946447,0.00069584604],"about_ca_topic_score_codex":0.0011204573,"about_ca_topic_score_gemma":0.0011074039,"teacher_disagreement_score":0.9467807,"about_ca_system_score_codex":0.0031844976,"about_ca_system_score_gemma":0.0053118146,"threshold_uncertainty_score":0.28145385},"labels":[],"label_agreement":null},{"id":"W2283637488","doi":"10.3138/cjpe.29.3.vii","title":"Introduction to Professionalization of Evaluation in Canada","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Engineering ethics; Political science; Professional development; Public relations; Professional association; Library science; Sociology; Medical education; Pedagogy; Engineering; Computer science; Law; Medicine","score_opus":0.40279152132935725,"score_gpt":0.5399497411847914,"score_spread":0.1371582198554342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2283637488","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031612557,0.09781751,0.034274347,0.39593956,0.022024138,0.0010917857,0.0011569123,0.00122318,0.44331142],"genre_scores_gemma":[0.1916764,0.21201213,0.09611835,0.16002972,0.008250928,0.0019661414,0.0020183376,0.001803102,0.3261248],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95644814,0.008623948,0.0026312922,0.0024858604,0.02510009,0.004710658],"domain_scores_gemma":[0.8978099,0.016554235,0.0015619698,0.002231088,0.06984154,0.01200126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037137415,0.00074630807,0.0009629128,0.0069311378,0.014650089,0.01480928,0.0034526098,0.0055371756,0.018710526],"category_scores_gemma":[0.06258437,0.000971051,0.00088829064,0.011971973,0.014562892,0.0049253376,0.0072551183,0.009618955,0.004330404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00003543634,0.00007723329,0.001150183,0.0009826485,0.000010429259,0.00024358828,0.0055347374,0.00045331012,0.00021345845,0.1316387,0.6329164,0.22674388],"study_design_scores_gemma":[0.0000081031385,0.000012605193,0.0027135503,0.00148293,0.0000040551276,0.000117449454,0.0016566307,0.00021194338,0.00009507638,0.010334178,0.983316,0.00004740461],"about_ca_topic_score_codex":0.9271729,"about_ca_topic_score_gemma":0.9509911,"teacher_disagreement_score":0.8155248,"about_ca_system_score_codex":0.1844752,"about_ca_system_score_gemma":0.38110316,"threshold_uncertainty_score":0.94589317},"labels":[],"label_agreement":null},{"id":"W2289811664","doi":"10.3138/cjpe.20.001","title":"Evaluability Assessment of a Survivors of Torture Program: Lessons Learned","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Torture; Accountability; Logic model; Program evaluation; Process (computing); Political science; Psychology; Public relations; Public administration; Computer science; Human rights; Law","score_opus":0.3722469645419353,"score_gpt":0.6063679190213934,"score_spread":0.23412095447945813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2289811664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8887905,0.0011954433,0.06423614,0.014745335,0.0001884144,0.005193666,0.00017867901,0.00034552047,0.025126342],"genre_scores_gemma":[0.94191647,0.00034992798,0.054562125,0.0004055598,0.000036363494,0.0012959968,0.000117272575,0.000032100186,0.0012842318],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9430974,0.040751953,0.0029831782,0.001054294,0.010216529,0.0018966692],"domain_scores_gemma":[0.8577762,0.07911028,0.0068253195,0.005012904,0.047182765,0.00409257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.085974246,0.00056639855,0.00067671295,0.0027197124,0.002050648,0.0033776283,0.0017731594,0.00084669277,0.00171037],"category_scores_gemma":[0.11768459,0.0002435004,0.0009137553,0.0013072087,0.0014516852,0.004222832,0.0033142068,0.0021413777,0.0001598822],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006487241,0.0052318615,0.117848314,0.0018619398,0.00017610511,0.00047013568,0.050508756,0.004880302,0.0020599782,0.00867826,0.006581613,0.8010541],"study_design_scores_gemma":[0.000728245,0.014486689,0.53104824,0.008185885,0.00050189404,0.0012828792,0.22890814,0.0744729,0.026959246,0.047100227,0.065827265,0.0004984282],"about_ca_topic_score_codex":0.016114218,"about_ca_topic_score_gemma":0.019395677,"teacher_disagreement_score":0.085974246,"about_ca_system_score_codex":0.009187624,"about_ca_system_score_gemma":0.016884975,"threshold_uncertainty_score":0.45468068},"labels":[],"label_agreement":null},{"id":"W2292486103","doi":"10.3138/cjpe.024.002","title":"Learning Through Evaluation? Reflections on Two Federal Community-Building Initiatives","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Western University","funders":"","keywords":"Stakeholder; Government (linguistics); Corporate governance; Policy learning; Political science; Public relations; Community engagement; Public administration; Stakeholder engagement; Collaborative governance; Action (physics); Business; Computer science","score_opus":0.6156032355612,"score_gpt":0.6355201743114897,"score_spread":0.01991693875028966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292486103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48570842,0.0030093098,0.012161646,0.4293215,0.002026107,0.002518917,0.00018282255,0.00023568433,0.06483557],"genre_scores_gemma":[0.9597897,0.00077516667,0.0063891425,0.021386022,0.00026687604,0.0013229914,0.000060320686,0.00013490857,0.009874773],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7863214,0.17167863,0.002807359,0.004615096,0.01223777,0.022339728],"domain_scores_gemma":[0.7746875,0.15753108,0.0047336523,0.008273578,0.027251696,0.027522437],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19265522,0.0009200751,0.0011607584,0.0023395568,0.052675083,0.021407701,0.0076201605,0.01637576,0.0042593107],"category_scores_gemma":[0.1647966,0.0012177634,0.0011365213,0.003021481,0.03201214,0.009827884,0.029296238,0.022694586,0.00044809323],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033592203,0.004210659,0.0047796946,0.00057180144,0.0000560242,0.004121655,0.73516834,0.0012961247,0.0015588845,0.09649716,0.05200438,0.099399365],"study_design_scores_gemma":[0.00019779672,0.00072087534,0.00474966,0.0008144151,0.000039275757,0.0005976089,0.72823125,0.0014259889,0.0028592765,0.01685295,0.24334331,0.00016764615],"about_ca_topic_score_codex":0.07198215,"about_ca_topic_score_gemma":0.12115761,"teacher_disagreement_score":0.92801785,"about_ca_system_score_codex":0.054893512,"about_ca_system_score_gemma":0.08605649,"threshold_uncertainty_score":0.99559987},"labels":[],"label_agreement":null},{"id":"W2294993183","doi":"","title":"Reviewer Acknowledgement / Remerciements aux lecteurs","year":2012,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Academic Writing and Publishing","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Acknowledgement; Psychology; Computer science","score_opus":0.23769820185154977,"score_gpt":0.39201952647908733,"score_spread":0.15432132462753756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294993183","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052292796,0.0036223629,0.002751556,0.18644941,0.8002306,0.00044770888,0.000918603,0.0007412962,0.0043155015],"genre_scores_gemma":[0.038534515,0.007154337,0.013311641,0.26626834,0.47749972,0.004016443,0.0020004064,0.0027395668,0.18847501],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9539439,0.009177133,0.0077749654,0.0035665317,0.02384703,0.0016904784],"domain_scores_gemma":[0.25466645,0.027392741,0.014738112,0.0076097064,0.68576974,0.009823327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030674256,0.0017583735,0.0030992432,0.007800639,0.0047647366,0.00760872,0.0038222282,0.007149088,0.036254443],"category_scores_gemma":[0.41474885,0.0010613677,0.0022537517,0.0032317685,0.0025002442,0.004183408,0.0047964915,0.008485924,0.024649998],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032784737,0.0000064154237,0.0004168062,0.00034051744,0.000018056462,0.00026888086,0.00053939014,0.000021801512,0.00023925115,0.0005559688,0.9901599,0.007400136],"study_design_scores_gemma":[0.000070999115,0.000022453894,0.0017343574,0.0013430921,0.00009018646,0.001041762,0.0015501363,0.0004744299,0.0006657795,0.0011146769,0.9917997,0.000092525435],"about_ca_topic_score_codex":0.0135782035,"about_ca_topic_score_gemma":0.021097155,"teacher_disagreement_score":0.036254443,"about_ca_system_score_codex":0.007727139,"about_ca_system_score_gemma":0.015340371,"threshold_uncertainty_score":0.16222292},"labels":[],"label_agreement":null},{"id":"W2297733333","doi":"10.3138/cjpe.29.1.138","title":"Chilisa, B. (2012). <i>Indigenous Research Methodologies.</i>","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Cultures and Socio-Education","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Psychology; Sociology; Political science; Biology","score_opus":0.36189966519442385,"score_gpt":0.5320901100763179,"score_spread":0.17019044488189405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297733333","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00867553,0.21145785,0.069856875,0.40498003,0.024327656,0.0024099508,0.004303025,0.0012957813,0.27269328],"genre_scores_gemma":[0.24673833,0.27440208,0.20695223,0.074899174,0.0051603517,0.007422177,0.0036210087,0.0014723403,0.17933233],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99287814,0.0029565282,0.0004697707,0.00031433158,0.003099115,0.00028205052],"domain_scores_gemma":[0.91223246,0.043174356,0.0034072127,0.0025415563,0.035390962,0.0032534525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023310812,0.00075852725,0.00055584963,0.006495918,0.008581038,0.006143488,0.002554516,0.0029736625,0.0128517635],"category_scores_gemma":[0.076567784,0.00075292937,0.00056743494,0.0076997774,0.0057938653,0.007600944,0.0036719001,0.008190353,0.0050092316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098816665,0.0000682221,0.004518689,0.002904522,0.000043002812,0.00013931091,0.01925454,0.00011661406,0.0005824262,0.028210733,0.63505095,0.3090121],"study_design_scores_gemma":[0.00004702619,0.0001044587,0.019084476,0.012708459,0.00018976006,0.0004196166,0.025942754,0.00023579765,0.0015442907,0.027668756,0.91196144,0.000093283576],"about_ca_topic_score_codex":0.1683487,"about_ca_topic_score_gemma":0.37057057,"teacher_disagreement_score":0.97668916,"about_ca_system_score_codex":0.010196515,"about_ca_system_score_gemma":0.034831032,"threshold_uncertainty_score":0.3347376},"labels":[],"label_agreement":null},{"id":"W2298222049","doi":"10.3138/cjpe.28.006","title":"Exemple d’application de l’évaluation formative centrée sur l’utilisation des résultats","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Intégré de Santé et de Services Sociaux des Laurentides","funders":"","keywords":"Formative assessment; Valuation (finance); Process (computing); Evaluation methods; Computer science; Process management; Risk analysis (engineering); Business; Psychology; Engineering; Reliability engineering; Pedagogy; Accounting","score_opus":0.29907530459644416,"score_gpt":0.4846502697928911,"score_spread":0.18557496519644695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298222049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11795196,0.001333387,0.7143464,0.012162019,0.0012489058,0.0043812445,0.00086441805,0.0032751884,0.14443642],"genre_scores_gemma":[0.4421252,0.00078372064,0.53455746,0.00088543765,0.00017875784,0.0020894813,0.0005390956,0.0005269669,0.0183139],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9470792,0.034717854,0.0021369294,0.0011849122,0.013796013,0.0010850608],"domain_scores_gemma":[0.9183102,0.05822788,0.0016755941,0.004563067,0.016496817,0.0007264358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042342328,0.0011382592,0.00066137215,0.0031166123,0.0031323584,0.0070931935,0.0018009765,0.0032030435,0.0074545587],"category_scores_gemma":[0.06550897,0.0005285867,0.0015615618,0.003074117,0.004117515,0.002573141,0.002838601,0.0029075297,0.0019923854],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018772989,0.0019013888,0.015164779,0.004092549,0.00033221729,0.0071164756,0.07304845,0.017464258,0.029823063,0.28223673,0.039336357,0.52760637],"study_design_scores_gemma":[0.0007605541,0.002592526,0.02890115,0.0049843853,0.00040804208,0.005737545,0.020708298,0.11624743,0.12999615,0.084279805,0.60478455,0.0005995114],"about_ca_topic_score_codex":0.014149839,"about_ca_topic_score_gemma":0.008246593,"teacher_disagreement_score":0.042342328,"about_ca_system_score_codex":0.0049622282,"about_ca_system_score_gemma":0.004386368,"threshold_uncertainty_score":0.22393024},"labels":[],"label_agreement":null},{"id":"W2299937421","doi":"10.3138/cjpe.28.003","title":"Outsource Versus In-House? An Identification of Organizational Conditions Influencing the Choice for Internal or External Evaluators","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outsourcing; Flemish; Pairwise comparison; Discretion; Identification (biology); Business; Public sector; Locus of control; Marketing; Computer science; Psychology; Social psychology; Political science; Law","score_opus":0.31042600741340926,"score_gpt":0.5320363808943255,"score_spread":0.22161037348091622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2299937421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877337,0.00022812192,0.0022598193,0.0007064317,0.000031675172,0.00019739708,0.00006252734,0.000015096189,0.008765205],"genre_scores_gemma":[0.99828523,0.00005681822,0.0010634013,0.00009975199,0.000011070127,0.00013690247,0.00002627923,0.000010673527,0.00030973819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9271256,0.059526138,0.0027241586,0.0020237355,0.0050173993,0.0035830147],"domain_scores_gemma":[0.6954092,0.23293298,0.030901972,0.009510519,0.015671892,0.01557355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06355909,0.00024284102,0.0004775615,0.0010775314,0.0015100793,0.00537579,0.0006518945,0.00077082665,0.005932205],"category_scores_gemma":[0.1778159,0.00023371117,0.0003843049,0.0012128911,0.0022580826,0.002224898,0.0032890036,0.0008172519,0.00064454135],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068700593,0.0021980624,0.76518005,0.00075804844,0.0002946296,0.00045320383,0.027190316,0.0011831999,0.0036262448,0.008308164,0.0029119293,0.18102609],"study_design_scores_gemma":[0.00075683,0.0031605759,0.8913553,0.0012876249,0.00029946724,0.00032053288,0.072200164,0.0038899132,0.0055521727,0.008218035,0.012810316,0.00014902299],"about_ca_topic_score_codex":0.0015950971,"about_ca_topic_score_gemma":0.002829279,"teacher_disagreement_score":0.06355909,"about_ca_system_score_codex":0.0022796784,"about_ca_system_score_gemma":0.004623576,"threshold_uncertainty_score":0.33613664},"labels":[],"label_agreement":null},{"id":"W2300085399","doi":"","title":"Evaluation of Resource Allocation Processes in Canadian Healthcare Organizations: The State of Practice","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Vancouver Coastal Health Research Institute; University of British Columbia; Canadian Centre for Applied Research in Cancer Control; Vancouver Coastal Health","funders":"","keywords":"Resource allocation; Health care; Function (biology); Resource (disambiguation); Key (lock); Process (computing); Business; Resource management (computing); Knowledge management; State (computer science); Healthcare system; Process management; Computer science; Management; Economics; Economic growth","score_opus":0.38994482572329775,"score_gpt":0.47754716761168664,"score_spread":0.08760234188838889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2300085399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62160903,0.09070317,0.023813473,0.13141908,0.0009900205,0.0035694707,0.0038045691,0.0005455506,0.123545706],"genre_scores_gemma":[0.97066957,0.010808363,0.014586392,0.0015120936,0.00006790778,0.00037267926,0.00055839046,0.000060006983,0.0013645862],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8787716,0.054931574,0.007983181,0.0041157664,0.046491675,0.007706155],"domain_scores_gemma":[0.6316072,0.12378459,0.024002662,0.007949343,0.19408138,0.018574918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11706245,0.0007878063,0.0016270245,0.008423187,0.007157074,0.010918618,0.0051287874,0.0012559204,0.0023848745],"category_scores_gemma":[0.31287074,0.0006401992,0.00086772384,0.017332267,0.00504892,0.0035149388,0.005138132,0.0025231303,0.00015884404],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0013206813,0.00058997807,0.12435162,0.006368568,0.0006107013,0.00013906027,0.023880923,0.012680029,0.0004152907,0.041956767,0.033054367,0.7546321],"study_design_scores_gemma":[0.0009788366,0.0013551944,0.69654775,0.02226349,0.00079865596,0.0001846054,0.046278827,0.04408806,0.0027301607,0.032451563,0.15115653,0.0011664038],"about_ca_topic_score_codex":0.9761511,"about_ca_topic_score_gemma":0.9777915,"teacher_disagreement_score":0.7472169,"about_ca_system_score_codex":0.25278312,"about_ca_system_score_gemma":0.36858752,"threshold_uncertainty_score":0.86666566},"labels":[],"label_agreement":null},{"id":"W2300607851","doi":"","title":"Editor's Remarks 27(2)","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.10218760977150392,"score_gpt":0.2880492411892362,"score_spread":0.18586163141773226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2300607851","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032727845,0.0028647722,0.00027908006,0.36528614,0.61939484,0.00011896093,0.00042783355,0.00016589541,0.011135121],"genre_scores_gemma":[0.0014235477,0.0010183529,0.00032582987,0.7488273,0.19837515,0.00017223146,0.00008205314,0.00009234795,0.049683172],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9874199,0.0010527023,0.0015613522,0.002384012,0.0052334378,0.0023485974],"domain_scores_gemma":[0.9778797,0.0070983632,0.0016781103,0.001641935,0.008811898,0.002890004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0136214,0.0025902216,0.00288177,0.0037271653,0.0069327,0.009487241,0.005587694,0.06095435,0.025568271],"category_scores_gemma":[0.04814672,0.00196284,0.0051410743,0.0028483206,0.003350019,0.0039364896,0.0035367196,0.042372745,0.020067465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003836545,0.0000210074,0.00013696862,0.00007200798,0.000024246081,0.00017419012,0.00003123033,0.00003081413,0.0000817777,0.0008942449,0.99563783,0.0028573347],"study_design_scores_gemma":[0.00009142564,0.000020133715,0.0016237699,0.00030944176,0.00008371625,0.00012674117,0.00007161526,0.00010817634,0.00021743582,0.001231226,0.9960562,0.000060232745],"about_ca_topic_score_codex":0.034359362,"about_ca_topic_score_gemma":0.07471044,"teacher_disagreement_score":0.06095435,"about_ca_system_score_codex":0.008191869,"about_ca_system_score_gemma":0.010353289,"threshold_uncertainty_score":0.085534394},"labels":[],"label_agreement":null},{"id":"W2301181303","doi":"","title":"Editor's Introductory Remarks","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.046890966708886254,"score_gpt":0.3958031909792963,"score_spread":0.34891222427041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2301181303","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009581901,0.0016072242,0.0001308451,0.2777999,0.71658796,0.000036405825,0.00008233407,0.00007334287,0.0035861512],"genre_scores_gemma":[0.0014608843,0.0013844189,0.0004401227,0.5685892,0.3819392,0.000100615754,0.00004820374,0.000079300095,0.045958094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98696065,0.001460687,0.0015069204,0.0019375805,0.006448788,0.0016853339],"domain_scores_gemma":[0.94805795,0.012887058,0.003892926,0.0024530727,0.026112376,0.0065966565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0132637685,0.002057865,0.0027777124,0.0030155412,0.0051732818,0.008983947,0.0050903526,0.038726147,0.030865395],"category_scores_gemma":[0.098225914,0.0012890791,0.003525758,0.0022472173,0.003431164,0.0035470175,0.002705457,0.032757938,0.023203053],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013336582,0.0000063910516,0.000038584203,0.000038259303,0.000006560318,0.000090398964,0.00001660746,0.000012179572,0.00003160617,0.00025892886,0.9977069,0.0017802719],"study_design_scores_gemma":[0.00004038405,0.000016321233,0.00056646403,0.00021102051,0.00002785876,0.00016402244,0.00010079422,0.000073163035,0.00012193716,0.000711678,0.9979348,0.00003154861],"about_ca_topic_score_codex":0.012477431,"about_ca_topic_score_gemma":0.031029819,"teacher_disagreement_score":0.038726147,"about_ca_system_score_codex":0.006993519,"about_ca_system_score_gemma":0.009702207,"threshold_uncertainty_score":0.10325503},"labels":[],"label_agreement":null},{"id":"W2309457767","doi":"10.3138/cjpe.028.001","title":"Les défis de l’évaluation développementale en recherche : une analyse d’implantation d’un projet «hôpital promoteur de santé»","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Valuation (finance); Context (archaeology); Sociology; Library science; Psychology; Computer science; Business; Geography","score_opus":0.4962628710410104,"score_gpt":0.5603129622147885,"score_spread":0.06405009117377813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2309457767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46643305,0.026330147,0.24534607,0.11239994,0.0010391286,0.003775685,0.00086729886,0.00031137478,0.14349738],"genre_scores_gemma":[0.9261191,0.0032566744,0.060048632,0.0038790945,0.00011431702,0.0032832515,0.000186533,0.00011626352,0.002996166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.478582,0.4256545,0.028902743,0.008973766,0.053138305,0.004748635],"domain_scores_gemma":[0.42863095,0.48770145,0.016460355,0.015353408,0.04931586,0.0025380012],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.369276,0.0016830356,0.0017626717,0.00788973,0.008072217,0.028133305,0.0042523555,0.0049231295,0.0018331654],"category_scores_gemma":[0.36741847,0.0014216825,0.0019146148,0.008616855,0.02660407,0.014269527,0.011664918,0.0067182304,0.0005784613],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007927441,0.0006043258,0.055513833,0.0067732064,0.00040500643,0.0008609605,0.25165328,0.0039350586,0.0022591902,0.39431432,0.0077360687,0.275152],"study_design_scores_gemma":[0.00077409996,0.0022870407,0.09100209,0.023669258,0.000740165,0.0034110998,0.41889322,0.01704881,0.01663131,0.177658,0.24727935,0.0006055777],"about_ca_topic_score_codex":0.02492975,"about_ca_topic_score_gemma":0.017151073,"teacher_disagreement_score":0.369276,"about_ca_system_score_codex":0.02425151,"about_ca_system_score_gemma":0.037948024,"threshold_uncertainty_score":0.777795},"labels":[],"label_agreement":null},{"id":"W2310610948","doi":"","title":"Informed Consent and Evaluation: 16 to 18 Year Old Participants in Evaluations","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Ethics and Legal Issues in Pediatric Healthcare","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Informed consent; Parental consent; Psychology; Ethics committee; Position (finance); Social psychology; Political science; Humanities; Medicine; Business; Philosophy; Public administration","score_opus":0.35098771201870843,"score_gpt":0.5219570172276162,"score_spread":0.1709693052089078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2310610948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3358775,0.014453558,0.090529844,0.16039346,0.0078550335,0.12592015,0.0018268481,0.00056653033,0.2625771],"genre_scores_gemma":[0.74981236,0.008038912,0.080107436,0.03357919,0.0013161553,0.09556196,0.00094688067,0.00017873195,0.030458296],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.73729086,0.21874925,0.018619975,0.003850807,0.011401776,0.010087301],"domain_scores_gemma":[0.8127954,0.08890558,0.01722083,0.02378987,0.036049504,0.021238727],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23184264,0.0007959202,0.0011765957,0.0017907694,0.008544645,0.005827806,0.0023052501,0.005651748,0.012875038],"category_scores_gemma":[0.26580578,0.0010455666,0.0012773289,0.0012515176,0.0073888856,0.006843794,0.0080267005,0.006786502,0.0030490044],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027525134,0.0018980129,0.05005809,0.003952054,0.00016572453,0.0090194475,0.3043321,0.00066526607,0.0036030528,0.10370496,0.13986166,0.3799871],"study_design_scores_gemma":[0.0014387288,0.0029830518,0.06409515,0.019053712,0.00015789624,0.008125578,0.14779086,0.0015742172,0.0064552785,0.06007996,0.68771946,0.0005261562],"about_ca_topic_score_codex":0.011356601,"about_ca_topic_score_gemma":0.030113433,"teacher_disagreement_score":0.76815736,"about_ca_system_score_codex":0.0069789337,"about_ca_system_score_gemma":0.087664545,"threshold_uncertainty_score":0.9472748},"labels":[],"label_agreement":null},{"id":"W2311752326","doi":"10.3138/cjpe.028.004","title":"Comparison of the Use of Self-Report Surveys and Organizational Documents in Knowledge Translation Research","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McMaster University; Brock University","funders":"","keywords":"Outcome (game theory); Computer science; Knowledge management; Psychology","score_opus":0.9236146674577769,"score_gpt":0.747266931184118,"score_spread":0.17634773627365885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2311752326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9131652,0.0098734,0.047447946,0.0022782953,0.00083034515,0.012591304,0.002653954,0.0002156924,0.010943839],"genre_scores_gemma":[0.93333596,0.0024127539,0.042308092,0.0007671226,0.000233716,0.018964585,0.0012402463,0.00005669212,0.00068085943],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.3033851,0.6093897,0.04445108,0.005437917,0.035748594,0.0015876084],"domain_scores_gemma":[0.14258242,0.71589303,0.074057125,0.02459627,0.041147105,0.0017241167],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34435079,0.0010757758,0.002302509,0.011459287,0.0012482045,0.006412139,0.001669231,0.0023281933,0.0019292671],"category_scores_gemma":[0.67005813,0.0011112054,0.0033078117,0.013861686,0.0026616682,0.0055598104,0.0043389243,0.001973979,0.00045585356],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025824457,0.006107036,0.40795743,0.01746135,0.011238425,0.0001339491,0.028865615,0.0030536985,0.001598368,0.0053523127,0.0023299232,0.49007747],"study_design_scores_gemma":[0.015232523,0.048588675,0.80630213,0.018274598,0.012953633,0.00046765752,0.026245005,0.025043068,0.017924963,0.008270394,0.019520834,0.001176466],"about_ca_topic_score_codex":0.0030059258,"about_ca_topic_score_gemma":0.0038541348,"teacher_disagreement_score":0.6556492,"about_ca_system_score_codex":0.004001207,"about_ca_system_score_gemma":0.007197648,"threshold_uncertainty_score":0.80853224},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2312660621","doi":"10.3138/cjpe.0020.008","title":"How Do You Evaluate a Network? A Canadian Child and Youth Health Network Experience","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"","keywords":"Key (lock); Child health; Value (mathematics); Program evaluation; Psychology; Knowledge management; Public relations; Business; Computer science; Medicine; Political science; Family medicine; Computer security; Machine learning; Public administration","score_opus":0.2193611529595739,"score_gpt":0.46515968894757764,"score_spread":0.24579853598800375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2312660621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83529294,0.003137999,0.001023243,0.06513005,0.00055911945,0.00037884698,0.00034140237,0.000064886364,0.094071455],"genre_scores_gemma":[0.98683816,0.0016180986,0.0007056188,0.0020208482,0.00002928242,0.0000838252,0.000103374965,0.000032778244,0.0085679935],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97649264,0.008547588,0.00046932424,0.00085149216,0.0070324894,0.006606425],"domain_scores_gemma":[0.95819587,0.0038727238,0.0016242625,0.0005390398,0.01226976,0.023498252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020869792,0.00036891285,0.00049357326,0.001565958,0.026500234,0.008645825,0.0027201988,0.0018247996,0.00458555],"category_scores_gemma":[0.033086833,0.0003617288,0.00035015238,0.0027059384,0.008342774,0.00419241,0.007670798,0.0038721948,0.00031716813],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002850059,0.0008709241,0.11934085,0.00030837435,0.00005327369,0.0018623157,0.6237332,0.0010022153,0.00055910624,0.031418543,0.083580345,0.13698578],"study_design_scores_gemma":[0.000041878462,0.00029428853,0.056110088,0.00056118646,0.000031467654,0.0003604581,0.76175827,0.0009942502,0.00047265927,0.0018404782,0.17740642,0.00012849785],"about_ca_topic_score_codex":0.94189125,"about_ca_topic_score_gemma":0.9703372,"teacher_disagreement_score":0.10585578,"about_ca_system_score_codex":0.10585578,"about_ca_system_score_gemma":0.11862825,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2313199284","doi":"10.3138/cjpe.30.2.231","title":"Donaldson, S. L. (Ed.). <i>The future of evaluation in society: A tribute to Michael Scriven.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tribute; Theology; Art; Political science; Philosophy; Art history","score_opus":0.25324641466730924,"score_gpt":0.4940376517860622,"score_spread":0.24079123711875294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313199284","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001626451,0.9208531,0.0016802667,0.05158802,0.007623212,0.000019883717,0.0003970754,0.00018386864,0.017491939],"genre_scores_gemma":[0.0036050677,0.9553924,0.002985776,0.0081331255,0.0037550477,0.00005345253,0.00033966405,0.00009232943,0.025643175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99785477,0.00064755237,0.00024807046,0.0001383798,0.0009998999,0.00011133337],"domain_scores_gemma":[0.99277335,0.0037033863,0.000498724,0.00017019069,0.0022164972,0.0006378442],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041298615,0.0019070684,0.0010727814,0.0060992385,0.001422733,0.0047247536,0.002366491,0.0037497752,0.025044061],"category_scores_gemma":[0.009535159,0.0012798273,0.0010261266,0.0063438853,0.0019008414,0.0072783236,0.001825267,0.0049243583,0.024561075],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022090753,0.000008565406,0.00026181474,0.00043536464,0.000009850807,0.000044521727,0.00024239688,0.00009370963,0.00004465171,0.002158938,0.8672827,0.12939534],"study_design_scores_gemma":[0.000011051526,0.000012127937,0.0010017848,0.0025903273,0.000027954133,0.0002586722,0.00043119726,0.00006985552,0.000161851,0.0047425386,0.9906729,0.000019655701],"about_ca_topic_score_codex":0.03845313,"about_ca_topic_score_gemma":0.100693665,"teacher_disagreement_score":0.9958701,"about_ca_system_score_codex":0.0030159226,"about_ca_system_score_gemma":0.0062532094,"threshold_uncertainty_score":0.083780706},"labels":[],"label_agreement":null},{"id":"W231595241","doi":"10.3138/cjpe.0015.006","title":"Incorporating Stakeholders in Standard Setting: What’s at Stake?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Representativeness heuristic; Stakeholder; Insider; Psychology; Scale (ratio); Decision maker; Applied psychology; Rating scale; Public relations; Social psychology; Political science; Management science; Economics","score_opus":0.5441481476401734,"score_gpt":0.5151732825914709,"score_spread":0.028974865048702503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W231595241","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3478865,0.004462243,0.24945718,0.2596808,0.0013976117,0.0021512066,0.00010697665,0.00034252432,0.13451491],"genre_scores_gemma":[0.9698982,0.0005309428,0.02384968,0.0036416403,0.00014641436,0.00044809154,0.000024784023,0.000035469933,0.0014248333],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7042856,0.25323367,0.005372545,0.004352473,0.02502022,0.007735472],"domain_scores_gemma":[0.8439048,0.10382651,0.011775523,0.007871256,0.023625676,0.008996277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19905643,0.0008765328,0.0012362007,0.0023059347,0.010789976,0.02079101,0.0031725485,0.008443471,0.003908744],"category_scores_gemma":[0.2097749,0.0008929856,0.00089850934,0.0027563246,0.017869674,0.026660142,0.014954248,0.006582718,0.0007703504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000548769,0.0010222378,0.04010129,0.0022435368,0.00037337848,0.0015902898,0.21175088,0.0038600639,0.006926747,0.3736603,0.009465517,0.3484569],"study_design_scores_gemma":[0.00021717376,0.0010547622,0.015936226,0.0050910395,0.00035171836,0.0009298368,0.2700365,0.011639328,0.013304,0.5640898,0.11699284,0.0003568842],"about_ca_topic_score_codex":0.0040871087,"about_ca_topic_score_gemma":0.004581197,"teacher_disagreement_score":0.19905643,"about_ca_system_score_codex":0.01086177,"about_ca_system_score_gemma":0.021009775,"threshold_uncertainty_score":0.987706},"labels":[],"label_agreement":null},{"id":"W2316547733","doi":"10.3138/cjpe.016.002","title":"The Strong Focus on Output Information: A Threat to Evaluation in the Swedish State Sector?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Public sector; Public interest; State (computer science); Quality (philosophy); Focus (optics); Business; Information management; Private sector; Management information systems; Information system; Public relations; Economics; Public economics; Political science; Economic growth; Computer science; Management","score_opus":0.39228625282051927,"score_gpt":0.5057903060285184,"score_spread":0.11350405320799911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316547733","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083839126,0.01604566,0.021587323,0.72634494,0.001415798,0.00023487877,0.000572433,0.00020673806,0.14975303],"genre_scores_gemma":[0.93047243,0.006100822,0.010934004,0.04340984,0.0012812242,0.00036479594,0.00021698533,0.00015992981,0.0070600593],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.706062,0.19652432,0.01259723,0.0059640855,0.070996515,0.007855764],"domain_scores_gemma":[0.22338107,0.6217951,0.025080143,0.01862092,0.103619486,0.0075032874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25959286,0.0006389892,0.002001962,0.007821637,0.0065045864,0.028086443,0.0027486912,0.007150341,0.00573559],"category_scores_gemma":[0.43091205,0.00089001434,0.0010228398,0.010382536,0.014806559,0.017189095,0.012319083,0.0094021205,0.0011422536],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075245847,0.00026043292,0.031422734,0.0022737742,0.00020338748,0.0002942944,0.02004851,0.0022044524,0.00074024603,0.3687584,0.060373377,0.51266795],"study_design_scores_gemma":[0.0003590254,0.0010853535,0.06912809,0.015298081,0.0005387436,0.0011952093,0.052179936,0.009683685,0.007989997,0.49428543,0.34755167,0.00070471904],"about_ca_topic_score_codex":0.038251996,"about_ca_topic_score_gemma":0.02810482,"teacher_disagreement_score":0.25959286,"about_ca_system_score_codex":0.021087721,"about_ca_system_score_gemma":0.03540715,"threshold_uncertainty_score":0.9130538},"labels":[],"label_agreement":null},{"id":"W2320230425","doi":"10.3138/cjpe.29.1.104","title":"Contributing Factors to the Continued Blurring of Evaluation and Research: Strategies for Moving Forward","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Terminology; Confusion; Management science; Psychology; Control (management); Political science; Engineering ethics; Computer science; Economics; Engineering; Artificial intelligence","score_opus":0.5421588467804487,"score_gpt":0.5906286609896096,"score_spread":0.048469814209160966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320230425","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017363592,0.02502836,0.022300992,0.94287753,0.004913406,0.00030038226,0.000024906825,0.000119664895,0.0026983456],"genre_scores_gemma":[0.35052052,0.03673281,0.20481502,0.38244018,0.015073636,0.0052330405,0.00012734078,0.0006111635,0.004446303],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.20099114,0.6322136,0.05689109,0.021730445,0.07785188,0.010321926],"domain_scores_gemma":[0.059644703,0.7810767,0.026790343,0.0348081,0.089741655,0.007938532],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.80836934,0.003917541,0.008438697,0.018720418,0.020485086,0.052935354,0.0140061695,0.04262701,0.0075753196],"category_scores_gemma":[0.80046123,0.003830778,0.0037325572,0.01727401,0.10902404,0.07864936,0.04181642,0.06501592,0.001716667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048192294,0.00031469064,0.0037786816,0.007053988,0.00025398945,0.00052577123,0.032556813,0.0014013012,0.0004659483,0.7173346,0.05310851,0.18272384],"study_design_scores_gemma":[0.00039557088,0.0003877303,0.003226204,0.03204655,0.00022686293,0.00075186713,0.056795977,0.0055659395,0.001363355,0.7062678,0.19218409,0.00078808365],"about_ca_topic_score_codex":0.022646403,"about_ca_topic_score_gemma":0.01749084,"teacher_disagreement_score":0.92286557,"about_ca_system_score_codex":0.077134445,"about_ca_system_score_gemma":0.1538007,"threshold_uncertainty_score":0.5596522},"labels":[],"label_agreement":null},{"id":"W232181897","doi":"10.3138/cjpe.025.005","title":"Using Web-Based Technologies to Increase Evaluation Capacity in Organizations Providing Child and Youth Mental Health Services","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; Natural Sciences and Engineering Research Council of Canada; Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Mental health; Excellence; Context (archaeology); Service provider; Process (computing); Capacity building; Face (sociological concept); Public relations; Medical education; Service (business); Business; Knowledge management; Psychology; Marketing; Computer science; Medicine; Sociology; Psychiatry; Political science","score_opus":0.31751165643650486,"score_gpt":0.4729386949800939,"score_spread":0.15542703854358902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W232181897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8975459,0.0008097989,0.046192486,0.0046075126,0.00010444371,0.0053494154,0.000512213,0.0041715163,0.040706784],"genre_scores_gemma":[0.88016677,0.00041160994,0.11293873,0.000427341,0.00008530379,0.003150689,0.00032023917,0.0001236423,0.0023756397],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9707912,0.024188235,0.0014073697,0.0007629996,0.0019414137,0.00090869603],"domain_scores_gemma":[0.80861557,0.16425808,0.006811108,0.007421334,0.006833086,0.006060785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032910064,0.00047916156,0.00044344898,0.003232071,0.0015002248,0.0037548055,0.0015641504,0.0007879902,0.007788299],"category_scores_gemma":[0.088279806,0.00059986225,0.00049045635,0.0018356529,0.001061221,0.004308489,0.00445124,0.0011359579,0.0011082692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013845746,0.008623603,0.043814555,0.0008303784,0.000092166025,0.00026492792,0.00965341,0.0024526704,0.0029907422,0.001671266,0.0090629505,0.9191588],"study_design_scores_gemma":[0.0065684607,0.021035628,0.5146611,0.008386381,0.0009877618,0.0023221893,0.05705778,0.1285015,0.052750297,0.029764244,0.1766816,0.001283012],"about_ca_topic_score_codex":0.0036736727,"about_ca_topic_score_gemma":0.0062885317,"teacher_disagreement_score":0.032910064,"about_ca_system_score_codex":0.0025610975,"about_ca_system_score_gemma":0.005021707,"threshold_uncertainty_score":0.17404711},"labels":[],"label_agreement":null},{"id":"W2322332679","doi":"10.3138/cjpe.30.3.07","title":"Considering the Social Determinants of Equity in International Development Evaluation Guidance Documents","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Equity (law); Business; Social equality; Public economics; Public relations; Political science; Accounting; Economics","score_opus":0.5190978300383406,"score_gpt":0.6044219470048832,"score_spread":0.08532411696654252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2322332679","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23330109,0.015751293,0.09677105,0.22499487,0.0013198166,0.0063843373,0.00049790734,0.0004521637,0.42052752],"genre_scores_gemma":[0.9390412,0.002410637,0.046813503,0.005375356,0.00032128053,0.0018946143,0.0001340385,0.00006491844,0.003944524],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6151212,0.29072607,0.020043956,0.002993474,0.062453575,0.008661706],"domain_scores_gemma":[0.44595358,0.40718418,0.03423904,0.010760771,0.09461954,0.007242876],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.31279516,0.00094400544,0.0009812261,0.008018583,0.007884192,0.023036465,0.002618478,0.004932272,0.004553647],"category_scores_gemma":[0.42696324,0.00068323145,0.0009813869,0.005798663,0.012158859,0.012755026,0.013850388,0.006014886,0.0003844876],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030949357,0.0009005373,0.04017117,0.0032713376,0.0001770934,0.00049001863,0.05321988,0.007523844,0.00109742,0.3751696,0.043551974,0.47411764],"study_design_scores_gemma":[0.0005468617,0.0019088613,0.07656398,0.033929124,0.0006469482,0.00063269766,0.086643845,0.018928852,0.01013253,0.26403826,0.5054038,0.00062419893],"about_ca_topic_score_codex":0.026337123,"about_ca_topic_score_gemma":0.043981392,"teacher_disagreement_score":0.31279516,"about_ca_system_score_codex":0.032069255,"about_ca_system_score_gemma":0.08126467,"threshold_uncertainty_score":0.8474459},"labels":[],"label_agreement":null},{"id":"W2324237053","doi":"10.3138/cjpe.30.3.390","title":"A Transcultural Global Systems Perspective: In Search of Blue Marble Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Framing (construction); Reflexivity; Indigenous; Sociology; Praxis; Perspective (graphical); Epistemology; Political science; Management science; Public relations; Engineering ethics; Social science; Computer science; Geography; Engineering","score_opus":0.33164886305323843,"score_gpt":0.5492553374225089,"score_spread":0.21760647436927044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324237053","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038840476,0.033644836,0.061302703,0.45837584,0.005865942,0.0004884606,0.00006412588,0.00028188142,0.4011358],"genre_scores_gemma":[0.82838297,0.016517933,0.040482856,0.07641774,0.002054451,0.0008228888,0.000063180465,0.0005359396,0.034722053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9233077,0.061938822,0.0013831734,0.0025904472,0.007082956,0.0036968298],"domain_scores_gemma":[0.93505067,0.0406809,0.0020235698,0.004365362,0.012917844,0.004961632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.082768306,0.0010580583,0.0012152871,0.0061006662,0.010886301,0.030636324,0.0029183517,0.00525841,0.0054302798],"category_scores_gemma":[0.06554596,0.0005126978,0.0006813688,0.005687824,0.074207865,0.02274885,0.015537951,0.011381726,0.0006565677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035540892,0.00006954614,0.0027312562,0.00072053063,0.0000334093,0.00028258582,0.15993963,0.0005523238,0.0002398341,0.7449596,0.02837085,0.06206492],"study_design_scores_gemma":[0.000024985742,0.00009610669,0.0017697145,0.0021756208,0.000034943205,0.00026704007,0.27756983,0.001092297,0.00049824227,0.3686788,0.34774628,0.00004612424],"about_ca_topic_score_codex":0.015725954,"about_ca_topic_score_gemma":0.023573328,"teacher_disagreement_score":0.082768306,"about_ca_system_score_codex":0.02055611,"about_ca_system_score_gemma":0.03468882,"threshold_uncertainty_score":0.4377259},"labels":[],"label_agreement":null},{"id":"W2324490698","doi":"10.3138/cjpe.30.3.394","title":"Hood, S., Hopson, R., &amp; Frierson, H., (2015). <i>Continuing the journey to reposition culture and cultural context in evaluation theory and practice.</i>","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Sociology; Psychology; History; Archaeology","score_opus":0.22758183789853317,"score_gpt":0.5146177563723437,"score_spread":0.2870359184738106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324490698","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047094873,0.102193095,0.026688723,0.6433228,0.0059938114,0.00026927175,0.0011255462,0.00041395912,0.21528323],"genre_scores_gemma":[0.32984352,0.25373134,0.067087494,0.15318592,0.00406432,0.00091067527,0.001468405,0.0009103254,0.18879803],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957065,0.00165077,0.00029721254,0.00016343532,0.0020581158,0.00012398184],"domain_scores_gemma":[0.95087844,0.028194694,0.0023795422,0.0011311624,0.015689367,0.0017267916],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012022469,0.00035529194,0.00033990154,0.002964032,0.004255221,0.008109794,0.0018457016,0.00270747,0.013899151],"category_scores_gemma":[0.05382413,0.00043850916,0.00033457446,0.003436477,0.004265888,0.008479493,0.002264778,0.004954531,0.005954977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048679194,0.0000364838,0.0023091205,0.0006873334,0.00002451,0.00004932079,0.0041502994,0.0000831467,0.00022997486,0.01860814,0.7427324,0.23104048],"study_design_scores_gemma":[0.000031574302,0.00007286492,0.013381667,0.0038658504,0.00006419088,0.0002048433,0.008120933,0.00024346352,0.0009819957,0.038864236,0.93411267,0.000055736822],"about_ca_topic_score_codex":0.059194863,"about_ca_topic_score_gemma":0.18894006,"teacher_disagreement_score":0.9879775,"about_ca_system_score_codex":0.005846118,"about_ca_system_score_gemma":0.012603853,"threshold_uncertainty_score":0.11770064},"labels":[],"label_agreement":null},{"id":"W2324880020","doi":"10.3138/cjpe.30.3.391","title":"Goodyear, L., Jewiss, J., Usinger, J., &amp; Barela, E. (Eds.). (2014). <i>Qualitative inquiry in evaluation: From theory to practice.</i>","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Epistemology; Philosophy","score_opus":0.4800931468809325,"score_gpt":0.5926954103586337,"score_spread":0.11260226347770119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324880020","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030333963,0.7015738,0.06000872,0.11053339,0.003765368,0.00040340677,0.0028133758,0.0013237786,0.11654486],"genre_scores_gemma":[0.041439176,0.82448775,0.06721609,0.0055718445,0.0011958798,0.00041875365,0.0017087626,0.00061002135,0.057351723],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967624,0.0011242374,0.00033836206,0.00021689595,0.0014367728,0.00012124447],"domain_scores_gemma":[0.9713496,0.02047839,0.001624409,0.0008700741,0.00462455,0.0010530755],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009728352,0.0010360571,0.0007284199,0.0071539977,0.0027607097,0.0068452945,0.0019138996,0.0024140773,0.021677954],"category_scores_gemma":[0.021834433,0.0012625812,0.0008339988,0.008936114,0.0032094105,0.010691251,0.0023616767,0.003803327,0.014676695],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036587924,0.000034042638,0.0012207327,0.0025659802,0.000024908524,0.000066396075,0.0050940807,0.00025740734,0.0003381867,0.007830364,0.39900196,0.58352935],"study_design_scores_gemma":[0.00002065136,0.00008004492,0.0048011634,0.008926621,0.00009575492,0.0004986358,0.006546317,0.00031529873,0.0010115703,0.023772018,0.9538463,0.00008561073],"about_ca_topic_score_codex":0.06275889,"about_ca_topic_score_gemma":0.13631506,"teacher_disagreement_score":0.9902716,"about_ca_system_score_codex":0.005046324,"about_ca_system_score_gemma":0.012355147,"threshold_uncertainty_score":0.12478721},"labels":[],"label_agreement":null},{"id":"W2326207554","doi":"","title":"Guest, G., MacQueen, K. M., & Namey, E. E. (2012). Applied Thematic Analysis","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thematic map; Business; Geography; Cartography","score_opus":0.16077355681032623,"score_gpt":0.49502238499250417,"score_spread":0.33424882818217794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326207554","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16262196,0.0264069,0.5396513,0.10998188,0.0066154385,0.023210578,0.01207506,0.001368801,0.11806813],"genre_scores_gemma":[0.39679393,0.013544817,0.5542793,0.0039946204,0.00029157574,0.011953663,0.0018019903,0.00067720335,0.016662927],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98086435,0.011450767,0.0014609725,0.001354045,0.004544025,0.00032570583],"domain_scores_gemma":[0.87410176,0.08745062,0.0048956866,0.005645535,0.026428567,0.001477704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059004758,0.0006904718,0.0011294091,0.0059145023,0.0074538523,0.005071977,0.0022737095,0.0010989252,0.005159136],"category_scores_gemma":[0.21424349,0.00085890753,0.0007464255,0.0072271335,0.0061696116,0.0064868806,0.004378346,0.0042674583,0.00076216605],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049802824,0.00018491213,0.026941894,0.0075593484,0.0002879888,0.0002891546,0.13382682,0.00093431433,0.0035785406,0.069318324,0.19175144,0.56482923],"study_design_scores_gemma":[0.00023272134,0.0004309071,0.07552738,0.012056977,0.0007372444,0.0005244406,0.1828368,0.0045850095,0.007943225,0.23685747,0.47799966,0.0002682065],"about_ca_topic_score_codex":0.02588534,"about_ca_topic_score_gemma":0.06670014,"teacher_disagreement_score":0.059004758,"about_ca_system_score_codex":0.007685669,"about_ca_system_score_gemma":0.015115153,"threshold_uncertainty_score":0.3120507},"labels":[],"label_agreement":null},{"id":"W233084541","doi":"10.3138/cjpe.017.006","title":"Public Training Programs in Canada: A Meta-evaluation","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Summative assessment; Formative assessment; Training (meteorology); Program evaluation; Medical education; Political science; Public relations; Psychology; Pedagogy; Public administration; Medicine; Geography","score_opus":0.9006990989952361,"score_gpt":0.5282974646477141,"score_spread":0.37240163434752205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W233084541","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3116767,0.6228138,0.008050878,0.0064136717,0.001709285,0.022735469,0.0180766,0.00034951596,0.008174106],"genre_scores_gemma":[0.88991684,0.08431486,0.00871772,0.0014911786,0.00022743658,0.010221937,0.0037806022,0.000059682963,0.0012697994],"study_design_codex":"meta_analysis","study_design_gemma":"systematic_review","domain_scores_codex":[0.934086,0.043896284,0.0057422477,0.002319257,0.012267266,0.0016888313],"domain_scores_gemma":[0.89746624,0.05419417,0.0132257575,0.0033868963,0.028053442,0.003673575],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.059121016,0.0022568111,0.0077091428,0.0060642064,0.0030198595,0.0026265113,0.0030676136,0.0018441657,0.0035732293],"category_scores_gemma":[0.13470954,0.0010837994,0.013379367,0.011514155,0.0018507369,0.0010837152,0.0019073308,0.0018906947,0.00014161416],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04153133,0.0014608236,0.07693619,0.1886291,0.551327,0.00037737217,0.0018841375,0.007328368,0.0004384176,0.0012158782,0.011884665,0.11698665],"study_design_scores_gemma":[0.023381345,0.004042233,0.10628773,0.054764505,0.7941281,0.0001302297,0.0013103024,0.002843445,0.00090030214,0.0007556625,0.011236363,0.00021974198],"about_ca_topic_score_codex":0.8252498,"about_ca_topic_score_gemma":0.8805843,"teacher_disagreement_score":0.940879,"about_ca_system_score_codex":0.059720833,"about_ca_system_score_gemma":0.091916814,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":["metaepi_broad"],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2331580938","doi":"10.3138/cjpe.30.3.02","title":"A Critical Exploration of Culture in International Development Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Context (archaeology); Engineering ethics; Epistemology","score_opus":0.5144255173283512,"score_gpt":0.58370906981695,"score_spread":0.06928355248859885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331580938","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09689896,0.32883576,0.14010103,0.20098619,0.0053859637,0.0014564358,0.00026013269,0.00019945331,0.22587597],"genre_scores_gemma":[0.90840894,0.04938227,0.026336297,0.011305368,0.00072045944,0.0012753124,0.00006724575,0.00019973818,0.0023042983],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.52860296,0.42184725,0.01577566,0.0049167587,0.025625667,0.0032316144],"domain_scores_gemma":[0.3908407,0.525955,0.015382981,0.016603855,0.048988022,0.002229391],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30277503,0.0010874562,0.0021817104,0.014543129,0.010010002,0.038963802,0.0038425731,0.004154768,0.0031616883],"category_scores_gemma":[0.29179966,0.0010369404,0.0010949287,0.017357161,0.05848233,0.03415407,0.01948835,0.008546423,0.0003056897],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007157081,0.00006373919,0.003018834,0.0073497086,0.0001428703,0.00037028553,0.30386183,0.00057473755,0.00037002677,0.5253039,0.0062312963,0.15264119],"study_design_scores_gemma":[0.000036359706,0.00015665118,0.003618502,0.05463069,0.00022723853,0.0005555096,0.43831676,0.0010558214,0.0019471324,0.18432914,0.3149887,0.00013759712],"about_ca_topic_score_codex":0.007183796,"about_ca_topic_score_gemma":0.0072252005,"teacher_disagreement_score":0.30277503,"about_ca_system_score_codex":0.034880564,"about_ca_system_score_gemma":0.046339437,"threshold_uncertainty_score":0.85980254},"labels":[],"label_agreement":null},{"id":"W2332681108","doi":"10.3138/cjpe.30.2.228","title":"Trevisan, M. S., &amp; Walser, T. M. (2015) <i>Evaluability assessment: Improving evaluation quality and use.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Philosophy; Epistemology","score_opus":0.6893862509287247,"score_gpt":0.6140360373202267,"score_spread":0.07535021360849803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2332681108","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00287946,0.11588673,0.047462843,0.5784533,0.01161708,0.0005793498,0.0019463995,0.0010127864,0.24016203],"genre_scores_gemma":[0.21345817,0.33742645,0.13046846,0.15304205,0.013271632,0.0017773341,0.003250809,0.0014321242,0.14587289],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99055594,0.004246309,0.00082224543,0.00029922492,0.0038616834,0.00021460211],"domain_scores_gemma":[0.91112447,0.0492553,0.006890342,0.0024357329,0.028376633,0.0019174562],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023872172,0.0004787055,0.00054109254,0.005863498,0.0020810785,0.0066194804,0.0026704445,0.002509652,0.018749466],"category_scores_gemma":[0.11689339,0.00036956146,0.000694015,0.0050656283,0.002990815,0.0044505172,0.0021780531,0.003984334,0.0077754357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004272823,0.000025165338,0.0013500766,0.0007730697,0.00002637129,0.000040523664,0.00081434136,0.00012871824,0.00023041308,0.006956711,0.74145436,0.24815756],"study_design_scores_gemma":[0.000036549543,0.00009172689,0.0134540545,0.007995787,0.00014329213,0.00034084608,0.0020730882,0.0006848803,0.001692793,0.028754422,0.94462806,0.00010447655],"about_ca_topic_score_codex":0.036257427,"about_ca_topic_score_gemma":0.10442495,"teacher_disagreement_score":0.9761278,"about_ca_system_score_codex":0.005884761,"about_ca_system_score_gemma":0.008834197,"threshold_uncertainty_score":0.12624961},"labels":[],"label_agreement":null},{"id":"W2337055065","doi":"","title":"Propos de l'éditeur","year":2012,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychoanalysis and Psychopathology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.17839612295583337,"score_gpt":0.48515777144898553,"score_spread":0.30676164849315213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337055065","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009236336,0.036574103,0.0056462907,0.17671219,0.69762564,0.00014321746,0.0011181324,0.0008224802,0.0721216],"genre_scores_gemma":[0.05809057,0.027047087,0.007836879,0.07731564,0.26063532,0.00037629108,0.0014367106,0.00088062463,0.5663809],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99735594,0.00058382086,0.00027477433,0.00034809127,0.0011735075,0.00026392477],"domain_scores_gemma":[0.99277556,0.0017158733,0.00046815042,0.0005311858,0.0038007786,0.00070845656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027843015,0.0007999925,0.0005120041,0.0016346414,0.001611032,0.0033176518,0.0010508107,0.0023921418,0.022906974],"category_scores_gemma":[0.013511464,0.00027246357,0.00064429507,0.0005793289,0.00089496095,0.0018224751,0.001765157,0.0027028942,0.00901321],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086131,0.00004164952,0.0009320389,0.0003720691,0.000034870834,0.0016182729,0.00039118252,0.00010604767,0.0006164673,0.0046937824,0.87686694,0.11424065],"study_design_scores_gemma":[0.000006007142,0.000015228689,0.0007633238,0.00007845823,0.000010773577,0.0010709057,0.000058913214,0.000036387395,0.00027757217,0.00035344725,0.99731964,0.000009384593],"about_ca_topic_score_codex":0.0071193352,"about_ca_topic_score_gemma":0.01178174,"teacher_disagreement_score":0.022906974,"about_ca_system_score_codex":0.0025384703,"about_ca_system_score_gemma":0.0030024212,"threshold_uncertainty_score":0.07663149},"labels":[],"label_agreement":null},{"id":"W2337090609","doi":"10.3138/cjpe.022.005","title":"A Participatory Approach to the Development of an Evaluation Framework: Process, Pitfalls, and Payoffs","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Alberta Health; Alberta Community Council on HIV; Public Health Agency of Canada","funders":"","keywords":"Citizen journalism; Participatory evaluation; Participatory GIS; Process (computing); Participatory development; Process management; Knowledge management; Business; Sociology; Management science; Computer science; Economics; Social science; World Wide Web","score_opus":0.5222899769278269,"score_gpt":0.5645426097571967,"score_spread":0.04225263282936986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337090609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016404372,0.0017093486,0.9071468,0.030532679,0.0004452469,0.009705694,0.000060995302,0.00020804933,0.033786748],"genre_scores_gemma":[0.257771,0.0006421912,0.7306971,0.001381565,0.00008369256,0.007610059,0.000035502948,0.000059179678,0.0017196822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.39187846,0.5616597,0.011106796,0.005195627,0.02610277,0.00405663],"domain_scores_gemma":[0.618196,0.28757718,0.011649317,0.01975302,0.05612039,0.0067041786],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4249276,0.0017186488,0.0015341225,0.005782678,0.015969858,0.015052219,0.005366095,0.0050812108,0.0035581612],"category_scores_gemma":[0.26664072,0.0013649715,0.001397669,0.0051499833,0.033774454,0.013109619,0.019965166,0.00888994,0.000460148],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017209622,0.0004840343,0.0032339226,0.002355772,0.00015608539,0.00083171984,0.10121861,0.007509625,0.0012426988,0.65374094,0.006217145,0.22283748],"study_design_scores_gemma":[0.00039748676,0.00075290236,0.002043,0.0077928146,0.00018568334,0.0007374353,0.06311563,0.029319959,0.004019943,0.7673873,0.12393216,0.00031577426],"about_ca_topic_score_codex":0.014975123,"about_ca_topic_score_gemma":0.020905608,"teacher_disagreement_score":0.5750724,"about_ca_system_score_codex":0.025683282,"about_ca_system_score_gemma":0.09186479,"threshold_uncertainty_score":0.70916665},"labels":[],"label_agreement":null},{"id":"W2337138915","doi":"10.3138/cjpe.024.004","title":"L’évaluation des programmes de développement en Afghanistan. étude de cas : une évaluation participative du Programme de Solidarité Nationale","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Politics and Conflicts in Afghanistan, Pakistan, and Middle East","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Program evaluation; Valuation (finance); Political science; Theory of change; Solidarity; Sociology; Welfare economics; Process management; Business; Public administration; Economics","score_opus":0.16253560686879964,"score_gpt":0.41533329681137315,"score_spread":0.2527976899425735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337138915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9567394,0.0007721654,0.007406386,0.0048365714,0.000067418696,0.0015246869,0.00008369711,0.000038555874,0.028531214],"genre_scores_gemma":[0.9904563,0.00030798832,0.004985532,0.00021617072,0.000016508104,0.0006533576,0.000034054203,0.00000964044,0.003320382],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9367196,0.053558994,0.0012414068,0.0011676983,0.0046662744,0.002645999],"domain_scores_gemma":[0.95295095,0.032948893,0.0036026,0.001696991,0.0065238765,0.0022766613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051325526,0.000646747,0.0003933644,0.0021904567,0.010051819,0.004715526,0.001281555,0.0020441154,0.0029143738],"category_scores_gemma":[0.051885005,0.00046076308,0.00037195822,0.0025589094,0.0046223537,0.0029685306,0.004214013,0.0019922385,0.0002579459],"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":[0.00093787705,0.003960839,0.05690547,0.0011581745,0.0000872878,0.0039334274,0.53146195,0.0041195676,0.0042693326,0.040915594,0.0041458597,0.34810466],"study_design_scores_gemma":[0.0005672084,0.003562228,0.12993066,0.0013473915,0.00010376857,0.0022689935,0.65717846,0.0074434592,0.013693985,0.008122022,0.17560358,0.00017821451],"about_ca_topic_score_codex":0.051865242,"about_ca_topic_score_gemma":0.055798955,"teacher_disagreement_score":0.051865242,"about_ca_system_score_codex":0.019320242,"about_ca_system_score_gemma":0.021227425,"threshold_uncertainty_score":0.2714386},"labels":[],"label_agreement":null},{"id":"W2338777541","doi":"10.3138/cjpe.0023.011","title":"Understanding Organization Capacity for Evaluation: Synthesis and Integration","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Context (archaeology); Empirical examination; Capacity building; Capacity development; Political science; Regional science; Process management; Knowledge management; Sociology; Business; Environmental resource management; Computer science; Geography; Economics; Archaeology","score_opus":0.6461461480260806,"score_gpt":0.5144417351249825,"score_spread":0.13170441290109813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338777541","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053988058,0.53772765,0.16687876,0.083785124,0.0023463443,0.0008022091,0.0014352159,0.00028861137,0.15274797],"genre_scores_gemma":[0.7887647,0.14576647,0.055860143,0.0029756268,0.0013100608,0.0016567245,0.0008417051,0.00019324779,0.0026312585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"systematic_review","domain_scores_codex":[0.96967906,0.020721288,0.003073616,0.001290546,0.004380941,0.0008545508],"domain_scores_gemma":[0.7812503,0.19471014,0.0051611955,0.0051480164,0.012765197,0.0009651449],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04813911,0.0009561449,0.0014236037,0.019586958,0.00219312,0.018048061,0.0015795473,0.0016941653,0.005061273],"category_scores_gemma":[0.08660619,0.0005489521,0.00096418237,0.020368159,0.008246149,0.018782018,0.006251995,0.0034657975,0.00028660859],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010491399,0.00014519556,0.01035812,0.01865835,0.00033483506,0.00017801476,0.047715243,0.0038798177,0.0004874363,0.48393613,0.014346263,0.41985565],"study_design_scores_gemma":[0.000029533534,0.00019426466,0.018364098,0.05131261,0.00044682494,0.00033233876,0.09442487,0.007274862,0.002235865,0.44079986,0.38445956,0.00012537473],"about_ca_topic_score_codex":0.0041358196,"about_ca_topic_score_gemma":0.004159071,"teacher_disagreement_score":0.9518609,"about_ca_system_score_codex":0.013427143,"about_ca_system_score_gemma":0.015534406,"threshold_uncertainty_score":0.254587},"labels":[],"label_agreement":null},{"id":"W2339769925","doi":"","title":"Evaluation of client satisfaction in a community mental health centre: Selection of a tool.","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mental health; Patient satisfaction; Customer satisfaction; Scale (ratio); Focus group; Psychology; Mental health service; Service (business); Applied psychology; Knowledge management; Nursing; Computer science; Medicine; Psychiatry; Business; Marketing","score_opus":0.3293164458208046,"score_gpt":0.5016345911981273,"score_spread":0.17231814537732265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339769925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9586001,0.0008966038,0.013857892,0.0011985864,0.00007909494,0.015249854,0.00090792484,0.00016819075,0.009041873],"genre_scores_gemma":[0.9191194,0.000719238,0.06530875,0.00029353864,0.000019058954,0.012635318,0.00087459286,0.00003750929,0.0009925977],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97542316,0.014489053,0.003552807,0.00034264495,0.005397064,0.00079522806],"domain_scores_gemma":[0.9665881,0.013379567,0.0037156835,0.0007379241,0.013372921,0.0022057968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029754048,0.00057865295,0.0009521423,0.0041333046,0.0010865047,0.0016094445,0.00087874255,0.00078694196,0.0013782983],"category_scores_gemma":[0.042484198,0.00035435744,0.0011600598,0.0035537332,0.000887019,0.0013160688,0.0020412363,0.0008767712,0.0003668395],"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":[0.0018641672,0.0023421485,0.5032266,0.0017845157,0.00018206859,0.0005652267,0.010298378,0.0006956782,0.0027991415,0.00072979106,0.004460853,0.47105142],"study_design_scores_gemma":[0.0011082166,0.012013842,0.9196605,0.0018449441,0.0004574577,0.0018301642,0.030628424,0.011357297,0.008902053,0.0010293977,0.010913595,0.00025408794],"about_ca_topic_score_codex":0.002774483,"about_ca_topic_score_gemma":0.0074912063,"teacher_disagreement_score":0.029754048,"about_ca_system_score_codex":0.0032294714,"about_ca_system_score_gemma":0.0059030633,"threshold_uncertainty_score":0.15735632},"labels":[],"label_agreement":null},{"id":"W2340392036","doi":"10.3138/cjpe.0026.007","title":"Trois conceptions de la nature des programmes : implications pour l’évaluation de programmes complexes en santé publique","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Dysfunctional family; Epistemology; Program evaluation; Valuation (finance); Psychology; Sociology; Business; Political science; Philosophy; Psychotherapist","score_opus":0.22282856566803982,"score_gpt":0.5388556115237819,"score_spread":0.3160270458557421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340392036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09482811,0.026750667,0.42741123,0.1453155,0.0012709525,0.0025481684,0.0008232766,0.00030709483,0.30074495],"genre_scores_gemma":[0.8634875,0.0033460448,0.12174327,0.0033681856,0.00023231305,0.0026783335,0.0002177558,0.000093439165,0.0048331884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8129813,0.14845833,0.0051439675,0.0043326505,0.02667547,0.0024082633],"domain_scores_gemma":[0.77883077,0.17392251,0.009412893,0.007874613,0.0267415,0.003217696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.119195886,0.0016735954,0.0016548935,0.010771746,0.0054484867,0.031712938,0.005024107,0.0070257005,0.010042531],"category_scores_gemma":[0.15208401,0.00094676175,0.0021092512,0.008276842,0.040096506,0.024413481,0.0068817437,0.010375278,0.00048705656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014438127,0.0001936597,0.0023892852,0.0007824391,0.00008975471,0.000052110372,0.008708178,0.005012575,0.00012573358,0.9425826,0.0018797584,0.038039513],"study_design_scores_gemma":[0.00025327574,0.0003448152,0.0066158976,0.004207041,0.00020402344,0.00015960226,0.017888172,0.022130266,0.0011643197,0.8893021,0.05758975,0.00014075261],"about_ca_topic_score_codex":0.018038189,"about_ca_topic_score_gemma":0.016715853,"teacher_disagreement_score":0.119195886,"about_ca_system_score_codex":0.04303408,"about_ca_system_score_gemma":0.022439405,"threshold_uncertainty_score":0.6303756},"labels":[],"label_agreement":null},{"id":"W237532803","doi":"10.3138/cjpe.26.006","title":"The Essential Skills Series in Evaluation: Assessing the Validity of the ESS Participant Workshop Evaluation Questionnaire","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre de Liaison Sur l'Intervention et la Prévention Psychosociales; Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Psychology; Medical education; Applied psychology; Medicine","score_opus":0.518137140465873,"score_gpt":0.548237636298514,"score_spread":0.03010049583264096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W237532803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97395587,0.00022647437,0.010943259,0.0005254866,0.00010086744,0.008986772,0.0005402564,0.00006029265,0.0046607177],"genre_scores_gemma":[0.96405023,0.00011964524,0.016907549,0.00019298909,0.000029106723,0.017583115,0.00038477546,0.000025780462,0.00070676877],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.88557833,0.079877056,0.014173015,0.0014914083,0.017317813,0.001562458],"domain_scores_gemma":[0.7400023,0.18005954,0.023584498,0.0071676355,0.044733368,0.004452685],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1516111,0.00048082013,0.0008418028,0.0022355171,0.001069703,0.0013417689,0.0014463726,0.0007988392,0.0018692387],"category_scores_gemma":[0.19294167,0.000486676,0.0012889814,0.0018792008,0.0015811055,0.001736898,0.0028595359,0.0010899849,0.00025544493],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005717937,0.004540256,0.6783242,0.002896255,0.0007728072,0.00042231946,0.042857956,0.0025444967,0.004593725,0.0035544336,0.0067184293,0.24705707],"study_design_scores_gemma":[0.0018966952,0.014978098,0.9214504,0.0012914431,0.0002610926,0.00043125497,0.020288117,0.010598962,0.0059035104,0.0019163499,0.020767365,0.00021663634],"about_ca_topic_score_codex":0.0024194806,"about_ca_topic_score_gemma":0.0036177866,"teacher_disagreement_score":0.8483889,"about_ca_system_score_codex":0.0032839754,"about_ca_system_score_gemma":0.005469129,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W242703065","doi":"10.3138/cjpe.0014.005","title":"Organizational Development and Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Organization development; Organizational learning; Organizational effectiveness; Organizational culture; Organizational behavior and human resources; Knowledge management; Facilitation; Organizational commitment; Organizational performance; Organizational studies; Organizational engineering; Process (computing); Psychology; Process management; Business; Computer science; Public relations; Political science; Social psychology","score_opus":0.3470470019193243,"score_gpt":0.5167326550286309,"score_spread":0.16968565310930656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W242703065","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019480003,0.010408708,0.1900172,0.026305016,0.0033914584,0.024704447,0.0042815465,0.0012157279,0.72019583],"genre_scores_gemma":[0.44193628,0.008756287,0.34856412,0.005584746,0.00089771935,0.040455192,0.0044454555,0.0010952447,0.14826494],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.79790974,0.15081733,0.011587174,0.00394011,0.032713067,0.003032513],"domain_scores_gemma":[0.791372,0.07033464,0.008957419,0.02432299,0.09888131,0.0061317193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14036667,0.00087250053,0.001384978,0.0071804435,0.0036283971,0.012722222,0.0022954077,0.0015317359,0.028157232],"category_scores_gemma":[0.16701648,0.0004347784,0.00072662847,0.0072817253,0.0050957263,0.00467689,0.0066659,0.0023501876,0.0073095076],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022609578,0.0003390887,0.004980696,0.0020564867,0.00008359922,0.00005946299,0.0051790825,0.0011457507,0.00035894781,0.27149627,0.07280471,0.64126986],"study_design_scores_gemma":[0.00016903982,0.0007180449,0.011925017,0.0063636494,0.00010545606,0.00017484337,0.011642605,0.0030174726,0.0022102748,0.084806554,0.8787739,0.00009318677],"about_ca_topic_score_codex":0.0052600713,"about_ca_topic_score_gemma":0.0036677157,"teacher_disagreement_score":0.14036667,"about_ca_system_score_codex":0.011650002,"about_ca_system_score_gemma":0.037378915,"threshold_uncertainty_score":0.7423388},"labels":[],"label_agreement":null},{"id":"W2460453024","doi":"10.3138/cjpe.026.004","title":"Development of a Classification System for Patients Referred to a Rehabilitation Program for Visual Impairment: A Method for Analysis and Budgetary Control","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"","keywords":"Rehabilitation; Dimension (graph theory); Control (management); Process (computing); Consumption (sociology); Homogeneous; Health care; Computer science; Economic evaluation; Actuarial science; Process management; Operations management; Risk analysis (engineering); Psychology; Business; Medicine; Physical therapy; Artificial intelligence; Economics","score_opus":0.4190927563370856,"score_gpt":0.48871601121342595,"score_spread":0.06962325487634036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2460453024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18948424,0.00037771632,0.78426754,0.0017034129,0.00031991547,0.008678744,0.006614033,0.0014818305,0.0070725037],"genre_scores_gemma":[0.2952739,0.00008604686,0.6922308,0.000114480994,0.00008547842,0.0070597264,0.003538375,0.0001625831,0.0014485706],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9856263,0.006839693,0.003104686,0.0013272671,0.0026890428,0.00041299794],"domain_scores_gemma":[0.9484734,0.029730361,0.004422427,0.0031742377,0.013419543,0.00078001054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021544756,0.0010082038,0.0015682479,0.012041906,0.0014602761,0.0032765095,0.0016400825,0.0011290261,0.008686988],"category_scores_gemma":[0.06674139,0.0004301077,0.0017790383,0.006451326,0.000897604,0.0017455359,0.0017886083,0.0022388848,0.0012489639],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002219582,0.0018626791,0.32134706,0.0005831463,0.0006159875,0.0002248319,0.0017872317,0.024526324,0.003934973,0.030128425,0.023477914,0.5892918],"study_design_scores_gemma":[0.0011526477,0.001131412,0.18739986,0.00054107007,0.000801632,0.00048937864,0.0027000539,0.7424049,0.0071214596,0.033684324,0.02219053,0.0003827198],"about_ca_topic_score_codex":0.015241478,"about_ca_topic_score_gemma":0.008641012,"teacher_disagreement_score":0.021544756,"about_ca_system_score_codex":0.004449341,"about_ca_system_score_gemma":0.0049309917,"threshold_uncertainty_score":0.113940895},"labels":[],"label_agreement":null},{"id":"W2482243048","doi":"","title":"L’étude d’évaluabilité : Une approche d’évaluation de programmes encore mal connue et peu utilisée","year":2016,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.2956668829198084,"score_gpt":0.49993669500760696,"score_spread":0.20426981208779854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482243048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11769474,0.016084908,0.4150046,0.043625463,0.00097071216,0.0035976649,0.0006235508,0.0007498779,0.40164837],"genre_scores_gemma":[0.7967105,0.0066011506,0.16242549,0.0034640126,0.0002447032,0.003677708,0.00032524057,0.00026775998,0.026283415],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8498915,0.12116988,0.004427305,0.0041996627,0.018288309,0.002023507],"domain_scores_gemma":[0.7963282,0.14838837,0.009813385,0.011685767,0.031460892,0.0023234806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08843244,0.0012726337,0.0013770511,0.005024908,0.0031314031,0.015045441,0.0029940999,0.003011165,0.01232376],"category_scores_gemma":[0.1319343,0.00068338803,0.0016950665,0.00460824,0.009212002,0.009713475,0.007031441,0.0039610113,0.0014224926],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055286306,0.0006355937,0.012081542,0.0065920916,0.0004816109,0.00023731246,0.040969018,0.0083586145,0.0023058446,0.36327407,0.009375606,0.5551358],"study_design_scores_gemma":[0.00040659853,0.0026526556,0.03348026,0.027079381,0.0011808781,0.00063854596,0.045506686,0.019742616,0.011260169,0.38789767,0.46981683,0.00033767146],"about_ca_topic_score_codex":0.005742708,"about_ca_topic_score_gemma":0.007334775,"teacher_disagreement_score":0.08843244,"about_ca_system_score_codex":0.013884212,"about_ca_system_score_gemma":0.01742605,"threshold_uncertainty_score":0.46768105},"labels":[],"label_agreement":null},{"id":"W2483463161","doi":"10.3138/cjpe.31.1.122","title":"Hallie Preskill et Darlene Russ-Eft. (2016). <i>Building evaluation capacity: Activities for teaching and training</i> (2nd ed.).","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Sociology; Physics","score_opus":0.4310966052308271,"score_gpt":0.5106947102029149,"score_spread":0.0795981049720878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2483463161","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091266364,0.7196499,0.010742233,0.19646627,0.021301087,0.00011504194,0.0016545664,0.000837629,0.04832063],"genre_scores_gemma":[0.025155066,0.6924748,0.025937783,0.055066753,0.006430501,0.0003716962,0.0016764441,0.0012474349,0.19163957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972191,0.00078164553,0.0003113741,0.00020832702,0.0012937115,0.00018582662],"domain_scores_gemma":[0.98591423,0.0057194433,0.0009456686,0.00037158097,0.0057863547,0.0012627187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009798957,0.0009532079,0.0008106186,0.0023912338,0.001642023,0.004798618,0.001427512,0.0031816154,0.03719293],"category_scores_gemma":[0.03372928,0.0008500099,0.0004123264,0.0025179535,0.0017930355,0.0054617454,0.002138133,0.0043553608,0.022454323],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035156303,0.000012123235,0.00033321718,0.0003954996,0.000005484753,0.000042055646,0.0005034371,0.000051607818,0.000076288576,0.0018830355,0.820234,0.17642796],"study_design_scores_gemma":[0.000011494963,0.000015382517,0.0016573273,0.0016488254,0.000015593778,0.00014895809,0.0006831952,0.00005191298,0.00023234828,0.00316815,0.99233466,0.000032159747],"about_ca_topic_score_codex":0.08271793,"about_ca_topic_score_gemma":0.21534412,"teacher_disagreement_score":0.08271793,"about_ca_system_score_codex":0.0029199116,"about_ca_system_score_gemma":0.017735437,"threshold_uncertainty_score":0.16447288},"labels":[],"label_agreement":null},{"id":"W2484173420","doi":"10.3138/cjpe.0026.006","title":"Logic Analysis: Testing Program Theory to Better Evaluate Complex Interventions","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"School Health and Nursing Education","field":"Health Professions","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"Canadian Institutes of Health Research; U.S. Public Health Service","keywords":"Psychological intervention; Computer science; Logic model; Risk analysis (engineering); Action (physics); Management science; Psychology; Medicine; Sociology; Engineering","score_opus":0.5926332520068205,"score_gpt":0.6085805738558242,"score_spread":0.015947321849003715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484173420","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09333058,0.0013277717,0.84084797,0.006185607,0.00040236156,0.0076176934,0.00096698187,0.001468863,0.047852155],"genre_scores_gemma":[0.29498807,0.00075537246,0.6933873,0.0012643232,0.000077956494,0.007764854,0.0004149264,0.00019234065,0.0011548201],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9091084,0.07468042,0.002843628,0.0030786411,0.009253605,0.0010352684],"domain_scores_gemma":[0.6580298,0.31282696,0.008331132,0.008367836,0.011315635,0.0011286337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09226405,0.0019210897,0.0015487382,0.004592285,0.0017213156,0.005196677,0.0026939858,0.0014607009,0.012513064],"category_scores_gemma":[0.23234466,0.00069659966,0.0022459337,0.0030060573,0.005577484,0.010702969,0.0035530492,0.0033721735,0.00076050323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018527558,0.002580944,0.02002324,0.0070292344,0.0012899484,0.00021709998,0.0067171813,0.048380367,0.0034370946,0.36169067,0.010043502,0.5367379],"study_design_scores_gemma":[0.0024267167,0.007819811,0.010793691,0.0049766717,0.0013189106,0.0002669004,0.0065184636,0.26864067,0.014876599,0.6487314,0.03326952,0.0003606158],"about_ca_topic_score_codex":0.004604562,"about_ca_topic_score_gemma":0.004116864,"teacher_disagreement_score":0.09226405,"about_ca_system_score_codex":0.008428888,"about_ca_system_score_gemma":0.014074395,"threshold_uncertainty_score":0.48794478},"labels":[],"label_agreement":null},{"id":"W2494669165","doi":"10.3138/cjpe.0026.001","title":"How Does Complexity Impact Evaluation? An Introduction to the Special Issue","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université de Sherbrooke; Université du Québec à Montréal; McGill University; École Nationale d'Administration Publique; York University","funders":"Canadian Institutes of Health Research; U.S. Public Health Service","keywords":"Psychological intervention; Impact evaluation; Management science; Program evaluation; Evaluation methods; Psychology; Computer science; Political science; Medicine; Economics; Engineering","score_opus":0.410774152797953,"score_gpt":0.5566967272910203,"score_spread":0.14592257449306728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494669165","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00068042224,0.2653338,0.013867716,0.4468581,0.25755912,0.0004063132,0.00031685573,0.00023799334,0.014739747],"genre_scores_gemma":[0.011152243,0.29891452,0.025584355,0.17578146,0.46896628,0.0011945398,0.0004995579,0.0008093244,0.01709765],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96693414,0.01916705,0.0042415475,0.001432509,0.0074804747,0.0007442643],"domain_scores_gemma":[0.7312951,0.22981855,0.0050827693,0.0041468567,0.026716912,0.0029398133],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.042549577,0.0017812202,0.0025595205,0.0052839145,0.0033034207,0.010026753,0.0025382482,0.007925987,0.016567225],"category_scores_gemma":[0.18684736,0.0012724167,0.002674799,0.0045913635,0.006864818,0.01451959,0.005983528,0.013165034,0.004305988],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006759579,0.00008112763,0.0008731547,0.0019269285,0.000076663084,0.000083655344,0.0005341012,0.0002661448,0.000116926,0.014780044,0.800094,0.18109961],"study_design_scores_gemma":[0.0000402676,0.00013473885,0.0018367909,0.0070334855,0.0001351365,0.00046002024,0.0005289413,0.00060528493,0.00016854955,0.044383027,0.9445835,0.000090222806],"about_ca_topic_score_codex":0.0048361984,"about_ca_topic_score_gemma":0.008294363,"teacher_disagreement_score":0.95745045,"about_ca_system_score_codex":0.005848566,"about_ca_system_score_gemma":0.0071114763,"threshold_uncertainty_score":0.22502637},"labels":[],"label_agreement":null},{"id":"W249659815","doi":"10.3138/cjpe.17.005","title":"New Partnerships Require New Approaches to Participatory Program Evaluations: Planning for the Future","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Participatory evaluation; Independence (probability theory); Citizen journalism; Work (physics); Government (linguistics); Affect (linguistics); Power (physics); Civil society; Public relations; Program evaluation; Process management; Business; Political science; Psychology; Public administration; Engineering; Politics","score_opus":0.8918311256608674,"score_gpt":0.5795271091974086,"score_spread":0.31230401646345884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W249659815","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017151207,0.012331274,0.09226482,0.79667056,0.0021287813,0.0049639875,0.00014628228,0.00046294494,0.07388007],"genre_scores_gemma":[0.35810027,0.01608999,0.5506514,0.044905867,0.0013265685,0.01198101,0.00044426383,0.00019713769,0.016303547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9153503,0.063850895,0.0030199327,0.0018634786,0.010666162,0.0052491752],"domain_scores_gemma":[0.79499954,0.088897966,0.011397217,0.009640966,0.04581149,0.049252816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13856569,0.00088913366,0.0009316119,0.0019219081,0.012431984,0.018997746,0.0042775646,0.009780518,0.015448271],"category_scores_gemma":[0.10843566,0.0010336756,0.0013682897,0.0020239034,0.013077535,0.020842675,0.012656354,0.011499089,0.0021294127],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034329953,0.0016645524,0.005828464,0.0033289334,0.000119120035,0.0008299728,0.016949754,0.006859917,0.001024612,0.46621135,0.13353948,0.36330044],"study_design_scores_gemma":[0.00036334156,0.0008375866,0.005285886,0.0059165955,0.00009728306,0.0004624635,0.05599458,0.005999437,0.0011447364,0.50917083,0.41439956,0.00032778067],"about_ca_topic_score_codex":0.0111898435,"about_ca_topic_score_gemma":0.0365006,"teacher_disagreement_score":0.13856569,"about_ca_system_score_codex":0.01731109,"about_ca_system_score_gemma":0.124813035,"threshold_uncertainty_score":0.7328142},"labels":[],"label_agreement":null},{"id":"W2498848778","doi":"10.3138/cjpe.307","title":"Evaluating a Prison-Based Intervention Program: Approaches and Challenges","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université Laval","funders":"","keywords":"Prison; Government (linguistics); Intervention (counseling); Process (computing); Face (sociological concept); Public relations; Psychology; Business; Process management; Political science; Sociology; Computer science; Criminology; Psychiatry","score_opus":0.7617709376605948,"score_gpt":0.5696057253886638,"score_spread":0.19216521227193095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2498848778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.598205,0.038892623,0.08352863,0.15621442,0.0011557431,0.027633687,0.0010702274,0.0005971629,0.09270249],"genre_scores_gemma":[0.89488775,0.004978487,0.089421496,0.002982063,0.000088721165,0.0057663433,0.00017204738,0.000042609332,0.0016604644],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.81574696,0.15791161,0.0058326935,0.002174211,0.014252619,0.004081822],"domain_scores_gemma":[0.79879075,0.10864821,0.009706885,0.005544904,0.06609948,0.011209831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13082717,0.001249748,0.0013872286,0.003211251,0.010124742,0.012213716,0.005614515,0.0027602292,0.0029865112],"category_scores_gemma":[0.14116055,0.0006041509,0.00087154796,0.0032863847,0.0046349927,0.0048472816,0.006351293,0.0046016634,0.000323091],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009224463,0.008547049,0.08617772,0.013144966,0.0009741028,0.0010765613,0.061822265,0.015651891,0.0019141224,0.036862493,0.025253316,0.7476532],"study_design_scores_gemma":[0.0015175379,0.013781755,0.27264267,0.061487,0.0015136953,0.0014647101,0.353827,0.0638443,0.009689539,0.080313064,0.13879494,0.0011238015],"about_ca_topic_score_codex":0.22797306,"about_ca_topic_score_gemma":0.35811654,"teacher_disagreement_score":0.22797306,"about_ca_system_score_codex":0.05813849,"about_ca_system_score_gemma":0.13171166,"threshold_uncertainty_score":0.69188845},"labels":[],"label_agreement":null},{"id":"W2505652211","doi":"10.3138/cjpe.225","title":"Improving Interprofessional Education and Collaborative Practice Through Evaluation: An Exploration of Current Trends","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Interdisciplinary Research in Rehabilitation; University of British Columbia","funders":"","keywords":"Political science; Humanities; Psychology; Sociology; Philosophy","score_opus":0.4583917648546845,"score_gpt":0.6133023389854954,"score_spread":0.15491057413081083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2505652211","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06826082,0.8293675,0.028096672,0.057735905,0.00057973684,0.0008650905,0.0003466547,0.00012585366,0.0146217365],"genre_scores_gemma":[0.75316703,0.20113952,0.038445365,0.00468348,0.0003947509,0.0013737868,0.00027103422,0.000077551435,0.00044738987],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7967174,0.15107365,0.02251203,0.0063629644,0.02097048,0.0023635225],"domain_scores_gemma":[0.3580594,0.5296283,0.02825192,0.012997244,0.068646014,0.0024172103],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29667005,0.0007890993,0.003038186,0.013681292,0.0022150362,0.013717333,0.0021385269,0.0023378846,0.0020196931],"category_scores_gemma":[0.33583447,0.00085061596,0.0019091025,0.021616735,0.0052819275,0.020282008,0.004833411,0.00287427,0.0002036785],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071009644,0.0004460396,0.047461703,0.046090066,0.0017925402,0.000065813845,0.011865834,0.00094358134,0.00039424602,0.03165821,0.002791825,0.8557802],"study_design_scores_gemma":[0.00054917025,0.0036337834,0.13294227,0.49061608,0.00843725,0.0008687084,0.07140439,0.015209773,0.0053369803,0.105947465,0.16445906,0.00059495604],"about_ca_topic_score_codex":0.008416909,"about_ca_topic_score_gemma":0.012472162,"teacher_disagreement_score":0.7033299,"about_ca_system_score_codex":0.016424326,"about_ca_system_score_gemma":0.031079093,"threshold_uncertainty_score":0.867331},"labels":[],"label_agreement":null},{"id":"W2507984178","doi":"10.3138/cjpe.262","title":"The Challenges Encountered During a Needs Assessment of International Student Partners: Considerations for Future Evaluations","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"International Student and Expatriate Challenges","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Needs assessment; Psychology; Medical education; Public relations; Population; Political science; Business; Medicine; Environmental health","score_opus":0.18075902035252298,"score_gpt":0.48743221254823105,"score_spread":0.3066731921957081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507984178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7174328,0.006408975,0.04239239,0.12052076,0.004653919,0.039067827,0.0006039678,0.00050109887,0.06841838],"genre_scores_gemma":[0.8561747,0.0042867353,0.08543834,0.007612563,0.00038600105,0.0394423,0.0005078536,0.00021122789,0.0059401765],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.81156904,0.14146811,0.011894869,0.0015956806,0.022106452,0.011365804],"domain_scores_gemma":[0.70444,0.09640781,0.01291611,0.0071514635,0.14274761,0.03633704],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28923023,0.00093350414,0.0022382555,0.002964624,0.01172771,0.013174405,0.004783798,0.0030954503,0.0052780933],"category_scores_gemma":[0.31092307,0.0010588458,0.001919306,0.0026289232,0.0030345588,0.009878643,0.011814184,0.006998283,0.0014361708],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008819968,0.005365078,0.06684258,0.0040308135,0.00013525912,0.0019794859,0.35425347,0.0011405791,0.0023085654,0.0067680697,0.031963184,0.52433085],"study_design_scores_gemma":[0.00021177989,0.003070861,0.0351257,0.007759863,0.00011579287,0.0009934646,0.87567425,0.0025067125,0.0020031338,0.004822447,0.067359015,0.00035702516],"about_ca_topic_score_codex":0.016394326,"about_ca_topic_score_gemma":0.060360897,"teacher_disagreement_score":0.28923023,"about_ca_system_score_codex":0.014988107,"about_ca_system_score_gemma":0.061439995,"threshold_uncertainty_score":0.8765057},"labels":[],"label_agreement":null},{"id":"W2508682278","doi":"10.3138/cjpe.258","title":"Capturing the Imagination: Arts-Informed Inquiry as a Method in Program Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"The arts; Context (archaeology); Representation (politics); Field (mathematics); Qualitative research; Arts in education; Sociology; Psychology; Pedagogy; Engineering ethics; Social science; Visual arts; Political science; Engineering; Art","score_opus":0.5462734858006425,"score_gpt":0.6255805119329582,"score_spread":0.07930702613231566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508682278","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07711542,0.0048378734,0.7042537,0.03774266,0.0008715362,0.010024971,0.0001730237,0.00034708422,0.16463369],"genre_scores_gemma":[0.61621565,0.0015355211,0.3626065,0.0032122303,0.000121828714,0.011529865,0.00005177429,0.0001345443,0.004592095],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5729653,0.41048586,0.003908968,0.0021322975,0.008984399,0.0015231519],"domain_scores_gemma":[0.58704805,0.37229666,0.006822057,0.017062064,0.013434644,0.0033364939],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26802912,0.00077311305,0.0009333618,0.0047971653,0.007208105,0.014321816,0.0027354872,0.0022629318,0.0050840513],"category_scores_gemma":[0.20221859,0.0007319221,0.00082458503,0.0034642597,0.03967156,0.01184891,0.016239518,0.004503148,0.00062753906],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002273593,0.0004358784,0.0029008973,0.0025594125,0.000055710636,0.0004251846,0.44746536,0.0016314777,0.0014196399,0.32383648,0.0051414263,0.21390115],"study_design_scores_gemma":[0.00043568396,0.00081169663,0.0030108043,0.0105257975,0.00012822711,0.00084622967,0.3244747,0.0067992024,0.0053194687,0.44776228,0.19965795,0.00022802911],"about_ca_topic_score_codex":0.003978803,"about_ca_topic_score_gemma":0.006439328,"teacher_disagreement_score":0.7319709,"about_ca_system_score_codex":0.011522858,"about_ca_system_score_gemma":0.026160771,"threshold_uncertainty_score":0.9026504},"labels":[],"label_agreement":null},{"id":"W2509640135","doi":"10.3138/cjpe.31.1.125","title":"Huey T. Chen. (2015). <i>Practical program evaluation: Theory-driven evaluation and the integrated evaluation perspective</i> (2nd ed.).","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Chen; Perspective (graphical); Evaluation methods; Sociology; Program evaluation; Epistemology; Management science; Psychology; Computer science; Mathematics; Philosophy; Statistics; Artificial intelligence; Economics; Engineering; Reliability engineering","score_opus":0.27595033564129184,"score_gpt":0.5513600661607184,"score_spread":0.2754097305194266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509640135","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033057895,0.46569833,0.1087729,0.26320583,0.011136681,0.0006648403,0.0029790308,0.002218234,0.14201845],"genre_scores_gemma":[0.11835058,0.4937855,0.19964938,0.0331784,0.004293473,0.0017962761,0.002239255,0.0012412705,0.14546587],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99487007,0.002426178,0.00038866056,0.00029253346,0.001867201,0.00015540337],"domain_scores_gemma":[0.9581345,0.026209472,0.0017700933,0.00083958195,0.011686539,0.0013599191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016567543,0.0010610386,0.00072580867,0.0042410535,0.0017719748,0.0042996067,0.001712489,0.0026147445,0.025053088],"category_scores_gemma":[0.045215737,0.00082694844,0.00053795404,0.0049007875,0.002764501,0.005420037,0.0019929279,0.0047947187,0.008304021],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049602106,0.000026181631,0.0011020115,0.0010396442,0.00002418225,0.00007038964,0.0013665904,0.000465667,0.00021710584,0.012020522,0.53152,0.4520982],"study_design_scores_gemma":[0.00005568805,0.00012190551,0.007470852,0.00929559,0.0001460371,0.00024186925,0.002358617,0.0016752396,0.0020248136,0.05656744,0.9199017,0.00014016501],"about_ca_topic_score_codex":0.06594884,"about_ca_topic_score_gemma":0.12723269,"teacher_disagreement_score":0.06594884,"about_ca_system_score_codex":0.0072329794,"about_ca_system_score_gemma":0.018671878,"threshold_uncertainty_score":0.13112998},"labels":[],"label_agreement":null},{"id":"W2512095165","doi":"10.3138/cjpe.274","title":"Evaluate This! A Case for Developing Evaluation Competencies","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Competition (biology); Psychology; Business; Medical education; Public relations; Political science; Medicine; Ecology","score_opus":0.5723191234277859,"score_gpt":0.562928248525481,"score_spread":0.009390874902304946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512095165","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061791465,0.0031664483,0.046655804,0.40023,0.0027439245,0.0008036566,0.00007478529,0.00033765787,0.48419625],"genre_scores_gemma":[0.7747942,0.0027005458,0.08674372,0.039013136,0.0004041151,0.00055232615,0.00008958946,0.00030906848,0.09539332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97603685,0.014646437,0.0006776058,0.00081777823,0.0041728946,0.0036484662],"domain_scores_gemma":[0.9802494,0.0065621743,0.0011092087,0.0014678148,0.0048873858,0.0057240883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02432379,0.00072612305,0.00044532557,0.001907278,0.013502849,0.01144018,0.002756668,0.008185374,0.007420649],"category_scores_gemma":[0.034093123,0.00048759257,0.0008466387,0.0011078175,0.018392622,0.011545153,0.015476495,0.013473206,0.0018626464],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068605426,0.0005099816,0.0080609545,0.00025696962,0.000017233731,0.055862807,0.07622306,0.00076020695,0.0012677339,0.6150978,0.15448357,0.08739106],"study_design_scores_gemma":[0.00004069076,0.00015674027,0.0027269525,0.0020634315,0.000025039726,0.03986606,0.11457349,0.0035706356,0.002155437,0.12396989,0.7107332,0.000118396376],"about_ca_topic_score_codex":0.019534128,"about_ca_topic_score_gemma":0.052952055,"teacher_disagreement_score":0.02432379,"about_ca_system_score_codex":0.01180776,"about_ca_system_score_gemma":0.023964487,"threshold_uncertainty_score":0.12863803},"labels":[],"label_agreement":null},{"id":"W2512861887","doi":"10.3138/cjpe.31.1.129","title":"Michael Bamberger, Jos Vassen, and Estelle Raimondo. (2016). <i>Dealing with complexity in development evaluation: A practical approach</i> .","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Complex Systems and Decision Making","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Sociology; Gerontology; Medicine","score_opus":0.49223052226534547,"score_gpt":0.4681439586388767,"score_spread":0.02408656362646877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512861887","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012727949,0.07322744,0.050963312,0.8084154,0.0054092132,0.00031223622,0.00023721792,0.00046028144,0.05970214],"genre_scores_gemma":[0.14173009,0.22553226,0.29982153,0.18749899,0.007961099,0.0016147932,0.0005831768,0.0011222732,0.13413575],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9875981,0.006239315,0.0007219621,0.00047040146,0.0045949086,0.0003753194],"domain_scores_gemma":[0.9640724,0.020931058,0.0024788792,0.00091461645,0.00907904,0.0025239598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028540695,0.0010098197,0.0008052978,0.003908273,0.004490324,0.0087076835,0.0026833136,0.006113908,0.021401236],"category_scores_gemma":[0.06968238,0.00085456873,0.00046851046,0.0045692814,0.005395473,0.012196579,0.0059447116,0.008340072,0.00749194],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008117045,0.000048015096,0.0014052034,0.0011167971,0.000024753987,0.00014405373,0.0038739643,0.0005101152,0.00032401367,0.06290446,0.6744096,0.2551577],"study_design_scores_gemma":[0.00006792292,0.00009238389,0.003167415,0.0064767958,0.000061142906,0.00046272806,0.0051230374,0.0011994072,0.0012404532,0.13800417,0.8439887,0.00011586894],"about_ca_topic_score_codex":0.021323893,"about_ca_topic_score_gemma":0.076989956,"teacher_disagreement_score":0.028540695,"about_ca_system_score_codex":0.0063214954,"about_ca_system_score_gemma":0.017364196,"threshold_uncertainty_score":0.15093946},"labels":[],"label_agreement":null},{"id":"W2517356492","doi":"10.3138/cjpe.267","title":"Process Flow Mapping for Systems Improvement: Lessons Learned","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Process (computing); Computer science; Context (archaeology); Process management; Flow (mathematics); Risk analysis (engineering); Management science; Engineering; Business; Mathematics; Geography","score_opus":0.5733614912876671,"score_gpt":0.5667968770536289,"score_spread":0.006564614234038202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517356492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01880953,0.084445015,0.5814845,0.23080492,0.00345205,0.0015118611,0.00026925773,0.0017161792,0.07750673],"genre_scores_gemma":[0.21675561,0.07737174,0.6877426,0.009848426,0.0014468009,0.0015352636,0.0002763631,0.00045327866,0.0045699417],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9658653,0.026629541,0.0011976749,0.0011456038,0.0044707325,0.0006910809],"domain_scores_gemma":[0.8944938,0.08503431,0.0013758027,0.004416412,0.012949534,0.0017302029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05790224,0.0020918685,0.0012840788,0.0038554093,0.0023804894,0.010243819,0.0038302322,0.003817135,0.006737927],"category_scores_gemma":[0.080268055,0.00066439883,0.0015123384,0.004338067,0.0063279714,0.01546131,0.004928042,0.006229623,0.0012326497],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011159662,0.00043101373,0.0023505457,0.004690605,0.00008348911,0.00014910594,0.0043193055,0.007314324,0.0003942028,0.16563478,0.016370151,0.7981509],"study_design_scores_gemma":[0.00021171062,0.0006913652,0.00425074,0.0228016,0.00015155881,0.00045803777,0.013225417,0.03417471,0.0041503813,0.6690505,0.2506117,0.00022236757],"about_ca_topic_score_codex":0.014929599,"about_ca_topic_score_gemma":0.01094337,"teacher_disagreement_score":0.05790224,"about_ca_system_score_codex":0.00787459,"about_ca_system_score_gemma":0.018454447,"threshold_uncertainty_score":0.30621994},"labels":[],"label_agreement":null},{"id":"W2520223558","doi":"10.3138/cjpe.261","title":"Data Quality Evaluation for Program Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Computer science; Philosophy; Epistemology","score_opus":0.8261497658997451,"score_gpt":0.6791874459859031,"score_spread":0.146962319913842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520223558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026954476,0.02873369,0.66362417,0.19707644,0.0052183564,0.017784268,0.0018402234,0.0009831153,0.05778528],"genre_scores_gemma":[0.38445637,0.01022684,0.5555944,0.021288546,0.0018611018,0.020291097,0.0010348334,0.0004729253,0.004773924],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.19653402,0.6873311,0.054874677,0.0045237676,0.05486862,0.0018678294],"domain_scores_gemma":[0.06681586,0.63073397,0.0431126,0.05556329,0.20056818,0.0032060938],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6795222,0.00093397923,0.0029215463,0.009125547,0.0042754086,0.0154440375,0.0046321973,0.0035882366,0.005775798],"category_scores_gemma":[0.7974698,0.0007566596,0.002605198,0.0089602545,0.0097932955,0.008244547,0.008508016,0.008663053,0.0012593272],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013254154,0.00043443925,0.028313048,0.014157557,0.0014799888,0.0001296372,0.010454312,0.0034283255,0.000956168,0.19462249,0.049368948,0.69532967],"study_design_scores_gemma":[0.0018676316,0.0030117922,0.039498996,0.0896488,0.0027579884,0.00064232724,0.013426994,0.026203657,0.015284038,0.36710688,0.43985075,0.0007001094],"about_ca_topic_score_codex":0.007094366,"about_ca_topic_score_gemma":0.0052776854,"teacher_disagreement_score":0.6795222,"about_ca_system_score_codex":0.01893633,"about_ca_system_score_gemma":0.061725397,"threshold_uncertainty_score":0.3952062},"labels":[],"label_agreement":null},{"id":"W2523734706","doi":"10.3138/cjpe.207","title":"L’étude d’évaluabilité : utilité et pertinence pour l’évaluation de programme","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science","score_opus":0.42773972430882595,"score_gpt":0.52477615985024,"score_spread":0.097036435541414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523734706","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34874302,0.027891034,0.44427046,0.019915527,0.0009526458,0.003836915,0.0007357002,0.0007123551,0.15294239],"genre_scores_gemma":[0.8780047,0.0028673636,0.11315494,0.00048871204,0.00022609865,0.0025017879,0.00018869965,0.00015475348,0.0024129048],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5580021,0.3496925,0.017381322,0.0056440006,0.06735093,0.0019291677],"domain_scores_gemma":[0.25023207,0.6509695,0.022227988,0.019171905,0.0555921,0.001806373],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34010202,0.0016997164,0.0016568147,0.012293181,0.0025041634,0.01681311,0.0026973472,0.0028277135,0.0047698137],"category_scores_gemma":[0.5485969,0.00094392453,0.002459351,0.009608186,0.0069843098,0.010517954,0.0054842005,0.0041687973,0.00051591464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086502335,0.00077731546,0.051662207,0.0079587195,0.0014599763,0.0002719583,0.041831926,0.010004262,0.0026161682,0.10597092,0.0036409104,0.7729406],"study_design_scores_gemma":[0.0008180488,0.005415685,0.29436943,0.035051756,0.002915676,0.0025422298,0.03876358,0.14004868,0.025665997,0.2682886,0.18497254,0.00114772],"about_ca_topic_score_codex":0.008412727,"about_ca_topic_score_gemma":0.00769343,"teacher_disagreement_score":0.659898,"about_ca_system_score_codex":0.012037493,"about_ca_system_score_gemma":0.011473902,"threshold_uncertainty_score":0.8137717},"labels":[],"label_agreement":null},{"id":"W2526774828","doi":"10.3138/cjpe.0022.008","title":"School Determinants of Achievement in Writing: Implications for School Management in Minority Settings","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Moncton; Université Laval","funders":"","keywords":"Pride; Logistic regression; Psychology; Academic achievement; Principal (computer security); Mathematics education; Political science; Medicine","score_opus":0.13587105891396706,"score_gpt":0.4334196601935093,"score_spread":0.29754860127954225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2526774828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99883527,0.0000913051,0.000028052442,0.00030340094,0.000003385179,0.000011327943,0.000043248056,0.0000017177435,0.0006823339],"genre_scores_gemma":[0.9997427,0.000028756413,0.00003746697,0.000014183325,0.0000015523407,0.000004985458,0.000025228004,5.6927e-7,0.00014452072],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990439,0.00028722547,0.000041055682,0.000098301294,0.00013937775,0.00039014226],"domain_scores_gemma":[0.9965432,0.00059565465,0.0007645087,0.000087209635,0.00063132175,0.0013781742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001470121,0.00025948163,0.00030281517,0.0008870845,0.0024934795,0.0013793776,0.00055762834,0.00024818844,0.0021074112],"category_scores_gemma":[0.005136226,0.0001141078,0.0001975842,0.00085017184,0.0008242308,0.000546459,0.0007815307,0.0005083801,0.00012385739],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049850012,0.00012295113,0.98812395,0.000016236554,0.000009517726,0.00006716886,0.004433365,0.00004376317,0.000140351,0.000111026144,0.0002617989,0.0066200076],"study_design_scores_gemma":[0.0000028088746,0.000039051938,0.9919376,0.000021035423,0.000004054326,0.00001102999,0.007569608,0.00008171821,0.00006360416,0.00003762572,0.00022944156,0.0000024253575],"about_ca_topic_score_codex":0.55837154,"about_ca_topic_score_gemma":0.7161278,"teacher_disagreement_score":0.55837154,"about_ca_system_score_codex":0.0052673337,"about_ca_system_score_gemma":0.008046113,"threshold_uncertainty_score":0.8884586},"labels":[],"label_agreement":null},{"id":"W2559795778","doi":"10.3138/cjpe.343","title":"Création de connaissances organisationnelles à la suite d’une intervention de développement professionnel en Centre de santé et de services sociaux (CSSS) : une évaluation des laboratoires de promotion de la santé","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Montfort Hospital; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; Université de Montréal","funders":"","keywords":"Externalization; Promotion (chess); Political science; Sociology; Psychology; Library science; Social psychology","score_opus":0.09309142943055639,"score_gpt":0.45285818728467986,"score_spread":0.3597667578541235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559795778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887579,0.0006638607,0.0028793982,0.00048956345,0.000039592855,0.0021825088,0.000044147502,0.000033062744,0.004910008],"genre_scores_gemma":[0.9895398,0.0004338005,0.0074428925,0.000083924926,0.000019335583,0.0014307632,0.0000480656,0.0000063173543,0.0009950885],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9532586,0.03823131,0.0012256077,0.0013082135,0.0042926017,0.0016836212],"domain_scores_gemma":[0.96156585,0.02709974,0.0033707742,0.0019791916,0.0034505306,0.002534032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026870817,0.0005974399,0.00055939466,0.001190173,0.0013894221,0.0025892584,0.0014018448,0.0013408976,0.0035268036],"category_scores_gemma":[0.03382728,0.00040032057,0.00096120324,0.00095806265,0.002444541,0.0015403456,0.003346062,0.0009827502,0.00028612724],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008817322,0.034794804,0.070389345,0.0052042943,0.0006109698,0.00038461422,0.051329505,0.003206557,0.0073738885,0.006005636,0.0010419731,0.810841],"study_design_scores_gemma":[0.015298508,0.17289868,0.6002177,0.0042495043,0.0027611128,0.0005217191,0.09982808,0.009823713,0.039409354,0.0057106814,0.049032517,0.00024832485],"about_ca_topic_score_codex":0.0064295097,"about_ca_topic_score_gemma":0.008983476,"teacher_disagreement_score":0.026870817,"about_ca_system_score_codex":0.0044616926,"about_ca_system_score_gemma":0.011384662,"threshold_uncertainty_score":0.14210814},"labels":[],"label_agreement":null},{"id":"W2559869212","doi":"10.3138/cjpe.304","title":"Étude d’évaluabilité d’une intervention visant à prévenir l’usage de substances psychoactives lors de la transition primaire-secondaire","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Logbook; Psychology; Intervention (counseling); Medical education; Program evaluation; Logic model; Data collection; Pedagogy; Medicine; Political science; Sociology; Psychiatry","score_opus":0.13013536005876167,"score_gpt":0.47886784992876436,"score_spread":0.3487324898700027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559869212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889774,0.0002908518,0.0035959017,0.0002629768,0.00003180046,0.003304367,0.0001418924,0.000047646587,0.0033471843],"genre_scores_gemma":[0.98510355,0.0002448507,0.009203828,0.000099127705,0.000016191707,0.004065707,0.00017393556,0.000012520123,0.0010802444],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96194017,0.028538264,0.0018365539,0.0015479161,0.004434875,0.001702202],"domain_scores_gemma":[0.9402554,0.038369272,0.0042318264,0.0022350622,0.013258587,0.0016498491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052316137,0.00084773253,0.0007875016,0.0012651689,0.0017357972,0.0016042015,0.0011287734,0.00076005905,0.0023380027],"category_scores_gemma":[0.07957215,0.00044109437,0.001306177,0.0009219044,0.0014681121,0.0011929106,0.001364271,0.0009920151,0.00025243475],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021291487,0.033388864,0.14482106,0.0038140318,0.0011661897,0.00037833964,0.070230216,0.0048750634,0.006737896,0.0014041495,0.0014344269,0.7104584],"study_design_scores_gemma":[0.008228663,0.13587564,0.74387765,0.0025054384,0.0028365627,0.0002490954,0.037162844,0.016888546,0.029587869,0.0012499356,0.021267425,0.00027039257],"about_ca_topic_score_codex":0.10551654,"about_ca_topic_score_gemma":0.12521845,"teacher_disagreement_score":0.10551654,"about_ca_system_score_codex":0.012291237,"about_ca_system_score_gemma":0.016878929,"threshold_uncertainty_score":0.27667755},"labels":[],"label_agreement":null},{"id":"W2559871496","doi":"10.3138/cjpe.263","title":"Evaluating System Change Initiatives: Advancing the Need for Adapting Evaluation Practices","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"PolicyWise for Children & Families; University of Alberta","funders":"","keywords":"Process management; Plan (archaeology); Context (archaeology); Strategic planning; Government (linguistics); Key (lock); Business; Outcome (game theory); Program evaluation; Monitoring and evaluation; Knowledge management; Political science; Management science; Computer science; Public administration; Engineering; Marketing; Economics; Computer security","score_opus":0.771827991309673,"score_gpt":0.6310206511420624,"score_spread":0.14080734016761054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559871496","genre_codex":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05835407,0.033971675,0.26203543,0.57079524,0.0042926623,0.010759934,0.00053752854,0.0015131923,0.057740293],"genre_scores_gemma":[0.31713146,0.010906192,0.64103436,0.020611065,0.0007077777,0.007959807,0.00024124206,0.00038472272,0.0010233304],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.25647953,0.6191784,0.035450578,0.011686977,0.069571525,0.0076329876],"domain_scores_gemma":[0.112337284,0.67337745,0.028175466,0.056362566,0.116706036,0.01304124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.7318178,0.0021897014,0.004107465,0.012356578,0.011986404,0.038825758,0.012174281,0.008762613,0.004124697],"category_scores_gemma":[0.7413005,0.0023090644,0.0022534966,0.009614414,0.02648786,0.032696262,0.029931394,0.021373266,0.0011414172],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003388354,0.0012340868,0.029797398,0.010590854,0.000527945,0.00029446307,0.06842017,0.006877442,0.0010222463,0.07282558,0.024233988,0.783837],"study_design_scores_gemma":[0.0014350045,0.0026348983,0.055037048,0.10390942,0.0008010029,0.000840769,0.2088015,0.019698944,0.005993649,0.30966634,0.28971872,0.0014628011],"about_ca_topic_score_codex":0.06345379,"about_ca_topic_score_gemma":0.0763068,"teacher_disagreement_score":0.7318178,"about_ca_system_score_codex":0.06421482,"about_ca_system_score_gemma":0.26154876,"threshold_uncertainty_score":0.4659133},"labels":[],"label_agreement":null},{"id":"W2559894788","doi":"10.3138/cjpe.31.2.268","title":"Katya Drozdova and Kurt Taylor Gaubatz. (2017). <i>Quantifying the Qualitative: Information Theory for Comparative Case Analysis</i> .","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Econometrics; Mathematics","score_opus":0.5159331862238253,"score_gpt":0.5940602957703359,"score_spread":0.07812710954651059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559894788","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006951445,0.2309884,0.269247,0.39021158,0.008831756,0.0004850505,0.0016702856,0.0011598808,0.090454556],"genre_scores_gemma":[0.22760795,0.33819216,0.30606955,0.034768052,0.0028501088,0.0023100327,0.0025593557,0.0017122021,0.08393051],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99495125,0.0025513803,0.00038743636,0.00034651262,0.0016253798,0.00013796255],"domain_scores_gemma":[0.9612353,0.026743326,0.0019880864,0.0013441282,0.007695145,0.0009940305],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01508765,0.000712539,0.0007003396,0.003457732,0.0021495197,0.0058948705,0.0013979705,0.002176456,0.015024525],"category_scores_gemma":[0.05559397,0.0006693926,0.00045167192,0.003440382,0.0039214245,0.011787364,0.0040042168,0.0043348265,0.008040262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017109171,0.00006961341,0.0017825002,0.0031111888,0.000045947992,0.00020113046,0.008043843,0.00060777547,0.00081924704,0.24462911,0.3734342,0.36708432],"study_design_scores_gemma":[0.000041209845,0.000055064727,0.0032562916,0.005622114,0.00006619341,0.0005142114,0.007410059,0.0013279804,0.0024050828,0.34685144,0.63229346,0.00015696524],"about_ca_topic_score_codex":0.00420835,"about_ca_topic_score_gemma":0.0075104525,"teacher_disagreement_score":0.98491234,"about_ca_system_score_codex":0.0024687685,"about_ca_system_score_gemma":0.005516558,"threshold_uncertainty_score":0.07979208},"labels":[],"label_agreement":null},{"id":"W2560013324","doi":"10.3138/cjpe.339","title":"La production de la théorie du programme dans le cadre d’une évaluation participative : une étude de cas","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Process management; Business","score_opus":0.2661443501415783,"score_gpt":0.4849594687576983,"score_spread":0.21881511861612002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560013324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20791298,0.017627785,0.535782,0.05096101,0.0008928012,0.001884265,0.00029740704,0.0003791692,0.18426257],"genre_scores_gemma":[0.8939101,0.0045177955,0.09423836,0.001320826,0.000104415405,0.0023228189,0.00011036294,0.00015497846,0.0033202253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8409586,0.13035797,0.0031569644,0.0038555658,0.018910637,0.0027602077],"domain_scores_gemma":[0.7116935,0.2585535,0.005747995,0.011682511,0.011205952,0.0011163818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12767489,0.0014936627,0.0014683093,0.008059811,0.009121158,0.019340852,0.003922622,0.00583462,0.0063812113],"category_scores_gemma":[0.16074905,0.0012383048,0.001884693,0.011380089,0.043153524,0.025444353,0.00941098,0.0074486616,0.0006744337],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011862711,0.0002561947,0.005265126,0.0019575183,0.00006723847,0.0008644099,0.1174432,0.0017651982,0.00036631047,0.7989216,0.0019769035,0.07099774],"study_design_scores_gemma":[0.00024817802,0.0004179267,0.009358187,0.012246746,0.0003110746,0.0026748036,0.1810997,0.02300521,0.0050243307,0.58045,0.18492888,0.00023497183],"about_ca_topic_score_codex":0.022053497,"about_ca_topic_score_gemma":0.012159547,"teacher_disagreement_score":0.12767489,"about_ca_system_score_codex":0.02582543,"about_ca_system_score_gemma":0.027310684,"threshold_uncertainty_score":0.67521745},"labels":[],"label_agreement":null},{"id":"W2560249367","doi":"10.3138/cjpe.31.2.262","title":"Kenneth Bush and Colleen Duggan (eds.). (2015). <i>Evaluation in the Extreme: Research, Impact and Politics in Violently Divided Societies</i> .","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Politics; Political science; Environmental ethics; Psychology; Criminology; Sociology; Law; Philosophy","score_opus":0.48133458098590837,"score_gpt":0.5657556512806122,"score_spread":0.08442107029470386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560249367","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028264866,0.93113476,0.0020920471,0.04724912,0.004837287,0.000029303472,0.00034080198,0.00011237498,0.013921718],"genre_scores_gemma":[0.0038600261,0.9787662,0.0026881192,0.0025070081,0.0018935056,0.00003196761,0.00019565436,0.000050861945,0.010006652],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99722147,0.0009371364,0.00029006804,0.0001966082,0.0012210703,0.00013356569],"domain_scores_gemma":[0.98894346,0.0063438243,0.0008480346,0.00022733843,0.0026056054,0.0010317252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007040726,0.0019059387,0.0014734673,0.003810702,0.0013739328,0.006714528,0.0017977093,0.003226983,0.013222872],"category_scores_gemma":[0.010925748,0.0014447488,0.0006118145,0.006736242,0.002421347,0.0065745935,0.0019200642,0.004497274,0.012498701],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054508542,0.000023374112,0.0005368604,0.0015141509,0.000024583433,0.000039234194,0.00053473655,0.00031839474,0.00008750355,0.0039718505,0.6941663,0.29872847],"study_design_scores_gemma":[0.000034531775,0.000035184115,0.0029562814,0.0065051,0.00008150268,0.00026379683,0.0014439967,0.00039521142,0.00040682184,0.012777648,0.97503453,0.00006553767],"about_ca_topic_score_codex":0.06488541,"about_ca_topic_score_gemma":0.1637328,"teacher_disagreement_score":0.06488541,"about_ca_system_score_codex":0.0045916443,"about_ca_system_score_gemma":0.015339291,"threshold_uncertainty_score":0.12901545},"labels":[],"label_agreement":null},{"id":"W2560370233","doi":"10.3138/cjpe.306","title":"Measuring Evaluation Capacity in Ontario Public Health Units","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Business; Capacity building; Process (computing); Evaluation methods; Knowledge management; Process management; Public health; Program evaluation; Public relations; Nursing; Medicine; Political science; Computer science; Public administration; Engineering","score_opus":0.9060914930214881,"score_gpt":0.5182209136786268,"score_spread":0.3878705793428613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560370233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904447,0.00034973558,0.0005609811,0.0009344448,0.000014330495,0.00037451775,0.00028898678,0.000026536538,0.007005837],"genre_scores_gemma":[0.9980913,0.00014609848,0.00073368795,0.000070411246,0.000004935684,0.00014623368,0.00013428029,0.0000050127546,0.00066811277],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9809694,0.007104488,0.0011063534,0.0010885898,0.0057410332,0.0039899857],"domain_scores_gemma":[0.9435164,0.013109086,0.008763645,0.0023340983,0.023643818,0.008632962],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018155634,0.0003447365,0.00047068574,0.002360853,0.005689996,0.0033927874,0.0025440473,0.00054980477,0.0029723437],"category_scores_gemma":[0.03643117,0.00059126556,0.00034958005,0.003297391,0.0038200514,0.0013325752,0.0048578023,0.00081373716,0.00023380031],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041945765,0.00050194556,0.85818917,0.00060925883,0.000111465575,0.00023814771,0.07226549,0.0015340284,0.0015166207,0.0013461013,0.003927798,0.059340596],"study_design_scores_gemma":[0.00003291716,0.00023692512,0.9336769,0.00023187972,0.000027197699,0.00003351982,0.055128947,0.0010922456,0.00067455857,0.00024876895,0.008577416,0.000038719],"about_ca_topic_score_codex":0.88446397,"about_ca_topic_score_gemma":0.915966,"teacher_disagreement_score":0.98184437,"about_ca_system_score_codex":0.069190465,"about_ca_system_score_gemma":0.108065434,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2560370905","doi":"10.3138/cjpe.31.2.265","title":"Katherine Eve Hay and Shubh Kumar-Range (eds.). (2014). <i>Making Evaluation Matter: Writings from South Asia</i> .","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hay; Range (aeronautics); South asia; History; Ancient history; Animal science; Engineering; Biology","score_opus":0.20613094438966154,"score_gpt":0.46084156104524177,"score_spread":0.25471061665558026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560370905","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025209345,0.8871961,0.0024291151,0.081662714,0.013102807,0.000019368967,0.00020887387,0.000067755114,0.015061194],"genre_scores_gemma":[0.003983376,0.96440756,0.0031505586,0.0059926636,0.004522324,0.000028454862,0.00013842853,0.000065961394,0.017710602],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981939,0.00046119577,0.00023665049,0.00016061745,0.0008689624,0.00007862802],"domain_scores_gemma":[0.9860225,0.007443171,0.0006104928,0.00024357991,0.0045498996,0.001130361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008110211,0.0013693247,0.0010299246,0.0031048479,0.0011229246,0.0047436305,0.0015231551,0.0022153503,0.010369175],"category_scores_gemma":[0.012075341,0.0007486206,0.00041646196,0.0049070073,0.0021199298,0.0060168994,0.0014562183,0.0057183756,0.009543336],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003835234,0.000018874145,0.0003579029,0.0014736257,0.00001555871,0.00007088589,0.00092334166,0.00019198055,0.00010795394,0.004729029,0.74875724,0.24331525],"study_design_scores_gemma":[0.0000072228445,0.0000138729865,0.00088324863,0.0031175904,0.000030020026,0.00023376466,0.0010747915,0.00009396915,0.00022832229,0.0052394844,0.98905396,0.000023790388],"about_ca_topic_score_codex":0.022603167,"about_ca_topic_score_gemma":0.05980334,"teacher_disagreement_score":0.022603167,"about_ca_system_score_codex":0.002640437,"about_ca_system_score_gemma":0.009934665,"threshold_uncertainty_score":0.044943154},"labels":[],"label_agreement":null},{"id":"W2560535401","doi":"10.3138/cjpe.276","title":"Canada’s National Alcohol Strategy: It’s Time to Assess Progress","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Centre on Substance Use and Addiction","funders":"","keywords":"Moderation; Harm; Alcohol; Political science; Risk analysis (engineering); Psychology; Business; Public relations; Social psychology","score_opus":0.5170074637952967,"score_gpt":0.5469577318808765,"score_spread":0.029950268085579768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560535401","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052478604,0.01089937,0.025065107,0.7579001,0.005481671,0.004175614,0.0039831204,0.0016102464,0.13840614],"genre_scores_gemma":[0.734339,0.010729163,0.1709172,0.052584514,0.00089452334,0.0048468704,0.003384277,0.0009403796,0.021364072],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8335755,0.059367765,0.0076449495,0.0031999645,0.08756476,0.008647007],"domain_scores_gemma":[0.6479455,0.043880187,0.013664961,0.011248534,0.2538457,0.029415082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15332893,0.0009297596,0.0017259151,0.0041604084,0.010996823,0.01861532,0.0047130072,0.002587939,0.0059443624],"category_scores_gemma":[0.232121,0.0005592491,0.0008092722,0.0059477556,0.006235258,0.008441439,0.005971014,0.005400947,0.0012488835],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035392176,0.00038567823,0.031266063,0.0017447934,0.00023194593,0.000092577255,0.010565499,0.001912371,0.0007659853,0.020658718,0.3891376,0.5428849],"study_design_scores_gemma":[0.00044446363,0.0013952418,0.14221847,0.015123983,0.0003912489,0.00011288156,0.054069847,0.007581358,0.005469669,0.026416121,0.7459708,0.00080598675],"about_ca_topic_score_codex":0.87025553,"about_ca_topic_score_gemma":0.9315767,"teacher_disagreement_score":0.15332893,"about_ca_system_score_codex":0.11779499,"about_ca_system_score_gemma":0.334031,"threshold_uncertainty_score":0.8546665},"labels":[],"label_agreement":null},{"id":"W2560721852","doi":"10.3138/cjpe.142.000","title":"L’analyse de données secondaires dans le cadre d’évaluation de programme : regard théorique et expérientiel","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Political science","score_opus":0.08776847791292303,"score_gpt":0.3604229456213472,"score_spread":0.27265446770842416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560721852","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64296865,0.0080114715,0.25175482,0.019794308,0.00042367098,0.0026030084,0.00087071536,0.00045489866,0.073118456],"genre_scores_gemma":[0.91404593,0.0014265956,0.07812241,0.0005823847,0.000066004104,0.0010293946,0.0003582687,0.000121058016,0.004247952],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.81184465,0.13753496,0.008744527,0.0065755327,0.032272734,0.003027589],"domain_scores_gemma":[0.4290422,0.5097086,0.011120505,0.016337004,0.031909965,0.0018817625],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17695709,0.0010988693,0.0015526703,0.009866738,0.004796061,0.016740292,0.0031337452,0.0032620202,0.005865327],"category_scores_gemma":[0.35607618,0.0010459109,0.0019183024,0.009222388,0.009384679,0.017449073,0.008181283,0.005337413,0.00071825186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008482277,0.0010738977,0.033348754,0.003736342,0.00043820494,0.0009991158,0.5536365,0.0033059928,0.0045515667,0.10549997,0.0048055667,0.28775588],"study_design_scores_gemma":[0.00032329262,0.0017876702,0.06985722,0.015183409,0.0007258693,0.0029347118,0.58515537,0.04221418,0.023780124,0.103687264,0.1536835,0.00066738494],"about_ca_topic_score_codex":0.024170332,"about_ca_topic_score_gemma":0.021517387,"teacher_disagreement_score":0.9854529,"about_ca_system_score_codex":0.014547093,"about_ca_system_score_gemma":0.015844729,"threshold_uncertainty_score":0.9358497},"labels":[],"label_agreement":null},{"id":"W2561874864","doi":"10.3138/cjpe.0023.009","title":"A Bumpy Journey to Evaluation Capacity: A Case Study of Evaluation Capacity Building in a Private Foundation","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Officer; Capacity building; Process (computing); Function (biology); Business; Sample (material); Evaluation methods; Public relations; Knowledge management; Engineering; Political science; Computer science","score_opus":0.6621746987407026,"score_gpt":0.5495807547365068,"score_spread":0.11259394400419576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561874864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9769557,0.00016278532,0.0030521126,0.0063988455,0.000043227457,0.000199897,0.000028504164,0.000031130465,0.013127706],"genre_scores_gemma":[0.993911,0.00016459178,0.0022585005,0.00037461074,0.000017053682,0.00006371052,0.000015149079,0.000018988794,0.0031762875],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98329884,0.011578292,0.00026525022,0.00045464796,0.0010329253,0.003369978],"domain_scores_gemma":[0.96512735,0.018049518,0.0022437451,0.0016010125,0.0029984738,0.009979873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015580634,0.00049916236,0.0004783967,0.0016259924,0.031430632,0.006656705,0.0023614708,0.0037231355,0.004695078],"category_scores_gemma":[0.021451905,0.00085223606,0.00047582804,0.0014913334,0.010984938,0.0045743375,0.007946797,0.0076744035,0.0005210618],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026061432,0.0031664595,0.020176373,0.0002597709,0.000043312244,0.027045436,0.8653645,0.002207944,0.0019962632,0.025195342,0.0090229465,0.045261145],"study_design_scores_gemma":[0.000027894828,0.00047135868,0.0056632613,0.00021883639,0.000015658268,0.002975573,0.9513671,0.001365202,0.00088102504,0.0019227519,0.03504163,0.000049755563],"about_ca_topic_score_codex":0.025576364,"about_ca_topic_score_gemma":0.07725015,"teacher_disagreement_score":0.031430632,"about_ca_system_score_codex":0.012472931,"about_ca_system_score_gemma":0.016586138,"threshold_uncertainty_score":0.09049785},"labels":[],"label_agreement":null},{"id":"W2570925638","doi":"10.3138/cjpe.30.3.397","title":"Peer Reviewers for Volume 30 and Manuscripts Submitted in 2015","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Educational Robotics and Engineering","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Psychology; Thermodynamics","score_opus":0.09959848792078341,"score_gpt":0.34654286666315837,"score_spread":0.24694437874237496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570925638","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007501411,0.0146485185,0.010661442,0.11583032,0.6365012,0.009414114,0.010123473,0.0046284054,0.19069116],"genre_scores_gemma":[0.015162305,0.006528547,0.0069733527,0.009999437,0.04441228,0.00226605,0.0048914957,0.002569643,0.9071969],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96700233,0.0041280007,0.003289112,0.0018836566,0.021713393,0.0019833792],"domain_scores_gemma":[0.668892,0.013437026,0.007678504,0.00762684,0.27372977,0.028635701],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024435919,0.001480138,0.0027270336,0.011542177,0.0054223384,0.014159907,0.0028540415,0.0049441443,0.365569],"category_scores_gemma":[0.13265088,0.00093465525,0.0015910312,0.0055078454,0.0014241624,0.004311665,0.004687583,0.0031931037,0.2141036],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015781376,0.00008145161,0.0004507465,0.0004402151,0.000022675013,0.000062008454,0.00010130612,0.000035502322,0.00036787576,0.00068444497,0.9497175,0.047878426],"study_design_scores_gemma":[0.000088765664,0.00010809514,0.002269081,0.00049751345,0.000037536167,0.00006915081,0.00030964744,0.00016742853,0.00071638555,0.0012798716,0.9944224,0.000034104007],"about_ca_topic_score_codex":0.0034586426,"about_ca_topic_score_gemma":0.012349511,"teacher_disagreement_score":0.365569,"about_ca_system_score_codex":0.0037252996,"about_ca_system_score_gemma":0.026917031,"threshold_uncertainty_score":0.9049388},"labels":[],"label_agreement":null},{"id":"W257962615","doi":"10.3138/cjpe.17.008","title":"Reviewing the Language Arts Program in a Large School District","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education and Technology Integration","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Association of Learned Journals","funders":"","keywords":"The arts; Language arts; School district; Sociology; English language; Pedagogy; Program evaluation; Division (mathematics); Psychology; Medical education; Mathematics education; Political science; Visual arts; Public administration; Medicine; Art","score_opus":0.13622974340045566,"score_gpt":0.43176224696299687,"score_spread":0.29553250356254124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W257962615","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88346213,0.0769674,0.0021159053,0.007842334,0.00091438356,0.0066973153,0.0015227603,0.00017358539,0.020304143],"genre_scores_gemma":[0.92925286,0.05185468,0.0077158823,0.0019559206,0.0003562669,0.001916784,0.0015063143,0.00007659805,0.005364775],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97759765,0.013339332,0.00247774,0.00071905623,0.0047012134,0.0011650934],"domain_scores_gemma":[0.89787376,0.04070439,0.007007955,0.0016126905,0.04977711,0.0030241222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019715138,0.00035187628,0.0009830798,0.008507727,0.0039875032,0.0031227563,0.0018412295,0.0010313478,0.001470025],"category_scores_gemma":[0.038458433,0.0005494284,0.00027874176,0.0096182,0.0011477896,0.0009655433,0.001655639,0.0011427489,0.00029429983],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006457049,0.0026314717,0.056509316,0.046497975,0.000483983,0.0024861677,0.11887218,0.0022494264,0.0070514204,0.0011946112,0.03230823,0.7290694],"study_design_scores_gemma":[0.0003277492,0.0056197327,0.46684474,0.020563314,0.0014790513,0.0011201632,0.2421744,0.0011446512,0.010648367,0.0002895755,0.2496106,0.00017764914],"about_ca_topic_score_codex":0.106031805,"about_ca_topic_score_gemma":0.31536135,"teacher_disagreement_score":0.106031805,"about_ca_system_score_codex":0.017228127,"about_ca_system_score_gemma":0.056180704,"threshold_uncertainty_score":0.21082926},"labels":[],"label_agreement":null},{"id":"W2591620871","doi":"10.3138/cjpe.0026.008","title":"Discussion: Practice-Based Evaluation as a Response to Adress Intervention Complexity","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal; Université du Québec à Montréal; McGill University; École Nationale d'Administration Publique","funders":"","keywords":"Intervention (counseling); Context (archaeology); Psychological intervention; Reading (process); Field (mathematics); Psychology; Management science; Computer science; Knowledge management; Political science; Engineering; History; Mathematics","score_opus":0.5295924933400027,"score_gpt":0.6233783243564389,"score_spread":0.09378583101643623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591620871","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032086305,0.0030036164,0.040930994,0.9031468,0.005453397,0.0016624825,0.00010663255,0.00021729154,0.013392449],"genre_scores_gemma":[0.67788845,0.0033942421,0.07013088,0.22919704,0.0031094975,0.0071617,0.00012052554,0.0002801752,0.008717501],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.66313523,0.26963514,0.0185441,0.005895678,0.035974238,0.0068156924],"domain_scores_gemma":[0.6072977,0.27598467,0.022793205,0.01414241,0.068302125,0.011479894],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25558,0.0008131659,0.0010545342,0.0020126414,0.009816749,0.013397797,0.005769829,0.015029826,0.0055593834],"category_scores_gemma":[0.32276607,0.00064265303,0.0013788417,0.0021970922,0.011480523,0.013733056,0.012220092,0.018949272,0.0006835922],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075915194,0.00072543556,0.012988457,0.011479196,0.00019360043,0.0018166095,0.2836115,0.0025249342,0.0045697526,0.27001044,0.1392341,0.27208683],"study_design_scores_gemma":[0.00035463824,0.00084522134,0.008185137,0.020211676,0.00013914666,0.0018650342,0.27384526,0.005911754,0.0059307697,0.10604169,0.57631785,0.00035177072],"about_ca_topic_score_codex":0.0047884043,"about_ca_topic_score_gemma":0.0061391243,"teacher_disagreement_score":0.25558,"about_ca_system_score_codex":0.018004792,"about_ca_system_score_gemma":0.038125463,"threshold_uncertainty_score":0.91800237},"labels":[],"label_agreement":null},{"id":"W2606229491","doi":"10.3138/cjpe.325","title":"Influential Mentoring Practices for Navigating Challenges and Optimizing Learning During an Evaluation Internship Experience","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Internship; Autonomy; Psychology; Context (archaeology); Medical education; Quality (philosophy); Professional development; Best practice; Pedagogy; Knowledge management; Applied psychology; Computer science; Medicine; Management; Political science","score_opus":0.6665644262235942,"score_gpt":0.6224087149164251,"score_spread":0.04415571130716911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606229491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92560273,0.0015708817,0.015049661,0.017553505,0.0002908969,0.0006079757,0.000049615144,0.000244348,0.039030366],"genre_scores_gemma":[0.98960006,0.0004227625,0.007258703,0.00036458485,0.000026052934,0.000082312254,0.000017102624,0.00002433185,0.002204149],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9677573,0.022129947,0.00073680223,0.0009181132,0.0054865177,0.0029713314],"domain_scores_gemma":[0.9465192,0.023849921,0.004473065,0.0031168119,0.009571591,0.012469412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02780518,0.00044590715,0.00025398802,0.0014536682,0.009661184,0.006755524,0.0019159447,0.0013644001,0.0018649243],"category_scores_gemma":[0.07178795,0.00037534288,0.0003934865,0.000883606,0.0042764354,0.0019548128,0.0067561255,0.0029430015,0.0002370137],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002707432,0.0009902271,0.09785468,0.0004935307,0.00008413093,0.002687952,0.49373302,0.00091587147,0.005608162,0.007250431,0.017882658,0.3722286],"study_design_scores_gemma":[0.000055454006,0.00079712895,0.10928114,0.0012440017,0.00012744189,0.0022082978,0.73500234,0.002683737,0.0050914907,0.0054804706,0.1377925,0.00023606181],"about_ca_topic_score_codex":0.03602295,"about_ca_topic_score_gemma":0.16637553,"teacher_disagreement_score":0.03602295,"about_ca_system_score_codex":0.0105085345,"about_ca_system_score_gemma":0.03241084,"threshold_uncertainty_score":0.1470496},"labels":[],"label_agreement":null},{"id":"W2606650297","doi":"10.3138/cjpe.386","title":"In Tribute to Lyn Shulha: The Authentic Evaluator","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"LYN; Honour; Tribute; Scholarship; Kindness; Fidelity; Sociology; Field (mathematics); Psychology; Environmental ethics; Psychoanalysis; History; Political science; Computer science; Art history; Law; Philosophy; Medicine; Telecommunications","score_opus":0.43053183270283146,"score_gpt":0.5840601491356326,"score_spread":0.15352831643280118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606650297","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039108354,0.001938795,0.00069271424,0.9644835,0.029654942,0.000024640865,0.000024365687,0.000052428244,0.0027375296],"genre_scores_gemma":[0.035597615,0.0031183446,0.0030955574,0.89137024,0.023752013,0.00021763875,0.000036658723,0.0003961707,0.042415705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9645269,0.015695116,0.0020458824,0.004438471,0.011246035,0.0020477076],"domain_scores_gemma":[0.86108065,0.050227053,0.0045471466,0.00445884,0.059447315,0.020239022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025276612,0.00092979503,0.0020641005,0.0012263814,0.016439723,0.01878328,0.0043098726,0.013702315,0.009158469],"category_scores_gemma":[0.18917994,0.00078492204,0.00087992306,0.0014045916,0.02058706,0.013178311,0.007559484,0.055676576,0.0055313758],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003474141,0.00001098673,0.00023529858,0.00010843204,0.000011589214,0.00022463483,0.005325533,0.000041175983,0.00012431748,0.010278542,0.97759455,0.006010224],"study_design_scores_gemma":[0.000017624445,0.000027756774,0.00034686888,0.00070977316,0.000017563587,0.00029669236,0.014560803,0.00025328677,0.00030310033,0.009598447,0.97375315,0.00011498282],"about_ca_topic_score_codex":0.042465452,"about_ca_topic_score_gemma":0.061543193,"teacher_disagreement_score":0.042465452,"about_ca_system_score_codex":0.012627559,"about_ca_system_score_gemma":0.027908187,"threshold_uncertainty_score":0.13367712},"labels":[],"label_agreement":null},{"id":"W2606670574","doi":"10.3138/cjpe.327","title":"The Oral History of Evaluation: An Interview with Lyn Shulha","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Formative assessment; Scholarship; LYN; Oral history; Psychology; Evaluation methods; Pedagogy; Medical education; Sociology; Political science; Medicine; Engineering; Anthropology","score_opus":0.6363883769916328,"score_gpt":0.5707644898010387,"score_spread":0.06562388719059409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606670574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6735707,0.0058332356,0.007584834,0.21986884,0.0020133827,0.001430295,0.00022564361,0.0002010061,0.08927202],"genre_scores_gemma":[0.9534363,0.0026797806,0.003310863,0.01579348,0.00020104536,0.00048038506,0.00006105612,0.00011580891,0.023921233],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9748556,0.018576937,0.0007309073,0.00081106316,0.0028696689,0.002155973],"domain_scores_gemma":[0.95532084,0.024499686,0.002401583,0.0008322552,0.008860012,0.008085717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021561867,0.000436783,0.0010174575,0.0021244192,0.024701342,0.0079451585,0.0017188075,0.0048613884,0.00601392],"category_scores_gemma":[0.060704272,0.0011311275,0.000465611,0.0019480491,0.0141149815,0.005937162,0.006680461,0.011554718,0.0011162147],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003349027,0.00005445461,0.0011250019,0.000066941866,0.000001913259,0.0014797082,0.9786663,0.00005016206,0.00074591406,0.0016836866,0.009644457,0.0064479895],"study_design_scores_gemma":[0.0000039696424,0.000054835615,0.0008805871,0.000223423,0.0000030199133,0.00042309982,0.9406583,0.000088618224,0.00019794842,0.00042930548,0.057000954,0.000035987323],"about_ca_topic_score_codex":0.08886941,"about_ca_topic_score_gemma":0.12481836,"teacher_disagreement_score":0.08886941,"about_ca_system_score_codex":0.018462157,"about_ca_system_score_gemma":0.023658428,"threshold_uncertainty_score":0.17670423},"labels":[],"label_agreement":null},{"id":"W2606709931","doi":"10.3138/cjpe.349","title":"Developing the Program Evaluation Utility Standards: Scholarly Foundations and Collaborative Processes","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Task (project management); Task force; Political science; Engineering ethics; Program evaluation; Management science; Computer science; Process management; Knowledge management; Business; Public administration; Engineering; Management; Economics","score_opus":0.5392904759997819,"score_gpt":0.6027993397034421,"score_spread":0.06350886370366027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606709931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022426443,0.0062585855,0.5160107,0.32374218,0.0029410934,0.0032622316,0.00019778973,0.0006687089,0.12449233],"genre_scores_gemma":[0.37433374,0.004941309,0.5959925,0.0057517015,0.0010076296,0.0016742579,0.00031830385,0.0004061657,0.015574448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.713895,0.17218304,0.018315507,0.006876738,0.08422773,0.0045019593],"domain_scores_gemma":[0.46827412,0.25690657,0.016288022,0.063795365,0.17914796,0.015587885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37700397,0.000792331,0.0010522703,0.012446851,0.0123450495,0.026782785,0.005688598,0.005127583,0.0031355463],"category_scores_gemma":[0.40130606,0.001271714,0.00092333544,0.008752666,0.024682663,0.01348373,0.018226333,0.014887834,0.0008335651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022440086,0.0003535495,0.0032721132,0.00036307453,0.00003005546,0.00010494479,0.01546347,0.0028141988,0.00042815635,0.67384994,0.032660525,0.27063754],"study_design_scores_gemma":[0.00007441109,0.00018739511,0.0054954486,0.004798777,0.000054735796,0.00017198738,0.02241772,0.011400901,0.0031247984,0.56858295,0.38345018,0.00024070549],"about_ca_topic_score_codex":0.04564105,"about_ca_topic_score_gemma":0.052407388,"teacher_disagreement_score":0.95771325,"about_ca_system_score_codex":0.042286772,"about_ca_system_score_gemma":0.2122281,"threshold_uncertainty_score":0.768265},"labels":[],"label_agreement":null},{"id":"W2607080017","doi":"10.3138/cjpe.387","title":"Introduction — Setting the Evaluation Use Context","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Business; History; Archaeology","score_opus":0.542769667312793,"score_gpt":0.5681665235554011,"score_spread":0.025396856242608123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607080017","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05875573,0.02527429,0.18688881,0.3317912,0.01350638,0.0069511067,0.007435831,0.0012432837,0.3681534],"genre_scores_gemma":[0.6370291,0.010106807,0.22567157,0.06867079,0.005817644,0.008283191,0.002171109,0.0007154684,0.041534342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98508644,0.007198579,0.0012851359,0.0022018894,0.002723756,0.0015042641],"domain_scores_gemma":[0.9753607,0.01122677,0.0015552385,0.0010544256,0.008146269,0.0026566517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016671738,0.00073678023,0.0009046541,0.0029710976,0.007997678,0.014452972,0.0023386956,0.005339504,0.018965797],"category_scores_gemma":[0.033867538,0.0010363355,0.00091372046,0.0032075378,0.0077173463,0.008596561,0.007190373,0.009560519,0.0026854326],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029783678,0.00037434333,0.013085245,0.0031560455,0.00003512804,0.00068819197,0.020135194,0.0010283575,0.0041568843,0.6657079,0.13364361,0.15769121],"study_design_scores_gemma":[0.000090463574,0.000156472,0.022111274,0.0057663275,0.00006914664,0.00035760005,0.024525588,0.0012764474,0.0037839117,0.115789704,0.8258663,0.0002066794],"about_ca_topic_score_codex":0.040430572,"about_ca_topic_score_gemma":0.07358474,"teacher_disagreement_score":0.040430572,"about_ca_system_score_codex":0.016825333,"about_ca_system_score_gemma":0.022937695,"threshold_uncertainty_score":0.12207693},"labels":[],"label_agreement":null},{"id":"W2607086309","doi":"10.3138/cjpe.335","title":"Reflections on the Meaning of Success in Collaborative Approaches to Evaluation: Results of an Empirical Study","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University; University of Ottawa; Carleton University","funders":"","keywords":"Meaning (existential); Set (abstract data type); Knowledge management; Core (optical fiber); Work (physics); Key (lock); Empirical research; Computer science; Conceptual framework; Psychology; Management science; Sociology; Epistemology; Engineering; Social science","score_opus":0.8398111028940528,"score_gpt":0.6344216308633112,"score_spread":0.20538947203074165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607086309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9516801,0.000872189,0.01054453,0.012909729,0.00007259157,0.00036468887,0.000027119771,0.00002361761,0.023505453],"genre_scores_gemma":[0.99774796,0.00015547524,0.0012814928,0.00036876363,0.00001159243,0.00012029788,0.0000041271055,0.000011315623,0.00029901063],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.73054343,0.22546901,0.008292402,0.004628813,0.024310991,0.006755339],"domain_scores_gemma":[0.32420307,0.60768783,0.019597795,0.01191981,0.030644914,0.0059466003],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21439151,0.0006576192,0.0011378,0.0048573483,0.012949361,0.018863903,0.003264421,0.0042146454,0.0026693437],"category_scores_gemma":[0.41139472,0.000809231,0.0006685561,0.005269391,0.035257187,0.016130306,0.017134957,0.008345946,0.0002712169],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007396444,0.00027987512,0.015859006,0.00021823673,0.000018270888,0.00028991434,0.9446747,0.00013513306,0.00024202123,0.01733546,0.00071612024,0.020157443],"study_design_scores_gemma":[0.000020947846,0.000112131456,0.00952888,0.00051589304,0.000017490565,0.00014317453,0.9776487,0.0006209339,0.0005170054,0.0057879416,0.00504827,0.000038563907],"about_ca_topic_score_codex":0.008470981,"about_ca_topic_score_gemma":0.0071483403,"teacher_disagreement_score":0.21439151,"about_ca_system_score_codex":0.013353114,"about_ca_system_score_gemma":0.01685745,"threshold_uncertainty_score":0.9687951},"labels":[],"label_agreement":null},{"id":"W2607364656","doi":"10.3138/cjpe.366","title":"Optimizing Use in the Field of Program Evaluation by Integrating Learning from the Knowledge Field","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University; Queen's University","funders":"","keywords":"Terminology; Field (mathematics); Knowledge translation; Body of knowledge; Health care; Engineering ethics; Psychology; Management science; Sociology; Knowledge management; Political science; Computer science; Engineering","score_opus":0.45805747849381845,"score_gpt":0.5653991971273034,"score_spread":0.1073417186334849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607364656","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14177392,0.019129189,0.48417675,0.10046853,0.00092707464,0.003006241,0.0001656338,0.0009503132,0.24940239],"genre_scores_gemma":[0.6988131,0.007556878,0.28415686,0.0033013837,0.00030350738,0.0013308554,0.000118092314,0.00021693196,0.0042025116],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82126707,0.14536351,0.006114154,0.004962644,0.01883654,0.0034561018],"domain_scores_gemma":[0.6311385,0.28286007,0.016182132,0.024577036,0.037721355,0.007520992],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15627845,0.001010181,0.0015462582,0.008398765,0.0058691264,0.020531705,0.0033163277,0.0029787633,0.005953831],"category_scores_gemma":[0.2221387,0.0007240218,0.001366438,0.00677998,0.014553806,0.017711585,0.017214922,0.0048883716,0.0009885362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016813261,0.0009923268,0.015502801,0.0024081827,0.00012330148,0.00012638689,0.030755123,0.0025599732,0.000633655,0.1071852,0.006058046,0.8334869],"study_design_scores_gemma":[0.00034199865,0.0013522354,0.037787665,0.020901086,0.0004918083,0.00048284716,0.06421104,0.01718542,0.009912461,0.6263235,0.22063744,0.00037245025],"about_ca_topic_score_codex":0.012005981,"about_ca_topic_score_gemma":0.016137747,"teacher_disagreement_score":0.84372157,"about_ca_system_score_codex":0.02151689,"about_ca_system_score_gemma":0.049963325,"threshold_uncertainty_score":0.8264893},"labels":[],"label_agreement":null},{"id":"W261013088","doi":"10.3138/cjpe.24.002","title":"A Promising New Approach to Eliminating Selection Bias","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Selection (genetic algorithm); Variance (accounting); Computer science; Process (computing); Selection bias; Transformation (genetics); Econometrics; Data science; Data mining; Machine learning; Artificial intelligence; Statistics; Mathematics; Economics","score_opus":0.5436381024989055,"score_gpt":0.5032713346008978,"score_spread":0.04036676789800775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W261013088","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018002453,0.00018783116,0.99339914,0.0018210179,0.00017419388,0.00011591857,0.00012628597,0.00015651135,0.0022188465],"genre_scores_gemma":[0.071324654,0.0005594312,0.91967213,0.0018308349,0.00065637956,0.0010352538,0.00026901925,0.00016662799,0.004485658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9619994,0.027777376,0.0011305233,0.0032992682,0.005354843,0.00043856012],"domain_scores_gemma":[0.95485353,0.031297702,0.002586777,0.0077966014,0.003088538,0.00037684108],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03433065,0.0011992137,0.001868006,0.0029431204,0.0015140913,0.0030422993,0.0034668287,0.0017943999,0.011481763],"category_scores_gemma":[0.088304065,0.0006123001,0.0029368459,0.004183227,0.0037062296,0.0041866372,0.003559105,0.0043697823,0.002001518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012292038,0.00015031478,0.0027796929,0.00042716158,0.0005891283,0.00011251692,0.00092059694,0.005970741,0.0010355422,0.7502031,0.00710261,0.23058563],"study_design_scores_gemma":[0.00020784567,0.00018406678,0.0017411388,0.00014730245,0.00013324265,0.00027665,0.00019610222,0.03087467,0.0011795467,0.93501234,0.029991597,0.00005552765],"about_ca_topic_score_codex":0.0016120694,"about_ca_topic_score_gemma":0.0015884785,"teacher_disagreement_score":0.96566933,"about_ca_system_score_codex":0.0011323807,"about_ca_system_score_gemma":0.0045562065,"threshold_uncertainty_score":0.18155998},"labels":[],"label_agreement":null},{"id":"W2612736585","doi":"10.3138/cjpe.0023.010","title":"Using Evaluation Capacity Building (ECB) to Interpret Evaluation Strategy and Practice in the United States National Tobacco Control Program (NTCP): A Preliminary Study","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tobacco control; Control (management); Disease control; State (computer science); Tobacco use; Business; Program evaluation; Environmental health; Computer science; Medicine; Political science; Public administration; Public health; Nursing","score_opus":0.5351127052858893,"score_gpt":0.5825620174973914,"score_spread":0.04744931221150217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612736585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5082411,0.0031321095,0.20677397,0.05081224,0.0002661648,0.010378438,0.00047959425,0.00023632223,0.21968007],"genre_scores_gemma":[0.9419576,0.00045370444,0.053207565,0.000947994,0.000014318024,0.0024146005,0.000090542075,0.000026596153,0.0008869262],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.8274165,0.15535301,0.003540674,0.0016881006,0.0076263268,0.004375465],"domain_scores_gemma":[0.7241605,0.22800706,0.009196176,0.0065229186,0.029110717,0.0030025402],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14633423,0.0008791056,0.00078188523,0.006913935,0.0058575394,0.008442828,0.0020618476,0.0018498334,0.0021323205],"category_scores_gemma":[0.2022749,0.00061193283,0.00075736793,0.0063704457,0.006976714,0.008276814,0.006621923,0.0034495888,0.00016533102],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029799176,0.002263326,0.10106994,0.00250406,0.00021213786,0.00078387855,0.17411329,0.0162788,0.00063644967,0.3685107,0.014401086,0.3189284],"study_design_scores_gemma":[0.00047387535,0.0012542522,0.13369392,0.008688027,0.00031618378,0.00045313596,0.49467,0.082718074,0.004138494,0.20567124,0.067585416,0.00033747038],"about_ca_topic_score_codex":0.04818979,"about_ca_topic_score_gemma":0.048870377,"teacher_disagreement_score":0.85366577,"about_ca_system_score_codex":0.02951625,"about_ca_system_score_gemma":0.043961767,"threshold_uncertainty_score":0.7738986},"labels":[],"label_agreement":null},{"id":"W261518190","doi":"10.3138/cjpe.0015.005","title":"Priorities and Values in Accountability Programs","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"School Choice and Performance","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"","keywords":"Accountability; Argument (complex analysis); Venn diagram; Value (mathematics); Principal (computer security); Sociology; Political science; Psychology; Mathematics education; Law; Computer science; Medicine","score_opus":0.15212433202417344,"score_gpt":0.42501663845329557,"score_spread":0.2728923064291221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W261518190","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22468041,0.005374889,0.087256,0.10489771,0.0009570958,0.00045887678,0.00027428314,0.00020615968,0.57589465],"genre_scores_gemma":[0.9878769,0.0006748543,0.007145452,0.0009038139,0.00009506806,0.00013943417,0.00004702729,0.000028359718,0.003089241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8892129,0.08664104,0.0020376123,0.0014681654,0.015048223,0.0055921134],"domain_scores_gemma":[0.90473413,0.05388855,0.008795993,0.0024458924,0.019723026,0.010412426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052148163,0.0004831421,0.00042884835,0.0073658847,0.007426151,0.022894481,0.0014589556,0.0022303923,0.004368946],"category_scores_gemma":[0.09903359,0.00048122177,0.00030298898,0.005767928,0.015222551,0.014316305,0.009581312,0.0035243428,0.00037904744],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060254013,0.00007480583,0.0071206517,0.00019613556,0.000019301915,0.000059882463,0.012656153,0.0011934649,0.00007867161,0.92992234,0.0041443706,0.04447398],"study_design_scores_gemma":[0.000047992675,0.00014056546,0.0077881077,0.001200261,0.0000349279,0.00008884735,0.031685546,0.0034820724,0.000757419,0.89574957,0.058969196,0.00005559761],"about_ca_topic_score_codex":0.00750415,"about_ca_topic_score_gemma":0.007912744,"teacher_disagreement_score":0.052148163,"about_ca_system_score_codex":0.023748267,"about_ca_system_score_gemma":0.025072841,"threshold_uncertainty_score":0.27578914},"labels":[],"label_agreement":null},{"id":"W261564656","doi":"10.3138/cjpe.23.008","title":"Moments of Truth: An Unexplored Dimension to Communicate Effectiveness","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Dimension (graph theory); Psychology; Mathematics; Computer science; Epistemology; Philosophy; Combinatorics","score_opus":0.6291875856848531,"score_gpt":0.5714788075621933,"score_spread":0.05770877812265984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W261564656","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3391432,0.016309831,0.09017048,0.17514971,0.0011621186,0.0004240609,0.00058693136,0.00022452051,0.37682915],"genre_scores_gemma":[0.99455523,0.00080607645,0.0033776,0.0006654176,0.00007607141,0.00004289996,0.000017742843,0.00001082515,0.00044806246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.946685,0.03898976,0.0021477845,0.0009832007,0.0092385225,0.0019556265],"domain_scores_gemma":[0.8476815,0.11101839,0.016248822,0.0067230905,0.013821171,0.0045069745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034041073,0.0004054134,0.0007060058,0.0034009102,0.0047639953,0.014406764,0.0015071371,0.0019814228,0.003941807],"category_scores_gemma":[0.10490742,0.00035191953,0.0004888815,0.0020474195,0.023010422,0.012963197,0.008219992,0.0036925513,0.00019952128],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005221245,0.0002474563,0.038668197,0.0019591427,0.00020576589,0.00033621813,0.15086402,0.0019265935,0.001076193,0.5429724,0.007750379,0.2534715],"study_design_scores_gemma":[0.00010856237,0.0007636911,0.05740435,0.00719758,0.0005013701,0.00081890187,0.2857933,0.006763058,0.003976892,0.5227328,0.113565266,0.00037428323],"about_ca_topic_score_codex":0.014823617,"about_ca_topic_score_gemma":0.021904124,"teacher_disagreement_score":0.034041073,"about_ca_system_score_codex":0.014938144,"about_ca_system_score_gemma":0.013633636,"threshold_uncertainty_score":0.18002856},"labels":[],"label_agreement":null},{"id":"W2616845762","doi":"10.3138/cjpe.328","title":"A Case Study of the Guiding Principles for Collaborative Approaches to Evaluation in a Developmental Evaluation Context","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Context (archaeology); Set (abstract data type); Reflection (computer programming); Engineering ethics; Sociology; Psychology; Knowledge management; Management science; Computer science; Engineering","score_opus":0.9106579329392426,"score_gpt":0.5628987801781327,"score_spread":0.3477591527611099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616845762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65281934,0.004745585,0.20419064,0.04494192,0.000576153,0.007495424,0.00016456116,0.00015398616,0.0849124],"genre_scores_gemma":[0.8871142,0.0011867865,0.105820306,0.0014320354,0.00004175797,0.0019074659,0.00003927751,0.000034227003,0.002423826],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7520316,0.22613081,0.0050547305,0.0026822067,0.009460728,0.00463991],"domain_scores_gemma":[0.8177432,0.140926,0.0069759837,0.008471324,0.01831669,0.007566898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14473827,0.0007205839,0.00074090547,0.0031019652,0.020585297,0.010036907,0.0037850763,0.0057830694,0.002136397],"category_scores_gemma":[0.12503244,0.00082811347,0.0011700701,0.0036790823,0.011362657,0.008499083,0.012349336,0.008813492,0.0003891419],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005688821,0.0047104876,0.0330016,0.0017028234,0.00011270104,0.026538327,0.5716545,0.0039473376,0.0020061964,0.15825392,0.010648246,0.18685496],"study_design_scores_gemma":[0.0004543808,0.002167401,0.014051635,0.0058344956,0.00018103683,0.014733547,0.714609,0.011513164,0.0066689793,0.058899857,0.17061485,0.000271656],"about_ca_topic_score_codex":0.008347312,"about_ca_topic_score_gemma":0.020760164,"teacher_disagreement_score":0.14473827,"about_ca_system_score_codex":0.013626897,"about_ca_system_score_gemma":0.020924844,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W262717460","doi":"10.3138/cjpe.018.010","title":"Reflections on the CES Case Competition: The Coaches’ Perspective","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Competition (biology); Enthusiasm; Perspective (graphical); Order (exchange); Curriculum; Psychology; Public relations; Mathematics education; Sociology; Pedagogy; Political science; Business; Computer science; Social psychology","score_opus":0.6127644386593305,"score_gpt":0.5922524016754245,"score_spread":0.020512036983906023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W262717460","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038174592,0.0037159016,0.002216318,0.87280625,0.009297511,0.00010270173,0.000055617507,0.00003691037,0.073594175],"genre_scores_gemma":[0.6197119,0.011201355,0.003524253,0.276439,0.007914636,0.0003504099,0.00013235175,0.00026579387,0.08046027],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9577284,0.023793226,0.0008433355,0.0019724541,0.007076022,0.008586515],"domain_scores_gemma":[0.9519517,0.020861832,0.0019819466,0.00082878553,0.010169679,0.014206014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027312502,0.0010633594,0.00088975317,0.00226984,0.0311492,0.023894556,0.0074879136,0.02283337,0.008686425],"category_scores_gemma":[0.054412708,0.00090645126,0.0013884276,0.0025369509,0.021261245,0.011993923,0.013837004,0.042022884,0.0014083043],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121697856,0.0006959333,0.0033499533,0.0004250327,0.00002995495,0.010511437,0.24400884,0.0009560459,0.0004800813,0.14198342,0.56462747,0.032810163],"study_design_scores_gemma":[0.000019235496,0.000108461834,0.0013771495,0.0005797397,0.0000066057605,0.0018558445,0.38194317,0.00043915733,0.0002442857,0.008627862,0.6047079,0.000090648835],"about_ca_topic_score_codex":0.0659869,"about_ca_topic_score_gemma":0.14425272,"teacher_disagreement_score":0.9340131,"about_ca_system_score_codex":0.020693855,"about_ca_system_score_gemma":0.017379614,"threshold_uncertainty_score":0.15014511},"labels":[],"label_agreement":null},{"id":"W263836974","doi":"10.3138/cjpe.0014.003","title":"A Framework for Characterizing the Practice of Evaluation, with Application to Empowerment Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empowerment; Sanctions; Diversity (politics); Context (archaeology); Management science; Engineering ethics; Epistemology; Sociology; Psychology; Knowledge management; Computer science; Political science; Engineering; Law","score_opus":0.21391735746675264,"score_gpt":0.545183003893987,"score_spread":0.33126564642723433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W263836974","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020697946,0.004687773,0.9426202,0.015190818,0.0002648506,0.0009360016,0.00013214404,0.00018365707,0.03391475],"genre_scores_gemma":[0.123574525,0.0018856248,0.86783063,0.0011565567,0.0002137241,0.003257027,0.00013662371,0.000063807776,0.0018814206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.880291,0.100190945,0.0070444793,0.0033742422,0.0073582204,0.0017412173],"domain_scores_gemma":[0.91232336,0.06270637,0.004979268,0.005361799,0.012341178,0.0022880912],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10764313,0.0021452112,0.002504278,0.015668215,0.0068697385,0.015325656,0.0042647985,0.007624788,0.0033454453],"category_scores_gemma":[0.07115547,0.0011121846,0.0025981006,0.01025344,0.058668625,0.015280645,0.00648941,0.007563903,0.0006738465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051043617,0.000014223868,0.00014530099,0.00010484628,0.000009061906,0.000031959113,0.0010833262,0.00096190383,0.000038073686,0.9905635,0.00070433505,0.0063383207],"study_design_scores_gemma":[0.000031357376,0.00003514976,0.0002789503,0.0007982287,0.000025718122,0.0001004931,0.0019269723,0.005234632,0.0001588226,0.9613761,0.030000018,0.000033579116],"about_ca_topic_score_codex":0.014331034,"about_ca_topic_score_gemma":0.011354427,"teacher_disagreement_score":0.8923569,"about_ca_system_score_codex":0.018263632,"about_ca_system_score_gemma":0.01962179,"threshold_uncertainty_score":0.56927806},"labels":[],"label_agreement":null},{"id":"W268578929","doi":"10.3138/cjpe.018.012","title":"The CES Case Competition: A Valuable Resource for Community-Based Agencies","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Competition (biology); Resource (disambiguation); Public relations; Limited resources; Marketing; Business; Political science; Computer science","score_opus":0.5127025743481258,"score_gpt":0.5276762218078191,"score_spread":0.014973647459693318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W268578929","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052630972,0.006747151,0.035694093,0.13748524,0.018860992,0.0063902675,0.011833564,0.008694165,0.72166353],"genre_scores_gemma":[0.24125618,0.008069505,0.1378591,0.018053742,0.0073781614,0.006021943,0.0155493915,0.004865762,0.5609462],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98828363,0.004360031,0.00066441105,0.0003855905,0.005001322,0.0013048284],"domain_scores_gemma":[0.93857646,0.013491417,0.0022238696,0.007952974,0.017924612,0.019830616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01585102,0.0008205057,0.000967574,0.004980355,0.009130226,0.007138952,0.00398539,0.003006765,0.10064169],"category_scores_gemma":[0.041685037,0.00087949104,0.0007359746,0.0034790556,0.0019389755,0.0041863928,0.013662186,0.0031317705,0.021947175],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042477343,0.00019700607,0.00072791206,0.00006433405,0.0000038727017,0.0010864959,0.0015587667,0.00016955893,0.00022044893,0.0029205435,0.9108979,0.08211073],"study_design_scores_gemma":[0.000034583925,0.000049376846,0.0013417577,0.00013184271,0.000002046865,0.00087364763,0.0041989717,0.00035172445,0.00011247032,0.0014059241,0.99145937,0.00003821646],"about_ca_topic_score_codex":0.052627213,"about_ca_topic_score_gemma":0.2721218,"teacher_disagreement_score":0.10064169,"about_ca_system_score_codex":0.0066975225,"about_ca_system_score_gemma":0.029909333,"threshold_uncertainty_score":0.33668},"labels":[],"label_agreement":null},{"id":"W268891095","doi":"10.3138/cjpe.0015.009","title":"A Performance Measurement and Evaluation Framework for Continuing Education","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Continuing education; Performance measurement; Data collection; Evaluation methods; Computer science; Process management; Business; Medical education; Engineering; Statistics; Reliability engineering; Mathematics; Medicine; Marketing","score_opus":0.44393524640381515,"score_gpt":0.5410512913199274,"score_spread":0.0971160449161122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W268891095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020840212,0.008095893,0.91648644,0.025922006,0.0006914799,0.0031785422,0.00040170192,0.00048008285,0.04265981],"genre_scores_gemma":[0.08064108,0.0033717616,0.9045873,0.001701422,0.00048466164,0.006232387,0.0005014497,0.00008507345,0.002394854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.73641074,0.20533115,0.013070523,0.0048197214,0.036959656,0.0034082548],"domain_scores_gemma":[0.86650175,0.07912498,0.008485863,0.004692676,0.037992515,0.003202142],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20549226,0.0034854857,0.0026947535,0.015883045,0.004677771,0.01925333,0.007673924,0.0064596357,0.004546677],"category_scores_gemma":[0.12466125,0.001061851,0.002568332,0.01238267,0.012984783,0.013410503,0.006793248,0.006041234,0.0016065631],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024443101,0.00009067642,0.00067653606,0.0008150149,0.000057115103,0.00008189588,0.0013329537,0.007667236,0.00010716591,0.9321924,0.008979758,0.047974836],"study_design_scores_gemma":[0.00011659734,0.00037648928,0.0016955142,0.0048202253,0.000104012564,0.00023981194,0.002444756,0.027561964,0.0006845132,0.7977104,0.16409841,0.00014721614],"about_ca_topic_score_codex":0.017702064,"about_ca_topic_score_gemma":0.010347457,"teacher_disagreement_score":0.98229796,"about_ca_system_score_codex":0.03223038,"about_ca_system_score_gemma":0.044540234,"threshold_uncertainty_score":0.97976947},"labels":[],"label_agreement":null},{"id":"W268922084","doi":"10.3138/cjpe.024.005","title":"Designing and Applying Project Fidelity Assessment for a Teacher Implemented Middle School Instructional Improvement Pilot Intervention","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fidelity; Intervention (counseling); Computer science; Test (biology); Program evaluation; Psychology; Medical education; Medicine; Statistics; Mathematics","score_opus":0.4891953344676366,"score_gpt":0.4914625622028917,"score_spread":0.0022672277352551173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W268922084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6940751,0.000067408844,0.2725072,0.000392389,0.00008357081,0.0283499,0.00013815616,0.0010330642,0.0033532484],"genre_scores_gemma":[0.68142146,0.00007116555,0.30336133,0.00007105244,0.000016428081,0.014286404,0.0001412657,0.000053613705,0.0005773438],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9479962,0.03869426,0.0043856823,0.001450871,0.006050285,0.0014226051],"domain_scores_gemma":[0.90207106,0.052337535,0.008041447,0.0084696235,0.02737887,0.0017014005],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05497399,0.0006743942,0.00054288073,0.001928419,0.0015744106,0.0017443573,0.0015118006,0.0009928888,0.0010465402],"category_scores_gemma":[0.123862796,0.0007345095,0.00085023954,0.0006641067,0.0010880807,0.0014691226,0.00208063,0.0012589673,0.00027928496],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017073816,0.011683236,0.15057744,0.0013829819,0.00025426026,0.0005980373,0.01829109,0.008580303,0.025866665,0.0021742475,0.002401094,0.77648324],"study_design_scores_gemma":[0.0034865683,0.11614043,0.49573326,0.0026900775,0.0011749646,0.0023066225,0.032873828,0.11789761,0.19950995,0.0049802144,0.02235014,0.00085632596],"about_ca_topic_score_codex":0.003154108,"about_ca_topic_score_gemma":0.0033435312,"teacher_disagreement_score":0.94502604,"about_ca_system_score_codex":0.0020684276,"about_ca_system_score_gemma":0.0057890443,"threshold_uncertainty_score":0.2907337},"labels":[],"label_agreement":null},{"id":"W2725327667","doi":"10.3138/cjpe.31124","title":"Finding Balance: An Evaluation Governance Model to Ease Tension between Independence and Inclusion","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Institutes of Health Research; Alberta Innovates","funders":"","keywords":"Independence (probability theory); Balance (ability); Inclusion (mineral); Corporate governance; Business; Psychology; Social psychology; Mathematics; Statistics; Neuroscience","score_opus":0.4753921117862232,"score_gpt":0.5589934326762455,"score_spread":0.08360132089002226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725327667","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06293253,0.00025537785,0.8481491,0.025759468,0.00026415868,0.0033036247,0.00009324835,0.0015211717,0.057721365],"genre_scores_gemma":[0.61707294,0.00010164791,0.37344787,0.0015140636,0.0000851614,0.0025856532,0.00010090989,0.00029818527,0.004793501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8741333,0.097507164,0.006634554,0.0068861973,0.0114566665,0.0033821382],"domain_scores_gemma":[0.8473615,0.0735671,0.013373134,0.024537073,0.030194694,0.010966414],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13267203,0.0007655093,0.0007667793,0.0046872073,0.0066964054,0.015427276,0.0031717448,0.0030407577,0.007177154],"category_scores_gemma":[0.15927553,0.0009716215,0.0008459565,0.0028247463,0.011957318,0.020196581,0.01455798,0.005083101,0.0015465836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039089553,0.0010642326,0.021441117,0.0005594489,0.00013292526,0.0005562635,0.049384806,0.009992202,0.0058960486,0.61730814,0.015295163,0.27797878],"study_design_scores_gemma":[0.000663511,0.0009916832,0.008820218,0.0017863734,0.00020611202,0.00051221007,0.025221841,0.104510784,0.008044275,0.70879346,0.14015746,0.0002920958],"about_ca_topic_score_codex":0.0023906776,"about_ca_topic_score_gemma":0.004155543,"teacher_disagreement_score":0.9976093,"about_ca_system_score_codex":0.009277616,"about_ca_system_score_gemma":0.016720023,"threshold_uncertainty_score":0.70164514},"labels":[],"label_agreement":null},{"id":"W2725947572","doi":"10.3138/cjpe.31142","title":"La fidélité d’implantation d’un programme probant au-delà de son implantation initiale : l’exemple de Ces années incroyables en protection de l’enfance de 2003 à 2013","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Fidelity; Sustainability; Computer science; Humanities; Philosophy; Telecommunications","score_opus":0.21206354201125907,"score_gpt":0.48399008829918905,"score_spread":0.27192654628793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725947572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9663159,0.0013654458,0.004151386,0.0059552067,0.00021362443,0.00024056151,0.00028069425,0.000060058643,0.02141713],"genre_scores_gemma":[0.9825982,0.0010266338,0.0052871937,0.00065330067,0.000052456173,0.00030716835,0.00021774166,0.000033676326,0.009823488],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9934523,0.0029486571,0.0003220572,0.00042183537,0.0014802576,0.0013749476],"domain_scores_gemma":[0.98235714,0.009280864,0.0029164501,0.00088372803,0.0018854869,0.002676349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008673484,0.00026092972,0.00029617755,0.0008677329,0.0028441132,0.0015599583,0.0012716128,0.0012910075,0.0050013163],"category_scores_gemma":[0.033021476,0.00036295457,0.0005555056,0.00072790886,0.0021796394,0.0009936591,0.0025431097,0.002619711,0.0004401296],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015693443,0.0024216822,0.36594275,0.0009195272,0.00013622877,0.007029012,0.09031221,0.0028176575,0.0050647412,0.024626672,0.014123664,0.48503655],"study_design_scores_gemma":[0.00017133368,0.0041797278,0.76131546,0.0023368865,0.00013076363,0.005326442,0.047776915,0.002883069,0.00895839,0.0029202977,0.163789,0.00021173638],"about_ca_topic_score_codex":0.08734387,"about_ca_topic_score_gemma":0.13509259,"teacher_disagreement_score":0.08734387,"about_ca_system_score_codex":0.0069262553,"about_ca_system_score_gemma":0.012777261,"threshold_uncertainty_score":0.17367095},"labels":[],"label_agreement":null},{"id":"W2726096271","doi":"10.3138/cjpe.24.007","title":"An Illustration of a Methodology to Maximize Mail Survey Response Rates in a Provincial School-Based Physical Activity Needs Assessment","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Youth Development and Social Support","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre for Addiction and Mental Health; University of Toronto; University of Guelph","funders":"","keywords":"Quality (philosophy); Psychology; Key (lock); Marketing; Medical education; Applied psychology; Business; Computer science; Medicine","score_opus":0.30199386652084187,"score_gpt":0.5050055444193803,"score_spread":0.2030116778985384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2726096271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043965075,0.0002399346,0.80562806,0.0028275358,0.00039464573,0.13820694,0.0009372228,0.0015127811,0.006287786],"genre_scores_gemma":[0.03768321,0.00005250716,0.8620102,0.0003619803,0.000041164003,0.099180095,0.00010045676,0.00006273613,0.0005076887],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.3519053,0.59426916,0.023389982,0.005014614,0.023485973,0.0019350916],"domain_scores_gemma":[0.54532486,0.3145195,0.0287179,0.057089765,0.052601356,0.0017466217],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42048353,0.0018971682,0.0012821442,0.005451834,0.0034203564,0.0022306778,0.0036730168,0.0031238666,0.00428022],"category_scores_gemma":[0.36253792,0.0019070702,0.0022020086,0.009962996,0.0029215044,0.0016016978,0.0040633027,0.0024643946,0.0018464942],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052573816,0.005060229,0.07376301,0.0067698625,0.00070158974,0.0010209214,0.029132469,0.015273297,0.033491645,0.032778107,0.02848737,0.7682641],"study_design_scores_gemma":[0.019333774,0.04288767,0.26607388,0.0068886983,0.0014238877,0.003515368,0.013363189,0.24168722,0.120629646,0.0496707,0.2327276,0.0017983293],"about_ca_topic_score_codex":0.006927128,"about_ca_topic_score_gemma":0.012201457,"teacher_disagreement_score":0.99307287,"about_ca_system_score_codex":0.0049566915,"about_ca_system_score_gemma":0.01015791,"threshold_uncertainty_score":0.714647},"labels":[],"label_agreement":null},{"id":"W2727038118","doi":"10.3138/cjpe.31039","title":"“Advocates Change the World; Evaluation Can Help”: A Literature Review and Key Insights from the Practice of Advocacy Evaluation","year":2017,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Public relations; Work (physics); Theory of change; Resource (disambiguation); Value (mathematics); Public administration; Sociology; Computer science","score_opus":0.5690707156508308,"score_gpt":0.5993917126532878,"score_spread":0.03032099700245705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727038118","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000069910224,0.9926644,0.000327161,0.005500074,0.0003299748,0.0000422776,0.000009264633,0.0000041762323,0.0010527617],"genre_scores_gemma":[0.0030241823,0.99284655,0.0012700406,0.0023227124,0.0002432496,0.000099715144,0.00001304255,0.000005320259,0.00017519006],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.96552247,0.021332607,0.003930349,0.0012999594,0.0072095343,0.00070503005],"domain_scores_gemma":[0.877451,0.10643421,0.0037976396,0.0014307534,0.009925275,0.00096111355],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.043853123,0.001535507,0.0031133296,0.012716816,0.002206661,0.0075584566,0.0024974819,0.0054577626,0.003018499],"category_scores_gemma":[0.08928325,0.0009245961,0.0018817461,0.017816968,0.0061836736,0.0088835135,0.003915584,0.006029143,0.0006842979],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006315827,0.00008113659,0.00044254633,0.12419349,0.00036788126,0.00014041143,0.0029074426,0.00033280705,0.0001282367,0.04338833,0.03744002,0.7905145],"study_design_scores_gemma":[0.00003828741,0.000066638546,0.0014462237,0.43590182,0.00055884867,0.000485269,0.0032026612,0.00022301552,0.0001979262,0.016255625,0.54156,0.000063777035],"about_ca_topic_score_codex":0.011163689,"about_ca_topic_score_gemma":0.023219079,"teacher_disagreement_score":0.9561469,"about_ca_system_score_codex":0.00989441,"about_ca_system_score_gemma":0.032063365,"threshold_uncertainty_score":0.23192024},"labels":[],"label_agreement":null},{"id":"W2727167739","doi":"10.3138/cjpe.32.1.146","title":"Thomas A. Schwandt. (2015). <i>Evaluation Foundations Revisited: Cultivating a Life of Mind for Practice</i> .","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy; Epistemology; Sociology","score_opus":0.5163532067272812,"score_gpt":0.6042933576740629,"score_spread":0.08794015094678165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727167739","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011262391,0.059553295,0.0094980495,0.8871734,0.008651542,0.000060274604,0.00016674111,0.00012927328,0.03364118],"genre_scores_gemma":[0.18030445,0.1853505,0.039660502,0.4175987,0.008425522,0.00068081665,0.00037591744,0.00054553687,0.1670581],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965089,0.0015938566,0.00026018659,0.0002418637,0.0012375163,0.00015775427],"domain_scores_gemma":[0.9684521,0.019263972,0.0014878471,0.00066466915,0.007873782,0.002257517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011730905,0.00047248567,0.0003510132,0.0015007206,0.003676615,0.005411851,0.0012498159,0.0057780715,0.014654687],"category_scores_gemma":[0.03604434,0.00044057582,0.00037200944,0.0018780285,0.005930909,0.0073345522,0.0027605272,0.010804201,0.0049837874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058612688,0.000033539334,0.0005659703,0.00050351117,0.0000120348195,0.00010272602,0.0032247002,0.00014222327,0.00022417492,0.09817217,0.7770477,0.11991267],"study_design_scores_gemma":[0.00004564937,0.00006138607,0.00327713,0.004383897,0.00003764143,0.00030287492,0.005422882,0.000530699,0.0011607339,0.18381095,0.8008935,0.00007266032],"about_ca_topic_score_codex":0.02007752,"about_ca_topic_score_gemma":0.049387038,"teacher_disagreement_score":0.02007752,"about_ca_system_score_codex":0.0034424376,"about_ca_system_score_gemma":0.013401617,"threshold_uncertainty_score":0.062039733},"labels":[],"label_agreement":null},{"id":"W2727192748","doi":"10.3138/cjpe.0015.010","title":"Evaluating the Learning Opportunities Program: Some Challenges and Lessons Learned","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Disability Education and Employment","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Christian ministry; Medical education; Accommodation; Psychology; Task (project management); Task force; Program evaluation; Public relations; Political science; Engineering; Medicine; Public administration","score_opus":0.7033468625392023,"score_gpt":0.5454137496245606,"score_spread":0.15793311291464174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727192748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49117714,0.035600726,0.0795203,0.27662352,0.0062513524,0.07415547,0.0016622733,0.0007973282,0.034211945],"genre_scores_gemma":[0.65223795,0.017558068,0.2591906,0.01314878,0.0013206645,0.047670983,0.001328354,0.0002486783,0.007295848],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.83789605,0.12437105,0.0117566185,0.0014023647,0.020709163,0.0038647174],"domain_scores_gemma":[0.81277305,0.10069254,0.004911039,0.005078409,0.065322794,0.01122206],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20689963,0.0012434272,0.0015963331,0.0015341232,0.0036046458,0.007286048,0.0046421764,0.0034619689,0.002139405],"category_scores_gemma":[0.15962271,0.00063305063,0.0018045788,0.0019549327,0.0020006476,0.0057253316,0.005277991,0.004835914,0.00044410003],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014048043,0.0068738824,0.0207649,0.0073913108,0.00036236012,0.00063080154,0.01651901,0.0039400514,0.0009579723,0.00551152,0.028140709,0.9075028],"study_design_scores_gemma":[0.010215322,0.08130194,0.20606701,0.06249619,0.0017650353,0.0028469888,0.1971219,0.049327172,0.019626804,0.033166684,0.33443835,0.0016265943],"about_ca_topic_score_codex":0.01747147,"about_ca_topic_score_gemma":0.03847968,"teacher_disagreement_score":0.20689963,"about_ca_system_score_codex":0.010070488,"about_ca_system_score_gemma":0.028736927,"threshold_uncertainty_score":0.97803396},"labels":[],"label_agreement":null},{"id":"W2727296767","doi":"10.3138/cjpe.30975","title":"Building Evaluation Culture and Capacity in a Community-Level Program: Lessons Learned from Evaluating Youth Futures","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Futures contract; General partnership; Context (archaeology); Political science; Humanities; Sociology; Library science; Business; Computer science; Geography","score_opus":0.8259677997461102,"score_gpt":0.605372997880777,"score_spread":0.2205948018653332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727296767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8013944,0.0019335423,0.04293272,0.075502135,0.0004030395,0.0029945073,0.000091788956,0.00027922433,0.07446859],"genre_scores_gemma":[0.9731539,0.000524705,0.022003628,0.0016994525,0.000033677636,0.00062289106,0.000037285175,0.00006231082,0.0018621987],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.86246324,0.118087135,0.0022365206,0.0022730299,0.008740755,0.006199294],"domain_scores_gemma":[0.84957576,0.0961994,0.0039734105,0.009047887,0.022384265,0.018819252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15069221,0.0005636522,0.0008027955,0.0015943728,0.016382596,0.016607143,0.003908941,0.00221214,0.003613662],"category_scores_gemma":[0.11044398,0.0005605368,0.0006025657,0.0011800206,0.016855435,0.009549435,0.018159274,0.0066053947,0.00028675236],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029667735,0.005965718,0.034857422,0.0011051858,0.00011920035,0.0012272296,0.5762296,0.0021117164,0.0016719085,0.03810634,0.014979701,0.32332936],"study_design_scores_gemma":[0.00020684897,0.0012379873,0.03553612,0.0033803515,0.00010424217,0.0008212931,0.8138289,0.005359578,0.005713329,0.032235533,0.10127492,0.0003009497],"about_ca_topic_score_codex":0.034626327,"about_ca_topic_score_gemma":0.08382906,"teacher_disagreement_score":0.15069221,"about_ca_system_score_codex":0.02493262,"about_ca_system_score_gemma":0.060506456,"threshold_uncertainty_score":0.7969461},"labels":[],"label_agreement":null},{"id":"W2727808690","doi":"10.3138/cjpe.018.008","title":"Students’ Perspective of the CES Case Competition","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Competition (biology); Presentation (obstetrics); Perspective (graphical); Task (project management); Relevance (law); Argument (complex analysis); Psychology; Medical education; Work (physics); Time limit; Management; Computer science; Medicine; Political science; Engineering; Law","score_opus":0.3255601195178861,"score_gpt":0.550185675195576,"score_spread":0.22462555567768994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727808690","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17562932,0.0013329053,0.004489108,0.3236297,0.0032066775,0.00034428193,0.00034050722,0.000105821666,0.4909217],"genre_scores_gemma":[0.82125247,0.0010398321,0.0015651581,0.031471208,0.0006525393,0.00021845847,0.00019483612,0.0000829829,0.14352252],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9846993,0.005698594,0.00043998484,0.00076200394,0.003796911,0.0046032444],"domain_scores_gemma":[0.97810614,0.005189203,0.00075840444,0.00046907642,0.008024673,0.0074525108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012637931,0.00053632417,0.00047922143,0.0014041949,0.020098705,0.020009682,0.0026774106,0.007473284,0.020211294],"category_scores_gemma":[0.0340636,0.00035802563,0.0006831751,0.001999026,0.009340479,0.0028637322,0.007820849,0.007717493,0.002525337],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001831244,0.00044055082,0.00990859,0.00015212111,0.00001940608,0.007207339,0.081014566,0.0018984065,0.0007509303,0.3922988,0.4656232,0.040502977],"study_design_scores_gemma":[0.000029737952,0.00009169033,0.0030945137,0.00015494562,0.0000049756723,0.00075247005,0.09732149,0.000900192,0.00042861572,0.012198214,0.8849569,0.00006624506],"about_ca_topic_score_codex":0.13965094,"about_ca_topic_score_gemma":0.20213518,"teacher_disagreement_score":0.13965094,"about_ca_system_score_codex":0.025415199,"about_ca_system_score_gemma":0.034797292,"threshold_uncertainty_score":0.27767617},"labels":[],"label_agreement":null},{"id":"W2727946467","doi":"10.3138/cjpe.31151","title":"Comment évaluer les effets des évaluations d’impact sur la santé : le potentiel de l’analyse de contribution","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Environmental and Social Impact Assessments","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Hôpital Charles-Le Moyne; Université de Sherbrooke","funders":"","keywords":"Health impact assessment; Public health; Public policy; Government (linguistics); Political science; Impact assessment; Business; Public health policy; Welfare economics; Environmental planning; Health policy; Public administration; Geography; Economics; Medicine; Nursing","score_opus":0.05900538957094628,"score_gpt":0.39432617977801926,"score_spread":0.33532079020707295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727946467","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2370942,0.034782685,0.15789208,0.2857847,0.004937556,0.0077624856,0.009355938,0.0014434594,0.26094696],"genre_scores_gemma":[0.8915346,0.0042521153,0.07898637,0.011337211,0.00082609104,0.003469059,0.00093879976,0.00043685274,0.008218912],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5567476,0.34716636,0.01571788,0.0070663365,0.06896316,0.00433868],"domain_scores_gemma":[0.23546794,0.64748615,0.017902901,0.01660386,0.08027831,0.0022607816],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.37795782,0.002307448,0.0022521988,0.0054961275,0.002449248,0.012702246,0.0035132826,0.0038839655,0.009226009],"category_scores_gemma":[0.6058287,0.00068560435,0.003948277,0.0074048745,0.0064993785,0.012164748,0.0060317093,0.0047602532,0.0009624129],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00813552,0.0011582565,0.094904914,0.02488806,0.008614334,0.0004957604,0.024578953,0.045024153,0.0036427102,0.18495063,0.07565724,0.5279495],"study_design_scores_gemma":[0.002819099,0.008218637,0.1673318,0.040657807,0.013508118,0.0007366958,0.03235036,0.08119925,0.039001074,0.25687343,0.35622227,0.0010814535],"about_ca_topic_score_codex":0.07210169,"about_ca_topic_score_gemma":0.056377273,"teacher_disagreement_score":0.37795782,"about_ca_system_score_codex":0.023666117,"about_ca_system_score_gemma":0.029862536,"threshold_uncertainty_score":0.7670888},"labels":[],"label_agreement":null},{"id":"W2728340321","doi":"10.3138/cjpe.31121","title":"Contribution Analysis: Theoretical and Practical Challenges and Prospects for Evaluators","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Toronto","funders":"","keywords":"Rigour; Management science; Causality (physics); Attribution; Engineering ethics; Psychological intervention; Epistemology; Psychology; Computer science; Sociology; Risk analysis (engineering); Medicine; Economics; Social psychology; Engineering; Philosophy","score_opus":0.35549175255489224,"score_gpt":0.5707339832883228,"score_spread":0.21524223073343057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2728340321","genre_codex":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015237122,0.037031814,0.3758616,0.51050144,0.005972018,0.0025872726,0.00025102822,0.0005168415,0.052040793],"genre_scores_gemma":[0.41278255,0.021359216,0.5183361,0.031091778,0.0026216886,0.008417757,0.00018506074,0.00052708667,0.0046788184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.43003294,0.52052486,0.012093807,0.008014379,0.026193976,0.003139997],"domain_scores_gemma":[0.1625745,0.70990825,0.013845983,0.037905917,0.06969826,0.006067165],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.59534574,0.0016744982,0.003564248,0.009266533,0.010951931,0.028634137,0.007439304,0.006483531,0.009269423],"category_scores_gemma":[0.6288502,0.001242863,0.0020019182,0.010275704,0.03760518,0.03656106,0.016528914,0.013128783,0.0015009528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021890114,0.00021287339,0.0058563193,0.005527712,0.0002001073,0.00013612663,0.03537477,0.0012836808,0.0002900131,0.55862004,0.027716227,0.3645631],"study_design_scores_gemma":[0.00014138593,0.00019167262,0.0022802763,0.0203041,0.00013911538,0.00017770422,0.041428875,0.0061270664,0.000726248,0.8185898,0.109732635,0.00016112477],"about_ca_topic_score_codex":0.007907366,"about_ca_topic_score_gemma":0.010991265,"teacher_disagreement_score":0.40465426,"about_ca_system_score_codex":0.016625047,"about_ca_system_score_gemma":0.058259945,"threshold_uncertainty_score":0.4990108},"labels":[],"label_agreement":null},{"id":"W2731403517","doi":"10.3138/cjpe.31077","title":"L’analyse logique comme outil de soutien à l’application des connaissances dans le domaine psychosocial","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal","funders":"","keywords":"Psychology; Psychosocial; Humanities; Sociology; Philosophy; Psychotherapist","score_opus":0.5003024271921066,"score_gpt":0.541141173021538,"score_spread":0.04083874582943137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731403517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31903654,0.032797918,0.221691,0.19271484,0.003663226,0.0015706274,0.0012071452,0.0004979327,0.22682072],"genre_scores_gemma":[0.92893773,0.0075250906,0.051703323,0.0027387042,0.0005943418,0.0013244096,0.00021132853,0.00013573274,0.0068292907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9516534,0.039146226,0.0013571304,0.0013463637,0.0058016665,0.00069519645],"domain_scores_gemma":[0.82810694,0.14739959,0.0052808477,0.004423449,0.013497198,0.0012919834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046694934,0.0012150325,0.0012238263,0.007907105,0.003868542,0.012962909,0.0015448094,0.002050965,0.009341061],"category_scores_gemma":[0.10827182,0.00057328725,0.0018721501,0.0058663813,0.014547176,0.011078533,0.0043369858,0.0056246193,0.0009040966],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019126067,0.00047661283,0.057006445,0.0027551102,0.0005052692,0.0009910902,0.13119869,0.0026381717,0.0016192966,0.46909022,0.011263842,0.32226402],"study_design_scores_gemma":[0.00012509225,0.0005040256,0.1413706,0.012101975,0.00036279653,0.0015647295,0.1921891,0.021843614,0.003437153,0.38222367,0.24396282,0.00031437603],"about_ca_topic_score_codex":0.04093489,"about_ca_topic_score_gemma":0.03312051,"teacher_disagreement_score":0.046694934,"about_ca_system_score_codex":0.013828606,"about_ca_system_score_gemma":0.019465247,"threshold_uncertainty_score":0.24694937},"labels":[],"label_agreement":null},{"id":"W2731415164","doi":"10.3138/cjpe.30961","title":"Analyse d’implantation d’une recherche-intervention sur le dépistage rapide du VIH dans la communauté gaie montréalaise","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program 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":true,"route_about_ca":true,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Intervention (counseling); Multidisciplinary team; General partnership; Multidisciplinary approach; Human immunodeficiency virus (HIV); Sociology; Psychology; Nursing; Political science; Medicine; Family medicine; Social science","score_opus":0.7566823879198299,"score_gpt":0.6582554973832049,"score_spread":0.09842689053662501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731415164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96562296,0.0022232071,0.0046825213,0.0055798227,0.00023791875,0.004999944,0.0007098861,0.00011945736,0.015824392],"genre_scores_gemma":[0.97582555,0.0013784296,0.007445054,0.00095913623,0.00006316531,0.0026151326,0.00025396675,0.000028833349,0.011430837],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9889853,0.0068276916,0.00024966346,0.0006735387,0.0011993495,0.0020644167],"domain_scores_gemma":[0.988624,0.0052169804,0.00083176466,0.0004344207,0.0026625863,0.002230293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013463632,0.0008187169,0.0005875998,0.0012179913,0.004121161,0.0021851177,0.0020394023,0.0016262471,0.006886676],"category_scores_gemma":[0.01590557,0.00058485894,0.0009342373,0.000942272,0.0025221258,0.0008126024,0.0026290081,0.0015176798,0.00042199326],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052375663,0.0125828395,0.18943089,0.004433866,0.00066264026,0.0068811164,0.15523265,0.0061866413,0.020690762,0.020738162,0.010578165,0.5673447],"study_design_scores_gemma":[0.0028906048,0.023113228,0.621879,0.003262898,0.00097007054,0.00095964794,0.14703034,0.0048250337,0.015449339,0.0017592406,0.1775259,0.00033470368],"about_ca_topic_score_codex":0.69806546,"about_ca_topic_score_gemma":0.76529807,"teacher_disagreement_score":0.69806546,"about_ca_system_score_codex":0.035663642,"about_ca_system_score_gemma":0.086947225,"threshold_uncertainty_score":0.60742533},"labels":[],"label_agreement":null},{"id":"W2731520452","doi":"10.3138/cjpe.32.1.143","title":"Patricia Burch and Carolyn J. Heinrich. (2015). <i>Mixed Methods for Policy Research and Program Evaluation</i> .","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Psychology; Psychoanalysis","score_opus":0.6318859600826949,"score_gpt":0.6992112929537181,"score_spread":0.06732533287102316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731520452","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018898902,0.24783209,0.17523275,0.5133523,0.03173677,0.0018597385,0.003049446,0.0011824724,0.023864646],"genre_scores_gemma":[0.059164964,0.25352427,0.4373685,0.17004445,0.010208834,0.012321306,0.002098703,0.0019819492,0.053287007],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9618419,0.028492376,0.0018950192,0.0012514078,0.0061047724,0.0004145943],"domain_scores_gemma":[0.725594,0.21596408,0.009544439,0.006029243,0.039832313,0.0030360236],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.085257575,0.0016713995,0.0015240961,0.0042376937,0.0043092403,0.0048911623,0.0042795916,0.0063917567,0.0251887],"category_scores_gemma":[0.3234574,0.002416799,0.0014232744,0.0051295245,0.0033780346,0.0071539297,0.004634663,0.010858078,0.0093822675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021264152,0.00003837366,0.0010265012,0.0024097785,0.00013113326,0.00010790678,0.0013038977,0.0003346351,0.00022977758,0.01405248,0.7900739,0.19007893],"study_design_scores_gemma":[0.00033003645,0.00019871208,0.006934741,0.017394869,0.0006524541,0.0004313723,0.0023652317,0.0021054426,0.0020298858,0.0770442,0.8902318,0.00028129356],"about_ca_topic_score_codex":0.042289022,"about_ca_topic_score_gemma":0.08722375,"teacher_disagreement_score":0.9147424,"about_ca_system_score_codex":0.0033245333,"about_ca_system_score_gemma":0.013553725,"threshold_uncertainty_score":0.45089054},"labels":[],"label_agreement":null},{"id":"W2732819684","doi":"10.3138/cjpe.20.006","title":"Evaluator Competencies in University-Based Evaluation Training Programs","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credentialing; Accreditation; Licensure; Certificate; Taxonomy (biology); Competence (human resources); Computer science; Medical education; Psychology; Medicine","score_opus":0.4101080033795569,"score_gpt":0.5034090358417598,"score_spread":0.09330103246220289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732819684","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2773012,0.004267698,0.48841086,0.024569811,0.0007547644,0.003616709,0.000315224,0.0014272053,0.19933659],"genre_scores_gemma":[0.81703436,0.0011219356,0.17003883,0.0013084995,0.00007797637,0.0015840743,0.00019440745,0.00011468936,0.008525131],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9176633,0.06173225,0.005109314,0.0017111723,0.011258777,0.0025251315],"domain_scores_gemma":[0.8736761,0.06451932,0.008238139,0.008433678,0.034494862,0.010637859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08040453,0.00042630945,0.0005821008,0.0038490982,0.003010608,0.0066469195,0.00200669,0.0018122119,0.0055379923],"category_scores_gemma":[0.10600684,0.00050742517,0.00037408117,0.001865434,0.0046965578,0.0065813866,0.008502889,0.003306116,0.00094280776],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030206228,0.0013987047,0.07055115,0.0017356513,0.000047072695,0.00024679716,0.03212453,0.0050163567,0.0019193073,0.2650756,0.022594832,0.59898794],"study_design_scores_gemma":[0.00035051093,0.0026161484,0.16402066,0.010714681,0.00012153139,0.0018171518,0.06441143,0.04918636,0.021288665,0.36908376,0.31591895,0.00047021566],"about_ca_topic_score_codex":0.0031703704,"about_ca_topic_score_gemma":0.00543895,"teacher_disagreement_score":0.08040453,"about_ca_system_score_codex":0.007107804,"about_ca_system_score_gemma":0.028518802,"threshold_uncertainty_score":0.42522484},"labels":[],"label_agreement":null},{"id":"W273644060","doi":"10.3138/cjpe.17.007","title":"Evaluating Organizational Capacity Development","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Danish International Development Agency; International Fund for Agricultural Development; Australian Centre for International Agricultural Research; Ministerie van Buitenlandse Zaken; Concordia University; Direktion für Entwicklung und Zusammenarbeit; International Development Research Centre","keywords":"Capacity development; Agricultural development; Capacity building; Process management; Business; Latin Americans; Organization development; Agriculture; Management science; Environmental resource management; Knowledge management; Political science; Computer science; Economic growth; Engineering; Economics","score_opus":0.6856435831176912,"score_gpt":0.546893715148618,"score_spread":0.1387498679690733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W273644060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77882344,0.001676276,0.05996141,0.004343685,0.00022957832,0.007769938,0.0018726033,0.0002856625,0.1450375],"genre_scores_gemma":[0.96691716,0.00036815956,0.02792507,0.00012247759,0.00002396615,0.002266416,0.0005618463,0.000018976749,0.0017958782],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93327653,0.04882344,0.0024519677,0.0014341557,0.011982705,0.0020310928],"domain_scores_gemma":[0.78171605,0.12502284,0.016836816,0.0070064715,0.06264524,0.00677264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054581657,0.00088165863,0.000539735,0.005829599,0.0018734274,0.004663102,0.001581567,0.0008145762,0.006354492],"category_scores_gemma":[0.14020506,0.00023606107,0.00059424766,0.0045913677,0.002531421,0.0037526637,0.0053329337,0.0012454451,0.000542681],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092380453,0.003185679,0.15760006,0.0030760393,0.00058461126,0.00016579582,0.012007114,0.04551961,0.0013184712,0.07596114,0.015049439,0.68460816],"study_design_scores_gemma":[0.0014092864,0.019471861,0.3987267,0.0106355185,0.0015090891,0.00033548527,0.12429549,0.16909616,0.041702673,0.1071892,0.12502582,0.0006027015],"about_ca_topic_score_codex":0.009974676,"about_ca_topic_score_gemma":0.010502487,"teacher_disagreement_score":0.054581657,"about_ca_system_score_codex":0.011465749,"about_ca_system_score_gemma":0.016503291,"threshold_uncertainty_score":0.28865886},"labels":[],"label_agreement":null},{"id":"W274204648","doi":"10.3138/cjpe.16.008","title":"Do Evaluator and Program Practitioner Perspectives Converge in Collaborative Evaluation?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Stakeholder; Participatory evaluation; Program evaluation; Citizen journalism; Collaborative model; Medical education; Psychology; Computer science; Knowledge management; Management science; Sociology; Public relations; Medicine; Political science; Engineering; World Wide Web","score_opus":0.21392616880582213,"score_gpt":0.5507446156045417,"score_spread":0.33681844679871953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W274204648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71315414,0.009996364,0.050795987,0.097133495,0.0007682197,0.00073283707,0.000081865954,0.00014039736,0.1271968],"genre_scores_gemma":[0.98853683,0.0016845173,0.0056063626,0.0026700904,0.00008061679,0.0002650853,0.000034270695,0.00004101563,0.0010812278],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5484972,0.3848763,0.008063462,0.0050474247,0.045864023,0.0076515926],"domain_scores_gemma":[0.54199815,0.34346464,0.020541908,0.011453518,0.070470996,0.012070791],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25998196,0.00061923167,0.0012623703,0.0076077664,0.01011042,0.018524777,0.002723142,0.0053901994,0.0029037488],"category_scores_gemma":[0.41042277,0.0009224544,0.00083221425,0.004354594,0.017878938,0.016780525,0.015587884,0.005310623,0.00044065205],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032470882,0.00013777617,0.032456014,0.0007048024,0.000121129204,0.00091564143,0.8340864,0.00026116418,0.00073311833,0.038415235,0.0028486708,0.08899528],"study_design_scores_gemma":[0.00011380318,0.00030936295,0.023571456,0.002473112,0.00015968028,0.00082676363,0.9030727,0.00127684,0.0009352311,0.027224164,0.03992984,0.00010700774],"about_ca_topic_score_codex":0.005591585,"about_ca_topic_score_gemma":0.006643199,"teacher_disagreement_score":0.25998196,"about_ca_system_score_codex":0.01196244,"about_ca_system_score_gemma":0.018076405,"threshold_uncertainty_score":0.912574},"labels":[],"label_agreement":null},{"id":"W2771643987","doi":"10.3138/cjpe.31144","title":"Théories du changement : comment élaborer des modèles utiles","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Causality (physics); Epistemology; Intervention (counseling); Psychological intervention; Theory of change; Computer science; Sociology; Psychology; Philosophy; Physics","score_opus":0.5023497063004002,"score_gpt":0.5392922766264496,"score_spread":0.03694257032604942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771643987","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0633897,0.006525162,0.6492327,0.099523954,0.001336842,0.0008573327,0.0013938237,0.0009137786,0.17682672],"genre_scores_gemma":[0.8014692,0.0042110016,0.17316331,0.0031110758,0.00036673478,0.0019846663,0.000691184,0.00027925504,0.014723601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9773018,0.016348768,0.00078977284,0.0013976421,0.0034184256,0.00074362406],"domain_scores_gemma":[0.9467524,0.04448442,0.0016438458,0.002670464,0.0039535253,0.0004952747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021021886,0.0016894613,0.001120183,0.0032081828,0.0022936773,0.010804745,0.0042810147,0.0056399857,0.011539718],"category_scores_gemma":[0.06443735,0.0009301268,0.0033177335,0.0045134397,0.008469728,0.01607895,0.0035717594,0.0061000623,0.0020101375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009384881,0.00011933216,0.0022740772,0.0003432186,0.000067397734,0.00010613167,0.0019202261,0.019240823,0.00009863582,0.958873,0.002970945,0.013892428],"study_design_scores_gemma":[0.0001554965,0.00012901814,0.0016155398,0.0008747279,0.00013451351,0.00020892317,0.0027033112,0.14339894,0.00081408006,0.789646,0.060223296,0.00009616145],"about_ca_topic_score_codex":0.021913774,"about_ca_topic_score_gemma":0.017882172,"teacher_disagreement_score":0.021913774,"about_ca_system_score_codex":0.00909455,"about_ca_system_score_gemma":0.0062961043,"threshold_uncertainty_score":0.111175716},"labels":[],"label_agreement":null},{"id":"W2771770473","doi":"10.3138/cjpe.31128","title":"Using Rubrics for an Evaluation: A National Research Council Pilot","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Rubric; Excellence; Relevance (law); Context (archaeology); Psychology; Political science; Computer science; Medical education; Pedagogy; Medicine; Geography","score_opus":0.9730025773537614,"score_gpt":0.7170565067688764,"score_spread":0.25594607058488494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771770473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4852779,0.0009471771,0.20345175,0.0044193603,0.0009786898,0.22093031,0.0057461224,0.0050078365,0.073240824],"genre_scores_gemma":[0.39354533,0.0007542982,0.49166965,0.0012363655,0.00014610846,0.086166404,0.005216519,0.0013479688,0.019917462],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9075254,0.06301938,0.005789492,0.00246958,0.018431755,0.002764232],"domain_scores_gemma":[0.7345852,0.07447094,0.0037769284,0.020447608,0.15901497,0.007704276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13006906,0.001216859,0.0012464207,0.0030580827,0.005096379,0.0026828158,0.004055235,0.0017463613,0.0072915005],"category_scores_gemma":[0.1566778,0.0011631919,0.001229064,0.003113368,0.002406629,0.0017250378,0.0039118812,0.003443125,0.0032101336],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048742266,0.03326654,0.01731692,0.0034341547,0.00016853152,0.0014292565,0.035385575,0.007374888,0.023478968,0.0069337506,0.09318785,0.7731494],"study_design_scores_gemma":[0.009778259,0.06273037,0.21698534,0.0040354254,0.000615876,0.0013225966,0.04846152,0.05575042,0.08119523,0.0072552706,0.5108091,0.0010604655],"about_ca_topic_score_codex":0.09864382,"about_ca_topic_score_gemma":0.11878434,"teacher_disagreement_score":0.13006906,"about_ca_system_score_codex":0.010778912,"about_ca_system_score_gemma":0.03339886,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"commentary","about_ca_system":true,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2773320306","doi":"10.3138/cjpe.32.2.288","title":"Chaplowe, S. G., &amp; Cousins, J. B. (2016). <i>Monitoring and evaluation training: A systematic approach.</i>","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Interprofessional Education and Collaboration","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.31776569494503054,"score_gpt":0.5239777368748721,"score_spread":0.2062120419298416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773320306","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00693839,0.5063295,0.056932747,0.35612348,0.015615897,0.012162233,0.006335492,0.00090425595,0.03865802],"genre_scores_gemma":[0.1385957,0.5181104,0.23733154,0.058922417,0.004025051,0.024721151,0.0032047746,0.0004760938,0.014612886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92793363,0.044776678,0.009762805,0.0011530018,0.015791487,0.00058237545],"domain_scores_gemma":[0.5651143,0.26191348,0.03745602,0.0155913,0.115039974,0.004884867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12659994,0.0007109244,0.001197181,0.013286678,0.0028016116,0.0051353457,0.0026527215,0.0021703546,0.0047480967],"category_scores_gemma":[0.46141776,0.0008686872,0.0013422167,0.009367613,0.003661048,0.0050026453,0.003614706,0.0037473177,0.0019083467],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036421407,0.00007340895,0.0071087726,0.029438311,0.00040902232,0.0000986196,0.004661107,0.00016322841,0.00054347137,0.003876122,0.35000628,0.6032574],"study_design_scores_gemma":[0.00035996313,0.0005271973,0.038303796,0.25611463,0.0015640015,0.00055714627,0.006433189,0.0006890949,0.002519208,0.01525748,0.67742467,0.00024960624],"about_ca_topic_score_codex":0.03079336,"about_ca_topic_score_gemma":0.10417839,"teacher_disagreement_score":0.12659994,"about_ca_system_score_codex":0.0073489356,"about_ca_system_score_gemma":0.030859698,"threshold_uncertainty_score":0.6695325},"labels":[],"label_agreement":null},{"id":"W2773683532","doi":"10.3138/cjpe.32.2.293","title":"Donaldson, S. I., Christie, C. A., &amp; Mark, M. M. (2015). <i>Credible and actionable evidence: The foundations for rigorous and influential evaluations</i> .","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Disaster Response and Management","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Positive economics; Economics; Psychology; Actuarial science","score_opus":0.3034838022400102,"score_gpt":0.5472157172066806,"score_spread":0.2437319149666704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773683532","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016784647,0.21112844,0.024369903,0.70792824,0.014503249,0.0019009976,0.0026398401,0.00019624147,0.035654653],"genre_scores_gemma":[0.1603388,0.3918629,0.1559661,0.251722,0.00627314,0.0076817684,0.0016297773,0.000500046,0.024025476],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95007926,0.026517242,0.0060237874,0.0010361143,0.015916849,0.00042677604],"domain_scores_gemma":[0.50647014,0.36389875,0.025967186,0.0072820936,0.08931958,0.0070622587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12336835,0.0006011231,0.0011242138,0.005168364,0.0027349489,0.006471456,0.0032209589,0.004223604,0.009287495],"category_scores_gemma":[0.5330676,0.0008656692,0.0011377702,0.003605225,0.004884295,0.005549954,0.0029713912,0.009403759,0.0025900938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046044792,0.000057472924,0.0042737327,0.015899941,0.00039850044,0.00009030118,0.001997528,0.00022900876,0.00029382404,0.01777035,0.6776069,0.28092194],"study_design_scores_gemma":[0.0005003263,0.0002589507,0.0089612845,0.07447965,0.0012803809,0.00027136973,0.0033155996,0.0006748394,0.0017174092,0.06676906,0.8416109,0.0001600982],"about_ca_topic_score_codex":0.023296475,"about_ca_topic_score_gemma":0.061235264,"teacher_disagreement_score":0.12336835,"about_ca_system_score_codex":0.007867017,"about_ca_system_score_gemma":0.03306565,"threshold_uncertainty_score":0.652442},"labels":[],"label_agreement":null},{"id":"W2773692454","doi":"10.3138/cjpe.31130","title":"The Impact of Practice on Pedagogy: Reflections of Novice Evaluation Teachers","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Practicum; Syllabus; Pedagogy; Psychology; Mathematics education; Medical education; Sociology; Medicine","score_opus":0.5343895073017358,"score_gpt":0.6801314847072718,"score_spread":0.14574197740553596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773692454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95490974,0.0008400067,0.0052608205,0.011257901,0.0003119404,0.00023411277,0.000046061043,0.0001048902,0.027034601],"genre_scores_gemma":[0.9883387,0.0004378498,0.0013049933,0.0011181562,0.00006212305,0.0000856454,0.000024105473,0.00011090993,0.008517546],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.972985,0.016509414,0.00089079177,0.0015078388,0.0046841307,0.0034228284],"domain_scores_gemma":[0.9182844,0.05243654,0.0038876708,0.0035977166,0.013393546,0.00840014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017099593,0.0006773592,0.00084685086,0.0018704535,0.009940646,0.012533314,0.0024181618,0.0038825267,0.003077976],"category_scores_gemma":[0.08716098,0.00090282934,0.00059385586,0.00079793495,0.011751847,0.004517244,0.010042072,0.010263757,0.00088755705],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009088957,0.0006340194,0.009667485,0.00020929267,0.000013924975,0.0026573772,0.9477775,0.00017713619,0.0018717261,0.0021026325,0.0042595635,0.030538442],"study_design_scores_gemma":[0.000019967216,0.00039827332,0.00896498,0.00031302086,0.000015827545,0.001195289,0.9518654,0.00034236867,0.002328705,0.0012754534,0.0332205,0.000060141112],"about_ca_topic_score_codex":0.0057491804,"about_ca_topic_score_gemma":0.010071675,"teacher_disagreement_score":0.017099593,"about_ca_system_score_codex":0.0069615827,"about_ca_system_score_gemma":0.005480904,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2773791117","doi":"10.3138/cjpe.0020.006","title":"Randomized and Quasi-Experimental Evaluations of Program Impact in Child Welfare in Canada: A Review","year":2006,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychological intervention; Welfare; Randomized controlled trial; Context (archaeology); Psychology; Impact evaluation; Applied psychology; Medicine; Political science; Psychiatry; Geography","score_opus":0.3183477250621403,"score_gpt":0.5792820356604422,"score_spread":0.2609343105983019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773791117","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035259298,0.9864631,0.00092655694,0.00084737147,0.0004892769,0.0054691792,0.0006644999,0.000027389742,0.0015866654],"genre_scores_gemma":[0.06795192,0.9150133,0.0065713003,0.0009385004,0.00023658497,0.008426731,0.0004264054,0.000016334108,0.00041892935],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9147427,0.052235346,0.010935039,0.002427911,0.018569862,0.0010891233],"domain_scores_gemma":[0.8255639,0.12419954,0.019048799,0.0039516957,0.025996316,0.001239776],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0737516,0.0014990988,0.008237099,0.0062250434,0.0017001939,0.0037872384,0.0030487985,0.0022822623,0.005598206],"category_scores_gemma":[0.21646662,0.0011760573,0.005907184,0.012488029,0.002079936,0.0016474231,0.001333161,0.0018815877,0.0003293448],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042405073,0.0005866008,0.0020326336,0.6944623,0.015478126,0.00008007195,0.00047850006,0.00084012654,0.00024668814,0.002503805,0.004070786,0.27497983],"study_design_scores_gemma":[0.0123405205,0.004179565,0.019525694,0.8112559,0.09884374,0.00016884414,0.0007737694,0.0008992641,0.0013213173,0.001834197,0.048704598,0.00015262804],"about_ca_topic_score_codex":0.20538707,"about_ca_topic_score_gemma":0.28645852,"teacher_disagreement_score":0.9704854,"about_ca_system_score_codex":0.029514626,"about_ca_system_score_gemma":0.079978,"threshold_uncertainty_score":0.40838313},"labels":[],"label_agreement":null},{"id":"W2774001204","doi":"10.3138/cjpe.31120","title":"Advancing Patient Engagement in Health Service Improvement: What Can the Evaluation Community Offer?","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Explication; Community engagement; Context (archaeology); Citizen journalism; Health care; Service (business); Quality (philosophy); Psychology; Public relations; Process management; Knowledge management; Business; Political science; Computer science; Marketing; Epistemology","score_opus":0.3496407206752722,"score_gpt":0.5270169854810507,"score_spread":0.1773762648057785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774001204","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024546692,0.06289853,0.0043366016,0.9199742,0.002604794,0.00031920127,0.00003851714,0.000060413175,0.00731308],"genre_scores_gemma":[0.43521535,0.18833557,0.07929368,0.27416223,0.011596879,0.008109782,0.00023851184,0.0003039482,0.002744087],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.48596725,0.44280145,0.01618696,0.0064236554,0.036940873,0.01167988],"domain_scores_gemma":[0.23390049,0.6303165,0.012570673,0.019192085,0.073539674,0.030480597],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.66077155,0.0019808637,0.008853328,0.010239755,0.023576,0.061951734,0.008687518,0.029815743,0.008706647],"category_scores_gemma":[0.6158457,0.0018659517,0.0041423473,0.008346763,0.0409328,0.053440705,0.04751628,0.022887873,0.0010273703],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013169998,0.0010909663,0.008732481,0.016196664,0.00080515794,0.0003412799,0.033622712,0.001499325,0.00018880189,0.24768202,0.08853269,0.59999096],"study_design_scores_gemma":[0.0015573646,0.0013174935,0.009875078,0.15885642,0.0010345624,0.00035245664,0.09911542,0.0038819276,0.0007885396,0.39316446,0.32942203,0.0006342723],"about_ca_topic_score_codex":0.021902852,"about_ca_topic_score_gemma":0.043471485,"teacher_disagreement_score":0.66077155,"about_ca_system_score_codex":0.041313894,"about_ca_system_score_gemma":0.16943133,"threshold_uncertainty_score":0.41832912},"labels":[],"label_agreement":null},{"id":"W2774233808","doi":"10.3138/cjpe.31158","title":"L’Ombudsman face aux défis de l’évaluation : est-il possible d’évaluer l’intangible?","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Ombudsman and Human Rights","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Strengths and weaknesses; Valuation (finance); Task (project management); Political science; Face (sociological concept); Business; Sociology; Management; Psychology; Accounting; Economics; Social psychology; Social science","score_opus":0.15142852316943903,"score_gpt":0.4234776728772624,"score_spread":0.27204914970782335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774233808","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23782723,0.02147858,0.08542871,0.4230579,0.0026061044,0.00044348976,0.00015363102,0.00024632787,0.22875808],"genre_scores_gemma":[0.96380377,0.0022880032,0.020289743,0.0061656875,0.00021545446,0.00026039133,0.000029126491,0.000082617385,0.00686527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.84080255,0.11778518,0.004725605,0.0040345816,0.027506687,0.005145401],"domain_scores_gemma":[0.8794845,0.07230514,0.009805927,0.005804619,0.02664583,0.0059540276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11492639,0.00053027645,0.0010428602,0.0037623686,0.009758902,0.020183805,0.002258437,0.00477358,0.004720367],"category_scores_gemma":[0.19543013,0.00048464298,0.00045027674,0.004039969,0.029103452,0.015761333,0.007829653,0.0068009584,0.000595392],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012847285,0.00013979606,0.0104391035,0.00052444724,0.00005322551,0.00016159135,0.03864777,0.0006447865,0.0006124651,0.76783025,0.018117111,0.16270106],"study_design_scores_gemma":[0.00008850368,0.00041550465,0.023709696,0.008973788,0.00012931037,0.00056108134,0.17764628,0.007372543,0.006948009,0.32846972,0.44539052,0.00029501365],"about_ca_topic_score_codex":0.03042467,"about_ca_topic_score_gemma":0.03241283,"teacher_disagreement_score":0.11492639,"about_ca_system_score_codex":0.029041732,"about_ca_system_score_gemma":0.04527026,"threshold_uncertainty_score":0.6077961},"labels":[],"label_agreement":null},{"id":"W2774864855","doi":"10.3138/10.3138/cjpe.31132","title":"Moving Beyond the Buzzword: A Framework for Teaching Culturally Responsive Approaches to Evaluation","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Sociology; Competence (human resources); Conceptual framework; Epistemology; Humanities; Psychology; Social science; Philosophy; Social psychology; Business","score_opus":0.6407724104552023,"score_gpt":0.5597165071488638,"score_spread":0.0810559033063385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774864855","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047408575,0.0038381468,0.86022705,0.04461905,0.0009540141,0.0011026566,0.000061178835,0.00060414115,0.083852924],"genre_scores_gemma":[0.14453173,0.0037499636,0.8292505,0.0051668896,0.0003050748,0.0026282405,0.0000966042,0.00047172228,0.013799246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93538684,0.05502274,0.0021625662,0.0016456229,0.0042838687,0.0014983823],"domain_scores_gemma":[0.9535828,0.033922292,0.0012432318,0.0028161814,0.0058632665,0.0025721784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06576261,0.0018314238,0.0012344604,0.0058655026,0.0074350233,0.016566502,0.005022863,0.005852554,0.005541181],"category_scores_gemma":[0.04693715,0.000981335,0.0015577616,0.0032168117,0.039131418,0.018200204,0.008325572,0.011588281,0.0018255493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020125419,0.00008323985,0.00027912334,0.00029658794,0.0000066782386,0.00013764709,0.028774114,0.0008824204,0.00048936845,0.9210273,0.0069095287,0.04109386],"study_design_scores_gemma":[0.00003947031,0.00008144984,0.0002890127,0.0018456242,0.000016195725,0.0002526561,0.01817088,0.004533883,0.0009897132,0.7418768,0.231835,0.000069253525],"about_ca_topic_score_codex":0.017355632,"about_ca_topic_score_gemma":0.02342018,"teacher_disagreement_score":0.06576261,"about_ca_system_score_codex":0.022050101,"about_ca_system_score_gemma":0.023052542,"threshold_uncertainty_score":0.34779006},"labels":[],"label_agreement":null},{"id":"W2775174218","doi":"10.3138/cjpe.31122","title":"Theory of Change Analysis: Building Robust Theories of Change","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":145,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Computer science; Management science; Risk analysis (engineering); Positive economics; Econometrics; Economics; Business; Management","score_opus":0.7318312016170765,"score_gpt":0.5642255157815168,"score_spread":0.16760568583555968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775174218","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060038073,0.0020201271,0.9592777,0.012189084,0.00036030193,0.0006774827,0.00023041165,0.0003110449,0.018930007],"genre_scores_gemma":[0.27028915,0.002102942,0.72070605,0.0015861505,0.0003486913,0.0034182034,0.0004119287,0.00017736915,0.00095951994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8728059,0.10354992,0.003953888,0.0062928824,0.012072734,0.0013246734],"domain_scores_gemma":[0.656586,0.2915028,0.010484801,0.023535667,0.016119046,0.0017716975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.108469434,0.0023460279,0.004492797,0.010102,0.0033527745,0.014689831,0.006293539,0.004998704,0.0072321747],"category_scores_gemma":[0.19732013,0.0014571485,0.0043413676,0.007173288,0.019791849,0.016342772,0.0071017086,0.0103381155,0.0010839036],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037763344,0.000104969535,0.0015209111,0.00073352247,0.0003193384,0.000052009596,0.0010963684,0.023259023,0.00008197864,0.94041175,0.002155964,0.030226458],"study_design_scores_gemma":[0.00003153388,0.000060491064,0.00043314518,0.00050090614,0.000054027896,0.000016895137,0.00042662333,0.036392603,0.00014352213,0.95750725,0.0044014887,0.000031484662],"about_ca_topic_score_codex":0.0037456783,"about_ca_topic_score_gemma":0.0032472704,"teacher_disagreement_score":0.108469434,"about_ca_system_score_codex":0.013409065,"about_ca_system_score_gemma":0.011785132,"threshold_uncertainty_score":0.5736481},"labels":[],"label_agreement":null},{"id":"W2775784773","doi":"10.3138/cjpe.31119","title":"Making Evaluation More Responsive to Policy Needs: The Case of the Labour Market Development Agreements","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Statistics Canada; Employment and Social Development Canada","funders":"","keywords":"Process (computing); Business; Key (lock); Market development; Policy development; Process management; Public economics; Economics; Computer science; Economic policy","score_opus":0.4694491553349992,"score_gpt":0.586143825088606,"score_spread":0.11669466975360676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775784773","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03803951,0.008028104,0.023296496,0.7914035,0.0015236816,0.0013565137,0.00017818398,0.00012639692,0.1360476],"genre_scores_gemma":[0.8407347,0.0054831877,0.04540532,0.09400248,0.0010244655,0.0022635933,0.000116744915,0.0002004547,0.010768973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.42656484,0.48980516,0.0096102385,0.007238723,0.037230633,0.02955041],"domain_scores_gemma":[0.3955122,0.51167655,0.008112905,0.013055797,0.05911184,0.01253069],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4452792,0.00090456475,0.0018854953,0.004486668,0.030099627,0.043784875,0.0069954335,0.019436244,0.0049028276],"category_scores_gemma":[0.41576684,0.0013047882,0.0014183539,0.007196571,0.040046375,0.026990607,0.022074202,0.025319928,0.00053366565],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021509512,0.0002535269,0.0051739467,0.001316202,0.00017427158,0.0022562132,0.07501679,0.007820992,0.00054035085,0.7414671,0.06069359,0.10507193],"study_design_scores_gemma":[0.00048777155,0.00022341288,0.007902894,0.00538809,0.00019012808,0.0005321149,0.12842466,0.007699689,0.0020078148,0.4040523,0.44266164,0.00042951328],"about_ca_topic_score_codex":0.3859751,"about_ca_topic_score_gemma":0.4373461,"teacher_disagreement_score":0.8788888,"about_ca_system_score_codex":0.12111121,"about_ca_system_score_gemma":0.23163326,"threshold_uncertainty_score":0.87872744},"labels":[],"label_agreement":null},{"id":"W2779494915","doi":"10.3138/cjpe.19.002","title":"Using Multi-Site Core Evaluation to Provide “Scientific” Evidence","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fidelity; Excellence; Core (optical fiber); Computer science; Program evaluation; Order (exchange); Management science; Service (business); Knowledge management; Process management; Engineering ethics; Engineering management; Business; Engineering; Political science","score_opus":0.8288838258260318,"score_gpt":0.6324526320169,"score_spread":0.19643119380913177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2779494915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22674401,0.008306019,0.5136428,0.007486301,0.0011557887,0.12749672,0.0024554795,0.0011430475,0.11156979],"genre_scores_gemma":[0.5681284,0.0009957007,0.3794292,0.0011997044,0.00011372176,0.04712068,0.0008355641,0.00010379299,0.0020732286],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.42971656,0.51395565,0.020475272,0.005533007,0.027984755,0.0023348108],"domain_scores_gemma":[0.310218,0.42232713,0.03648316,0.062411506,0.16135977,0.0072004464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.43155253,0.0015383806,0.003243291,0.010359598,0.004001325,0.00801127,0.003397316,0.0032013722,0.0076887314],"category_scores_gemma":[0.42602816,0.0010324232,0.0020024364,0.008021318,0.0030730169,0.008556809,0.009674949,0.0030637577,0.0011795267],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009468226,0.00621701,0.044545323,0.021078425,0.0045265956,0.0003340229,0.0092521,0.014502405,0.003096665,0.050191354,0.015847994,0.8209398],"study_design_scores_gemma":[0.019926641,0.06824238,0.21688534,0.07670423,0.010562533,0.0015285306,0.030348804,0.15067105,0.05108293,0.19986582,0.17296755,0.0012142726],"about_ca_topic_score_codex":0.0055318032,"about_ca_topic_score_gemma":0.012031852,"teacher_disagreement_score":0.43155253,"about_ca_system_score_codex":0.011622785,"about_ca_system_score_gemma":0.026004309,"threshold_uncertainty_score":0.70099694},"labels":[],"label_agreement":null},{"id":"W2796920759","doi":"10.3138/cjpe.43178","title":"Linking Evaluation to Expenditure Reviews: Neither Realistic nor a Good Idea","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Religion, Society, and Development","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Christian ministry; Public economics; Psychological intervention; Energy expenditure; Economics; Evaluation methods; Positive economics; Actuarial science; Political science; Psychology; Law; Engineering; Medicine","score_opus":0.15312878588308554,"score_gpt":0.43907444564148057,"score_spread":0.28594565975839503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796920759","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031411878,0.036471717,0.10072195,0.8214627,0.016073095,0.0016309873,0.00030724032,0.00029226096,0.019898819],"genre_scores_gemma":[0.3697932,0.043823205,0.2362614,0.3008801,0.029801227,0.010651576,0.00043665274,0.00054273894,0.0078097726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.23019223,0.6889589,0.027216313,0.0081169,0.04267919,0.002836453],"domain_scores_gemma":[0.09800263,0.7500622,0.034714743,0.0376534,0.074501544,0.0050655175],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6272286,0.001635314,0.0052561457,0.009713278,0.004911834,0.031434987,0.0054222713,0.019016622,0.007903731],"category_scores_gemma":[0.8088334,0.0020991876,0.0024569165,0.00767716,0.026966853,0.046658404,0.011846409,0.021740157,0.0019005906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008393027,0.0003442587,0.0052935956,0.013981585,0.0014361441,0.00014907375,0.0043063518,0.0032565934,0.000320223,0.61803657,0.12020114,0.23183514],"study_design_scores_gemma":[0.000778374,0.0006694678,0.0037134548,0.06664783,0.000986442,0.0001892467,0.0053706565,0.007653087,0.0012799512,0.6816295,0.23060127,0.00048083047],"about_ca_topic_score_codex":0.004367219,"about_ca_topic_score_gemma":0.003665681,"teacher_disagreement_score":0.98430854,"about_ca_system_score_codex":0.01569145,"about_ca_system_score_gemma":0.037264317,"threshold_uncertainty_score":0.45969355},"labels":[],"label_agreement":null},{"id":"W2797293182","doi":"10.3138/cjpe.42961","title":"Regards sur l’expérience de la Commission de révision permanente des programmes au Québec","year":2018,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria; Université du Québec à Montréal","funders":"","keywords":"Commission; Humanities; Political science; Sociology; Philosophy","score_opus":0.0824148591559746,"score_gpt":0.41761825870197566,"score_spread":0.3352033995460011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797293182","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66657126,0.018091638,0.0031582557,0.18588537,0.0015108195,0.0006223608,0.0011098342,0.0002221427,0.122828275],"genre_scores_gemma":[0.9654289,0.002889596,0.0008889121,0.0057208734,0.00013666709,0.00010070763,0.00016593766,0.00003456428,0.02463385],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97328264,0.010519178,0.00082692405,0.0012346621,0.009652071,0.0044845287],"domain_scores_gemma":[0.8954476,0.036887392,0.0069441493,0.002666238,0.043447558,0.01460707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030572327,0.00026724447,0.0005262884,0.0024071697,0.007919406,0.008201055,0.002122125,0.0028785316,0.006181186],"category_scores_gemma":[0.06301666,0.0004102689,0.00034252767,0.0041276636,0.005341247,0.0019859031,0.003739026,0.003631638,0.00022749994],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046135252,0.00052012334,0.11105713,0.0026716879,0.00023795276,0.004655098,0.27894664,0.003548789,0.0038834717,0.08272369,0.15017115,0.36112297],"study_design_scores_gemma":[0.00006656312,0.00043807368,0.25043127,0.0016348377,0.00011610056,0.000443542,0.0981221,0.001276238,0.0011833371,0.0015929844,0.6445187,0.00017621693],"about_ca_topic_score_codex":0.9385391,"about_ca_topic_score_gemma":0.9426422,"teacher_disagreement_score":0.89882743,"about_ca_system_score_codex":0.10117259,"about_ca_system_score_gemma":0.1712878,"threshold_uncertainty_score":0.73406196},"labels":[],"label_agreement":null},{"id":"W2797491711","doi":"10.3138/cjpe.43180","title":"Expenditure Reviews and the Federal Experience: Program Evaluation and Its Contribution to Assurance Provision","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Function (biology); Business; Accounting; Public administration; Administration (probate law); Focus (optics); Public relations; Finance; Political science; Law","score_opus":0.2778351949623966,"score_gpt":0.5486718860554921,"score_spread":0.2708366910930955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797491711","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2576288,0.017702136,0.0055596284,0.5499521,0.0017471081,0.0002981408,0.00022460251,0.0002519258,0.16663565],"genre_scores_gemma":[0.974649,0.0037316333,0.001747725,0.011455495,0.0004673302,0.00009647942,0.000054413074,0.00006856426,0.0077293846],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7573222,0.19030944,0.008486597,0.0031616038,0.026446804,0.01427335],"domain_scores_gemma":[0.57995826,0.2555805,0.04428513,0.010658003,0.07616129,0.03335677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13876566,0.000293124,0.00064433715,0.0043022754,0.010823257,0.015535755,0.00205882,0.004335232,0.005122074],"category_scores_gemma":[0.26215458,0.0008135934,0.0005586016,0.0039569535,0.0074231997,0.0054753083,0.0091454405,0.007345812,0.0003585944],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050810014,0.00090605876,0.07684978,0.0015116784,0.00027488166,0.0011964253,0.102775216,0.0018172947,0.0008606412,0.18365769,0.19365966,0.43598256],"study_design_scores_gemma":[0.00012849912,0.00095701905,0.20663102,0.004068031,0.00024613537,0.0010196333,0.073488116,0.0024414903,0.0027450987,0.021974346,0.68568444,0.00061610655],"about_ca_topic_score_codex":0.12553325,"about_ca_topic_score_gemma":0.16107024,"teacher_disagreement_score":0.96111447,"about_ca_system_score_codex":0.038885545,"about_ca_system_score_gemma":0.07990568,"threshold_uncertainty_score":0.7338717},"labels":[],"label_agreement":null},{"id":"W2797507478","doi":"10.3138/cjpe.32.3.vi","title":"Un mot de la rédactrice","year":2018,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.09207310104476685,"score_gpt":0.37894328356865975,"score_spread":0.2868701825238929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797507478","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018920569,0.013418087,0.092315145,0.1643397,0.054786846,0.0009790008,0.0078282235,0.012263412,0.635149],"genre_scores_gemma":[0.11290233,0.008586117,0.06625143,0.021439932,0.014684757,0.0013769607,0.0068845213,0.0066294293,0.76124454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9724851,0.011084457,0.0011842196,0.0023099182,0.01180219,0.0011340831],"domain_scores_gemma":[0.96362966,0.009992888,0.0014676083,0.0034927453,0.019959154,0.001457922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014623268,0.0020595638,0.0015427346,0.0035720211,0.005931755,0.01560749,0.0019182622,0.004643483,0.092633225],"category_scores_gemma":[0.04801931,0.0010265181,0.0018646822,0.0029297932,0.0034353046,0.008988707,0.004354122,0.011279062,0.033787325],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005898941,0.00021705666,0.0018415082,0.0009398877,0.000071958304,0.00065757125,0.003308285,0.0010931733,0.0041785236,0.14199084,0.51289153,0.3322198],"study_design_scores_gemma":[0.00006406114,0.000044968398,0.0011899587,0.00025757717,0.000016253953,0.00038918894,0.00074875605,0.0006200569,0.0015807281,0.0048174765,0.99021727,0.000053686632],"about_ca_topic_score_codex":0.08248943,"about_ca_topic_score_gemma":0.050592273,"teacher_disagreement_score":0.092633225,"about_ca_system_score_codex":0.01057423,"about_ca_system_score_gemma":0.010768235,"threshold_uncertainty_score":0.30988896},"labels":[],"label_agreement":null},{"id":"W2797550683","doi":"10.3138/cjpe.43179","title":"Strategic Evaluation Utilization in the Canadian Federal Government","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; École Nationale d'Administration Publique","funders":"","keywords":"Government (linguistics); Focus group; Program evaluation; Function (biology); Business; Public relations; Public policy; Content analysis; Key (lock); Qualitative research; Psychology; Marketing; Public administration; Political science; Sociology; Computer science","score_opus":0.6515255366463052,"score_gpt":0.5637168640848468,"score_spread":0.08780867256145841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797550683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76779056,0.010632845,0.0048575597,0.040029276,0.00049272226,0.001240768,0.0009397432,0.00034200057,0.17367458],"genre_scores_gemma":[0.99169075,0.0014998312,0.0020415823,0.0009172028,0.00002232486,0.00010246369,0.00014842894,0.000020751271,0.0035566273],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9352121,0.02688237,0.0025609294,0.0024533977,0.024672732,0.008218473],"domain_scores_gemma":[0.8531897,0.036678974,0.0093180295,0.0046141976,0.08361454,0.012584613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048776716,0.00036856873,0.00046355708,0.009379648,0.013637003,0.011270786,0.0025306335,0.0010606757,0.0020824198],"category_scores_gemma":[0.067933306,0.0005467661,0.00034284472,0.010105548,0.005767411,0.0020672744,0.006199929,0.0018259188,0.00017929498],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00047137792,0.00050089083,0.13059857,0.0024018628,0.00017000706,0.0018815079,0.164674,0.0028408782,0.00280298,0.05614063,0.052831903,0.5846854],"study_design_scores_gemma":[0.000059872826,0.00047710678,0.30346605,0.002454115,0.00013915394,0.00064968935,0.3021006,0.0034200703,0.0045603523,0.005527913,0.37675965,0.0003853936],"about_ca_topic_score_codex":0.90068674,"about_ca_topic_score_gemma":0.946577,"teacher_disagreement_score":0.83632994,"about_ca_system_score_codex":0.16367005,"about_ca_system_score_gemma":0.34934962,"threshold_uncertainty_score":0.9700242},"labels":[],"label_agreement":null},{"id":"W2797791889","doi":"10.3138/cjpe.43177","title":"The Role of Evaluation in Spending Review","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Fiscal Policy and Economic Growth","field":"Economics, Econometrics and Finance","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fiscal space; Public economics; Economics; Quality (philosophy); Fiscal policy; Health spending; Process (computing); Public spending; Financial crisis; Business; Macroeconomics; Health care; Economic growth; Computer science; Politics; Political science","score_opus":0.13155448740228104,"score_gpt":0.3341782477424542,"score_spread":0.20262376034017315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797791889","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009625006,0.10489397,0.123323,0.6138643,0.016090922,0.005121197,0.00049659144,0.00049080595,0.12609422],"genre_scores_gemma":[0.6425353,0.052208785,0.19336574,0.080274485,0.010883253,0.011118521,0.0003844641,0.0006312096,0.008598223],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.120825745,0.79094374,0.036752418,0.005752383,0.04213292,0.0035927026],"domain_scores_gemma":[0.038783852,0.79050136,0.024852684,0.02268725,0.11533676,0.007838134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.74896246,0.0014253076,0.0048687505,0.016147485,0.008019714,0.03237997,0.0063194344,0.008535033,0.006043238],"category_scores_gemma":[0.8551279,0.0014539812,0.0020479495,0.012917244,0.027323417,0.025514077,0.015173194,0.01460153,0.0013151184],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008670654,0.00020888742,0.008362512,0.007970302,0.00063652685,0.00034991707,0.011836051,0.0027277896,0.0002173392,0.26531923,0.092025965,0.6094785],"study_design_scores_gemma":[0.0005681447,0.0007824471,0.011757746,0.062008753,0.0011406892,0.00067539216,0.010108859,0.009696326,0.002032624,0.43162414,0.46892023,0.0006845471],"about_ca_topic_score_codex":0.014632189,"about_ca_topic_score_gemma":0.016157389,"teacher_disagreement_score":0.98536783,"about_ca_system_score_codex":0.03974886,"about_ca_system_score_gemma":0.10432324,"threshold_uncertainty_score":0.309574},"labels":[],"label_agreement":null},{"id":"W2797845965","doi":"10.3138/cjpe.43176","title":"Linking Evaluation and Spending Reviews: Challenges and Prospects","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Economic, financial, and policy analysis","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University; University of Victoria","funders":"","keywords":"Rationing; Government spending; Government (linguistics); Psychological intervention; Economics; Public economics; Development economics; Inequality; Business; Economic growth; Medicine; Market economy; Welfare; Health care","score_opus":0.25087934887651614,"score_gpt":0.35629288304749096,"score_spread":0.10541353417097482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797845965","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029326815,0.13702297,0.015037598,0.80302477,0.015886102,0.0016599449,0.0014321341,0.0008093969,0.022194445],"genre_scores_gemma":[0.14841636,0.25079805,0.13484083,0.35015747,0.06531687,0.016447281,0.009153372,0.0015517654,0.02331795],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.30637333,0.571777,0.039533023,0.01419514,0.059034213,0.009087297],"domain_scores_gemma":[0.048542026,0.63338584,0.049214847,0.035464097,0.20564187,0.027751282],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6415285,0.0035721227,0.009155904,0.036265325,0.0069226455,0.043995842,0.011950199,0.027527463,0.02810648],"category_scores_gemma":[0.7949237,0.004932714,0.0040483833,0.042375512,0.011168422,0.06162639,0.028064283,0.014121465,0.009093738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010475898,0.0009851196,0.014930868,0.012985626,0.001006543,0.00029158016,0.003878525,0.0020702342,0.0001505486,0.055020273,0.37856966,0.5290634],"study_design_scores_gemma":[0.001164829,0.0007906494,0.015690299,0.056295604,0.0007652004,0.00042902323,0.0076765814,0.0058466247,0.00038602427,0.15654264,0.753768,0.0006444862],"about_ca_topic_score_codex":0.025547976,"about_ca_topic_score_gemma":0.021745889,"teacher_disagreement_score":0.9739642,"about_ca_system_score_codex":0.02603579,"about_ca_system_score_gemma":0.14244911,"threshold_uncertainty_score":0.44205922},"labels":[],"label_agreement":null},{"id":"W2798137084","doi":"10.3138/cjpe.43184","title":"Sunshine, Scrutiny, and Spending Review in Canada, Trudeau to Trudeau: From Program Evaluation and Policy to Commitment and Results","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Victoria","funders":"","keywords":"Scrutiny; Cabinet (room); Government (linguistics); Public administration; Public relations; Political science; Adaptation (eye); Public policy; Psychology; Law","score_opus":0.3498588876004434,"score_gpt":0.5499745996534898,"score_spread":0.2001157120530464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798137084","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080076255,0.4611766,0.0013371126,0.39370614,0.0021963879,0.00019674265,0.00088039413,0.00009173322,0.060338527],"genre_scores_gemma":[0.8227635,0.12702064,0.0020258042,0.039215177,0.00081733544,0.00014549564,0.0003117849,0.000092690774,0.0076075504],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.92019963,0.02668166,0.0032106678,0.0029341094,0.039196007,0.007777805],"domain_scores_gemma":[0.7761813,0.07984625,0.015660865,0.0042164135,0.10932203,0.014773167],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0592538,0.00035466297,0.0014136188,0.006551497,0.00834055,0.014885169,0.0024601172,0.0023590804,0.0018614818],"category_scores_gemma":[0.19050789,0.0005003776,0.00060277537,0.014996127,0.0136041315,0.0041527185,0.0033488318,0.0040930347,0.00013157493],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0006243026,0.00015826944,0.057361223,0.008351365,0.0007619956,0.00047853205,0.027002586,0.0016682663,0.00052399293,0.21371724,0.2213931,0.46795923],"study_design_scores_gemma":[0.00016083913,0.00025482956,0.22502472,0.021368895,0.000827176,0.0002553548,0.0284342,0.0013144076,0.0016972672,0.02755176,0.6926743,0.00043638755],"about_ca_topic_score_codex":0.98062205,"about_ca_topic_score_gemma":0.9863383,"teacher_disagreement_score":0.9407462,"about_ca_system_score_codex":0.19843285,"about_ca_system_score_gemma":0.4723044,"threshold_uncertainty_score":0.9297043},"labels":[],"label_agreement":null},{"id":"W2809971035","doi":"10.3138/cjpe.42159","title":"Evaluating Academic Research Networks","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Hôpital Charles-Le Moyne; Université de Montréal","funders":"","keywords":"Productivity; Position (finance); Institutional research; Curriculum; Knowledge management; Political science; Business; Public relations; Sociology; Computer science; Higher education; Economics; Economic growth","score_opus":0.9653113425368469,"score_gpt":0.7773576803100251,"score_spread":0.18795366222682186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809971035","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9302591,0.001065088,0.016821528,0.00093035825,0.000107891436,0.001201605,0.0037260463,0.00013289833,0.045755338],"genre_scores_gemma":[0.9875728,0.00020584212,0.009030851,0.00002743931,0.000033396074,0.0005085457,0.0015163618,0.000011063469,0.0010936687],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9658626,0.01768128,0.003133284,0.002407714,0.009820873,0.0010943372],"domain_scores_gemma":[0.78070337,0.13756536,0.03427009,0.0059931767,0.03467247,0.0067955344],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.02752687,0.0006518392,0.0007223585,0.020672694,0.0023717291,0.0063071433,0.0011708523,0.0010911609,0.0056689433],"category_scores_gemma":[0.1557159,0.00020965528,0.00066396216,0.021308344,0.0010584843,0.0055371523,0.0038631675,0.00055379805,0.00075462786],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054853293,0.00037198424,0.8441113,0.0006543446,0.0006197435,0.00014787425,0.0027800945,0.016889382,0.00045053425,0.015859328,0.0040936475,0.113473274],"study_design_scores_gemma":[0.0002361651,0.0013509277,0.683625,0.0008180151,0.0009211244,0.00036346746,0.02949053,0.2070571,0.004342381,0.038854357,0.03278381,0.00015709664],"about_ca_topic_score_codex":0.012963527,"about_ca_topic_score_gemma":0.012059601,"teacher_disagreement_score":0.9793273,"about_ca_system_score_codex":0.006877798,"about_ca_system_score_gemma":0.0047640116,"threshold_uncertainty_score":0.14557773},"labels":[],"label_agreement":null},{"id":"W2810200651","doi":"10.3138/cjpe.36295","title":"Building Community Capacity: Self-Assessment Performance Metrics for Canadian Microcredit Programs","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Community Development and Social Impact","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Business; Capacity building; Microfinance; Economic growth; Economics","score_opus":0.23214070923039085,"score_gpt":0.3541149974243884,"score_spread":0.12197428819399755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810200651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84544045,0.0009900307,0.009638019,0.0030983624,0.000117236355,0.0018905244,0.010634244,0.00047376467,0.12771732],"genre_scores_gemma":[0.98758453,0.00018406496,0.0062187905,0.00007446379,0.000010314198,0.0004526368,0.0022178898,0.000026746671,0.0032305256],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99390596,0.0013292809,0.00022356996,0.00025830182,0.0032156652,0.0010672276],"domain_scores_gemma":[0.969361,0.002479164,0.002628868,0.00071159477,0.020310942,0.004508342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008835776,0.00052780483,0.0003207646,0.006191916,0.002610438,0.00270996,0.0014356176,0.00042121677,0.004383194],"category_scores_gemma":[0.029247265,0.00013538594,0.00044263768,0.0058752424,0.0009928982,0.0014583187,0.0025404512,0.0007894615,0.00043181962],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041065365,0.0013481583,0.63698566,0.00045060957,0.00018332215,0.0000965722,0.005538881,0.018578216,0.0005104574,0.013411492,0.04402846,0.27845746],"study_design_scores_gemma":[0.00006875952,0.00063882244,0.9157726,0.0005199792,0.000116296505,0.000040571635,0.01013203,0.03020742,0.0022010002,0.003102141,0.03706522,0.00013508424],"about_ca_topic_score_codex":0.8512543,"about_ca_topic_score_gemma":0.91228783,"teacher_disagreement_score":0.14874572,"about_ca_system_score_codex":0.03659955,"about_ca_system_score_gemma":0.041740414,"threshold_uncertainty_score":0.2992434},"labels":[],"label_agreement":null},{"id":"W2810409615","doi":"10.3138/cjpe.31143","title":"NorthBEAT’s Capacity-to-Consent Protocol for Obtaining Informed Consent from Youth Evaluation Participants: An Alternative to Parental Consent","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"St Joseph's Health Care; Lakehead University; NOSM University; St. Joseph's Care Group","funders":"","keywords":"Informed consent; Protocol (science); Parental consent; Psychology; Context (archaeology); Social psychology; Medical education; Medicine; Alternative medicine","score_opus":0.8231304617021894,"score_gpt":0.6000909639797573,"score_spread":0.22303949772243215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810409615","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011428481,0.00034393003,0.2296047,0.013783934,0.003500687,0.7106376,0.001504345,0.0011876783,0.028008666],"genre_scores_gemma":[0.02460468,0.00029504026,0.15280098,0.005236596,0.00052340416,0.8094025,0.00037369927,0.00028870552,0.00647441],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.66977394,0.27016374,0.033064757,0.0067823655,0.015156128,0.0050590076],"domain_scores_gemma":[0.5876993,0.2183397,0.019986747,0.094909675,0.06824796,0.010816576],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.31766272,0.0018483019,0.002242212,0.004144923,0.008504936,0.0056853434,0.0040203813,0.010670094,0.059360437],"category_scores_gemma":[0.3938917,0.002620743,0.002003421,0.0036699907,0.007958904,0.008268629,0.006913234,0.0152422935,0.017923042],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008407205,0.0035310825,0.0031954567,0.007721401,0.00019728567,0.007840197,0.10876264,0.0016929696,0.017338248,0.15674916,0.3744723,0.31009206],"study_design_scores_gemma":[0.008418344,0.0028318113,0.00766397,0.013315589,0.00016629008,0.003229476,0.020495327,0.009827526,0.013660678,0.083779745,0.83579886,0.00081248704],"about_ca_topic_score_codex":0.0026383533,"about_ca_topic_score_gemma":0.00675017,"teacher_disagreement_score":0.31766272,"about_ca_system_score_codex":0.005290739,"about_ca_system_score_gemma":0.050213683,"threshold_uncertainty_score":0.84144336},"labels":[],"label_agreement":null},{"id":"W2810597755","doi":"10.3138/cjpe.31160","title":"Evaluating the Process and Outcomes of a Knowledge Translation Approach to Supporting Use of the Diabetes Population Risk Tool (DPoRT) in Public Health Practice","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Partnership Against Cancer; Manitoba Health; University of Manitoba; Western University; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"","keywords":"Knowledge translation; Population; Public health; Observational study; Knowledge management; Action (physics); Psychology; Process (computing); Focus group; Business; Medicine; Environmental health; Nursing; Computer science; Marketing","score_opus":0.8399212608434334,"score_gpt":0.7085101647295762,"score_spread":0.13141109611385726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810597755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9642442,0.00023456138,0.009267479,0.001430425,0.00007169672,0.018612845,0.00017637233,0.00014665365,0.0058158897],"genre_scores_gemma":[0.9210282,0.0004275797,0.06067598,0.0004162604,0.000026910862,0.016572002,0.00017434191,0.000034410987,0.0006442346],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.84741145,0.12727705,0.0070962044,0.0025369336,0.011003612,0.0046747467],"domain_scores_gemma":[0.75796485,0.17532325,0.016002614,0.009947863,0.03468002,0.006081396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16169903,0.001037767,0.000982086,0.0028878038,0.0035135264,0.0051065,0.0022275406,0.0016786781,0.0022714087],"category_scores_gemma":[0.23879336,0.00086549966,0.0011742874,0.002726481,0.002014782,0.0040834965,0.008304394,0.0017647201,0.00035983746],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005526088,0.038589012,0.077267244,0.0083515365,0.0005562062,0.00051534007,0.13766003,0.004002921,0.0029105428,0.0030317507,0.0021613876,0.71942794],"study_design_scores_gemma":[0.016639467,0.148809,0.3023128,0.018944798,0.0054856413,0.00064986484,0.36088067,0.056348458,0.04901467,0.011375351,0.028643351,0.00089587574],"about_ca_topic_score_codex":0.01408445,"about_ca_topic_score_gemma":0.015738897,"teacher_disagreement_score":0.16169903,"about_ca_system_score_codex":0.013751838,"about_ca_system_score_gemma":0.044972856,"threshold_uncertainty_score":0.8551564},"labels":[],"label_agreement":null},{"id":"W2810598379","doi":"10.3138/cjpe.31127","title":"Un outil à visée pédagogique pour discuter de méthodologie","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Operationalization; Process (computing); Quality (philosophy); Computer science; Psychology; Management science; Process management; Knowledge management; Epistemology; Engineering","score_opus":0.2932941509464601,"score_gpt":0.47447249150458165,"score_spread":0.18117834055812154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810598379","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019501102,0.015184478,0.9160374,0.037644923,0.012041547,0.005387874,0.000987939,0.0032796187,0.007486206],"genre_scores_gemma":[0.031185782,0.0069193,0.91416824,0.010718783,0.0023012722,0.02685126,0.00056653254,0.002260639,0.005028114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.47022325,0.4679952,0.02790247,0.008922026,0.023858296,0.0010988312],"domain_scores_gemma":[0.18662557,0.70506155,0.012244556,0.06281264,0.031632613,0.0016230175],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4178808,0.0031106863,0.003735007,0.016252374,0.003984705,0.019795548,0.0062022735,0.0059277164,0.025494486],"category_scores_gemma":[0.62745315,0.0025786096,0.007111298,0.009428186,0.010303233,0.017522326,0.011134848,0.013300245,0.005620452],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007993846,0.0003556115,0.0012689827,0.048131377,0.0024366372,0.0007369763,0.03311566,0.0026559576,0.0023837362,0.40458035,0.09738923,0.40614614],"study_design_scores_gemma":[0.0010486203,0.00027950635,0.0009427714,0.07407522,0.001443354,0.00077134813,0.005037358,0.010417348,0.0043219533,0.2596191,0.6417058,0.00033774858],"about_ca_topic_score_codex":0.0039625787,"about_ca_topic_score_gemma":0.0043946938,"teacher_disagreement_score":0.4178808,"about_ca_system_score_codex":0.011286525,"about_ca_system_score_gemma":0.031810414,"threshold_uncertainty_score":0.71785665},"labels":[],"label_agreement":null},{"id":"W2810719550","doi":"10.3138/cjpe.31094","title":"Construct-Aligned Rating Scales Improve the Reliability of Program Evaluation Data","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Innovations in Medical Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generalizability theory; Sophistication; Construct (python library); Reliability (semiconductor); Rating scale; Construct validity; Psychology; Independence (probability theory); Applied psychology; Computer science; Psychometrics; Statistics; Clinical psychology; Mathematics; Developmental psychology; Sociology","score_opus":0.13511042286109173,"score_gpt":0.4605146374006852,"score_spread":0.32540421453959345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810719550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5364389,0.0010945713,0.4167878,0.0010200081,0.0010000152,0.008878772,0.0014964372,0.00196549,0.03131804],"genre_scores_gemma":[0.81280416,0.0002113719,0.17878121,0.0003287373,0.0001976773,0.005391757,0.0009745963,0.00034562426,0.00096489873],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7866536,0.15876916,0.021035798,0.008146566,0.024185142,0.0012096693],"domain_scores_gemma":[0.55197686,0.25668085,0.04459223,0.059271038,0.085500665,0.0019782635],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14354417,0.0010241083,0.0015666531,0.004109301,0.0012643852,0.002649049,0.0009660439,0.0010394724,0.0020888846],"category_scores_gemma":[0.37096232,0.0007370074,0.0019606152,0.005143682,0.0018022336,0.0030741857,0.0030476162,0.002043981,0.0010006202],"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":[0.0044609737,0.0021258553,0.5086483,0.0019575716,0.0024471001,0.00016993888,0.009383839,0.008163537,0.0091140475,0.0089503685,0.011112374,0.43346614],"study_design_scores_gemma":[0.0007912248,0.003335506,0.891521,0.000947351,0.0008118083,0.00025197622,0.0033767088,0.047747307,0.011919177,0.015986161,0.023024041,0.000287621],"about_ca_topic_score_codex":0.0010693041,"about_ca_topic_score_gemma":0.0023271192,"teacher_disagreement_score":0.8564558,"about_ca_system_score_codex":0.0010166154,"about_ca_system_score_gemma":0.0015569414,"threshold_uncertainty_score":0.7591432},"labels":[],"label_agreement":null},{"id":"W2810759134","doi":"10.3138/cjpe.33.1.171","title":"Hallie Preskill and Darlene Russ-Eft. (2016). <i>Building Evaluation Capacity: Activities for Teaching and Training</i> . 2nd ed.","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Sociology; Physics","score_opus":0.41552976865334557,"score_gpt":0.5066036827221413,"score_spread":0.09107391406879572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810759134","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011520536,0.64914644,0.028545616,0.22772178,0.019758668,0.00023047072,0.0027199383,0.0017000117,0.069025],"genre_scores_gemma":[0.027236512,0.66812795,0.052488115,0.03685171,0.0060548275,0.00053976814,0.0023211685,0.0014036256,0.20497636],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956821,0.0011447738,0.00054065435,0.00030685897,0.0021139462,0.00021165103],"domain_scores_gemma":[0.9728717,0.010712412,0.0013176949,0.00072617125,0.012362441,0.0020096186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013154328,0.0012672528,0.00090752373,0.00452403,0.0019697056,0.0049699056,0.0020512412,0.0028658393,0.032774303],"category_scores_gemma":[0.039027292,0.0012600446,0.0005175977,0.0044668764,0.0020682733,0.0063346825,0.0023380893,0.0052202544,0.028641416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003126838,0.000016601365,0.00033819585,0.00041228492,0.0000061360765,0.000040269115,0.0005470156,0.00008552169,0.00010911469,0.0017567016,0.7713256,0.22533138],"study_design_scores_gemma":[0.00001818821,0.000025407247,0.0027747229,0.0029585485,0.000026817084,0.00019394522,0.0010398615,0.00013012959,0.000462247,0.006458632,0.985852,0.00005958278],"about_ca_topic_score_codex":0.07289367,"about_ca_topic_score_gemma":0.21496566,"teacher_disagreement_score":0.07289367,"about_ca_system_score_codex":0.0036352768,"about_ca_system_score_gemma":0.017982438,"threshold_uncertainty_score":0.14493877},"labels":[],"label_agreement":null},{"id":"W2810879288","doi":"10.3138/cjpe.42116","title":"Using Logic Models and the Action Model/Change Model Schema in Planning the Learning Community Program: A Comparative Case Study","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Schema (genetic algorithms); Logic model; Computer science; Strengths and weaknesses; Logic program; Management science; Action (physics); Theory of change; Artificial intelligence; Process management; Knowledge management; Data science; Machine learning; Psychology; Logic programming; Sociology; Engineering; Social psychology","score_opus":0.9477306850220157,"score_gpt":0.6849694826574051,"score_spread":0.26276120236461065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810879288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8822368,0.0003487477,0.04394875,0.003445611,0.00003846385,0.00274883,0.0002198245,0.00009743747,0.06691554],"genre_scores_gemma":[0.9510813,0.00033030234,0.045368157,0.00016551295,0.0000054023135,0.0011038707,0.00007774366,0.000027602648,0.001840088],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97632295,0.020839883,0.00043523894,0.00038622582,0.0013056366,0.00070995337],"domain_scores_gemma":[0.96193886,0.032272056,0.001213134,0.0015389154,0.0023098136,0.0007271689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027844746,0.0005846195,0.00042610487,0.0020500058,0.004964511,0.003550044,0.0024054248,0.0020917512,0.0047271866],"category_scores_gemma":[0.031422447,0.0004282472,0.00057920086,0.0031812328,0.0040582195,0.0049137734,0.003516927,0.0029539468,0.0003068074],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015396802,0.016067805,0.061624248,0.001911658,0.0001258595,0.010299442,0.25355795,0.06347058,0.0028998428,0.22914338,0.008288638,0.35107085],"study_design_scores_gemma":[0.0011460172,0.008113258,0.034675814,0.0026241078,0.00032896284,0.0027052301,0.5698121,0.19174159,0.012806425,0.06954271,0.106161796,0.00034192012],"about_ca_topic_score_codex":0.030845435,"about_ca_topic_score_gemma":0.058396425,"teacher_disagreement_score":0.030845435,"about_ca_system_score_codex":0.014240426,"about_ca_system_score_gemma":0.009459924,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2811037761","doi":"10.3138/cjpe.31106","title":"Expanding the Role of Digital Photographs in Evaluation Practice: Documenting, Sense-Making, and Imagining","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Participatory Visual Research Methods","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sense (electronics); Psychology; Aesthetics; Art; Engineering","score_opus":0.46381908807601513,"score_gpt":0.65529785512173,"score_spread":0.19147876704571487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811037761","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32033587,0.023572855,0.19657195,0.066533566,0.0016380267,0.0042691478,0.00029935443,0.00076719816,0.386012],"genre_scores_gemma":[0.89303756,0.0063231695,0.09252961,0.0017679359,0.00017770333,0.0014709682,0.000053517666,0.00011814971,0.0045213904],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8734743,0.11306814,0.0028804643,0.0017876,0.0076654386,0.0011240157],"domain_scores_gemma":[0.82645124,0.1322092,0.007828757,0.016368493,0.01482908,0.0023132672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10577377,0.0007175981,0.00052364636,0.0052771075,0.006549775,0.013213337,0.0021283266,0.0020896976,0.005286399],"category_scores_gemma":[0.116176195,0.0006388467,0.00044018796,0.0032857617,0.019699614,0.011823194,0.013345055,0.0026673907,0.0006186497],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001528335,0.00028621953,0.008457059,0.003051698,0.000037602273,0.00059449644,0.34645194,0.0007689757,0.0030941733,0.061143287,0.0076029124,0.5683588],"study_design_scores_gemma":[0.00014004644,0.00064471824,0.016470362,0.015177848,0.0001644131,0.0015949976,0.5044977,0.0020267204,0.010229634,0.07761176,0.37124252,0.00019931102],"about_ca_topic_score_codex":0.0062010773,"about_ca_topic_score_gemma":0.011380562,"teacher_disagreement_score":0.10577377,"about_ca_system_score_codex":0.007531646,"about_ca_system_score_gemma":0.0129981125,"threshold_uncertainty_score":0.55939186},"labels":[],"label_agreement":null},{"id":"W2811284056","doi":"10.3138/cjpe.33.1.168","title":"Colin Robson. (2017). <i>Small-Scale Evaluation: Principles and Practice</i> . 2nd ed.","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Waterloo","funders":"","keywords":"Scale (ratio); Psychology; Sociology; Applied psychology; Psychoanalysis; Geography; Cartography","score_opus":0.4912241652614992,"score_gpt":0.5469421384034869,"score_spread":0.05571797314198773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811284056","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089242106,0.5374131,0.052849714,0.3135896,0.025307054,0.00060377957,0.0015463007,0.0015670276,0.0662309],"genre_scores_gemma":[0.033575352,0.58020514,0.13993038,0.080670536,0.013683866,0.0022517694,0.0014717946,0.0021860874,0.14602508],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98788273,0.0046106125,0.0014540979,0.0006884871,0.0050887223,0.00027536316],"domain_scores_gemma":[0.8912484,0.058602925,0.0055622943,0.0033307518,0.03706487,0.004190827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0331716,0.0018836823,0.0013073045,0.0053381925,0.0022238777,0.006149715,0.0031539297,0.0054361317,0.021361375],"category_scores_gemma":[0.094535194,0.0015714121,0.0007171473,0.006109384,0.0056455475,0.006535431,0.003080223,0.008069312,0.016398972],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047616213,0.00001759582,0.0005014928,0.0010933289,0.000015257422,0.000057315843,0.000507915,0.00023370206,0.00018366503,0.007862395,0.73595864,0.25352108],"study_design_scores_gemma":[0.000029011031,0.000042716558,0.0024667645,0.008535783,0.000051788433,0.00023425803,0.0007247984,0.00043995806,0.00067140604,0.026165862,0.96054274,0.00009488287],"about_ca_topic_score_codex":0.07843633,"about_ca_topic_score_gemma":0.18023331,"teacher_disagreement_score":0.07843633,"about_ca_system_score_codex":0.007228211,"about_ca_system_score_gemma":0.02296058,"threshold_uncertainty_score":0.17543036},"labels":[],"label_agreement":null},{"id":"W281362470","doi":"10.3138/cjpe.23.004","title":"Challenges in Applying Indigenous Evaluation Practices in Mainstream Grant Programs to Indigenous Communities","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Mainstream; Government (linguistics); Substance abuse prevention; Competence (human resources); Cultural competence; Traditional knowledge; Political science; Culturally appropriate; Public relations; Substance use; Sociology; Psychology; Medicine; Pedagogy; Gerontology; Social psychology","score_opus":0.6836246640574786,"score_gpt":0.5359148392352847,"score_spread":0.14770982482219386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W281362470","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28333142,0.014740713,0.19508094,0.33817166,0.0051439963,0.017979337,0.00030904886,0.0008169795,0.1444258],"genre_scores_gemma":[0.8363304,0.0035290075,0.12774415,0.015638055,0.0007229202,0.010518271,0.00007537909,0.00021500963,0.0052268077],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.4068881,0.48832107,0.030412488,0.0081513915,0.057227492,0.008999411],"domain_scores_gemma":[0.34667522,0.41796467,0.021191534,0.037192732,0.16483739,0.012138437],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5871889,0.0008533945,0.0018507456,0.004591893,0.015231018,0.018641217,0.007853328,0.00336508,0.0040527517],"category_scores_gemma":[0.56193495,0.0010666095,0.0011739263,0.0036179998,0.018389953,0.011212183,0.01625092,0.008165898,0.00060052006],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006706282,0.001965955,0.037973758,0.0065253573,0.00071409927,0.0008546591,0.33695805,0.00615229,0.0021423865,0.09436827,0.023091808,0.48858273],"study_design_scores_gemma":[0.0010137055,0.003058686,0.08268696,0.02514409,0.00055034325,0.000979626,0.47223204,0.014309101,0.0057634925,0.19815919,0.1952512,0.00085162814],"about_ca_topic_score_codex":0.081226304,"about_ca_topic_score_gemma":0.14845964,"teacher_disagreement_score":0.97126824,"about_ca_system_score_codex":0.028731737,"about_ca_system_score_gemma":0.11401515,"threshold_uncertainty_score":0.5090696},"labels":[],"label_agreement":null},{"id":"W285975702","doi":"10.3138/cjpe.23.005","title":"Using Technology to Enhance Aboriginal Evaluations","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Focus (optics); Sociology; Data collection; Knowledge management; Engineering ethics; Computer science; Social science; Engineering; History; Archaeology","score_opus":0.4108376583250716,"score_gpt":0.6419507109411706,"score_spread":0.23111305261609905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W285975702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49288988,0.0061982335,0.14417197,0.011743255,0.00054413447,0.0032625224,0.00018428145,0.00083794736,0.3401677],"genre_scores_gemma":[0.897687,0.0020164533,0.09461185,0.00033980337,0.00009136565,0.0013766751,0.000052800075,0.00004598546,0.0037779522],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92377615,0.06873001,0.0016746824,0.0006608452,0.004118687,0.001039712],"domain_scores_gemma":[0.9269558,0.059953183,0.0027790589,0.0024235845,0.0066613755,0.0012270291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040325414,0.00054618926,0.0005086789,0.004256965,0.002406368,0.0070481533,0.0009197591,0.0008206497,0.006018867],"category_scores_gemma":[0.07569426,0.00027906563,0.00045435078,0.0024245924,0.0022405973,0.0044068336,0.0058155884,0.0010947979,0.0005666642],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000656542,0.001328382,0.019646563,0.002564482,0.00014662153,0.00081589,0.079508565,0.002610979,0.004532249,0.05547404,0.009444523,0.8232713],"study_design_scores_gemma":[0.0010128289,0.007976346,0.07431842,0.017561372,0.00083627226,0.0021986535,0.19162624,0.018152883,0.03501315,0.1288803,0.52189326,0.0005301793],"about_ca_topic_score_codex":0.003059483,"about_ca_topic_score_gemma":0.0046995385,"teacher_disagreement_score":0.040325414,"about_ca_system_score_codex":0.0035810338,"about_ca_system_score_gemma":0.005718715,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W286621326","doi":"10.3138/cjpe.017.002","title":"A Peer Support Approach to Evaluation: Assessing Supported Employment Programs for People with Developmental Disabilities","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Agency (philosophy); Peer support; Psychology; Peer review; Medical education; Applied psychology; Knowledge management; Computer science; Sociology; Political science; Medicine","score_opus":0.4885163999449404,"score_gpt":0.4936480799662604,"score_spread":0.005131680021320029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W286621326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6126487,0.009790704,0.21048838,0.010711033,0.0009717806,0.03501895,0.00043357056,0.00037719987,0.11955962],"genre_scores_gemma":[0.77704227,0.0031687808,0.20389077,0.0005461882,0.00013882718,0.011983378,0.00013287015,0.000035943824,0.003060865],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.90310895,0.083094686,0.003328466,0.0008851378,0.008391946,0.0011908032],"domain_scores_gemma":[0.9627739,0.02057349,0.0020051359,0.0010702609,0.01153127,0.0020459127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03848451,0.0007903862,0.0009482919,0.005627228,0.003828477,0.006440802,0.002181673,0.0013649357,0.0026569106],"category_scores_gemma":[0.052450668,0.0003608956,0.0011091776,0.0027416328,0.0032435006,0.0033261152,0.0052529676,0.0021982556,0.00033712262],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052037823,0.0040962747,0.0421467,0.0053872247,0.00046205957,0.00077620585,0.04216458,0.003940595,0.0020043897,0.02923772,0.0075933374,0.8616705],"study_design_scores_gemma":[0.0026673188,0.03263333,0.18805116,0.019391764,0.0027470586,0.0057828627,0.41422194,0.053485803,0.028538547,0.09493628,0.15674554,0.0007984168],"about_ca_topic_score_codex":0.0040392205,"about_ca_topic_score_gemma":0.009567687,"teacher_disagreement_score":0.03848451,"about_ca_system_score_codex":0.0056648534,"about_ca_system_score_gemma":0.01481225,"threshold_uncertainty_score":0.20352799},"labels":[],"label_agreement":null},{"id":"W2898915049","doi":"10.3138/cjpe.43065","title":"Démocratisation et efficience sont-elles antinomiques au niveau local? Le cas des réformes managériales des administrations publiques locales en Wallonie","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Public Policy and Administration Research","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Appropriation; Democracy; Political science; Welfare economics; Politics; Public administration; Power (physics); Administration (probate law); Action (physics); Humanities; Economics; Law; Philosophy; Epistemology; Physics","score_opus":0.1492779577131579,"score_gpt":0.4559123270947218,"score_spread":0.30663436938156385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898915049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8479138,0.0019848517,0.0029894162,0.00837815,0.000039786948,0.00007610963,0.00011346598,0.00006774084,0.13843656],"genre_scores_gemma":[0.99259734,0.00023502941,0.0004007748,0.00008205919,0.00001046072,0.000017178261,0.000016336615,0.000012501826,0.0066283615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99317306,0.004099121,0.00011441481,0.0004916121,0.00085391186,0.0012679159],"domain_scores_gemma":[0.990918,0.004304246,0.0013187822,0.0007249844,0.0014415082,0.0012925527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063645537,0.00020606516,0.0005603998,0.0012416979,0.0023776905,0.0061813644,0.0008655982,0.0008501448,0.010292472],"category_scores_gemma":[0.012335571,0.00016705418,0.00025864973,0.00187705,0.0060861376,0.0027119042,0.002722053,0.0012374511,0.00068891095],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011408431,0.0007831842,0.17841695,0.001136319,0.00022087092,0.0010015737,0.05805806,0.008870773,0.0041644415,0.55226904,0.0071762865,0.18676169],"study_design_scores_gemma":[0.00027061193,0.0010359903,0.54073846,0.001339255,0.00027958612,0.00060608354,0.13482668,0.010254084,0.005789142,0.053811938,0.25093794,0.00011013938],"about_ca_topic_score_codex":0.040150158,"about_ca_topic_score_gemma":0.07807516,"teacher_disagreement_score":0.040150158,"about_ca_system_score_codex":0.01014087,"about_ca_system_score_gemma":0.005930597,"threshold_uncertainty_score":0.07983291},"labels":[],"label_agreement":null},{"id":"W2902223401","doi":"10.3138/cjpe.42203","title":"Les conditions gagnantes et les défis pour une participation active des parties prenantes dans un contexte d’évaluation de programmes d’intervention psychosociale","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Jeunesse de Quebec; Université du Québec en Outaouais","funders":"","keywords":"Appropriation; Valuation (finance); Sociology; Welfare economics; Business; Political science; Psychology; Economics; Epistemology; Philosophy","score_opus":0.1628068826015187,"score_gpt":0.4615998622400226,"score_spread":0.2987929796385039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902223401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7327359,0.0052736877,0.036290213,0.09463658,0.000655151,0.0025765244,0.0004149012,0.00015353067,0.12726353],"genre_scores_gemma":[0.99086493,0.00044506177,0.0058476077,0.00072620355,0.000057693975,0.0013710085,0.00004333815,0.000016361253,0.0006279853],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5038634,0.3849405,0.03678972,0.01132886,0.051501226,0.011576311],"domain_scores_gemma":[0.50158274,0.39958584,0.042488646,0.0143032465,0.033706035,0.008333443],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3018409,0.00076174416,0.0013405668,0.003261231,0.0112340795,0.024398725,0.002392614,0.007942494,0.0045518293],"category_scores_gemma":[0.40084553,0.0010013632,0.0009532651,0.003420442,0.027371062,0.012840801,0.011654251,0.007041599,0.0004234044],"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":[0.0017777908,0.0009666331,0.09621761,0.0049117263,0.00027670347,0.002584339,0.47388574,0.002215652,0.004989884,0.25548443,0.00450743,0.15218204],"study_design_scores_gemma":[0.000636625,0.0018697475,0.12727238,0.012708273,0.00034368344,0.0035063485,0.5562517,0.004975971,0.011973338,0.16411701,0.11597916,0.00036581059],"about_ca_topic_score_codex":0.010219192,"about_ca_topic_score_gemma":0.009830575,"teacher_disagreement_score":0.3018409,"about_ca_system_score_codex":0.018478766,"about_ca_system_score_gemma":0.036832612,"threshold_uncertainty_score":0.86095446},"labels":[],"label_agreement":null},{"id":"W2902241131","doi":"10.3138/cjpe.42201","title":"Introduction : transcender les frontières disciplinaires : l’enjeu de la contribution des parties prenantes","year":2018,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique; Université du Québec à Montréal","funders":"","keywords":"Political science; Business","score_opus":0.058019099468699646,"score_gpt":0.3794307970255544,"score_spread":0.3214116975568547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902241131","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069237794,0.03203175,0.015216636,0.79513943,0.033609882,0.00029287045,0.00034119564,0.00017664033,0.1162678],"genre_scores_gemma":[0.28573224,0.053155698,0.044936042,0.30770186,0.036003295,0.001663647,0.00078847335,0.00087731984,0.26914135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9730119,0.014663302,0.0013033001,0.0022535224,0.0069992603,0.0017686263],"domain_scores_gemma":[0.94438994,0.04134583,0.0017472854,0.0014503059,0.008396549,0.0026701272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028436795,0.0006314706,0.00070876844,0.0015249555,0.008930744,0.016581012,0.0022321078,0.012274534,0.022404006],"category_scores_gemma":[0.049696803,0.00059723004,0.000791911,0.002548823,0.01295353,0.012979229,0.006362889,0.014456682,0.0032533647],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007578314,0.000092710754,0.0010202691,0.0010415403,0.000015064327,0.00029030137,0.027586007,0.00024073865,0.00073010294,0.4514167,0.42801067,0.08948014],"study_design_scores_gemma":[0.000012377107,0.00002600656,0.0013047211,0.0016210191,0.000008558741,0.00022207847,0.011583857,0.00014632939,0.00033729488,0.039680753,0.9450234,0.000033616594],"about_ca_topic_score_codex":0.02817024,"about_ca_topic_score_gemma":0.046088167,"teacher_disagreement_score":0.98871446,"about_ca_system_score_codex":0.011285515,"about_ca_system_score_gemma":0.026885888,"threshold_uncertainty_score":0.15038997},"labels":[],"label_agreement":null},{"id":"W2902333961","doi":"10.3138/cjpe.31156","title":"Applications of Social Network Analysis in Evaluation: Challenges, Suggestions, and Opportunities for the Future","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Social network analysis; Value (mathematics); Social network (sociolinguistics); Work (physics); Computer science; Network analysis; Data science; Coding (social sciences); Management science; Knowledge management; Sociology; World Wide Web; Engineering; Social media; Social science","score_opus":0.41063426937091085,"score_gpt":0.5169534008564959,"score_spread":0.10631913148558503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902333961","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03419506,0.033159886,0.1828912,0.71033096,0.0035115636,0.0020326532,0.00035408404,0.0009729741,0.032551672],"genre_scores_gemma":[0.36315095,0.027105007,0.5807827,0.016532928,0.0021406803,0.0045474516,0.00037675988,0.0004696479,0.004893736],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.642046,0.32332388,0.0068590944,0.0035345526,0.02012777,0.0041086897],"domain_scores_gemma":[0.33959466,0.5284733,0.009920499,0.022695702,0.08661703,0.01269885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32830358,0.0021117276,0.0027007114,0.007068804,0.006935097,0.024180828,0.006287604,0.0065625114,0.0071336236],"category_scores_gemma":[0.30453,0.00126742,0.0020609128,0.0111484025,0.01390234,0.0325239,0.009706244,0.009068931,0.0013452345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004341115,0.0010882528,0.028637504,0.005954436,0.00033376538,0.00080033165,0.033690147,0.009126783,0.0012775605,0.112581894,0.06662758,0.7394476],"study_design_scores_gemma":[0.00026489203,0.0008031442,0.015680663,0.023511063,0.00023878452,0.0009620319,0.17453009,0.04929458,0.002611805,0.45652527,0.2749177,0.00065999787],"about_ca_topic_score_codex":0.023302302,"about_ca_topic_score_gemma":0.039322153,"teacher_disagreement_score":0.6716964,"about_ca_system_score_codex":0.012052916,"about_ca_system_score_gemma":0.03632509,"threshold_uncertainty_score":0.8283213},"labels":[],"label_agreement":null},{"id":"W2902455350","doi":"10.3138/cjpe.31157","title":"Three Steps Toward Sustainability: Spreadsheets as a Data-Analysis System for Non-Profit Organizations","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Spreadsheets and End-User Computing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Leverage (statistics); Sustainability; Profit (economics); Business; Data collection; Work (physics); Computer science; Competitive advantage; Knowledge management; Process management; Marketing; Economics; Microeconomics","score_opus":0.11743503204363287,"score_gpt":0.3777692065265517,"score_spread":0.26033417448291885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902455350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06364526,0.00015329712,0.82529557,0.0084375115,0.00014950454,0.0041465983,0.0011188796,0.07991709,0.017136255],"genre_scores_gemma":[0.1166499,0.00013640338,0.87137485,0.00081057503,0.00006685612,0.0017089177,0.0011847113,0.0018030327,0.0062648067],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98624307,0.006366728,0.00140289,0.0009062395,0.004651166,0.00042996032],"domain_scores_gemma":[0.95815855,0.019425381,0.0021632637,0.008232142,0.0090029705,0.0030178125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026150044,0.0010622385,0.00060453307,0.004713826,0.002329504,0.00901362,0.002517539,0.002231837,0.006954091],"category_scores_gemma":[0.043998662,0.0012173459,0.00077787694,0.0027577078,0.0020571817,0.010326417,0.0062666703,0.003400781,0.003652799],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018351587,0.0033302747,0.033036776,0.00062943535,0.0002486844,0.001335596,0.02017793,0.012696453,0.02943737,0.084639736,0.060968738,0.75166386],"study_design_scores_gemma":[0.001098369,0.002521727,0.022454549,0.002259802,0.00033222482,0.0013668758,0.007996752,0.2970709,0.12423451,0.14281243,0.39676106,0.0010908832],"about_ca_topic_score_codex":0.0035073846,"about_ca_topic_score_gemma":0.0025592356,"teacher_disagreement_score":0.026150044,"about_ca_system_score_codex":0.002709071,"about_ca_system_score_gemma":0.007484151,"threshold_uncertainty_score":0.1382963},"labels":[],"label_agreement":null},{"id":"W2902608297","doi":"10.3138/cjpe.42195","title":"One-Room School: The Summer Institute in Program Evaluation","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"General partnership; Medical education; Program evaluation; Community service; Service-learning; Service (business); Psychology; Sociology; Pedagogy; Political science; Public relations; Business; Medicine; Public administration; Marketing","score_opus":0.5726173863159311,"score_gpt":0.5775178005696558,"score_spread":0.004900414253724783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902608297","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14963132,0.012750437,0.2521066,0.29399556,0.025818404,0.008869952,0.000797325,0.0069809,0.24904963],"genre_scores_gemma":[0.58227044,0.0030383249,0.31170896,0.030961521,0.0062259375,0.0057680043,0.00069694984,0.0016692263,0.05766077],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9435165,0.043333583,0.0010351738,0.0026385756,0.0036949513,0.005781163],"domain_scores_gemma":[0.94070435,0.013041453,0.0021023804,0.0048091053,0.006228625,0.033113986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.069758385,0.001047006,0.00082282064,0.0015587838,0.0075484267,0.005935488,0.0039722812,0.002562969,0.015770545],"category_scores_gemma":[0.021712875,0.0010846484,0.0009713938,0.0016807024,0.008670578,0.004741342,0.015057919,0.011170697,0.0040264023],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001214738,0.0077953595,0.011986937,0.0009360566,0.00005690819,0.0008263129,0.030327743,0.0015731666,0.0035603035,0.057471182,0.29488543,0.58936596],"study_design_scores_gemma":[0.0013131652,0.004322549,0.029100716,0.0016895653,0.00007731901,0.0012453803,0.036556415,0.002349459,0.0037731542,0.038851164,0.8804572,0.00026395242],"about_ca_topic_score_codex":0.0035981094,"about_ca_topic_score_gemma":0.019285891,"teacher_disagreement_score":0.069758385,"about_ca_system_score_codex":0.009513944,"about_ca_system_score_gemma":0.04295551,"threshold_uncertainty_score":0.368922},"labels":[],"label_agreement":null},{"id":"W2902873563","doi":"10.3138/cjpe.42204","title":"L’évaluateur et la sagesse pratique : vecteurs essentiels pour assurer la crédibilité de l’évaluation","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Healthcare Systems and Practices","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Valuation (finance); Officer; Psychology; Sociology; Welfare economics; Political science; Business; Economics; Law; Accounting","score_opus":0.25578386142977977,"score_gpt":0.5725764055949931,"score_spread":0.31679254416521335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902873563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31723985,0.028682664,0.21855405,0.15996411,0.004152975,0.0021998608,0.0002623555,0.0011223496,0.2678217],"genre_scores_gemma":[0.91022027,0.004330703,0.064654484,0.0043887044,0.00045770622,0.0011301354,0.00008776588,0.00027731448,0.0144529715],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8102745,0.14617702,0.005583558,0.003274994,0.031945005,0.002745001],"domain_scores_gemma":[0.7254603,0.19625188,0.011420696,0.013550762,0.045474034,0.0078424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13036449,0.0008033702,0.00091773306,0.004675119,0.008195813,0.021891555,0.0018897491,0.0039839763,0.00758077],"category_scores_gemma":[0.24128437,0.00069591723,0.00074716733,0.0026191766,0.013805184,0.017556293,0.010068192,0.006644492,0.0017613473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000546707,0.0005839101,0.017216029,0.0022545657,0.00011356919,0.0006330613,0.2445809,0.0009089752,0.0029015809,0.18361966,0.027532965,0.51910806],"study_design_scores_gemma":[0.00024013282,0.0011814674,0.032662533,0.010853877,0.00015292819,0.0021936453,0.26684412,0.008104043,0.0081205685,0.11467366,0.5545685,0.00040443637],"about_ca_topic_score_codex":0.009009502,"about_ca_topic_score_gemma":0.011884399,"teacher_disagreement_score":0.13036449,"about_ca_system_score_codex":0.013135691,"about_ca_system_score_gemma":0.030614357,"threshold_uncertainty_score":0.68944156},"labels":[],"label_agreement":null},{"id":"W2902911821","doi":"10.3138/cjpe.42238","title":"Readiness in Evaluation: Three Prompts for Evaluators","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Process (computing); Tacit knowledge; Psychology; Knowledge management; Power (physics); Public relations; Process management; Computer science; Business; Sociology; Political science","score_opus":0.5904033203647878,"score_gpt":0.6029827397166689,"score_spread":0.012579419351881116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902911821","genre_codex":"empirical","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28119078,0.002772564,0.25294548,0.28097582,0.004759406,0.0062592486,0.0002699032,0.005695674,0.16513115],"genre_scores_gemma":[0.86727697,0.0006795645,0.10163619,0.018241879,0.00035167145,0.0034122146,0.00014700193,0.00043079918,0.0078237355],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.79297346,0.17858988,0.008227567,0.0027240685,0.011345156,0.0061397958],"domain_scores_gemma":[0.6240653,0.26134962,0.014998865,0.013023591,0.06035835,0.026204392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1649315,0.001055832,0.0009501486,0.0030172693,0.011266977,0.0124350935,0.0024049685,0.009933919,0.008116563],"category_scores_gemma":[0.36309755,0.0009310188,0.00094233576,0.0018745414,0.011704041,0.016989976,0.018226884,0.0153020425,0.0023105117],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095479295,0.0013516066,0.025103942,0.0017530005,0.000043869903,0.0035288334,0.52143633,0.0016828533,0.005258711,0.16679266,0.08840189,0.18369144],"study_design_scores_gemma":[0.0003149032,0.0013362081,0.013796201,0.004036708,0.00008327497,0.0018999898,0.42703,0.007702124,0.0062918747,0.1735394,0.36327884,0.0006905071],"about_ca_topic_score_codex":0.0016016383,"about_ca_topic_score_gemma":0.002142404,"teacher_disagreement_score":0.1649315,"about_ca_system_score_codex":0.0122146085,"about_ca_system_score_gemma":0.021282177,"threshold_uncertainty_score":0.87225163},"labels":[],"label_agreement":null},{"id":"W2902952593","doi":"10.3138/cjpe.53072","title":"Rosalind Eyben, Irene Guijt, Chris Roche, and Cathy Shutt. (2015). <i>The Politics of Evidence and Results in International Development: Playing the Game to Change the Rules?</i>","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"International Development and Aid","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Politics; Sociology; Art; Media studies; Political science; Law","score_opus":0.22400184059883346,"score_gpt":0.417551602755687,"score_spread":0.19354976215685352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902952593","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019018877,0.04082683,0.0019255935,0.9220501,0.012683745,0.000085760454,0.00024718625,0.00009543604,0.021895157],"genre_scores_gemma":[0.029495008,0.068375506,0.010259315,0.81201315,0.010790253,0.0007749543,0.00047993893,0.0005070863,0.0673048],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.97681683,0.011679732,0.0019603102,0.0009503069,0.007720015,0.0008728078],"domain_scores_gemma":[0.8202615,0.12164415,0.007052541,0.002227884,0.03822113,0.010592834],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.052251235,0.0011296435,0.0012014181,0.0034497085,0.0063165035,0.013643912,0.005020814,0.015725931,0.025873238],"category_scores_gemma":[0.17595743,0.0012322149,0.0007237852,0.0035852373,0.006614672,0.016652862,0.0071761645,0.02236338,0.012074029],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003697956,0.000008254686,0.0002218983,0.00022111647,0.0000098308155,0.000019816756,0.0003427222,0.00002658868,0.0000302285,0.010393407,0.9722055,0.016483651],"study_design_scores_gemma":[0.00009095584,0.000032972384,0.0016838912,0.003208624,0.000044839744,0.00006189797,0.0019800693,0.00011620289,0.00028190957,0.02544583,0.9669688,0.00008401313],"about_ca_topic_score_codex":0.060736354,"about_ca_topic_score_gemma":0.19178334,"teacher_disagreement_score":0.9936835,"about_ca_system_score_codex":0.0070503196,"about_ca_system_score_gemma":0.019349962,"threshold_uncertainty_score":0.27633423},"labels":[],"label_agreement":null},{"id":"W2903094745","doi":"10.3138/cjpe.42205","title":"L’implication des parties prenantes dans la démarche évaluative : facteurs de succès et leçons à retenir","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; École Nationale d'Administration Publique","funders":"","keywords":"Stakeholder; Thematic analysis; Key (lock); Political science; Public relations; Business; Psychology; Sociology; Knowledge management; Computer science; Qualitative research; Social science","score_opus":0.4102600005407451,"score_gpt":0.539958481627281,"score_spread":0.12969848108653592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903094745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33177635,0.02412717,0.18354708,0.14068434,0.0022182849,0.0010860696,0.0006049432,0.0002739834,0.31568173],"genre_scores_gemma":[0.9725859,0.0030917395,0.013937647,0.0019448356,0.00022482297,0.00058015186,0.00011226359,0.00012535704,0.0073973243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8325301,0.11305567,0.009672762,0.0073776008,0.031257685,0.0061062477],"domain_scores_gemma":[0.5106432,0.3896826,0.02064653,0.013194928,0.058295134,0.0075375913],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20484284,0.0007150546,0.00096568186,0.0076300977,0.010933052,0.033325385,0.0032424848,0.0056519406,0.007947959],"category_scores_gemma":[0.3634502,0.0008388578,0.0015332849,0.00866243,0.018380284,0.031051757,0.012389175,0.0092360005,0.00089214626],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038268277,0.0001762195,0.044513483,0.0016813844,0.00034815632,0.00075419125,0.22263491,0.0021825226,0.00083343347,0.52217877,0.009088322,0.1952259],"study_design_scores_gemma":[0.00010436179,0.0003755484,0.07787251,0.008363702,0.0004256676,0.0007738942,0.20358461,0.004144473,0.004771488,0.427565,0.27164695,0.00037184294],"about_ca_topic_score_codex":0.019049931,"about_ca_topic_score_gemma":0.01944912,"teacher_disagreement_score":0.20484284,"about_ca_system_score_codex":0.018338157,"about_ca_system_score_gemma":0.016918434,"threshold_uncertainty_score":0.9805703},"labels":[],"label_agreement":null},{"id":"W2903213303","doi":"10.3138/cjpe.53073","title":"David Grembowski. (2016). <i>The Practice of Health Program Evaluation</i> .","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Psychology","score_opus":0.21734164810972262,"score_gpt":0.5512799041171679,"score_spread":0.33393825600744526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903213303","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010830893,0.22946513,0.002803699,0.7182856,0.03167401,0.00008338076,0.00046337204,0.0003202786,0.016796267],"genre_scores_gemma":[0.012742577,0.4506468,0.015988778,0.39079607,0.048992954,0.00072995166,0.00078683463,0.000923627,0.07839241],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9831693,0.0069587473,0.0026054794,0.00079803844,0.0059780097,0.00049046957],"domain_scores_gemma":[0.8807165,0.057312183,0.007515535,0.0034102232,0.041636568,0.009408958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034587137,0.0014236782,0.0012367778,0.005715503,0.002438414,0.0054851375,0.0033065514,0.00834702,0.019467967],"category_scores_gemma":[0.12374327,0.0010912352,0.0007890193,0.00557714,0.006207943,0.0059153405,0.00408376,0.013902641,0.016437357],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016709191,0.0000066859434,0.00014177048,0.00033700845,0.0000058426053,0.000020093796,0.000119591816,0.00002386921,0.000019410732,0.0032266995,0.94926035,0.04682189],"study_design_scores_gemma":[0.000051370578,0.00002062768,0.0013947103,0.0047572404,0.000025544374,0.00014118377,0.000534579,0.0000906751,0.00013867728,0.0114850085,0.98131114,0.000049227176],"about_ca_topic_score_codex":0.045670427,"about_ca_topic_score_gemma":0.106899485,"teacher_disagreement_score":0.045670427,"about_ca_system_score_codex":0.0049965964,"about_ca_system_score_gemma":0.021007534,"threshold_uncertainty_score":0.1829164},"labels":[],"label_agreement":null},{"id":"W2903255761","doi":"10.3138/cjpe.42202","title":"Où en sommes-nous avec l’implication des parties prenantes?","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Theme (computing); Value (mathematics); Selection (genetic algorithm); Process (computing); Business; Political science; Psychology; Sociology; Knowledge management; Computer science","score_opus":0.23400314505815445,"score_gpt":0.493716958982599,"score_spread":0.25971381392444454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903255761","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13391997,0.007825759,0.06459125,0.27060518,0.004467782,0.0004081761,0.00020359884,0.00020493421,0.5177734],"genre_scores_gemma":[0.9090142,0.0028612046,0.020545712,0.018223379,0.00061440485,0.00033337524,0.00009502159,0.00021920372,0.04809344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9414558,0.041888054,0.001255183,0.0026269942,0.009513358,0.0032607233],"domain_scores_gemma":[0.960334,0.021580307,0.0030259453,0.0018590965,0.010470176,0.0027304075],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04064946,0.0006277146,0.0006938137,0.0013737346,0.007134611,0.014932328,0.0020851644,0.006351167,0.022254955],"category_scores_gemma":[0.086718775,0.0002957805,0.0010413671,0.0014990031,0.008793848,0.011100448,0.0056850393,0.0072339005,0.0023657964],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047820297,0.00042831904,0.0178649,0.00065985904,0.00018860404,0.00313708,0.06531733,0.0009767029,0.0024775,0.6916462,0.029432336,0.18739292],"study_design_scores_gemma":[0.00008389881,0.00021620409,0.009292684,0.0028839272,0.00013920752,0.0014274105,0.11108734,0.0016657567,0.0058997204,0.19967441,0.66749465,0.00013489355],"about_ca_topic_score_codex":0.016705353,"about_ca_topic_score_gemma":0.017575327,"teacher_disagreement_score":0.99099696,"about_ca_system_score_codex":0.009003051,"about_ca_system_score_gemma":0.012231356,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2903412726","doi":"10.3138/cjpe.53091","title":"Chris Fox, Robert Grimm, and Rute Caldeira. (2017). <i>An Introduction to Evaluation</i> .","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Law and economics; Economics","score_opus":0.31517400767919956,"score_gpt":0.5246237159077208,"score_spread":0.20944970822852127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903412726","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034396796,0.37215203,0.030252475,0.48479474,0.021912247,0.0004776458,0.0009850587,0.0007877456,0.08829409],"genre_scores_gemma":[0.02105717,0.54597706,0.06821413,0.15897787,0.016509175,0.0011851736,0.0010335513,0.001304655,0.18574132],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867792,0.004945581,0.0010589415,0.0004994269,0.0062860115,0.00043087336],"domain_scores_gemma":[0.9406622,0.028909253,0.002795728,0.0010353768,0.022927985,0.0036694398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032061145,0.0012343174,0.00093538896,0.0063640866,0.002699344,0.007079639,0.0023462311,0.005091418,0.03497472],"category_scores_gemma":[0.055113737,0.00095248804,0.0007024201,0.0052357884,0.004845375,0.008894722,0.003210529,0.008274137,0.0201984],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020157942,0.00001880196,0.0002892344,0.0005658017,0.000008385053,0.000026256961,0.00035466344,0.00010693135,0.00006680287,0.011149906,0.8849498,0.10244325],"study_design_scores_gemma":[0.00001711495,0.00002287023,0.0008996061,0.0033294414,0.000013740397,0.00013113298,0.0006196012,0.00011158338,0.00015141873,0.023100136,0.9715646,0.00003872046],"about_ca_topic_score_codex":0.05282899,"about_ca_topic_score_gemma":0.119167484,"teacher_disagreement_score":0.05282899,"about_ca_system_score_codex":0.008738364,"about_ca_system_score_gemma":0.02100258,"threshold_uncertainty_score":0.16955757},"labels":[],"label_agreement":null},{"id":"W2918217012","doi":"10.3138/cjpe.33.3.v","title":"Editor’s Remarks","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Biography; Bourgeoisie; Library science; Administration (probate law); Art; Sociology; Classics; Art history; Political science; Law; Computer science; Politics","score_opus":0.1939142377051118,"score_gpt":0.5103476077944012,"score_spread":0.31643337008928946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918217012","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001020686,0.0014793172,0.0001778691,0.3595703,0.6342458,0.000040514024,0.00013811013,0.00006487429,0.004181208],"genre_scores_gemma":[0.0017493305,0.0018545586,0.0007523719,0.60105073,0.3483057,0.00016656394,0.00008123362,0.00009235787,0.045947064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9848316,0.0017452309,0.002198349,0.0023345018,0.007494464,0.0013959457],"domain_scores_gemma":[0.9267165,0.019949324,0.0036952794,0.0030560386,0.040386185,0.006196702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021694392,0.0018067395,0.0020381205,0.0029731097,0.005175034,0.009633575,0.005126462,0.030518448,0.019403867],"category_scores_gemma":[0.14048252,0.001104353,0.0030400758,0.0022537562,0.0030331076,0.0052986243,0.0023387412,0.03223159,0.015677955],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012328802,0.00000817717,0.000051353894,0.00003905398,0.000007433712,0.00007644297,0.000021943846,0.000019732997,0.000021326448,0.00057594513,0.9971263,0.0020398903],"study_design_scores_gemma":[0.000033187163,0.000012002023,0.0003415615,0.00018685493,0.000022193562,0.000106301166,0.000083066596,0.00008468361,0.00010868243,0.0008956088,0.9981007,0.000025169355],"about_ca_topic_score_codex":0.011308815,"about_ca_topic_score_gemma":0.017211067,"teacher_disagreement_score":0.030518448,"about_ca_system_score_codex":0.0061352686,"about_ca_system_score_gemma":0.012259628,"threshold_uncertainty_score":0.114732265},"labels":[],"label_agreement":null},{"id":"W2918531645","doi":"10.3138/cjpe.53007","title":"Can’t See the Wood for the Logframe: Integrating Logframes and Theories of Change in Development Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Development theory; Context (archaeology); Development (topology); Computer science; Management science; Epistemology; Engineering ethics; Process management; Sociology; Business; Engineering; History; Economics; Economic growth","score_opus":0.41664340785434323,"score_gpt":0.5285682281708979,"score_spread":0.11192482031655465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918531645","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032788962,0.010332228,0.6042263,0.20116481,0.0022070785,0.0011791938,0.00025835435,0.0008998008,0.14694324],"genre_scores_gemma":[0.6451907,0.0050973254,0.32587737,0.009620631,0.00038593882,0.0018717084,0.00016685281,0.00049136556,0.011298089],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93930966,0.05177737,0.0010910515,0.0014639925,0.0053456123,0.0010122064],"domain_scores_gemma":[0.9001199,0.07495884,0.003877532,0.0077315695,0.010841531,0.0024706183],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.067496195,0.0007901227,0.00087769446,0.005335294,0.0053236866,0.015564443,0.0020409285,0.0039817896,0.009498235],"category_scores_gemma":[0.11738776,0.0007205025,0.00087650097,0.0057086023,0.022385575,0.030806186,0.006730113,0.0067701326,0.00136972],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009111823,0.0001075812,0.0019839716,0.0004078444,0.000028803528,0.000073733936,0.010300893,0.0014528859,0.00014952847,0.868245,0.013974773,0.103183925],"study_design_scores_gemma":[0.000088180735,0.00017136573,0.0019034892,0.0028442,0.000046160483,0.00007816673,0.017641194,0.008030143,0.00062067364,0.8633543,0.10513743,0.00008473274],"about_ca_topic_score_codex":0.019215463,"about_ca_topic_score_gemma":0.0291831,"teacher_disagreement_score":0.9325038,"about_ca_system_score_codex":0.017735776,"about_ca_system_score_gemma":0.023695024,"threshold_uncertainty_score":0.35695827},"labels":[],"label_agreement":null},{"id":"W2918728998","doi":"10.3138/cjpe.53008","title":"Does Your Implementation Fit Your Theory of Change?","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Coding (social sciences); Action (physics); Theory of change; Domain (mathematical analysis); Management science; Computer science; Psychology; Epistemology; Sociology; Mathematics; Social science; Economics","score_opus":0.6341084431107532,"score_gpt":0.590531744540158,"score_spread":0.04357669857059521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918728998","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079575986,0.008430371,0.09880889,0.52289516,0.00326143,0.0011505601,0.0005724943,0.0008340358,0.28447115],"genre_scores_gemma":[0.92806524,0.004341299,0.039374545,0.019838521,0.0004013434,0.0007723531,0.00024104153,0.00026204865,0.0067035463],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9411583,0.039547667,0.002155327,0.0017459939,0.011804256,0.0035884487],"domain_scores_gemma":[0.91655666,0.040504463,0.0062168376,0.008026938,0.024984317,0.0037108026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052674655,0.00050884066,0.0010275934,0.0023495103,0.0029666994,0.011977762,0.0025452913,0.004892344,0.012409237],"category_scores_gemma":[0.15196842,0.00041356045,0.001175649,0.0032764003,0.0077640843,0.012620206,0.0032606295,0.005025745,0.0032481565],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027314248,0.0010163971,0.045180283,0.004012634,0.00026664344,0.00030168562,0.014163745,0.0032356947,0.0006583977,0.41671523,0.05547487,0.45870128],"study_design_scores_gemma":[0.0002723147,0.0021559263,0.050963785,0.014090123,0.00064243266,0.0010232528,0.0826837,0.022041334,0.006206555,0.40520296,0.4143643,0.00035326922],"about_ca_topic_score_codex":0.00985094,"about_ca_topic_score_gemma":0.008735023,"teacher_disagreement_score":0.052674655,"about_ca_system_score_codex":0.009108699,"about_ca_system_score_gemma":0.018237408,"threshold_uncertainty_score":0.2785735},"labels":[],"label_agreement":null},{"id":"W2918818064","doi":"10.3138/cjpe.52945","title":"Meta-Modeling Housing First: A Theory-Based Synthesis Approach","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Management science; Development theory; Engineering; Economics","score_opus":0.5504276300599835,"score_gpt":0.5041718616222928,"score_spread":0.04625576843769075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918818064","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029045537,0.007366512,0.9569192,0.0051698717,0.0010274249,0.017555017,0.0014567254,0.0005773789,0.0070233317],"genre_scores_gemma":[0.02911477,0.0025349304,0.9388207,0.00084187154,0.00012557968,0.027600342,0.00034669595,0.00010864802,0.0005063511],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.6783915,0.28906146,0.011507823,0.008225275,0.011957391,0.00085664465],"domain_scores_gemma":[0.6123396,0.335987,0.008138236,0.020768229,0.021853684,0.00091322325],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24919212,0.0036654563,0.0065767146,0.015601176,0.0031335172,0.009599079,0.0071629984,0.0034196672,0.013543994],"category_scores_gemma":[0.32732826,0.001924472,0.0099727735,0.011140205,0.004003437,0.0068350094,0.006162406,0.005575966,0.0012200914],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010090893,0.0003829664,0.0018684247,0.09000763,0.014444971,0.000334977,0.017092766,0.025072515,0.0018048557,0.53651303,0.016442277,0.29502642],"study_design_scores_gemma":[0.0014164521,0.0009558382,0.0013686919,0.053651962,0.018531011,0.0002422743,0.005365976,0.05231949,0.005512584,0.7183618,0.14187104,0.00040282623],"about_ca_topic_score_codex":0.0033956037,"about_ca_topic_score_gemma":0.0054118386,"teacher_disagreement_score":0.24919212,"about_ca_system_score_codex":0.013137768,"about_ca_system_score_gemma":0.021383023,"threshold_uncertainty_score":0.9258798},"labels":[],"label_agreement":null},{"id":"W2919316438","doi":"10.3138/cjpe.52946","title":"Using Actor-Based Theories of Change to Conduct Robust Evaluation in Complex Settings","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Democracy; Management science; Computer science; Psychological intervention; Process management; Sociology; Operations research; Business; Risk analysis (engineering); Political science; Economics; Psychology; Management; Mathematics; Law","score_opus":0.8242816801062659,"score_gpt":0.5913763997790368,"score_spread":0.23290528032722912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919316438","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024834111,0.0008145169,0.9341268,0.0046148743,0.00024198709,0.004779272,0.00025385362,0.00035602142,0.029978499],"genre_scores_gemma":[0.40091026,0.00046712902,0.58923715,0.00058232364,0.000043913504,0.007612561,0.00016124776,0.000100120815,0.0008852998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6669112,0.3042743,0.005982872,0.007918364,0.0132142,0.0016991568],"domain_scores_gemma":[0.5476487,0.38129118,0.01871288,0.029542523,0.020195827,0.0026088273],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23320101,0.0018886692,0.0022146495,0.0058490457,0.00359972,0.010902235,0.0039631603,0.0029366617,0.008679924],"category_scores_gemma":[0.33769426,0.0011286819,0.0023637929,0.003538313,0.015416517,0.012871948,0.01007703,0.0058678496,0.00088778377],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004883928,0.00089775474,0.01957136,0.0041077994,0.0012350158,0.00018295787,0.014480846,0.11677562,0.0010555477,0.6436063,0.0038882645,0.19371015],"study_design_scores_gemma":[0.0004825768,0.0011895966,0.006556317,0.004536991,0.00042795998,0.00009241816,0.009385366,0.21670869,0.0028985695,0.7329442,0.02458816,0.0001891511],"about_ca_topic_score_codex":0.007963577,"about_ca_topic_score_gemma":0.010459181,"teacher_disagreement_score":0.766799,"about_ca_system_score_codex":0.015015022,"about_ca_system_score_gemma":0.021931145,"threshold_uncertainty_score":0.9455997},"labels":[],"label_agreement":null},{"id":"W2919940519","doi":"10.3138/cjpe.53055","title":"Till Time (and Poor Planning) Do Us Part: Programs as Dynamic Systems—Incorporating Planning of Sustainability into Theories of Change","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Complex Systems and Decision Making","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sustainability; Representation (politics); Process (computing); Process management; Accountability; Management science; Computer science; Business; Economics; Political science; Ecology","score_opus":0.20022946666442681,"score_gpt":0.4448810042794837,"score_spread":0.24465153761505687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919940519","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074175246,0.009776923,0.25427836,0.24604817,0.0010956719,0.0004433364,0.00036445743,0.00026954245,0.41354826],"genre_scores_gemma":[0.9606826,0.0031065776,0.024785986,0.0034670723,0.00010148503,0.0001940491,0.000058215894,0.000085571985,0.0075184563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9874631,0.008770908,0.00032950667,0.00080815377,0.0018168105,0.0008115262],"domain_scores_gemma":[0.974964,0.015193078,0.0023369181,0.0030952285,0.0031487485,0.0012619611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014277644,0.00047065387,0.00050841714,0.0019521799,0.003972551,0.01102334,0.0013953049,0.0028008642,0.0064561116],"category_scores_gemma":[0.035317466,0.00032902125,0.0005024552,0.0035795663,0.029287333,0.020238588,0.005314877,0.0049170437,0.0004011004],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022974202,0.000027437347,0.0017639427,0.00017513716,0.000016428115,0.000058190868,0.006637426,0.0053348406,0.00008378271,0.9528694,0.0027106989,0.03029966],"study_design_scores_gemma":[0.000009414496,0.00004030879,0.0011234677,0.0005674136,0.000025492114,0.00005351258,0.008138874,0.0052409987,0.00040483446,0.9098259,0.07454068,0.000029104027],"about_ca_topic_score_codex":0.0323739,"about_ca_topic_score_gemma":0.03945016,"teacher_disagreement_score":0.0323739,"about_ca_system_score_codex":0.014463545,"about_ca_system_score_gemma":0.019838037,"threshold_uncertainty_score":0.10494083},"labels":[],"label_agreement":null},{"id":"W2920077988","doi":"10.3138/cjpe.53070","title":"How We Model Matters: A Manifesto for the Next Generation of Program Theorizing","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Manifesto; Sociology; Epistemology; Scale (ratio); Engineering ethics; Computer science; Political science; Law; Philosophy; Engineering","score_opus":0.63617589694431,"score_gpt":0.5222816882781216,"score_spread":0.11389420866618838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920077988","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009891292,0.0034796018,0.16957635,0.69302,0.0040450604,0.0002558897,0.00029272362,0.0005490835,0.11889],"genre_scores_gemma":[0.7560239,0.005851338,0.17060058,0.03278971,0.0020035214,0.001112479,0.00042669722,0.001214824,0.029977012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95879775,0.033016115,0.0010859607,0.0014494009,0.0044530947,0.001197651],"domain_scores_gemma":[0.8779532,0.09158253,0.0027389082,0.013858003,0.009770689,0.00409676],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08827783,0.0009073569,0.0006804931,0.0021635033,0.009002012,0.020243093,0.0023937866,0.004444743,0.0072014956],"category_scores_gemma":[0.07406461,0.00049058284,0.00071006315,0.002413021,0.04817071,0.023532193,0.008193519,0.014830931,0.000951202],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013930316,0.00002247175,0.00016007778,0.000057298093,0.0000036512329,0.000039177972,0.010716639,0.000273775,0.00013540559,0.9667585,0.013241318,0.0085776625],"study_design_scores_gemma":[0.00002437628,0.00002836676,0.00014729491,0.00056144904,0.000010820922,0.000048883587,0.010905231,0.001975135,0.00051929854,0.7482776,0.23746534,0.00003618192],"about_ca_topic_score_codex":0.010042888,"about_ca_topic_score_gemma":0.011500406,"teacher_disagreement_score":0.9117222,"about_ca_system_score_codex":0.015447314,"about_ca_system_score_gemma":0.028865853,"threshold_uncertainty_score":0.4668634},"labels":[],"label_agreement":null},{"id":"W2920130717","doi":"10.3138/cjpe.56900","title":"The Current Landscape of Program Theorizing","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Current (fluid); Sociology; Epistemology; Environmental resource management; Environmental planning; Geography; Engineering; Environmental science; Philosophy","score_opus":0.2918100568654653,"score_gpt":0.5403306206497496,"score_spread":0.24852056378428428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920130717","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084518903,0.13398059,0.0035329892,0.7361677,0.09811451,0.000021431259,0.00011864538,0.0001469756,0.027071893],"genre_scores_gemma":[0.09848252,0.23278546,0.014275464,0.1463703,0.46714568,0.00019164495,0.00026442084,0.00055588904,0.03992855],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926804,0.0029410038,0.00035989867,0.0011896783,0.002353408,0.00047565607],"domain_scores_gemma":[0.84567773,0.114828244,0.00272907,0.0032859598,0.025964169,0.007514747],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023479758,0.000665072,0.0013319731,0.005195245,0.0035175069,0.01702265,0.003028834,0.004980341,0.018771427],"category_scores_gemma":[0.07753252,0.00052606576,0.0005066958,0.0033564873,0.01628658,0.011602894,0.0037779252,0.012911208,0.0021940898],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005198082,0.00003568837,0.00042105326,0.00068073935,0.0000113085225,0.000075163545,0.0018424679,0.00026703096,0.00009797445,0.30901107,0.5914697,0.09603583],"study_design_scores_gemma":[0.00001598033,0.000017855624,0.0003374434,0.0019529662,0.000010244884,0.00008917533,0.0021368784,0.000609417,0.00008701418,0.13509598,0.8596118,0.000035212208],"about_ca_topic_score_codex":0.012930534,"about_ca_topic_score_gemma":0.015940158,"teacher_disagreement_score":0.97652024,"about_ca_system_score_codex":0.009768033,"about_ca_system_score_gemma":0.013954241,"threshold_uncertainty_score":0.1241743},"labels":[],"label_agreement":null},{"id":"W2921768415","doi":"10.3138/cjpe.53011","title":"Knitting Theory in STEM Performance Stories: Experiences in Developing a Performance Framework","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Career Development and Diversity","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Simon Fraser University; Université de Sherbrooke; Mount Saint Vincent University; University of Manitoba; University of Ottawa","funders":"","keywords":"Inclusion (mineral); Context (archaeology); Empowerment; Identity (music); Promotion (chess); Representation (politics); Theory of change; Sociology; Public relations; Psychology; Gender studies; Political science","score_opus":0.10462487059310398,"score_gpt":0.3449984442915891,"score_spread":0.2403735736984851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921768415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46477485,0.0025442068,0.10508862,0.06377676,0.0006420792,0.0014663864,0.00015198911,0.0003354502,0.36121956],"genre_scores_gemma":[0.9576956,0.00088713394,0.025482146,0.0015609754,0.000054914795,0.00033945253,0.000079167025,0.00015041656,0.013750182],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9659503,0.027198654,0.00045542288,0.0010600559,0.0029701036,0.0023654758],"domain_scores_gemma":[0.9716169,0.02021593,0.0009855311,0.0013946194,0.0032071979,0.0025797188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03542123,0.0012002982,0.0005781204,0.0044264966,0.025505457,0.01660575,0.0046382123,0.003585459,0.0067748413],"category_scores_gemma":[0.030108863,0.00048686506,0.0005356368,0.0035093867,0.047144447,0.01251872,0.016473636,0.007215927,0.0008602573],"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":[0.000014259557,0.00013279454,0.0014459499,0.00009815609,0.0000030532797,0.0004910021,0.83682466,0.00035455418,0.0001660467,0.12373942,0.0036496548,0.033080447],"study_design_scores_gemma":[0.000006817889,0.000052388783,0.000706593,0.00035022598,0.000005054304,0.00027136688,0.8799549,0.001529938,0.0004739036,0.032737058,0.083889335,0.000022377566],"about_ca_topic_score_codex":0.04524617,"about_ca_topic_score_gemma":0.07272026,"teacher_disagreement_score":0.04524617,"about_ca_system_score_codex":0.027730769,"about_ca_system_score_gemma":0.019966593,"threshold_uncertainty_score":0.20120174},"labels":[],"label_agreement":null},{"id":"W292912147","doi":"10.3138/cjpe.0023.007","title":"Informing Evaluation Capacity Building Through Profiling Organizational Capacity for Evaluation: An Empirical Examination of four Canadian Federal Government Organizations","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Organization development; Government (linguistics); Capacity building; Evaluation methods; Knowledge management; Organizational effectiveness; Order (exchange); Business; Organizational performance; Process management; Computer science; Political science; Finance; Engineering","score_opus":0.43136025450021587,"score_gpt":0.49320319992613026,"score_spread":0.0618429454259144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W292912147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99694175,0.000055003962,0.00022881608,0.00025804056,0.0000026637156,0.00014493315,0.000054063537,0.0000049341998,0.0023098632],"genre_scores_gemma":[0.99885476,0.000048318772,0.0005878384,0.00005062301,9.632648e-7,0.0000758651,0.000048067184,0.0000025399377,0.00033118442],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9844356,0.0044440585,0.00075592124,0.001012629,0.0057032323,0.0036485093],"domain_scores_gemma":[0.92838424,0.023063151,0.009132685,0.002951202,0.029939318,0.0065293666],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02320449,0.0004499706,0.0005361484,0.0067533776,0.016768469,0.00489308,0.0028780415,0.00096840714,0.0013812733],"category_scores_gemma":[0.04739523,0.00071596657,0.0004174451,0.00865444,0.007865978,0.0019238007,0.004692736,0.0018222894,0.00012284819],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018022006,0.000519723,0.62767476,0.0001840612,0.000045759723,0.00029989923,0.32099757,0.0005923452,0.0009191569,0.0049387035,0.0017798942,0.041867867],"study_design_scores_gemma":[0.000013178027,0.00012089489,0.5619986,0.000121608704,0.000017678285,0.000044939214,0.42916307,0.0018086229,0.00055282534,0.00049048354,0.0055967406,0.00007137303],"about_ca_topic_score_codex":0.94562435,"about_ca_topic_score_gemma":0.97145736,"teacher_disagreement_score":0.9767955,"about_ca_system_score_codex":0.099586904,"about_ca_system_score_gemma":0.12665504,"threshold_uncertainty_score":0.72255695},"labels":[],"label_agreement":null},{"id":"W293512544","doi":"10.3138/cjpe.23.012","title":"Latent Profiles of Evaluators’ Self-Reported Practices","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Facilitator; Latent class model; Stakeholder; Psychology; Class (philosophy); Degree (music); Social psychology; Applied psychology; Computer science; Artificial intelligence; Machine learning; Political science; Public relations","score_opus":0.5814887145472366,"score_gpt":0.5616080822872708,"score_spread":0.019880632259965836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W293512544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99668026,0.000038336893,0.0021295603,0.00003661605,0.0000017011935,0.00006750103,0.0001497196,0.00001061229,0.00088574603],"genre_scores_gemma":[0.9989135,0.000018581308,0.0006737189,0.0000048963047,0.0000010855041,0.000060804454,0.00017233292,0.000003571604,0.00015149571],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9911317,0.005049553,0.0009823794,0.00057908066,0.0017322201,0.0005250038],"domain_scores_gemma":[0.92065054,0.043002076,0.017018238,0.0065960367,0.010780835,0.0019521187],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011930924,0.00023847554,0.00035477203,0.0030129906,0.00074777997,0.0020071666,0.00051322486,0.00057975453,0.0013489209],"category_scores_gemma":[0.05521978,0.00024172297,0.00042245555,0.001521003,0.0010365992,0.0013194574,0.0015133222,0.00069640053,0.00034083446],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024730875,0.00017038391,0.9533986,0.000066949266,0.000056446057,0.00004890728,0.025192138,0.00040504575,0.0010734901,0.00047680692,0.00019861244,0.018665291],"study_design_scores_gemma":[0.00002334351,0.00032679256,0.9523359,0.000103860555,0.000027585498,0.00019171996,0.037328377,0.0056794942,0.0013719252,0.0010391466,0.0015085653,0.000063318104],"about_ca_topic_score_codex":0.0017476919,"about_ca_topic_score_gemma":0.001974979,"teacher_disagreement_score":0.98806906,"about_ca_system_score_codex":0.0011201794,"about_ca_system_score_gemma":0.0009922397,"threshold_uncertainty_score":0.06309754},"labels":[],"label_agreement":null},{"id":"W2945068297","doi":"10.3138/cjpe.42239","title":"20 Years Later: Reflections on the CES Student Evaluation Case Competition","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland; University of Waterloo","funders":"","keywords":"Competition (biology); Teamwork; Psychology; Computer-assisted web interviewing; Medical education; Social psychology; Applied psychology; Marketing; Management; Medicine; Business; Economics","score_opus":0.44939411653968636,"score_gpt":0.5776639702248278,"score_spread":0.1282698536851415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945068297","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28764635,0.0022002005,0.0010473167,0.6471612,0.015025787,0.0003337227,0.000212597,0.00009994847,0.04627285],"genre_scores_gemma":[0.80420166,0.002517001,0.0014084104,0.12044277,0.0047223126,0.00042360643,0.00026050812,0.00021829818,0.06580559],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95008916,0.023887068,0.0013075279,0.0016076511,0.010634355,0.012474198],"domain_scores_gemma":[0.89949685,0.016240302,0.003898836,0.0019069213,0.025092307,0.053364735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05172373,0.00092211994,0.0009309195,0.0016017052,0.031678982,0.020171653,0.0060895565,0.013103987,0.009550915],"category_scores_gemma":[0.08409288,0.0007901223,0.0015367182,0.0016199526,0.009261522,0.0054961094,0.014701403,0.027310126,0.0023483783],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002647069,0.0030920513,0.01595653,0.0002414663,0.00006917189,0.01480394,0.33797973,0.0004148877,0.0010557683,0.016973693,0.5439876,0.06516051],"study_design_scores_gemma":[0.000043440108,0.0004335897,0.010891521,0.0003903072,0.000015392714,0.0021145053,0.5166534,0.00034670637,0.0004510318,0.0019986005,0.466498,0.00016356615],"about_ca_topic_score_codex":0.072613016,"about_ca_topic_score_gemma":0.21915932,"teacher_disagreement_score":0.072613016,"about_ca_system_score_codex":0.02697572,"about_ca_system_score_gemma":0.030060848,"threshold_uncertainty_score":0.2735445},"labels":[],"label_agreement":null},{"id":"W2945107123","doi":"10.3138/cjpe.43216","title":"Scaling Up Programs: Reflections on the Importance of Process Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"General partnership; Scale (ratio); Process (computing); Program evaluation; Public relations; Process management; Computer science; Psychology; Business; Political science; Medical education; Public administration; Medicine; Finance","score_opus":0.569979886420681,"score_gpt":0.6000537481211533,"score_spread":0.030073861700472326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945107123","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014224928,0.025748936,0.027811993,0.90348566,0.0026022007,0.0017208118,0.00008473404,0.00024772823,0.024072982],"genre_scores_gemma":[0.60466754,0.037167404,0.14743057,0.19579662,0.0025061679,0.0057424675,0.00011893834,0.0008047161,0.005765525],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.38533494,0.50029576,0.01932883,0.0094676055,0.07129613,0.014276737],"domain_scores_gemma":[0.1761922,0.7108731,0.007321544,0.012186246,0.08047525,0.0129516525],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5902271,0.0018812286,0.002268019,0.006046728,0.017172983,0.029200492,0.0112418365,0.015507813,0.00514044],"category_scores_gemma":[0.4671737,0.0015724069,0.0032363278,0.0052109817,0.048177816,0.032223396,0.017927164,0.039517146,0.0006682153],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005501951,0.0017934532,0.008088786,0.009184608,0.00035912363,0.0009242231,0.18575078,0.003582717,0.00095186976,0.22291835,0.115411095,0.45048478],"study_design_scores_gemma":[0.0008213797,0.0018969525,0.011188155,0.028716726,0.0003457844,0.0009952495,0.23393843,0.005335251,0.0039596637,0.15331453,0.5588617,0.0006261546],"about_ca_topic_score_codex":0.11558251,"about_ca_topic_score_gemma":0.1014183,"teacher_disagreement_score":0.40977287,"about_ca_system_score_codex":0.09023738,"about_ca_system_score_gemma":0.21917458,"threshold_uncertainty_score":0.6547211},"labels":[],"label_agreement":null},{"id":"W2945132513","doi":"10.3138/cjpe.43319","title":"Secure Data Handling: An Essential Competence for Evaluators","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Confidentiality; Harm; Competence (human resources); Computer security; Data collection; Information security; Data security; Internet privacy; Knowledge management; Business; Computer science; Public relations; Psychology; Sociology; Political science; Social psychology; Encryption","score_opus":0.21540598061449356,"score_gpt":0.47612473678496137,"score_spread":0.2607187561704678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945132513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060360692,0.0039131283,0.42728266,0.39095366,0.0017002871,0.0063437764,0.00049883366,0.0012513407,0.10769563],"genre_scores_gemma":[0.58872116,0.0024575223,0.36965972,0.0256116,0.00057287543,0.0036653664,0.00032220944,0.00037527192,0.008614157],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.64871585,0.26152602,0.026562866,0.007388532,0.047078177,0.008728634],"domain_scores_gemma":[0.43137872,0.32299367,0.026146354,0.054864466,0.13880244,0.025814239],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3157213,0.0006140349,0.0013708078,0.0039120764,0.014291409,0.023077194,0.0028050214,0.005805407,0.003919523],"category_scores_gemma":[0.30152896,0.0010405688,0.0009797614,0.0022874451,0.03085028,0.017673193,0.01610883,0.01232285,0.0017521883],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003020134,0.0006499147,0.016412731,0.0027883155,0.00016008985,0.0011578753,0.33878475,0.001786146,0.007358023,0.2877404,0.07545354,0.26740626],"study_design_scores_gemma":[0.00014745836,0.00046884923,0.016576089,0.011717727,0.00014312695,0.0022740995,0.16984327,0.004012056,0.009426417,0.31870395,0.46619394,0.0004929916],"about_ca_topic_score_codex":0.009389272,"about_ca_topic_score_gemma":0.009225051,"teacher_disagreement_score":0.6842787,"about_ca_system_score_codex":0.010395744,"about_ca_system_score_gemma":0.10756631,"threshold_uncertainty_score":0.8438375},"labels":[],"label_agreement":null},{"id":"W2945573974","doi":"10.3138/cjpe.42118","title":"Community, Theory, and Guidance: Benefits and Lessons Learned in Evaluation Peer Mentoring","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Peer mentoring; Psychology; Professional development; Work (physics); Medical education; Peer review; Field (mathematics); Empirical research; Public relations; Pedagogy; Political science; Medicine; Engineering","score_opus":0.5039995996250785,"score_gpt":0.5605583430272246,"score_spread":0.05655874340214617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945573974","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20391122,0.03773283,0.12477252,0.41892058,0.003375614,0.0027739133,0.000083764484,0.00082325184,0.20760636],"genre_scores_gemma":[0.9016031,0.008976458,0.07668684,0.0061745257,0.0006705843,0.0012314281,0.000043964006,0.00013753521,0.0044756276],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.88773954,0.09827054,0.0011742396,0.0014586928,0.009645156,0.0017117697],"domain_scores_gemma":[0.7829431,0.18010417,0.0026876437,0.009791773,0.014202308,0.010270952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09959565,0.00066157413,0.0009825245,0.0029024526,0.0047726575,0.00818784,0.0030230912,0.0032035552,0.0055973222],"category_scores_gemma":[0.16033217,0.00041654095,0.0008206481,0.0021560725,0.011893686,0.008030934,0.010810292,0.0042805737,0.0006221502],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017944879,0.0015292764,0.007807644,0.0013042346,0.00006990579,0.00040178697,0.026517019,0.0011458149,0.00014499425,0.05539845,0.013975933,0.8915255],"study_design_scores_gemma":[0.00090048247,0.00409523,0.03742019,0.018874407,0.00031049876,0.0025940286,0.15482906,0.018835122,0.0018576578,0.57429993,0.18562041,0.00036308292],"about_ca_topic_score_codex":0.006385156,"about_ca_topic_score_gemma":0.0142347915,"teacher_disagreement_score":0.09959565,"about_ca_system_score_codex":0.005417524,"about_ca_system_score_gemma":0.017151916,"threshold_uncertainty_score":0.52671844},"labels":[],"label_agreement":null},{"id":"W2945587103","doi":"10.3138/cjpe.42190","title":"Evaluation Literacy: Perspectives of Internal Evaluators in Non-Government Organizations","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Context (archaeology); Conversation; Narrative; Literacy; Public relations; Psychology; Knowledge management; Sociology; Political science; Pedagogy; Computer science","score_opus":0.11217340830553922,"score_gpt":0.49166201961879946,"score_spread":0.3794886113132602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945587103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8731806,0.0024935268,0.0042937007,0.06157008,0.00031329432,0.00022061054,0.00004007143,0.00004679373,0.057841316],"genre_scores_gemma":[0.99110305,0.00069627963,0.0007002539,0.003930991,0.000049323426,0.00006912853,0.00001129291,0.000030488474,0.003409307],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8732608,0.10601166,0.0025403993,0.0021000232,0.007519554,0.008567649],"domain_scores_gemma":[0.7886861,0.15597129,0.011939421,0.0043831957,0.022163698,0.016856302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.085609645,0.00067610055,0.0009881698,0.003409746,0.023136677,0.024292976,0.0021810285,0.0046033734,0.0043237275],"category_scores_gemma":[0.10456429,0.00087338267,0.00077805074,0.001990687,0.038327415,0.008457511,0.015645683,0.011221596,0.00043072354],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024038118,0.0000619148,0.0053544557,0.00010081758,0.00000770707,0.00041281804,0.98199123,0.00003737804,0.00020201752,0.0055354494,0.0014916515,0.0047804187],"study_design_scores_gemma":[0.000005598311,0.00004606976,0.0022733829,0.00043516344,0.000008591164,0.00023160526,0.976384,0.00014192135,0.00025420467,0.0015030437,0.018689362,0.000026949527],"about_ca_topic_score_codex":0.023986755,"about_ca_topic_score_gemma":0.025126193,"teacher_disagreement_score":0.085609645,"about_ca_system_score_codex":0.022662245,"about_ca_system_score_gemma":0.024823125,"threshold_uncertainty_score":0.45275247},"labels":[],"label_agreement":null},{"id":"W2945590379","doi":"10.3138/cjpe.53169","title":"Anne Markiewicz and Ian Patrick. (2016). <i>Developing Monitoring and Evaluation Frameworks</i> .","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sociology; Psychology; Environmental ethics; Philosophy","score_opus":0.2223609311383748,"score_gpt":0.4917329420662098,"score_spread":0.269372010927835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945590379","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048895256,0.35597038,0.009698357,0.52718353,0.06470337,0.00032159008,0.0008712932,0.00024640057,0.04051606],"genre_scores_gemma":[0.023139387,0.58618355,0.028481608,0.15825067,0.024370693,0.00088233734,0.0013488539,0.0006856294,0.17665724],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99040496,0.0036835603,0.00093338126,0.0006766281,0.0040360754,0.0002653222],"domain_scores_gemma":[0.9238383,0.022819908,0.005056628,0.0015219514,0.04392774,0.002835466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019829271,0.0010445676,0.0007429233,0.004055114,0.0022212965,0.0049854596,0.0017921159,0.0034257127,0.015997997],"category_scores_gemma":[0.08063032,0.0007560433,0.00054921396,0.004216078,0.0032463847,0.007454283,0.0031451986,0.008038273,0.012017632],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023578614,0.0000076535425,0.00026649173,0.00091449346,0.00000799,0.000033487562,0.00057319016,0.00006169905,0.00010740718,0.0053102104,0.9274439,0.06524991],"study_design_scores_gemma":[0.0000071784552,0.000010461009,0.00085652416,0.00410346,0.000014044482,0.0000931672,0.0007604336,0.00005248458,0.00022202895,0.003958704,0.9899003,0.000021301577],"about_ca_topic_score_codex":0.02536543,"about_ca_topic_score_gemma":0.05004096,"teacher_disagreement_score":0.02536543,"about_ca_system_score_codex":0.003079375,"about_ca_system_score_gemma":0.015964964,"threshold_uncertainty_score":0.10486847},"labels":[],"label_agreement":null},{"id":"W2946489075","doi":"10.3138/cjpe.43050","title":"Principles, Approaches, and Methods for Evaluation in Indigenous Contexts: A Grey Literature Scoping Review","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Public Health Ontario","funders":"","keywords":"Grey literature; Indigenous; Interpretation (philosophy); Management science; Engineering ethics; Sociology; Psychology; Computer science; MEDLINE; Political science; Engineering; Ecology","score_opus":0.47385647968230576,"score_gpt":0.5813766564612814,"score_spread":0.10752017677897568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946489075","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063845348,0.71411175,0.15795742,0.054193337,0.002644047,0.020060003,0.0012414341,0.00029475795,0.043112714],"genre_scores_gemma":[0.068215355,0.53037995,0.36284748,0.0052546207,0.00049841206,0.029348748,0.0008140798,0.00014089113,0.0025004332],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.7905819,0.13501422,0.036793318,0.004119088,0.030826064,0.0026655062],"domain_scores_gemma":[0.68164134,0.2392655,0.013810537,0.010195534,0.05333888,0.0017482621],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26068592,0.0022200996,0.004923676,0.04545834,0.007002658,0.01881349,0.004943403,0.004821462,0.0031686784],"category_scores_gemma":[0.28841582,0.0018521282,0.004334516,0.04250257,0.012428167,0.014980837,0.010655743,0.0061247516,0.0009553327],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011408783,0.00017800777,0.0028249053,0.18906717,0.0007278605,0.0004904763,0.0463493,0.0023473632,0.0008235762,0.1312186,0.017208504,0.6086502],"study_design_scores_gemma":[0.000068339396,0.000121252546,0.0028027825,0.6729056,0.0009757883,0.00034402378,0.034183882,0.0014920379,0.00082641054,0.09093033,0.19518703,0.00016255616],"about_ca_topic_score_codex":0.03219179,"about_ca_topic_score_gemma":0.04793666,"teacher_disagreement_score":0.7393141,"about_ca_system_score_codex":0.028591413,"about_ca_system_score_gemma":0.13214305,"threshold_uncertainty_score":0.91170585},"labels":[],"label_agreement":null},{"id":"W2946538741","doi":"10.3138/cjpe.56975","title":"David M. Fetterman, Liliana Rodríguez-Campos, Ann P. Zukoski, et al. (2018). <i>Collaborative, Participatory, and Empowerment Evaluation: Stakeholder Involvement Approaches</i> .","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; University of Toronto","funders":"","keywords":"Empowerment; Sociology; Citizen journalism; Stakeholder; Participatory evaluation; Humanities; Social science; Management; Computer science; Political science; Philosophy; Economics; World Wide Web","score_opus":0.5392699120588643,"score_gpt":0.4912646171455749,"score_spread":0.04800529491328942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946538741","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005471,0.58640325,0.005203366,0.32286713,0.05224663,0.00027334213,0.00054746657,0.000113319904,0.03179841],"genre_scores_gemma":[0.019949844,0.78294766,0.00985908,0.082330875,0.01158178,0.0006707269,0.0008338487,0.00032186846,0.091504335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99151224,0.003450223,0.00044205028,0.0007709376,0.0036131984,0.00021135359],"domain_scores_gemma":[0.9460218,0.019708809,0.001984491,0.0008393881,0.02969873,0.001746791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017486202,0.00088079466,0.00086039095,0.003981625,0.0028397092,0.0045284145,0.0021481437,0.0036563794,0.015618931],"category_scores_gemma":[0.06724502,0.00047555822,0.0005301996,0.0031476829,0.0034817196,0.0053868974,0.002461434,0.006054408,0.008849743],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047549358,0.000010209494,0.0002740387,0.00252034,0.00001737167,0.000039380575,0.00085864484,0.000060683302,0.000117147625,0.00670375,0.9084,0.08095084],"study_design_scores_gemma":[0.000016907015,0.000016587977,0.0007349398,0.0070862053,0.0000290008,0.00010575839,0.0008486425,0.000047344784,0.00020568813,0.0033309343,0.9875486,0.000029364095],"about_ca_topic_score_codex":0.028990982,"about_ca_topic_score_gemma":0.07946575,"teacher_disagreement_score":0.028990982,"about_ca_system_score_codex":0.0039933287,"about_ca_system_score_gemma":0.014454072,"threshold_uncertainty_score":0.092476964},"labels":[],"label_agreement":null},{"id":"W2946705940","doi":"10.3138/cjpe.42976","title":"Evaluating Youth Drop-In Programs: The Utility of Process Evaluation Methods","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Youth Development and Social Support","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"The King's University; Western University; Centre for Addiction and Mental Health","funders":"","keywords":"Disadvantaged; Psychological intervention; Mandate; Drop out; Neighbourhood (mathematics); Social work; Psychology; Public relations; Process (computing); Knowledge management; Business; Sociology; Applied psychology; Medical education; Political science; Computer science; Medicine","score_opus":0.377349202583381,"score_gpt":0.5473020014855827,"score_spread":0.16995279890220172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946705940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4445159,0.011591602,0.3661044,0.003774522,0.00073324307,0.13741507,0.0010995899,0.000611808,0.03415396],"genre_scores_gemma":[0.5255275,0.002975222,0.4061951,0.0004441292,0.00006584534,0.063325904,0.0002809842,0.00005468029,0.0011306489],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.65826046,0.30532485,0.012610224,0.0025257883,0.01989835,0.0013802564],"domain_scores_gemma":[0.5460188,0.37996572,0.022224851,0.008676422,0.040393647,0.0027204785],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25815144,0.0013885398,0.0017586866,0.0062939925,0.0017805499,0.0065964023,0.0018334166,0.0011439219,0.0024093187],"category_scores_gemma":[0.31288108,0.0006810627,0.0016614627,0.0050908,0.0020690253,0.004439365,0.004306418,0.00187367,0.000241147],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004013224,0.00681864,0.04400329,0.012399561,0.0012780635,0.00010598484,0.033887967,0.00532164,0.0011274245,0.011837267,0.002620536,0.87658644],"study_design_scores_gemma":[0.016163766,0.08100231,0.28336093,0.07301711,0.00879766,0.0006566897,0.1540035,0.17282106,0.035474025,0.09856979,0.07452832,0.0016048589],"about_ca_topic_score_codex":0.0046605836,"about_ca_topic_score_gemma":0.00952047,"teacher_disagreement_score":0.25815144,"about_ca_system_score_codex":0.007963848,"about_ca_system_score_gemma":0.018340725,"threshold_uncertainty_score":0.91483134},"labels":[],"label_agreement":null},{"id":"W2946749889","doi":"10.3138/cjpe.43101","title":"Évaluation du processus d’implantation de l’approche axée sur les forces, en s’appuyant sur la théorie de la diffusion de l’innovation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Welfare economics; Scope (computer science); Valuation (finance); Promotion (chess); Mental health; Business; Psychology; Political science; Economics; Computer science; Accounting; Psychotherapist","score_opus":0.3542655148268165,"score_gpt":0.5597778808759223,"score_spread":0.20551236604910578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946749889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8020439,0.0014184713,0.087978035,0.007208822,0.0006598184,0.03267181,0.00063145574,0.0006660082,0.06672162],"genre_scores_gemma":[0.8116327,0.00082806684,0.1624341,0.00060236687,0.00006478173,0.015063962,0.00026517228,0.00013574203,0.008973083],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8274313,0.13632403,0.006931231,0.003506006,0.02214912,0.0036582649],"domain_scores_gemma":[0.69869953,0.21566306,0.012045578,0.01353467,0.05449103,0.00556612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1546147,0.0012376887,0.00087543274,0.0035962241,0.0044361064,0.008252082,0.002474568,0.0031542957,0.015166049],"category_scores_gemma":[0.22979847,0.0009894741,0.0020018704,0.0023434767,0.0027866235,0.0052149408,0.005453504,0.0030709985,0.0017119577],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006225239,0.00915858,0.03435385,0.0089293225,0.00063768786,0.00036613503,0.07796463,0.009899892,0.008514644,0.045818347,0.007190496,0.7909412],"study_design_scores_gemma":[0.010150582,0.06462663,0.19070885,0.032171603,0.003335592,0.00058792316,0.18569502,0.070098,0.114710666,0.062887184,0.2638982,0.0011298053],"about_ca_topic_score_codex":0.014162096,"about_ca_topic_score_gemma":0.013430233,"teacher_disagreement_score":0.1546147,"about_ca_system_score_codex":0.014916758,"about_ca_system_score_gemma":0.04157155,"threshold_uncertainty_score":0.8176905},"labels":[],"label_agreement":null},{"id":"W2946752631","doi":"10.3138/cjpe.43118","title":"Perceived Facilitators and Barriers to Evaluative Thinking in a Small Development NGO","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Work (physics); Sustainability; Process (computing); Psychology; Quality (philosophy); Political science; Public relations; Business; Computer science; Epistemology","score_opus":0.2243927961696357,"score_gpt":0.47516494741048165,"score_spread":0.25077215124084595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946752631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99214137,0.0000774801,0.0007326954,0.0018066822,0.000015479949,0.00020381619,0.000016075797,0.000006614321,0.0049997303],"genre_scores_gemma":[0.9981622,0.00009228778,0.0006891996,0.0002072983,0.00000445021,0.000193484,0.000009330456,0.000005024023,0.00063683],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9720668,0.021247374,0.0011221747,0.0007582367,0.002698768,0.0021067113],"domain_scores_gemma":[0.8528661,0.10905779,0.009137664,0.0024512825,0.016491093,0.009995982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044877857,0.00032216302,0.00040858964,0.0014359936,0.009643238,0.006556412,0.00096549693,0.00096706237,0.004825209],"category_scores_gemma":[0.08410046,0.00035106455,0.00022536905,0.0011482512,0.0065574185,0.0023153708,0.0049427464,0.0020680644,0.0003256531],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053821324,0.001747385,0.15103683,0.0005009145,0.000032911095,0.0012522935,0.79727894,0.00028827993,0.0021110591,0.0036148925,0.0015207737,0.040077504],"study_design_scores_gemma":[0.00006059145,0.0005566683,0.064241484,0.00050334627,0.00002347248,0.00016570129,0.92233276,0.0006928137,0.0011208436,0.0019909989,0.008255693,0.00005560497],"about_ca_topic_score_codex":0.013332467,"about_ca_topic_score_gemma":0.02551812,"teacher_disagreement_score":0.044877857,"about_ca_system_score_codex":0.008220175,"about_ca_system_score_gemma":0.018367846,"threshold_uncertainty_score":0.23733962},"labels":[],"label_agreement":null},{"id":"W2946805187","doi":"10.3138/cjpe.52823","title":"Perceptions of the Use of an Outcome Monitoring Tool in a Clinical Psychology Training Centre: Lessons Learned for Performance Measurement","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychiatric care and mental health services","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Saint Paul University","funders":"","keywords":"Perception; Psychology; Applied psychology; Mental health; Medical education; Outcome (game theory); Focus group; Medicine; Psychiatry; Sociology","score_opus":0.7266806947764031,"score_gpt":0.5797470132556877,"score_spread":0.1469336815207154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946805187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96808463,0.00095899834,0.005239518,0.021749215,0.00017325318,0.00043175282,0.00004671227,0.000071095565,0.0032447772],"genre_scores_gemma":[0.9898127,0.0006784908,0.008106753,0.00091642747,0.000050877956,0.00017144851,0.000028064589,0.000017741822,0.00021761851],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9491219,0.035399616,0.002765982,0.00077627646,0.009787301,0.0021488694],"domain_scores_gemma":[0.85872704,0.08598492,0.012265986,0.003741549,0.023419991,0.015860522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.081790075,0.0003583309,0.0004279122,0.000776168,0.0016735864,0.0032863505,0.0013612313,0.00089811604,0.0011829868],"category_scores_gemma":[0.11965647,0.00029377168,0.0003744024,0.00056462066,0.0020169523,0.0024898993,0.002474535,0.0028821812,0.00017388204],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004343017,0.00256159,0.32128927,0.002176329,0.00011408053,0.00075020146,0.17718105,0.0007322502,0.0040526586,0.0008792099,0.008843771,0.4809853],"study_design_scores_gemma":[0.00012698464,0.0072962814,0.5679609,0.003944829,0.000120271594,0.0011451523,0.3888682,0.0036258055,0.0029925837,0.0011099986,0.022557862,0.00025109772],"about_ca_topic_score_codex":0.008728849,"about_ca_topic_score_gemma":0.013060302,"teacher_disagreement_score":0.9182099,"about_ca_system_score_codex":0.004224501,"about_ca_system_score_gemma":0.012252552,"threshold_uncertainty_score":0.43255246},"labels":[],"label_agreement":null},{"id":"W2992485618","doi":"10.3138/cjpe.024.001","title":"The Lay of the Land: Evaluation Practice in Canada in 2009","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Public Health Agency of Canada; University of Victoria; Ministère des Ressources naturelles et des Forêts (Québec)","funders":"","keywords":"CLARITY; Certification; Public relations; Sophistication; Psychology; Business; Political science; Sociology; Law; Social science","score_opus":0.2269249594352962,"score_gpt":0.5186252407657015,"score_spread":0.29170028133040526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992485618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5730907,0.07099273,0.011819475,0.20142493,0.0020280008,0.0014522849,0.0015939836,0.0005793112,0.13701856],"genre_scores_gemma":[0.963488,0.007867195,0.005562157,0.0049517695,0.00006203943,0.0001240214,0.00023867574,0.00013423782,0.01757192],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9723911,0.008626137,0.0019249651,0.001762745,0.010244913,0.005050118],"domain_scores_gemma":[0.89435756,0.0133366175,0.0034983628,0.001670404,0.07200912,0.015127939],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034430787,0.00037633083,0.00071718724,0.0036224013,0.01981442,0.008541508,0.0030595777,0.001882116,0.003252833],"category_scores_gemma":[0.06634478,0.00064303534,0.0003581301,0.0073318896,0.0061858776,0.0019650122,0.0057000155,0.0027468344,0.00024202067],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00084001315,0.00036659802,0.08429607,0.002533766,0.00016503016,0.0026536146,0.15676473,0.0023385147,0.0023524256,0.040945232,0.15038946,0.55635446],"study_design_scores_gemma":[0.000078202895,0.00023840861,0.21313123,0.0031391417,0.00011118106,0.0005973021,0.18193214,0.0035408237,0.0031122277,0.004204937,0.5895639,0.0003504383],"about_ca_topic_score_codex":0.9885634,"about_ca_topic_score_gemma":0.9935309,"teacher_disagreement_score":0.9655692,"about_ca_system_score_codex":0.27373713,"about_ca_system_score_gemma":0.44627568,"threshold_uncertainty_score":0.842362},"labels":[],"label_agreement":null},{"id":"W2994626447","doi":"10.3138/cjpe.68444","title":"Increasing Cultural Competence in Support of Indigenous-Led Evaluation: A Necessary Step toward Indigenous-Led Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Aotearoa; Competence (human resources); Traditional knowledge; Sociology; Political science; Psychology; Gender studies; Social psychology","score_opus":0.23459713410538083,"score_gpt":0.4965004891018339,"score_spread":0.2619033549964531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994626447","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05537521,0.006183899,0.124659054,0.6068597,0.00270026,0.005261755,0.00006341627,0.0010118195,0.19788492],"genre_scores_gemma":[0.7194207,0.003547235,0.20181051,0.055481404,0.0008343394,0.0041026003,0.00008899379,0.00050269795,0.014211531],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.69214135,0.229683,0.011386809,0.007740245,0.04740827,0.011640363],"domain_scores_gemma":[0.45209858,0.2641355,0.018234747,0.038469523,0.17143352,0.05562811],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3049125,0.00092447235,0.0017012446,0.003500422,0.015974721,0.022012904,0.0057664216,0.00518769,0.008296595],"category_scores_gemma":[0.3056246,0.0011390586,0.0013278631,0.002262598,0.024148192,0.019581113,0.034034256,0.017575813,0.0020125897],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001990297,0.00202115,0.015749773,0.0034233087,0.00024386769,0.000879227,0.3734418,0.0012344879,0.0045847064,0.10348365,0.05446995,0.44026893],"study_design_scores_gemma":[0.0003362156,0.00065354514,0.02712517,0.013985908,0.00017534752,0.0011676687,0.23388352,0.002574485,0.004625417,0.13084997,0.584097,0.00052565814],"about_ca_topic_score_codex":0.037734088,"about_ca_topic_score_gemma":0.061725426,"teacher_disagreement_score":0.9718041,"about_ca_system_score_codex":0.028195944,"about_ca_system_score_gemma":0.17858413,"threshold_uncertainty_score":0.85716665},"labels":[],"label_agreement":null},{"id":"W2994882198","doi":"10.3138/cjpe.67976","title":"Creating New Stories: The Role of Evaluation in Truth and Reconciliation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Status quo; Commission; Environmental ethics; Sociology; Truth telling; Political science; Natural (archaeology); Public relations; Engineering ethics; Law; Psychology; History; Archaeology","score_opus":0.25760580415152334,"score_gpt":0.4974978039906295,"score_spread":0.23989199983910614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994882198","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020568926,0.029201362,0.08085459,0.47034338,0.002791373,0.00070537033,0.0001443078,0.00042434756,0.39496636],"genre_scores_gemma":[0.8824975,0.017018411,0.05794301,0.019708026,0.00092194404,0.00061353954,0.00010774137,0.00037234335,0.020817462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.78618413,0.17086993,0.004110039,0.00402365,0.027536254,0.0072760563],"domain_scores_gemma":[0.7353697,0.17972504,0.010854313,0.0102709355,0.047924556,0.015855538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16733113,0.0008756913,0.0013643736,0.008019516,0.027018916,0.04589815,0.0045114583,0.005940937,0.007362431],"category_scores_gemma":[0.14313433,0.00074144267,0.0007761972,0.005416686,0.07743261,0.02252699,0.022220962,0.010272965,0.0008839479],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085147556,0.000085116866,0.0030052538,0.0009126822,0.000065938766,0.00042625007,0.15585285,0.0011704066,0.00027211767,0.599112,0.04773622,0.1912761],"study_design_scores_gemma":[0.00004175619,0.000071231414,0.0027954543,0.004733356,0.000062659376,0.00025271362,0.1340201,0.0019848866,0.00082258886,0.331399,0.5236332,0.00018303731],"about_ca_topic_score_codex":0.2668359,"about_ca_topic_score_gemma":0.30441383,"teacher_disagreement_score":0.922067,"about_ca_system_score_codex":0.077933,"about_ca_system_score_gemma":0.14954618,"threshold_uncertainty_score":0.8849422},"labels":[],"label_agreement":null},{"id":"W2994962470","doi":"10.3138/cjpe.67978","title":"White Privilege and the Decolonization Work Needed in Evaluation to Support Indigenous Sovereignty and Self-Determination","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; White privilege; Aotearoa; Privilege (computing); Sovereignty; Injustice; Sociology; Colonialism; White (mutation); Economic Justice; Gender studies; Decolonization; Law; Environmental ethics; Political science; Racism; Politics","score_opus":0.1310915805611923,"score_gpt":0.4568472619130539,"score_spread":0.3257556813518616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994962470","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18307844,0.008888691,0.061866123,0.3353962,0.0022479617,0.001832132,0.00008475765,0.00049631414,0.40610936],"genre_scores_gemma":[0.95165104,0.0013269953,0.01938033,0.010643866,0.00023800791,0.00070050283,0.000030890216,0.00014415398,0.015884252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8827433,0.08896872,0.0033558398,0.003025544,0.014929764,0.0069768154],"domain_scores_gemma":[0.86261445,0.08022955,0.007392665,0.007900869,0.02900265,0.012859856],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.1252633,0.0004814521,0.0010692629,0.0027857719,0.02251624,0.023178585,0.0022094597,0.003180356,0.008792272],"category_scores_gemma":[0.11215103,0.0006282964,0.00063681573,0.0018459116,0.037910894,0.016402109,0.0170321,0.0071388134,0.00088757783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026722165,0.0008186224,0.011448243,0.0014081277,0.00007899562,0.0006286088,0.26391265,0.00124565,0.0024045755,0.3552438,0.044649236,0.31789425],"study_design_scores_gemma":[0.00019140699,0.00065281196,0.01765643,0.005910393,0.000101568505,0.0005324332,0.26935858,0.002529095,0.005131249,0.18026505,0.5173932,0.00027783774],"about_ca_topic_score_codex":0.044895753,"about_ca_topic_score_gemma":0.071781754,"teacher_disagreement_score":0.97748375,"about_ca_system_score_codex":0.025671346,"about_ca_system_score_gemma":0.08059317,"threshold_uncertainty_score":0.66246355},"labels":[],"label_agreement":null},{"id":"W2995189513","doi":"10.3138/cjpe.67977","title":"Nation-to-Nation Evaluation: Governance, Tribal Sovereignty, and Systems Thinking through Culturally Responsive Indigenous Evaluations","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Sovereignty; Transformative learning; Corporate governance; Colonialism; Environmental ethics; Sociology; Harm; Political science; Doctrine; Law; Politics; Management","score_opus":0.2965348623635574,"score_gpt":0.5006583896229647,"score_spread":0.2041235272594073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995189513","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15283799,0.0074240933,0.092481405,0.14707176,0.0009975994,0.0014710223,0.00010721278,0.00025982352,0.59734917],"genre_scores_gemma":[0.9698111,0.0015551551,0.02032619,0.0023562068,0.00006539996,0.00050227623,0.000019040444,0.000068957255,0.0052957074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8940331,0.096738204,0.0009407405,0.0012449898,0.004747648,0.0022952345],"domain_scores_gemma":[0.9046675,0.07633475,0.0025862623,0.0039645205,0.008867728,0.0035792727],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09512521,0.0006670096,0.0006108257,0.0029593152,0.011281797,0.020185549,0.0023344604,0.0021090615,0.0067616827],"category_scores_gemma":[0.087198645,0.00037725165,0.00046995317,0.0018647985,0.05062811,0.012173535,0.012349533,0.0054433416,0.0002829595],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093479175,0.00018751092,0.0038066574,0.00077328307,0.00005687291,0.00024395213,0.2435404,0.001561193,0.0003081198,0.6417181,0.010513926,0.09719648],"study_design_scores_gemma":[0.00006676995,0.00017107197,0.0047661206,0.0039373427,0.00010298827,0.00017193882,0.38146636,0.004858257,0.0017433629,0.44243544,0.1601818,0.00009858533],"about_ca_topic_score_codex":0.048030674,"about_ca_topic_score_gemma":0.08064441,"teacher_disagreement_score":0.9679633,"about_ca_system_score_codex":0.032036737,"about_ca_system_score_gemma":0.04477154,"threshold_uncertainty_score":0.5030762},"labels":[],"label_agreement":null},{"id":"W2995252437","doi":"10.3138/cjpe.61279","title":"Démocratie et évaluation des politiques publiques","year":2019,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Political science; Humanities; Valuation (finance); Sociology; Philosophy; Economics","score_opus":0.18509947444494254,"score_gpt":0.4395693876790462,"score_spread":0.2544699132341036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995252437","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052006237,0.01733595,0.03535715,0.032110564,0.0011065234,0.0007475522,0.00079643365,0.00030869085,0.8602309],"genre_scores_gemma":[0.8509047,0.015558279,0.025772655,0.0024359582,0.0006743028,0.0012984022,0.0005802529,0.0003357183,0.102439806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.88670784,0.07720479,0.002444043,0.002376402,0.028559353,0.0027074772],"domain_scores_gemma":[0.94360775,0.03854618,0.0033155598,0.0034448071,0.009813755,0.0012718819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04962044,0.00072805217,0.00083784293,0.006970991,0.0038674397,0.015541146,0.0008955985,0.0017456099,0.017547907],"category_scores_gemma":[0.0808935,0.00037048265,0.000657964,0.008634385,0.00930583,0.008336227,0.004284994,0.002908282,0.0014120311],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013977732,0.00021469026,0.004081821,0.0014185284,0.00010802761,0.00008671277,0.01323192,0.0019847683,0.0009447976,0.76518804,0.01675607,0.19584477],"study_design_scores_gemma":[0.00017020256,0.0005897817,0.026081134,0.0042104195,0.00013733932,0.00030902878,0.023531193,0.003582698,0.0065603172,0.2636796,0.67101043,0.00013792011],"about_ca_topic_score_codex":0.027827384,"about_ca_topic_score_gemma":0.030584686,"teacher_disagreement_score":0.04962044,"about_ca_system_score_codex":0.01975484,"about_ca_system_score_gemma":0.026620265,"threshold_uncertainty_score":0.26242107},"labels":[],"label_agreement":null},{"id":"W2995471644","doi":"10.3138/cjpe.53365","title":"“Deliverology” and Evaluation: A Tale of Two Worlds","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Corporate governance; Politics; Context (archaeology); Value (mathematics); Public value; Public management; Critical reflection; Political science; Public relations; Reflection (computer programming); Complement (music); Public administration; Sociology; Economics; Management; Law; Computer science; History","score_opus":0.2895418597302168,"score_gpt":0.5351081862029722,"score_spread":0.2455663264727554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995471644","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006102795,0.034323048,0.11818699,0.6961049,0.0077670207,0.00075631996,0.00008925844,0.00034363678,0.13632606],"genre_scores_gemma":[0.6515962,0.02214062,0.15422504,0.1361746,0.0068511697,0.002642073,0.000110913075,0.00086761406,0.025391707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6286276,0.31962684,0.0076411325,0.007214174,0.032154724,0.0047355024],"domain_scores_gemma":[0.7007428,0.23069024,0.007041307,0.021827403,0.030310966,0.009387316],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27494532,0.00161982,0.0027670865,0.0125421975,0.01388811,0.0454921,0.003683038,0.010963491,0.0064148833],"category_scores_gemma":[0.20622337,0.0011325496,0.0015359969,0.0072752163,0.16297157,0.038437165,0.022063067,0.021641215,0.0008812744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005701758,0.000052134492,0.00057762023,0.00056537817,0.0000598825,0.000110116714,0.023937745,0.00031882845,0.00012912866,0.90885264,0.018463558,0.046876106],"study_design_scores_gemma":[0.000072566414,0.0001354614,0.0006762002,0.0046334825,0.00005834758,0.00016044201,0.03050996,0.000787959,0.00047546191,0.6694869,0.29284555,0.00015773466],"about_ca_topic_score_codex":0.016153434,"about_ca_topic_score_gemma":0.014161178,"teacher_disagreement_score":0.7250547,"about_ca_system_score_codex":0.041720897,"about_ca_system_score_gemma":0.047099806,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2995480421","doi":"10.3138/cjpe.43685","title":"Self-Evaluation Tool for Action in Partnership: Translation and Cultural Adaptation of the Original Quebec French Tool to Canadian English","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Equivalence (formal languages); Adaptation (eye); General partnership; Action (physics); Process (computing); Computer science; Linguistics; Sociology; Knowledge management; Psychology; Political science; Law","score_opus":0.3247910086417194,"score_gpt":0.4861257559367303,"score_spread":0.1613347472950109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995480421","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43311223,0.0059550796,0.22333181,0.016323095,0.003136944,0.037490897,0.028534198,0.0030098653,0.24910583],"genre_scores_gemma":[0.56999546,0.003148729,0.3538949,0.0014657376,0.000081957936,0.03382855,0.0066988133,0.00059589965,0.030290024],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98650175,0.0067710085,0.0013421994,0.0005175399,0.0041547394,0.0007128234],"domain_scores_gemma":[0.9570873,0.0130923325,0.0010542864,0.0013356032,0.026459929,0.0009704958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019657483,0.0007996529,0.00067348283,0.004320961,0.0035808096,0.0036793058,0.0015283739,0.00056495954,0.0112744],"category_scores_gemma":[0.04848841,0.0003245723,0.0010724697,0.0046355138,0.0017613581,0.0011941292,0.002478342,0.0014132068,0.0010608996],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049751083,0.0005839573,0.026955307,0.0036066212,0.00014268326,0.0005041169,0.061290268,0.0025059003,0.002670505,0.02937381,0.07785816,0.7940113],"study_design_scores_gemma":[0.00041560418,0.000623096,0.15848304,0.008184489,0.00024344937,0.00056431675,0.049271986,0.006155512,0.0072142743,0.0058465363,0.76244056,0.00055707013],"about_ca_topic_score_codex":0.7229331,"about_ca_topic_score_gemma":0.8120631,"teacher_disagreement_score":0.2770669,"about_ca_system_score_codex":0.038976625,"about_ca_system_score_gemma":0.08242736,"threshold_uncertainty_score":0.5573971},"labels":[],"label_agreement":null},{"id":"W2995564338","doi":"10.3138/cjpe.44172","title":"Dramatizing Learning, Performing Ourselves: Stories of Theatre-Based Evaluation in Vancouver's Downtown Eastside","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Downtown; Experiential learning; Citizen journalism; Process (computing); Sociology; Work (physics); Psychology; Visual arts; Pedagogy; Computer science; Art; History; Engineering; World Wide Web; Archaeology","score_opus":0.18181349197951518,"score_gpt":0.4904914886895171,"score_spread":0.3086779967100019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995564338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84829247,0.0016004308,0.007838365,0.02136555,0.000491133,0.00050888676,0.00027024827,0.0001604733,0.11947233],"genre_scores_gemma":[0.97918475,0.00073770934,0.0022847056,0.0007353752,0.00004900713,0.00018004309,0.00007275065,0.0001146662,0.016640985],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98239017,0.0122921895,0.000220822,0.000488853,0.0024086123,0.00219927],"domain_scores_gemma":[0.98357195,0.009058098,0.0005429618,0.0005980172,0.002425059,0.003803822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010247567,0.000954885,0.00073655345,0.0013723752,0.025175635,0.0092845345,0.0021316288,0.0021937129,0.0041469582],"category_scores_gemma":[0.016460484,0.0005416098,0.00037011728,0.0014284184,0.016702535,0.0017156777,0.0070685092,0.0051845456,0.0005376234],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020305743,0.00022649282,0.003918021,0.0003392167,0.000033578483,0.0028843787,0.92112386,0.0009291236,0.0015691752,0.008556333,0.018164119,0.042052757],"study_design_scores_gemma":[0.000018474277,0.00013277667,0.0044387444,0.0004769693,0.000022589029,0.0005494309,0.8729966,0.0005951845,0.0015982316,0.0017334524,0.11737354,0.00006397945],"about_ca_topic_score_codex":0.2802618,"about_ca_topic_score_gemma":0.6126303,"teacher_disagreement_score":0.7197382,"about_ca_system_score_codex":0.022280643,"about_ca_system_score_gemma":0.017903036,"threshold_uncertainty_score":0.557261},"labels":[],"label_agreement":null},{"id":"W2995590052","doi":"10.3138/cjpe.67854","title":"Anne Vo and Christina A. Christie (Eds.). (2015). <i>Evaluation Use and Decision Making in Society: A Tribute to Marvin C. Alkin.</i>","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tribute; Sociology; Psychology; Art history; Art","score_opus":0.19169266228507312,"score_gpt":0.4845022894400607,"score_spread":0.2928096271549876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995590052","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017290605,0.8831389,0.0030525846,0.056119096,0.011590321,0.000032661428,0.00035124025,0.00018378058,0.04535856],"genre_scores_gemma":[0.0024388565,0.89098966,0.0032332654,0.007421263,0.004615257,0.0000474525,0.0003059418,0.00012821736,0.09082],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990676,0.00021132575,0.000073594565,0.00008762321,0.0005119981,0.000047891543],"domain_scores_gemma":[0.99640757,0.001940255,0.00021392926,0.00007836166,0.0010655087,0.00029446007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002258679,0.001293065,0.0009769747,0.002123648,0.00078845036,0.0049631936,0.0010324543,0.0021707655,0.028664019],"category_scores_gemma":[0.0055075083,0.0008440816,0.0005422723,0.0031068174,0.0010064499,0.0045520626,0.0011604362,0.003784902,0.029287618],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014058377,0.000006613713,0.0001047398,0.00048824775,0.0000062952986,0.000019919851,0.00013282135,0.0000854699,0.00004789058,0.0022904072,0.84963053,0.14717297],"study_design_scores_gemma":[0.0000044092935,0.000007381537,0.00034004299,0.0013281687,0.000011992346,0.0001357637,0.00017028711,0.00008413399,0.00008581311,0.0031287516,0.9946905,0.000012783354],"about_ca_topic_score_codex":0.014831293,"about_ca_topic_score_gemma":0.041396827,"teacher_disagreement_score":0.028664019,"about_ca_system_score_codex":0.00161679,"about_ca_system_score_gemma":0.004631294,"threshold_uncertainty_score":0.0958907},"labels":[],"label_agreement":null},{"id":"W2995666448","doi":"10.3138/cjpe.67892","title":"Scott G. Chaplowe and J. Bradley Cousins. (2016). <i>Monitoring and Evaluation Training: A Systematic Approach.</i>","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Gerontology; Psychology; Training (meteorology); Sociology; Geography; Medicine","score_opus":0.3839926982165331,"score_gpt":0.4813167098258325,"score_spread":0.09732401160929943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995666448","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022035136,0.25188735,0.03440481,0.6522878,0.02002246,0.0034013663,0.0026586596,0.00071688887,0.03241715],"genre_scores_gemma":[0.08459701,0.49035218,0.16374841,0.1909787,0.008751152,0.00848242,0.0029948363,0.0009856191,0.049109645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9361987,0.03850936,0.0066263457,0.001407374,0.016548267,0.0007099698],"domain_scores_gemma":[0.63684714,0.17720889,0.020951565,0.009110297,0.14780289,0.008079196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13195516,0.0011104055,0.0015343006,0.009489862,0.003002006,0.0061893254,0.0033931793,0.004966836,0.01158163],"category_scores_gemma":[0.37710822,0.0013930777,0.0012959365,0.007945166,0.004233495,0.006426875,0.004684465,0.0070768204,0.006172507],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019092974,0.000045505967,0.001862535,0.008071702,0.00012328009,0.00006634391,0.0020382355,0.00019210853,0.0002727545,0.004169035,0.69656855,0.286399],"study_design_scores_gemma":[0.0003214398,0.00036004183,0.013238058,0.10991279,0.0006566965,0.0002973107,0.004620395,0.0005472022,0.0015917378,0.02326875,0.8448657,0.00031977892],"about_ca_topic_score_codex":0.047575153,"about_ca_topic_score_gemma":0.12760632,"teacher_disagreement_score":0.13195516,"about_ca_system_score_codex":0.0061593726,"about_ca_system_score_gemma":0.049277093,"threshold_uncertainty_score":0.6978539},"labels":[],"label_agreement":null},{"id":"W2995777958","doi":"10.3138/cjpe.67979","title":"Introduction to Articles Prepared by CES Calgary 2018 Keynote Panel Members on Reconciliation and Culturally Responsive Evaluation—Rhetoric or Reality?","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rhetoric; Sociology; Psychology; Political science; Linguistics; Philosophy","score_opus":0.298192845152364,"score_gpt":0.482247239067281,"score_spread":0.184054393914917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995777958","genre_codex":"editorial","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002851697,0.009061459,0.0015325465,0.37384295,0.54768884,0.00070584955,0.0015150681,0.00034704438,0.065021046],"genre_scores_gemma":[0.0038088039,0.011030795,0.0030745824,0.277899,0.28036627,0.0013528027,0.0012243246,0.00046161748,0.42078182],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99346864,0.0017320161,0.0005402023,0.00059383904,0.0030960857,0.0005691467],"domain_scores_gemma":[0.9427877,0.02513418,0.0024807127,0.0013951267,0.022719806,0.0054824664],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0147834895,0.0014220171,0.001315131,0.0036771498,0.004808461,0.009147943,0.0031341042,0.015808513,0.1316318],"category_scores_gemma":[0.047910932,0.0007191128,0.0016211129,0.0026501415,0.0024733795,0.0041166586,0.003606878,0.011957593,0.055772744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012831847,0.000011830318,0.000015029543,0.00007688725,0.0000016265657,0.000017744007,0.000021414178,0.000013700277,0.000044726465,0.00064978143,0.99529797,0.003836443],"study_design_scores_gemma":[0.00001512845,0.000016313123,0.00028244336,0.00042268354,0.00000503082,0.000015550955,0.000112661815,0.000022468676,0.000068419315,0.0015624646,0.99746156,0.000015354486],"about_ca_topic_score_codex":0.011022976,"about_ca_topic_score_gemma":0.031579696,"teacher_disagreement_score":0.99429566,"about_ca_system_score_codex":0.005704344,"about_ca_system_score_gemma":0.009011482,"threshold_uncertainty_score":0.44035226},"labels":[],"label_agreement":null},{"id":"W2995932983","doi":"10.3138/cjpe.56989","title":"Comparison of Canadian and American Graduate Evaluation Education Programs","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Professionalization; Graduate education; Graduate students; Population; Political science; Medical education; Program evaluation; Higher education; Library science; Sociology; Public administration; Medicine; Demography; Computer science","score_opus":0.5628449880548297,"score_gpt":0.5884740088916572,"score_spread":0.0256290208368275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995932983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8544526,0.002705099,0.0035252115,0.004464329,0.00023197933,0.0008375124,0.0071814014,0.00029043196,0.12631154],"genre_scores_gemma":[0.97997206,0.0015581109,0.0029641662,0.0005751414,0.000040782794,0.00033751733,0.004467698,0.0000597775,0.01002472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9894651,0.0010825384,0.00035352923,0.0005395331,0.006791782,0.00176754],"domain_scores_gemma":[0.9458715,0.0034303514,0.0025258872,0.0007189118,0.037456624,0.009996739],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0081034135,0.00035338267,0.00030890063,0.008239012,0.0028354162,0.0025542171,0.0018030617,0.00041926283,0.004562097],"category_scores_gemma":[0.030234434,0.00025920692,0.00044374246,0.011051426,0.00091483287,0.00079202576,0.0023155217,0.0008601799,0.000459843],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086799474,0.0007404218,0.595954,0.00073018664,0.00015253451,0.00011532788,0.012385615,0.0012860217,0.00089421734,0.010404703,0.051732276,0.3247367],"study_design_scores_gemma":[0.000039778093,0.00015637257,0.9351622,0.00030979785,0.000050927632,0.000082391074,0.007490042,0.00074363756,0.00057443173,0.00026709173,0.0550837,0.00003965416],"about_ca_topic_score_codex":0.8785822,"about_ca_topic_score_gemma":0.94346416,"teacher_disagreement_score":0.99189657,"about_ca_system_score_codex":0.05895828,"about_ca_system_score_gemma":0.09559872,"threshold_uncertainty_score":0.42777425},"labels":[],"label_agreement":null},{"id":"W2995943763","doi":"10.3138/cjpe.53185","title":"Applying the Collaborative Approaches to Evaluation (CAE) Principles in an Educational Evaluation: Reflections from the Field","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reflection (computer programming); Context (archaeology); Field (mathematics); Engineering ethics; Pedagogy; Sociology; Computer science; Engineering","score_opus":0.7739294717178385,"score_gpt":0.5731835285755595,"score_spread":0.200745943142279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995943763","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15466648,0.009080122,0.29072934,0.4527046,0.0074338648,0.0042015403,0.00009891125,0.00040098088,0.080684185],"genre_scores_gemma":[0.74982905,0.007327589,0.19025849,0.036105234,0.0011419392,0.0024516473,0.000057333582,0.00045975077,0.012369011],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.616528,0.33823153,0.008198509,0.0055044335,0.023271201,0.008266326],"domain_scores_gemma":[0.54678035,0.3706951,0.0066326973,0.012113836,0.05587939,0.007898616],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.26330516,0.0015229747,0.0011572588,0.002478756,0.018682668,0.017889459,0.006107216,0.010108902,0.0014178785],"category_scores_gemma":[0.25130546,0.0014741466,0.001536201,0.0019811504,0.04078633,0.014145582,0.016493319,0.02889003,0.0006370622],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014330221,0.00073649536,0.0017466394,0.0012382971,0.000066914035,0.0021064463,0.7800308,0.0018960964,0.002057475,0.055503663,0.02478303,0.12969092],"study_design_scores_gemma":[0.00011809942,0.0006905606,0.0013100676,0.004004953,0.000056185858,0.002285376,0.61680156,0.0029364545,0.004678075,0.040626425,0.32610926,0.00038290786],"about_ca_topic_score_codex":0.014104355,"about_ca_topic_score_gemma":0.015592859,"teacher_disagreement_score":0.26330516,"about_ca_system_score_codex":0.017481655,"about_ca_system_score_gemma":0.03123498,"threshold_uncertainty_score":0.9084759},"labels":[],"label_agreement":null},{"id":"W2996414405","doi":"10.3138/cjpe.52185","title":"Évaluation de la mise en œuvre du programme d'intervention <i>In vivo</i> chez les jeunes de 11–12 ans d'une école primaire québécoise présentant un problème de comportements intériorisés : une étude exploratoire","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Psychology; Mental health; Anxiety; Psychotherapist; Psychiatry","score_opus":0.04525908592435794,"score_gpt":0.31553786206018763,"score_spread":0.2702787761358297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996414405","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965184,0.00013333833,0.00024973505,0.00011235848,0.00003239061,0.0017529164,0.00008922208,0.000020575319,0.0010910888],"genre_scores_gemma":[0.98947304,0.00050257624,0.0033093384,0.0001554996,0.00004280866,0.0033243634,0.00031417175,0.0000069897883,0.0028711476],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989128,0.0005596588,0.00006194474,0.00010994286,0.00012676668,0.00022880759],"domain_scores_gemma":[0.99774003,0.0005676826,0.00026693696,0.00010598746,0.0004573162,0.00086213974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022515333,0.0006249421,0.00051257125,0.00045182413,0.0012279173,0.00059974875,0.0009292973,0.00087266107,0.0037080138],"category_scores_gemma":[0.0034330378,0.0003734811,0.0005448262,0.00030038,0.0005766016,0.00027850107,0.00092127436,0.0007347325,0.00023163341],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026045162,0.13880882,0.12582931,0.0028528338,0.000644253,0.0011831734,0.020414641,0.0032021252,0.026680553,0.0006464863,0.0024883559,0.6512043],"study_design_scores_gemma":[0.010192322,0.2909837,0.6682482,0.0009010859,0.0005775453,0.00027772106,0.009301728,0.001619145,0.0059702448,0.00011589922,0.011726778,0.00008564435],"about_ca_topic_score_codex":0.094808266,"about_ca_topic_score_gemma":0.15228921,"teacher_disagreement_score":0.9051917,"about_ca_system_score_codex":0.0025051045,"about_ca_system_score_gemma":0.007515381,"threshold_uncertainty_score":0.18851286},"labels":[],"label_agreement":null},{"id":"W2996731041","doi":"10.3138/cjpe.68004","title":"Revisiting Contribution Analysis","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Set (abstract data type); Epistemology; Positive economics; Causal analysis; Narrative; Key (lock); Sociology; Economics; Computer science; Econometrics; Philosophy","score_opus":0.27443773986693065,"score_gpt":0.5383881020311411,"score_spread":0.2639503621642104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996731041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01758275,0.007140194,0.7351795,0.06402627,0.005026862,0.0009416489,0.00058847474,0.00061255804,0.16890174],"genre_scores_gemma":[0.656426,0.0045012864,0.29821563,0.011041092,0.0029529112,0.0020551886,0.0006152268,0.0008889288,0.0233037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8375855,0.113888845,0.0064261467,0.011390014,0.02726659,0.0034429587],"domain_scores_gemma":[0.6595421,0.25274605,0.011506725,0.026874766,0.046946753,0.0023836598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14479312,0.0023207567,0.0018681143,0.0115852235,0.008483631,0.015471382,0.0074099763,0.005425608,0.019210324],"category_scores_gemma":[0.25244293,0.0010140443,0.0032703078,0.0095270155,0.027313624,0.031161426,0.016385986,0.010546149,0.0031451224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047798476,0.00003466893,0.0014694036,0.0006378937,0.00010788484,0.00013207253,0.008657114,0.0009049669,0.0000830348,0.932396,0.00846075,0.047068484],"study_design_scores_gemma":[0.000029600145,0.000030099904,0.0007217259,0.0015215084,0.000075370815,0.0001285475,0.0040650517,0.004394604,0.00046618178,0.90526634,0.08326541,0.00003554532],"about_ca_topic_score_codex":0.0054248925,"about_ca_topic_score_gemma":0.0040994775,"teacher_disagreement_score":0.14479312,"about_ca_system_score_codex":0.0136642745,"about_ca_system_score_gemma":0.015644971,"threshold_uncertainty_score":0.7657484},"labels":[],"label_agreement":null},{"id":"W300774755","doi":"10.3138/cjpe.23.007","title":"Bureaucratic Competence as an Essential Factor in Cross-Cultural/Multicultural Program Evaluations","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Bureaucracy; Multiculturalism; Competence (human resources); Equity (law); Affirmative action; Public relations; Social psychology; Political science; Cultural diversity; Sociology; Psychology; Law","score_opus":0.3771933823224479,"score_gpt":0.5862658034914479,"score_spread":0.20907242116899993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W300774755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7548477,0.0022420932,0.05866294,0.036044214,0.00054761005,0.0011982658,0.000057404854,0.00021273136,0.1461871],"genre_scores_gemma":[0.99446315,0.0000902919,0.004017712,0.00066026463,0.000056721125,0.00018457793,0.000006824269,0.00002514751,0.000495398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.66454023,0.24599332,0.02558334,0.0062096147,0.047624234,0.010049225],"domain_scores_gemma":[0.35758212,0.48585954,0.046525,0.034765653,0.05566453,0.019603258],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31234393,0.00042237417,0.00087207544,0.0037413163,0.008279907,0.016889304,0.0015090766,0.002288623,0.0033980024],"category_scores_gemma":[0.42569923,0.0011264167,0.0006648359,0.0018777425,0.020445775,0.0092645725,0.012390213,0.0060091186,0.0002691346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001153,0.0019203012,0.24739315,0.0021209405,0.0006439709,0.0010004974,0.11601218,0.0050703273,0.0026513247,0.3363138,0.007808003,0.27791247],"study_design_scores_gemma":[0.0006110595,0.00223242,0.41298893,0.007263016,0.0007667664,0.0018990678,0.113297835,0.025162632,0.01633442,0.37177113,0.046731487,0.00094131916],"about_ca_topic_score_codex":0.0046867933,"about_ca_topic_score_gemma":0.008791545,"teacher_disagreement_score":0.68765604,"about_ca_system_score_codex":0.0103468755,"about_ca_system_score_gemma":0.02674944,"threshold_uncertainty_score":0.8480024},"labels":[],"label_agreement":null},{"id":"W3009054679","doi":"10.3138/cjpe.69006","title":"Section 35 Legal Framework: Implications for Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Government (linguistics); General partnership; Duty; Political science; Public administration; Indigenous rights; Law; Work (physics); Sociology; Human rights; Engineering","score_opus":0.5534072977341611,"score_gpt":0.5909154903539823,"score_spread":0.03750819261982119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009054679","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031626958,0.011459393,0.027447805,0.69588643,0.006052669,0.0026807555,0.0020806736,0.0004607755,0.2507689],"genre_scores_gemma":[0.24979301,0.010510151,0.1280932,0.53166175,0.0062178713,0.011895551,0.0023315304,0.00050246954,0.058994547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.6539452,0.19882739,0.02238671,0.011613856,0.092505425,0.02072148],"domain_scores_gemma":[0.38295445,0.372275,0.014236968,0.02049093,0.19647118,0.013571532],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.32731825,0.0015966857,0.0030857155,0.0062563014,0.01677251,0.040499263,0.012581495,0.029150708,0.015798716],"category_scores_gemma":[0.4869625,0.0015898811,0.0025575673,0.009454849,0.036609456,0.019065185,0.010735077,0.021050392,0.003457203],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008806819,0.00008717492,0.00088537927,0.00064203027,0.000042181615,0.00010437561,0.0022930643,0.0009539762,0.00010303641,0.85032016,0.12172062,0.022759905],"study_design_scores_gemma":[0.00039359447,0.00015844313,0.0030031155,0.011253022,0.00022098966,0.00015321113,0.0056808726,0.0036214092,0.0005508632,0.47494757,0.49971834,0.00029854212],"about_ca_topic_score_codex":0.69176745,"about_ca_topic_score_gemma":0.5556845,"teacher_disagreement_score":0.32731825,"about_ca_system_score_codex":0.12947348,"about_ca_system_score_gemma":0.45480168,"threshold_uncertainty_score":0.9394002},"labels":[],"label_agreement":null},{"id":"W3009478627","doi":"10.3138/cjpe.68831","title":"Indigenous Health Service Evaluation: Principles and Guidelines from a Provincial “Three Ribbon” Expert Panel","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Public Health Ontario","funders":"","keywords":"Indigenous; Service (business); Public relations; Sociology; Set (abstract data type); Political science; Business; Computer science; Marketing","score_opus":0.7302785118808507,"score_gpt":0.5552141874564791,"score_spread":0.1750643244243716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009478627","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013455401,0.028508963,0.26480946,0.46259108,0.008016544,0.14353037,0.0020603715,0.0012391785,0.07578862],"genre_scores_gemma":[0.08618327,0.012898361,0.7590334,0.04361481,0.0013278266,0.0786226,0.0014052585,0.00056100317,0.016353449],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.5796834,0.29412118,0.06524356,0.0065054893,0.046086743,0.008359685],"domain_scores_gemma":[0.54103047,0.16337645,0.019123642,0.02612995,0.22950502,0.02083444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5289559,0.0014303427,0.002272294,0.0077467277,0.010575826,0.011641127,0.01150194,0.012393469,0.0037396369],"category_scores_gemma":[0.34538493,0.0027291246,0.0039326698,0.008066515,0.011709327,0.0053304024,0.013928066,0.014596427,0.0022856037],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066850136,0.0009963862,0.0066928444,0.018347992,0.00046874318,0.0023992578,0.14654446,0.005635356,0.0053576306,0.06988867,0.3969636,0.3460365],"study_design_scores_gemma":[0.0006693575,0.00044245186,0.010444967,0.050498854,0.00041018176,0.001171647,0.028371919,0.00469773,0.0022403677,0.05198929,0.8484705,0.00059268455],"about_ca_topic_score_codex":0.09410243,"about_ca_topic_score_gemma":0.20678759,"teacher_disagreement_score":0.96679145,"about_ca_system_score_codex":0.03320853,"about_ca_system_score_gemma":0.24135211,"threshold_uncertainty_score":0.5808813},"labels":[],"label_agreement":null},{"id":"W3009649701","doi":"10.3138/cjpe.68866","title":"Identifying Key Epistemological Challenges Evaluating in Indigenous Contexts: Achieving <i>Bimaadiziwin</i> through Youth Futures","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Futures contract; Sociology; General partnership; Privilege (computing); Reciprocity (cultural anthropology); Field (mathematics); Agency (philosophy); Accountability; Government (linguistics); Work (physics); Public relations; Epistemology; Political science; Social science; Business; Law","score_opus":0.6425698594806223,"score_gpt":0.5452973114993448,"score_spread":0.09727254798127749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009649701","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27495128,0.009917412,0.08970822,0.18176313,0.0006279667,0.0009832564,0.0001787791,0.00018608186,0.44168386],"genre_scores_gemma":[0.9616936,0.0026876368,0.027771423,0.0019099175,0.00006357448,0.00043411765,0.00003405302,0.00005486895,0.0053506726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.930696,0.051415093,0.001972066,0.0018550837,0.010272981,0.0037887474],"domain_scores_gemma":[0.92795867,0.045392696,0.0035688377,0.0041687028,0.015962154,0.0029490276],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10208574,0.0005428608,0.00083732174,0.0038214112,0.019396054,0.027575461,0.0034266228,0.003058833,0.004886982],"category_scores_gemma":[0.066242,0.0005460992,0.00050013966,0.0047092303,0.042612065,0.015889412,0.015899645,0.0061131753,0.0004113731],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059578477,0.00013330553,0.005170624,0.0008842554,0.00003247004,0.0004478027,0.22904152,0.0008338106,0.00046778825,0.6724461,0.004389681,0.086093135],"study_design_scores_gemma":[0.00001984474,0.00008645115,0.004430189,0.0028517637,0.00006085755,0.00023088121,0.64238995,0.0022570712,0.0021365436,0.23832555,0.10712399,0.00008686934],"about_ca_topic_score_codex":0.114354216,"about_ca_topic_score_gemma":0.14562498,"teacher_disagreement_score":0.96264976,"about_ca_system_score_codex":0.037350222,"about_ca_system_score_gemma":0.062417317,"threshold_uncertainty_score":0.5398874},"labels":[],"label_agreement":null},{"id":"W3009664453","doi":"10.3138/cjpe.69095","title":"Reflections on Evaluating in Indigenous Contexts: Looking to the Future","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Sociology; Psychology; Environmental ethics; Political science; Philosophy; Ecology; Biology","score_opus":0.4296188597017498,"score_gpt":0.5859342152437196,"score_spread":0.1563153555419698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009664453","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001911011,0.00905234,0.0011310078,0.9740461,0.0022397041,0.00004022901,0.000017829872,0.000015136591,0.011546748],"genre_scores_gemma":[0.36042285,0.07460238,0.02671835,0.50305605,0.006367562,0.0005374898,0.00009356148,0.00020450885,0.027997212],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9156445,0.05583114,0.003164805,0.0020897086,0.015766693,0.0075031905],"domain_scores_gemma":[0.73325557,0.1742046,0.0039863368,0.0060007325,0.06296996,0.019582829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12370193,0.00062784355,0.0014219419,0.0017199755,0.0117727155,0.018620348,0.006228809,0.013345608,0.013398092],"category_scores_gemma":[0.1952107,0.00036435467,0.0012587113,0.0027777413,0.03962814,0.031109521,0.008504401,0.026281927,0.0010980567],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014832494,0.00027854738,0.0030021882,0.0031429224,0.00005386804,0.00085746153,0.10093989,0.0009002825,0.00072709034,0.4087519,0.30377093,0.17742655],"study_design_scores_gemma":[0.00003243426,0.00018919056,0.0046533886,0.0097068865,0.00007911373,0.0004287877,0.25954646,0.00050136267,0.00088144495,0.13448995,0.5893196,0.00017137789],"about_ca_topic_score_codex":0.24900801,"about_ca_topic_score_gemma":0.32050332,"teacher_disagreement_score":0.24900801,"about_ca_system_score_codex":0.033865105,"about_ca_system_score_gemma":0.10442389,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3009813686","doi":"10.3138/cjpe.68857","title":"Reflections on Being a Learner: The Value of Relationship-based Community Evaluations in Indigenous Communities","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Transformative learning; Indigenous; General partnership; Sociology; Value (mathematics); Power (physics); Work (physics); Process (computing); Traditional knowledge; Epistemology; Pedagogy; Political science; Computer science; Law","score_opus":0.6524773854460769,"score_gpt":0.5870706981648242,"score_spread":0.06540668728125276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009813686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4430474,0.0042661605,0.011266781,0.30024013,0.0010845192,0.0005238679,0.000056687688,0.00008659178,0.23942788],"genre_scores_gemma":[0.9870113,0.0009920244,0.001961495,0.003853421,0.00010934223,0.00013685047,0.0000071809286,0.000045135985,0.0058832285],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8783843,0.10812015,0.00094219745,0.0013162399,0.006887675,0.0043493453],"domain_scores_gemma":[0.87143016,0.104390755,0.0025124196,0.003044689,0.012594187,0.0060277777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09658711,0.0005791158,0.00073829346,0.0019799683,0.024906162,0.01829397,0.003229826,0.00476388,0.005025359],"category_scores_gemma":[0.095519744,0.00039703742,0.00048303732,0.0014279826,0.052545007,0.01531898,0.018799588,0.013334794,0.00042696728],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027509162,0.00008799708,0.00096390786,0.00011050904,0.0000063919224,0.0004462515,0.95020604,0.00009934073,0.00014185623,0.029482579,0.0038121587,0.014615421],"study_design_scores_gemma":[0.000009462916,0.000045989156,0.0007786971,0.00040051318,0.000008779612,0.00015584928,0.9455543,0.00020444664,0.00034622804,0.008415866,0.04405351,0.000026408143],"about_ca_topic_score_codex":0.081714384,"about_ca_topic_score_gemma":0.13409063,"teacher_disagreement_score":0.09658711,"about_ca_system_score_codex":0.027286336,"about_ca_system_score_gemma":0.027931252,"threshold_uncertainty_score":0.5108075},"labels":[],"label_agreement":null},{"id":"W3010143613","doi":"10.3138/cjpe.68914","title":"EvalIndigenous Origin Story: Effective Practices within Local Contexts to Inform the Field and Practice of Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Politics; Sovereignty; Field (mathematics); Traditional knowledge; Work (physics); Political science; Sociology; Environmental ethics; Law; Ecology; Engineering","score_opus":0.32734472912731394,"score_gpt":0.5695930311312456,"score_spread":0.24224830200393166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010143613","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04159581,0.020113116,0.008943391,0.72991306,0.0026950897,0.0001957744,0.00013832805,0.00011392074,0.19629164],"genre_scores_gemma":[0.88914007,0.00851557,0.012323483,0.057809424,0.00060585834,0.00038890573,0.00007587033,0.00020497458,0.030935874],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9723139,0.021781452,0.00047927472,0.0011867691,0.0027508456,0.0014877192],"domain_scores_gemma":[0.95901346,0.032627128,0.00081459555,0.0018925378,0.0034013188,0.0022509866],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02999107,0.00055987237,0.00055193284,0.002698928,0.016498378,0.017731547,0.002199844,0.005628301,0.0077616125],"category_scores_gemma":[0.02999724,0.00034825385,0.00037051356,0.0024242937,0.041762527,0.016753271,0.0132099055,0.0117278155,0.0005655303],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006040544,0.000097623735,0.002011209,0.00046084754,0.000009863362,0.00072447106,0.23799951,0.0001898831,0.0002884595,0.6003434,0.10700435,0.050809927],"study_design_scores_gemma":[0.000014878153,0.000052528867,0.0017165642,0.0020370693,0.0000095482155,0.00045537765,0.20636395,0.0003540885,0.00065964827,0.06825422,0.72004306,0.000039146707],"about_ca_topic_score_codex":0.021908415,"about_ca_topic_score_gemma":0.05215341,"teacher_disagreement_score":0.978989,"about_ca_system_score_codex":0.021010995,"about_ca_system_score_gemma":0.015434533,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3010351954","doi":"10.3138/cjpe.68837","title":"Indigenous Evaluation in the Northwest Territories: Opportunities and Challenges","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Service (business); Service delivery framework; Traditional knowledge; Service provider; Culturally appropriate; Economic growth; Political science; Business; Environmental planning; Geography; Medicine; Marketing; Economics; Gerontology","score_opus":0.6396488333319937,"score_gpt":0.4982009790427576,"score_spread":0.14144785428923612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010351954","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067420945,0.124645494,0.0149644185,0.6930933,0.00259934,0.001529652,0.0004868367,0.00022476765,0.09503525],"genre_scores_gemma":[0.7783988,0.10513299,0.05232215,0.044501543,0.0019202598,0.0033314107,0.00048079164,0.00016606694,0.013745969],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7267481,0.21425739,0.011919217,0.0035631105,0.03148368,0.012028521],"domain_scores_gemma":[0.49954343,0.33947116,0.017278144,0.015306985,0.09681312,0.031587146],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29353416,0.0006180945,0.00245966,0.0036708203,0.01118297,0.016155427,0.0058833105,0.0034588135,0.0053822924],"category_scores_gemma":[0.20842648,0.00064109947,0.0010791323,0.005930457,0.012937761,0.009460174,0.014708478,0.0068664406,0.00054588687],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005524533,0.0011782668,0.04901986,0.011973751,0.00040164165,0.0010744855,0.055597812,0.0030886023,0.0004363577,0.11421446,0.060125027,0.7023372],"study_design_scores_gemma":[0.0003311783,0.0010176955,0.1394254,0.059049033,0.0003489597,0.0012201329,0.2884261,0.006910954,0.0012793262,0.11768866,0.38370916,0.0005934114],"about_ca_topic_score_codex":0.5125111,"about_ca_topic_score_gemma":0.59746957,"teacher_disagreement_score":0.9487685,"about_ca_system_score_codex":0.051231496,"about_ca_system_score_gemma":0.2798584,"threshold_uncertainty_score":0.9807197},"labels":[],"label_agreement":null},{"id":"W3010495354","doi":"10.3138/cjpe.69010","title":"Evaluation in Indigenous Contexts: An Introduction to Practice","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Sociology; Psychology; Engineering ethics; Engineering; Ecology","score_opus":0.34926966146980354,"score_gpt":0.5540992470149855,"score_spread":0.20482958554518194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010495354","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022789733,0.60669005,0.10834169,0.14033113,0.025036514,0.001128229,0.00037964474,0.0007569812,0.11505676],"genre_scores_gemma":[0.0417983,0.6666888,0.17962131,0.028120488,0.018018499,0.0022410105,0.00032742854,0.00065553037,0.06252865],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9866349,0.0074644256,0.0018327304,0.00060399115,0.00308629,0.00037766303],"domain_scores_gemma":[0.9767496,0.01560728,0.0007890298,0.0009901096,0.004656055,0.0012078781],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025158672,0.0010649236,0.0014933733,0.0054693497,0.0025913033,0.0057671787,0.0019499172,0.0041490267,0.010174488],"category_scores_gemma":[0.029888202,0.00080201245,0.0009983567,0.0056395847,0.008870068,0.006787225,0.004550004,0.005905524,0.004060348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057208672,0.00023934033,0.0006762819,0.008280532,0.000040044994,0.0004788119,0.008600338,0.0010423816,0.0011478561,0.10089006,0.25946382,0.6190833],"study_design_scores_gemma":[0.000008187027,0.00010560124,0.0021850092,0.0099609075,0.000012100702,0.00094479375,0.0028911629,0.00032017194,0.00025432126,0.07293527,0.9103207,0.00006173397],"about_ca_topic_score_codex":0.008556474,"about_ca_topic_score_gemma":0.019045563,"teacher_disagreement_score":0.97484136,"about_ca_system_score_codex":0.007934435,"about_ca_system_score_gemma":0.0117728105,"threshold_uncertainty_score":0.13305336},"labels":[],"label_agreement":null},{"id":"W3010543578","doi":"10.3138/cjpe.6844","title":"Reconciliaton and Energy Democracy","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Democracy; Equity (law); Energy security; Nationalism; Sustainable development; Political science; Economic growth; Renewable energy; Economics; Politics; Law; Engineering","score_opus":0.08948314794921465,"score_gpt":0.3672465896127884,"score_spread":0.27776344166357375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010543578","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26952326,0.005331766,0.015061306,0.1139729,0.00062704855,0.0012519861,0.00044687118,0.0002540103,0.5935309],"genre_scores_gemma":[0.9748902,0.0011953679,0.0060265777,0.0057344697,0.00003777819,0.0003162194,0.000095155316,0.00004948726,0.0116548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.91099423,0.06219409,0.0011421615,0.001454985,0.014632473,0.009581999],"domain_scores_gemma":[0.97493356,0.009515784,0.0021141877,0.003060444,0.0071620345,0.0032140051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044296913,0.00036200084,0.00055667915,0.0019322516,0.009058962,0.008509971,0.001422279,0.0019381248,0.0064538424],"category_scores_gemma":[0.051419225,0.00017685085,0.00057073194,0.0033788998,0.015620096,0.0052868025,0.01522033,0.003635871,0.0003427459],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019760642,0.00037824697,0.01099644,0.0006333448,0.00009750096,0.00009749761,0.029818693,0.0023808498,0.0004171661,0.6566476,0.024295038,0.27404004],"study_design_scores_gemma":[0.00028719034,0.0008259462,0.03427368,0.002970796,0.0002552412,0.00015366473,0.10358128,0.0022411,0.0040264195,0.32599416,0.5252579,0.00013270284],"about_ca_topic_score_codex":0.21573503,"about_ca_topic_score_gemma":0.36825362,"teacher_disagreement_score":0.784265,"about_ca_system_score_codex":0.03718628,"about_ca_system_score_gemma":0.12179955,"threshold_uncertainty_score":0.4289586},"labels":[],"label_agreement":null},{"id":"W301099006","doi":"","title":"Impacts of the Canadian Evaluation Society's Evaluation Competitions for Students: Guest Editors' Introduction.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Psychology; Sociology","score_opus":0.24853880815214335,"score_gpt":0.5377223463397195,"score_spread":0.28918353818757614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W301099006","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039370246,0.11523758,0.0016319882,0.38412642,0.4358829,0.0002933321,0.0024096037,0.00044202068,0.056039102],"genre_scores_gemma":[0.102122374,0.18934079,0.008903717,0.15591308,0.22963472,0.00046938713,0.0040932475,0.00077900675,0.30874366],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9921961,0.0007658772,0.00033845977,0.00027477986,0.005698498,0.00072630733],"domain_scores_gemma":[0.9681245,0.0042392835,0.0008661496,0.000283578,0.022514492,0.003971941],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009822275,0.0011468016,0.00070388353,0.0032554963,0.0031902716,0.0052388515,0.0022628284,0.0034697407,0.016344275],"category_scores_gemma":[0.025274375,0.00036666784,0.000999834,0.0032025075,0.0015947758,0.0020410584,0.0018251558,0.0044419775,0.002941586],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002606457,0.00001974485,0.00032470646,0.00024174567,0.000005853323,0.00004835494,0.000076405275,0.00008894386,0.00008202008,0.0009694896,0.97517174,0.02294498],"study_design_scores_gemma":[0.000015137421,0.00004395209,0.008051286,0.00044223157,0.000023224005,0.0000792342,0.00067261513,0.00015791586,0.00025643667,0.0012809056,0.9889176,0.000059384434],"about_ca_topic_score_codex":0.23086652,"about_ca_topic_score_gemma":0.5712657,"teacher_disagreement_score":0.99017775,"about_ca_system_score_codex":0.012229939,"about_ca_system_score_gemma":0.023439856,"threshold_uncertainty_score":0.45904547},"labels":[],"label_agreement":null},{"id":"W302460285","doi":"10.3138/cjpe.0014.007","title":"Enhancing Managers’ Evaluation Capacity: A Case Study from Ontario Public Health","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Community Health and Development","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Empowerment; Program evaluation; Capacity building; Business; Knowledge management; Process management; Stock (firearms); Engineering management; Public relations; Medical education; Computer science; Engineering; Medicine; Political science; Economic growth; Economics","score_opus":0.6101207119649323,"score_gpt":0.5007025240941987,"score_spread":0.10941818787073365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W302460285","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739618,0.00035580536,0.00072449085,0.009996254,0.000043934735,0.00045031126,0.000041603314,0.000035364148,0.014390528],"genre_scores_gemma":[0.9910143,0.00042564573,0.0012421719,0.0010252604,0.000026748183,0.00018648423,0.000027099615,0.00001792708,0.006034333],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98948014,0.0053718966,0.0002811764,0.00029256544,0.0015835393,0.002990632],"domain_scores_gemma":[0.984248,0.0055928905,0.001304745,0.00042659225,0.003284722,0.005143089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011517259,0.0005084116,0.00033873378,0.0010874755,0.019617084,0.0037165512,0.0016706,0.0022839035,0.004651329],"category_scores_gemma":[0.020013563,0.00054342614,0.00032893248,0.0013989807,0.004292969,0.0016007221,0.0033022389,0.0028506618,0.00039557007],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029456549,0.0029355285,0.07397753,0.00036121547,0.00003833989,0.015867077,0.8239469,0.0004647295,0.0018153999,0.0044699376,0.01675754,0.059071258],"study_design_scores_gemma":[0.00012890605,0.0009899328,0.060104705,0.0004180483,0.00004967354,0.0020273684,0.8580921,0.0009868523,0.0015791572,0.0007620402,0.0747867,0.00007459969],"about_ca_topic_score_codex":0.46539867,"about_ca_topic_score_gemma":0.7736695,"teacher_disagreement_score":0.53460133,"about_ca_system_score_codex":0.04731685,"about_ca_system_score_gemma":0.04924441,"threshold_uncertainty_score":0.9253795},"labels":[],"label_agreement":null},{"id":"W3028612984","doi":"10.3138/cjpe.61841","title":"Predicting Credentialed Evaluator Status: Characteristics, Comparisons, and Implications for the CE Program","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria; University of Saskatchewan","funders":"","keywords":"Scope (computer science); Sustainability; Order (exchange); Accounting; Political science; Actuarial science; Sociology; Public economics; Business; Economics; Computer science; Finance","score_opus":0.4209077424068388,"score_gpt":0.5372251137668627,"score_spread":0.11631737136002385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028612984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942211,0.00014250523,0.00055366004,0.0006568501,0.000022451903,0.0001223526,0.00076595636,0.000016020116,0.0034992087],"genre_scores_gemma":[0.9983076,0.000054983804,0.00042074162,0.000052571595,0.000009536127,0.00005914843,0.000415992,0.0000048738257,0.00067452335],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941134,0.002699771,0.0006296678,0.0003555001,0.0013442964,0.00085739157],"domain_scores_gemma":[0.93940294,0.024062224,0.009888734,0.002112407,0.014897357,0.009636346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015157925,0.00013352209,0.00029685858,0.003923159,0.0008725309,0.002132081,0.0007633036,0.0004084722,0.0051101646],"category_scores_gemma":[0.080587775,0.00010257795,0.00025057708,0.0031211206,0.00061908824,0.0013228535,0.0015076172,0.00063263316,0.0008811531],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016650841,0.00016896722,0.9826753,0.000024774934,0.00001000641,0.000037965216,0.0008518078,0.00014857604,0.000082782455,0.00018366563,0.0010037951,0.014645909],"study_design_scores_gemma":[0.0000139410995,0.00019013301,0.9885048,0.000059385016,0.000010992071,0.00010389923,0.0060708304,0.0015419711,0.00030549537,0.00021456087,0.0029734278,0.00001052508],"about_ca_topic_score_codex":0.011177678,"about_ca_topic_score_gemma":0.015251521,"teacher_disagreement_score":0.015157925,"about_ca_system_score_codex":0.0016300242,"about_ca_system_score_gemma":0.0027951954,"threshold_uncertainty_score":0.08016372},"labels":[],"label_agreement":null},{"id":"W3029887321","doi":"10.3138/cjpe.61270","title":"A Rapid Review of Evaluation Capacity-Building Strategies for Chronic Disease Prevention","year":2020,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Impact; University of Waterloo","funders":"","keywords":"CLARITY; Context (archaeology); Capacity building; Grey literature; Medicine; Political science; Public relations; Psychology; Business; MEDLINE; Biology","score_opus":0.6926985361281605,"score_gpt":0.6014460517410005,"score_spread":0.09125248438715994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029887321","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023713797,0.99214524,0.0010888567,0.0029337222,0.000671099,0.00087415654,0.00025610742,0.000028056993,0.0017656394],"genre_scores_gemma":[0.0034813245,0.9884588,0.0050692423,0.001192153,0.0001880472,0.0010761729,0.00018220145,0.000011664679,0.00034044858],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9719821,0.012507734,0.0068460004,0.0008629603,0.0071773287,0.00062386587],"domain_scores_gemma":[0.87069386,0.083914064,0.012068981,0.0023646578,0.029501582,0.001456786],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04393735,0.0017841425,0.0045871288,0.023611583,0.0011407416,0.005119188,0.002594732,0.0023957128,0.007614645],"category_scores_gemma":[0.12336361,0.0012322459,0.00586329,0.017484473,0.0012823329,0.00581622,0.003146452,0.002760975,0.0011562934],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007953402,0.000042242737,0.0002636465,0.5160381,0.000977884,0.00008009875,0.00045276407,0.0002421309,0.00022380105,0.0038588364,0.017757775,0.45998317],"study_design_scores_gemma":[0.000053758133,0.00009639061,0.0011122862,0.8364339,0.002395172,0.0001294096,0.00033553364,0.00010796812,0.00018682226,0.0013311504,0.15778352,0.000033993252],"about_ca_topic_score_codex":0.012189538,"about_ca_topic_score_gemma":0.036994293,"teacher_disagreement_score":0.9560627,"about_ca_system_score_codex":0.011936412,"about_ca_system_score_gemma":0.04491284,"threshold_uncertainty_score":0.23236573},"labels":[],"label_agreement":null},{"id":"W3030401821","doi":"10.3138/cjpe.62847","title":"Évaluation des effets dans le domaine de l’éducation à la sexualité au primaire : Exemple tiré d’une évaluation d’un programme de prévention de la sexualisation précoce","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Adolescent Sexual and Reproductive Health","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Human sexuality; Psychology; Health promotion; Humanities; Sociology; Medicine; Nursing; Public health; Art; Gender studies","score_opus":0.29657303710125227,"score_gpt":0.47613910953757954,"score_spread":0.17956607243632727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030401821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9560209,0.0037495603,0.002527568,0.0019274403,0.00023080091,0.017434357,0.0005101729,0.00006514057,0.017534122],"genre_scores_gemma":[0.9732376,0.0032252963,0.010511971,0.000714647,0.0001044442,0.007320288,0.00028078744,0.000015166158,0.004589862],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98342645,0.011678932,0.0008618821,0.00068117934,0.0024067375,0.00094485073],"domain_scores_gemma":[0.9784272,0.012919968,0.0016149029,0.00079429266,0.004561605,0.0016821167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0163415,0.00076261105,0.0009997693,0.000657273,0.0017660351,0.0011504665,0.0008606349,0.0016423897,0.0047678268],"category_scores_gemma":[0.021296702,0.00036471052,0.0014465648,0.0008646301,0.001207088,0.0007210878,0.0011460017,0.0017536108,0.0004815914],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.042465243,0.11946597,0.034481514,0.01356224,0.0030327074,0.000489883,0.009453641,0.004630434,0.009372753,0.002078192,0.0030128707,0.7579546],"study_design_scores_gemma":[0.033099327,0.5031455,0.3766713,0.007712208,0.005285649,0.0002823323,0.00652106,0.0046121576,0.030474665,0.0017074028,0.03031595,0.00017252752],"about_ca_topic_score_codex":0.084891744,"about_ca_topic_score_gemma":0.12483166,"teacher_disagreement_score":0.084891744,"about_ca_system_score_codex":0.0063300915,"about_ca_system_score_gemma":0.010776578,"threshold_uncertainty_score":0.16879523},"labels":[],"label_agreement":null},{"id":"W3031036335","doi":"10.3138/cjpe.61624","title":"Evaluation in the Provinces and Territories: A Cross-Canada Snapshot and Call to Action","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island; University of Victoria; Université Laval; Dalhousie University","funders":"","keywords":"Snapshot (computer storage); Government (linguistics); Public administration; Political science; State (computer science); Action (physics); Regional science; Public relations; Geography; Computer science","score_opus":0.4273514882657697,"score_gpt":0.5421958438593792,"score_spread":0.11484435559360956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031036335","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28145885,0.17891322,0.005042935,0.44265252,0.0021471914,0.0024918478,0.007773884,0.00042206963,0.07909746],"genre_scores_gemma":[0.8865341,0.05943068,0.018902201,0.020819657,0.00014127106,0.0006580315,0.0027252145,0.00010048504,0.01068836],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.94900024,0.016010225,0.0036981052,0.0017202183,0.016321786,0.013249444],"domain_scores_gemma":[0.7930371,0.04012758,0.0061869137,0.004893066,0.12705635,0.028698994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056350593,0.0005378946,0.001121044,0.005645671,0.014256843,0.013760073,0.0031850121,0.0025433335,0.0029507116],"category_scores_gemma":[0.059045725,0.0007514249,0.0009912084,0.012759445,0.0054170126,0.0042031896,0.0066320687,0.0041320603,0.00023876995],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0010237759,0.000521581,0.20824118,0.011758011,0.0006445058,0.0020748244,0.05047722,0.0029602884,0.0023646771,0.041549467,0.15197587,0.52640855],"study_design_scores_gemma":[0.00009964994,0.0003077618,0.50157344,0.012451907,0.00037558872,0.00062236266,0.13202606,0.0018004085,0.0015437412,0.0033327593,0.34551364,0.00035265583],"about_ca_topic_score_codex":0.990824,"about_ca_topic_score_gemma":0.9962059,"teacher_disagreement_score":0.9436494,"about_ca_system_score_codex":0.29250228,"about_ca_system_score_gemma":0.586039,"threshold_uncertainty_score":0.82059705},"labels":[],"label_agreement":null},{"id":"W3031398259","doi":"10.3138/jpe.68217","title":"Sheila B. Robinson and Kimberly Firth Leonard. (2019). Designing Quality Survey Questions. Thousand Oaks, CA: SAGE.","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Firth; SAGE; Quality (philosophy); Sociology; Psychology; Philosophy; Oceanography; Epistemology; Geology; Physics","score_opus":0.34420288166074114,"score_gpt":0.4873499817116084,"score_spread":0.14314710005086728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031398259","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008362423,0.39802486,0.10294521,0.38227034,0.019671045,0.002695343,0.013106345,0.0022033202,0.07072109],"genre_scores_gemma":[0.076506756,0.5133617,0.2264506,0.060353182,0.003885848,0.006053599,0.009113708,0.0013586893,0.10291596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99135816,0.004424727,0.0008163847,0.00041294767,0.002834038,0.00015369864],"domain_scores_gemma":[0.93284786,0.03783193,0.0029899974,0.0014034888,0.023118122,0.0018086922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027558997,0.001036696,0.00086590427,0.0052288836,0.0019696972,0.002751996,0.001433438,0.0017885657,0.028616289],"category_scores_gemma":[0.105057135,0.0016677037,0.0007649296,0.005381655,0.0014641379,0.003971219,0.0013222144,0.005262804,0.020133045],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006034028,0.000041705196,0.0034022254,0.0010946129,0.000022040123,0.00004398972,0.0012161628,0.0000712356,0.00020864692,0.0020092435,0.6799476,0.31188226],"study_design_scores_gemma":[0.00012287314,0.00019691215,0.027408248,0.01653707,0.00021005735,0.00030565524,0.004277869,0.0005521643,0.00097157044,0.01280621,0.93643916,0.00017216786],"about_ca_topic_score_codex":0.046254802,"about_ca_topic_score_gemma":0.09566527,"teacher_disagreement_score":0.046254802,"about_ca_system_score_codex":0.0015109702,"about_ca_system_score_gemma":0.010050002,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W3031535673","doi":"10.3138/cjpe.61660","title":"A Transdisciplinary Model of Program Outcomes for Enhanced Evaluation Practice","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Taxonomy (biology); Management science; Context (archaeology); Psychology; Program evaluation; Cognition; Computer science; Knowledge management; Process management; Political science; Ecology; Business; Engineering","score_opus":0.6071453782410605,"score_gpt":0.6059684492511166,"score_spread":0.0011769289899439261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031535673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012888216,0.0008628981,0.8483451,0.014416969,0.0001807155,0.0014368139,0.0001739408,0.00024945065,0.121445775],"genre_scores_gemma":[0.47308373,0.00073493744,0.51608396,0.0010265873,0.00009055904,0.0041541695,0.00017921031,0.00010711786,0.004539663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9206824,0.06669853,0.0026917774,0.002620698,0.0061764657,0.0011299886],"domain_scores_gemma":[0.91499764,0.059481498,0.0033040114,0.007251381,0.012749973,0.0022155433],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07079374,0.0012440366,0.00084898993,0.0070467023,0.0025971234,0.010180949,0.002922073,0.0032638456,0.010807172],"category_scores_gemma":[0.09594746,0.0005972565,0.0018095537,0.0057561547,0.012920691,0.016338121,0.006773606,0.0043194103,0.0011860856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046537683,0.00011264188,0.0015390367,0.00029794243,0.000037618094,0.000056446628,0.003972187,0.0029269455,0.00009462223,0.9563186,0.00085805013,0.03373942],"study_design_scores_gemma":[0.00011353076,0.00025609718,0.0018572599,0.0010965291,0.00010461268,0.00016491271,0.002988809,0.028980758,0.00039157673,0.9416423,0.02236622,0.000037519356],"about_ca_topic_score_codex":0.003707984,"about_ca_topic_score_gemma":0.0037012573,"teacher_disagreement_score":0.92920625,"about_ca_system_score_codex":0.010854882,"about_ca_system_score_gemma":0.012981863,"threshold_uncertainty_score":0.37439758},"labels":[],"label_agreement":null},{"id":"W3031759560","doi":"10.3138/cjpe.69030","title":"Kylie Hutchinson, ed. (2018). <i>Evaluation Failures: 22 Tales of Mistakes Made and Lessons Learned</i> .","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Innovations in Medical Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology","score_opus":0.16149339113724046,"score_gpt":0.41954114501483364,"score_spread":0.25804775387759316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031759560","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028425115,0.3252078,0.002578029,0.62575865,0.030275857,0.000042014846,0.0002917838,0.00036167479,0.015199974],"genre_scores_gemma":[0.012029114,0.7318454,0.0077905487,0.15572035,0.024072278,0.00019788617,0.00065819226,0.00077505497,0.06691124],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.989842,0.0026875825,0.0012037507,0.0007437661,0.0050628404,0.0004601513],"domain_scores_gemma":[0.93214345,0.026358627,0.0046407133,0.0015633927,0.028483177,0.00681062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027083691,0.0013134949,0.00087416737,0.005087219,0.003060753,0.008452798,0.002757339,0.005144746,0.020481495],"category_scores_gemma":[0.09793482,0.0010045182,0.00059197034,0.0037198893,0.005266787,0.009640306,0.0052844235,0.010916976,0.014764855],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010695795,0.00000424106,0.00038455284,0.00029012738,0.0000048735506,0.000039790364,0.00046420467,0.000026249432,0.00002311378,0.0012091569,0.92359173,0.07395127],"study_design_scores_gemma":[0.000014436456,0.000014180551,0.0019930927,0.006317027,0.00002229404,0.0003952497,0.0020202787,0.00008448853,0.00015908637,0.006984657,0.9819479,0.00004723872],"about_ca_topic_score_codex":0.043085687,"about_ca_topic_score_gemma":0.102406554,"teacher_disagreement_score":0.043085687,"about_ca_system_score_codex":0.0068132146,"about_ca_system_score_gemma":0.028752139,"threshold_uncertainty_score":0.14323395},"labels":[],"label_agreement":null},{"id":"W3031765893","doi":"10.3138/cjpe.56949","title":"Reflections on Inter-University Collaboration to Deliver a Graduate Certificate in Evaluation to Government of the Northwest Territories Employees","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Northwest Territories; Carleton University; University of Victoria","funders":"","keywords":"Credential; Negotiation; Government (linguistics); Certificate; Public relations; Higher education; Process (computing); sort; Political science; Sociology; Medical education; Business; Computer science; Medicine","score_opus":0.596189237013459,"score_gpt":0.5212415559789882,"score_spread":0.0749476810344708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031765893","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25381073,0.0013580832,0.03516005,0.6426053,0.004548545,0.0011372393,0.0000997527,0.00031395105,0.060966432],"genre_scores_gemma":[0.89939284,0.0012655517,0.023044107,0.046855863,0.0007363364,0.00092004484,0.00007260458,0.0003889597,0.027323628],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7422854,0.19789174,0.0055243927,0.0066994554,0.021975031,0.025624013],"domain_scores_gemma":[0.7514212,0.12737827,0.00880984,0.009904873,0.044079483,0.058406323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14719927,0.0009320803,0.00079516903,0.0012299125,0.054898284,0.018054625,0.008259531,0.017663822,0.007112203],"category_scores_gemma":[0.17168482,0.0017569645,0.0012423494,0.0015294622,0.0213944,0.0076783337,0.031915028,0.039965555,0.0019590363],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021953533,0.0021675567,0.005684035,0.00032297007,0.00005876536,0.0068049594,0.79086345,0.0017253372,0.0035662763,0.031026201,0.07609275,0.0814682],"study_design_scores_gemma":[0.000054605054,0.00048302923,0.0023770316,0.00049881655,0.000014636969,0.0008323947,0.8364927,0.0008393025,0.0014521582,0.004483663,0.1523278,0.00014391608],"about_ca_topic_score_codex":0.07431499,"about_ca_topic_score_gemma":0.12373121,"teacher_disagreement_score":0.9587082,"about_ca_system_score_codex":0.04129176,"about_ca_system_score_gemma":0.08957943,"threshold_uncertainty_score":0.7784735},"labels":[],"label_agreement":null},{"id":"W3032040493","doi":"10.3138/cjpe.43168","title":"Putting Theory of Change into Use in Complex Settings","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Agricultural Innovations and Practices","field":"Agricultural and Biological Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Selkirk College","funders":"","keywords":"Vision; Intervention (counseling); Theory of change; Work (physics); Business; Process management; Public relations; Knowledge management; Sociology; Political science; Psychology; Management; Economics; Computer science; Engineering","score_opus":0.5201552233493004,"score_gpt":0.37210959024056367,"score_spread":0.14804563310873675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032040493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024479538,0.0054358733,0.71643484,0.06990245,0.0016598423,0.0006220947,0.00024601634,0.0005791486,0.18064016],"genre_scores_gemma":[0.80513245,0.0031918746,0.18013203,0.003542356,0.0003487463,0.001475862,0.00015087941,0.00015385098,0.0058720573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9674866,0.026844552,0.00074807025,0.0019792854,0.0019193729,0.0010221788],"domain_scores_gemma":[0.93262184,0.056596015,0.001950187,0.004738247,0.0024295226,0.001664176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029832885,0.0015997833,0.0019173961,0.0064959,0.00437669,0.014627445,0.004353318,0.0048757712,0.009319169],"category_scores_gemma":[0.03685002,0.0008952747,0.0020333545,0.003718973,0.04198566,0.019118339,0.009297385,0.0065411674,0.00089633657],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019230618,0.000090561574,0.0013971707,0.0004008961,0.00007360097,0.000209949,0.0068802377,0.0070840055,0.00007321161,0.96321625,0.0019824214,0.01857248],"study_design_scores_gemma":[0.000028665141,0.00004626485,0.0003675232,0.0004619488,0.000026459673,0.000082464605,0.0045970525,0.008527114,0.0001267846,0.964316,0.021393728,0.000026143205],"about_ca_topic_score_codex":0.008243497,"about_ca_topic_score_gemma":0.0070562307,"teacher_disagreement_score":0.029832885,"about_ca_system_score_codex":0.0139532825,"about_ca_system_score_gemma":0.010942332,"threshold_uncertainty_score":0.15777326},"labels":[],"label_agreement":null},{"id":"W3032165765","doi":"10.3138/cjpe.56898","title":"Scope Creep and Purposeful Pivots in Developmental Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Scope (computer science); Stakeholder; Set (abstract data type); Session (web analytics); Psychology; Knowledge management; Engineering ethics; Plenary session; Process management; Pedagogy; Public relations; Business; Political science; Computer science; Engineering; World Wide Web; Library science","score_opus":0.5926935965616887,"score_gpt":0.5368839960960672,"score_spread":0.055809600465621556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032165765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22687986,0.0032192336,0.5781754,0.039825495,0.0007317312,0.0040337746,0.00010767076,0.001094007,0.14593281],"genre_scores_gemma":[0.8940837,0.00036648367,0.09606443,0.0025896356,0.00007140686,0.0027221446,0.000040542356,0.000249832,0.003811814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.6176476,0.32014453,0.015576535,0.011674309,0.027809938,0.0071471813],"domain_scores_gemma":[0.454653,0.43919134,0.018064456,0.052708372,0.02851466,0.006868119],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35110244,0.0010483889,0.0014913192,0.0041210963,0.008679108,0.016649256,0.0042330506,0.005182844,0.004000185],"category_scores_gemma":[0.34067634,0.0019969305,0.0013445402,0.0020876375,0.05045634,0.024692602,0.029442556,0.0086393,0.00073965685],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030439845,0.00028459882,0.010449726,0.0014191644,0.00007515753,0.0013179523,0.18338758,0.0019319075,0.0029209114,0.6624235,0.003662393,0.13182274],"study_design_scores_gemma":[0.00027183024,0.00062235584,0.005103697,0.0042539714,0.00009239878,0.0013186883,0.09124701,0.008118622,0.0082583,0.75834674,0.12215406,0.0002123277],"about_ca_topic_score_codex":0.0016870847,"about_ca_topic_score_gemma":0.0027383508,"teacher_disagreement_score":0.6488975,"about_ca_system_score_codex":0.012937208,"about_ca_system_score_gemma":0.021770101,"threshold_uncertainty_score":0.80020624},"labels":[],"label_agreement":null},{"id":"W3032883522","doi":"10.3138/cjpe.69364","title":"Une analyse engagée de la professionnalisation des pratiques d’évaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.5170717312114368,"score_gpt":0.571406395676147,"score_spread":0.05433466446471025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032883522","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23260392,0.022003248,0.419184,0.05909024,0.0019413448,0.0011663019,0.00039345707,0.000603852,0.2630135],"genre_scores_gemma":[0.86205953,0.0053446707,0.10416436,0.001674337,0.0006259178,0.0013131604,0.00024082474,0.00020811433,0.02436899],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.80748117,0.1438517,0.0063390066,0.0037459752,0.036721032,0.0018611257],"domain_scores_gemma":[0.69943106,0.24378723,0.011615207,0.009726959,0.034007713,0.0014318088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.093506284,0.00080820295,0.0007921454,0.005191412,0.0046434547,0.016770402,0.001623845,0.0035782652,0.0067636846],"category_scores_gemma":[0.19469963,0.0006585211,0.0014519306,0.0074948547,0.016870677,0.008647693,0.0049627325,0.00722254,0.00092463713],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026671356,0.00031555828,0.006421165,0.0021421022,0.00010061752,0.00071813946,0.19425577,0.0018115622,0.0032102517,0.53734183,0.005247203,0.24816906],"study_design_scores_gemma":[0.00017197027,0.00053409446,0.023211198,0.004740989,0.00011365857,0.0019997186,0.12429703,0.010859795,0.007723628,0.121961705,0.7042237,0.00016252883],"about_ca_topic_score_codex":0.018762821,"about_ca_topic_score_gemma":0.010799763,"teacher_disagreement_score":0.093506284,"about_ca_system_score_codex":0.014578283,"about_ca_system_score_gemma":0.019612031,"threshold_uncertainty_score":0.4945144},"labels":[],"label_agreement":null},{"id":"W304700293","doi":"10.3138/cjpe.0025.007","title":"Program Evaluation without a Client: The Case of the Disappearing Intended Users","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Negotiation; Meaning (existential); Business; Knowledge management; Process management; Public relations; Computer science; Psychology; Sociology; Political science","score_opus":0.5459869971696891,"score_gpt":0.541121227098997,"score_spread":0.00486577007069211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W304700293","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57025665,0.0014067764,0.024948226,0.26549533,0.00043482924,0.00095605844,0.00008705131,0.00028510325,0.13612993],"genre_scores_gemma":[0.963714,0.00054523075,0.007450673,0.012273772,0.00008136998,0.00044843982,0.000027607755,0.00013322518,0.015325757],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89011693,0.0862505,0.0024557267,0.002949453,0.008891759,0.0093357125],"domain_scores_gemma":[0.89200467,0.07018451,0.0039921,0.004344154,0.012348275,0.017126275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06822452,0.000816647,0.0012250836,0.0017617985,0.042984772,0.015947219,0.0045270156,0.014292403,0.009520228],"category_scores_gemma":[0.09801487,0.0014308542,0.0013028757,0.002185465,0.024915567,0.010024288,0.015312293,0.019352866,0.0013752896],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065661845,0.0018426905,0.038955517,0.0006190397,0.00009830279,0.082195185,0.5516702,0.0021041688,0.0020696777,0.20273769,0.042098973,0.07495187],"study_design_scores_gemma":[0.00023029263,0.0009607472,0.009557485,0.0015750348,0.00014007188,0.02598017,0.7524915,0.008436726,0.0037397372,0.046734203,0.14984168,0.00031224347],"about_ca_topic_score_codex":0.038027845,"about_ca_topic_score_gemma":0.0518901,"teacher_disagreement_score":0.93177545,"about_ca_system_score_codex":0.024376104,"about_ca_system_score_gemma":0.037792094,"threshold_uncertainty_score":0.36081004},"labels":[],"label_agreement":null},{"id":"W3091954143","doi":"10.3138/cjpe.015.004","title":"Mieux comprendre l’impact par l’analyse de l’implantation: le cas d’un programme de prévention chez des travailleurs avec ordinateur","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Context (archaeology); Psychology","score_opus":0.2511611236671157,"score_gpt":0.4718500405389296,"score_spread":0.2206889168718139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091954143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9806008,0.0012623268,0.0062024086,0.0027145457,0.00019015041,0.00032267044,0.00010137738,0.000060610637,0.00854514],"genre_scores_gemma":[0.9897752,0.00075603166,0.004158428,0.00025915058,0.00011530838,0.00024079131,0.0000819491,0.000018465023,0.004594829],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9935834,0.003498095,0.0002922688,0.00037575117,0.0014625975,0.0007879065],"domain_scores_gemma":[0.99144334,0.0058032214,0.0007469834,0.00033973804,0.0010138019,0.0006528733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051091462,0.000675398,0.00037430093,0.001478216,0.001398071,0.0018026781,0.00076966366,0.0022920913,0.0077398284],"category_scores_gemma":[0.019043412,0.00027307653,0.0010284946,0.000724055,0.0012179085,0.000939379,0.0010056448,0.0011856203,0.0006386318],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007951065,0.00786419,0.36535785,0.0016880679,0.00032270432,0.008618987,0.032211784,0.0043664454,0.016353743,0.006643845,0.002432855,0.5461885],"study_design_scores_gemma":[0.0007597708,0.024914432,0.8446087,0.0014651685,0.0007057167,0.006939945,0.033541787,0.013504719,0.025681475,0.0034952825,0.044186924,0.00019612096],"about_ca_topic_score_codex":0.018122848,"about_ca_topic_score_gemma":0.01189396,"teacher_disagreement_score":0.98187715,"about_ca_system_score_codex":0.0015605303,"about_ca_system_score_gemma":0.0033483813,"threshold_uncertainty_score":0.036034703},"labels":[],"label_agreement":null},{"id":"W3099096212","doi":"10.3138/cjpe.69324","title":"Leila C. Kahwati &amp; Heather L. Kane. (2019). <i>Qualitative Comparative Analysis in Mixed Methods Research and Evaluation</i> .","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Qualitative analysis; Sociology; Qualitative research; Art; Social science","score_opus":0.7584619623873686,"score_gpt":0.6928246748903362,"score_spread":0.06563728749703246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099096212","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023362249,0.7312153,0.008286782,0.12327243,0.016645921,0.00025306887,0.0007132878,0.00046934423,0.118910246],"genre_scores_gemma":[0.0046448405,0.59361243,0.013105873,0.034373123,0.0037427095,0.0006046147,0.0006856813,0.0006299824,0.34860075],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997297,0.0006479352,0.00016114161,0.00027774987,0.0015214445,0.00009489944],"domain_scores_gemma":[0.9886246,0.0061117723,0.0006300058,0.00028813185,0.0038368625,0.00050862855],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0065980987,0.00088389654,0.00078406127,0.0036363653,0.001989828,0.0042100647,0.0016922269,0.0028644293,0.051631957],"category_scores_gemma":[0.013651692,0.001029694,0.00044522586,0.00455468,0.0024694765,0.0069235633,0.0027720938,0.004410398,0.031207269],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010604566,0.000005695677,0.00006769104,0.0010463314,0.0000042480547,0.000041855805,0.00047302115,0.000022525443,0.00009585001,0.0053072213,0.7966005,0.19632442],"study_design_scores_gemma":[0.0000038250478,0.000006574784,0.00021933418,0.0021584148,0.0000060958296,0.00010730431,0.00026808956,0.0000294642,0.00008886741,0.0025388626,0.9945621,0.000011079823],"about_ca_topic_score_codex":0.02335823,"about_ca_topic_score_gemma":0.06928526,"teacher_disagreement_score":0.9934019,"about_ca_system_score_codex":0.0034245816,"about_ca_system_score_gemma":0.008446362,"threshold_uncertainty_score":0.1727261},"labels":[],"label_agreement":null},{"id":"W3099471317","doi":"10.3138/cjpe.70004","title":"Sustainability Analysis of Intervention Benefits: A Theory of Change Approach","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sustainability; Intervention (counseling); Spell; Sustainability organizations; Work (physics); Environmental economics; Business; Environmental resource management; Economics; Psychology; Engineering; Sociology; Ecology","score_opus":0.6214875283452821,"score_gpt":0.5413536083546764,"score_spread":0.0801339199906057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099471317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014678284,0.0035213786,0.8407967,0.022973558,0.00088179234,0.0015373,0.00042970688,0.0002419983,0.11493935],"genre_scores_gemma":[0.69954664,0.003581203,0.28387222,0.002691414,0.00041043328,0.0035474002,0.00021204322,0.00016174269,0.00597688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9538644,0.03785364,0.00080547214,0.0017359813,0.004735942,0.001004614],"domain_scores_gemma":[0.9216486,0.069558844,0.0023473015,0.0018345072,0.0038658353,0.00074476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035998143,0.002627802,0.002473149,0.009978209,0.0023512724,0.008729459,0.0037669935,0.004051335,0.014659068],"category_scores_gemma":[0.05351125,0.0009190356,0.0038255504,0.0053642425,0.014115698,0.0063117323,0.004594982,0.006593397,0.0006266288],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000708402,0.0003202189,0.0016778056,0.0010301213,0.00038634543,0.00007913912,0.00091913325,0.043482825,0.0001371335,0.9190918,0.002415804,0.030388845],"study_design_scores_gemma":[0.000077397584,0.00034509247,0.001313271,0.0012590208,0.0002844528,0.00006261359,0.0018382942,0.07944666,0.00042030783,0.89895535,0.015940404,0.000057194717],"about_ca_topic_score_codex":0.0062320884,"about_ca_topic_score_gemma":0.006074107,"teacher_disagreement_score":0.035998143,"about_ca_system_score_codex":0.018111216,"about_ca_system_score_gemma":0.0135968905,"threshold_uncertainty_score":0.19037867},"labels":[],"label_agreement":null},{"id":"W3100381562","doi":"10.3138/cjpe.68497","title":"Dancing between “Zoom In” and “Zoom Out” Perspectives to Evaluate Social Innovation Labs","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Innovative Approaches in Technology and Social Development","field":"Business, Management and Accounting","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Zoom; Computer science; Process (computing); Class (philosophy); Knowledge management; Data science; Sociology; Artificial intelligence; Engineering","score_opus":0.18126137121193428,"score_gpt":0.35516217455872573,"score_spread":0.17390080334679145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100381562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2854356,0.004033142,0.3822922,0.047475412,0.00090900034,0.0031436237,0.0002867202,0.00080035074,0.27562413],"genre_scores_gemma":[0.8760596,0.0006439203,0.1132269,0.0033835,0.00008024635,0.0021309003,0.000046371413,0.00014312526,0.004285421],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.85676485,0.12832779,0.002252801,0.0022559755,0.008650876,0.0017476556],"domain_scores_gemma":[0.8316865,0.1380344,0.0074449433,0.008587279,0.011335717,0.0029111668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08150323,0.0012507817,0.00072355865,0.0062407325,0.005105291,0.0118168285,0.0022281152,0.002792959,0.007978712],"category_scores_gemma":[0.10815547,0.00048223065,0.0008816965,0.0033028931,0.03743617,0.014911994,0.013175143,0.005630743,0.0005423214],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004797071,0.0007025064,0.008917582,0.0017771148,0.000108631444,0.0003300933,0.22545613,0.00204832,0.0046210056,0.5865568,0.008164011,0.16083808],"study_design_scores_gemma":[0.00047755073,0.0023135673,0.013429379,0.004722757,0.00026270162,0.00045853914,0.33324838,0.009780941,0.015974885,0.45991728,0.1591464,0.00026775754],"about_ca_topic_score_codex":0.003275782,"about_ca_topic_score_gemma":0.0064349705,"teacher_disagreement_score":0.08150323,"about_ca_system_score_codex":0.010810001,"about_ca_system_score_gemma":0.008404192,"threshold_uncertainty_score":0.4310354},"labels":[],"label_agreement":null},{"id":"W3101505332","doi":"10.3138/cjpe.69796","title":"Application of an Evaluation Framework for Extra-Organizational Communities of Practice: Assessment and Refinement","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; University of Toronto","funders":"","keywords":"Knowledge management; Community of practice; Reflection (computer programming); Work (physics); Content analysis; Value (mathematics); Qualitative research; Psychology; Sociology; Computer science; Pedagogy","score_opus":0.39468624739554886,"score_gpt":0.5735482175325376,"score_spread":0.17886197013698873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101505332","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20106699,0.0025627832,0.667495,0.011516896,0.00041944085,0.06166014,0.00087345985,0.0005477831,0.053857498],"genre_scores_gemma":[0.35697654,0.00030575396,0.61962086,0.0003239603,0.000018177649,0.021810465,0.0002832866,0.00003738101,0.0006236627],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6696373,0.26273897,0.023337645,0.005753277,0.03489096,0.0036418205],"domain_scores_gemma":[0.4937855,0.34108385,0.017124891,0.02038994,0.12396573,0.0036500369],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2981482,0.0013073817,0.0018575921,0.010798505,0.005916305,0.008250322,0.0033937325,0.0023086634,0.0027132793],"category_scores_gemma":[0.33161783,0.0010022159,0.003075997,0.0077696443,0.008869322,0.009392967,0.008304744,0.00314172,0.00028943227],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058464386,0.001777413,0.062627986,0.013324166,0.0005834919,0.0003086188,0.08670515,0.010379617,0.0019885437,0.24322017,0.007078375,0.57142186],"study_design_scores_gemma":[0.0020093555,0.006525538,0.14437263,0.051495012,0.0024206017,0.0011865615,0.20652659,0.17248072,0.01546986,0.2572119,0.13929696,0.0010043114],"about_ca_topic_score_codex":0.023047742,"about_ca_topic_score_gemma":0.03404623,"teacher_disagreement_score":0.2981482,"about_ca_system_score_codex":0.04465921,"about_ca_system_score_gemma":0.0659109,"threshold_uncertainty_score":0.8655082},"labels":[],"label_agreement":null},{"id":"W3102015017","doi":"10.3138/cjpe.61723","title":"Anticipating and Addressing Stakeholders’ Stereotypes of Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Process (computing); Psychology; Focus (optics); Applied psychology; Knowledge management; Social psychology; Public relations; Computer science; Political science","score_opus":0.8194598612454987,"score_gpt":0.5817553033009218,"score_spread":0.2377045579445769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102015017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5555628,0.001436177,0.15945975,0.1501399,0.00082142325,0.001662333,0.00009727693,0.0006436851,0.13017672],"genre_scores_gemma":[0.9414562,0.000481588,0.047334284,0.005797894,0.000070685106,0.00080254796,0.000035612968,0.000093564704,0.0039277105],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7864963,0.17804836,0.0075388867,0.0030946285,0.019366926,0.005454929],"domain_scores_gemma":[0.7128217,0.21239313,0.018365366,0.012003615,0.039065436,0.005350666],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20494811,0.0007286348,0.000546584,0.0021037313,0.011807249,0.011796616,0.002265087,0.0038407352,0.0034579197],"category_scores_gemma":[0.23043509,0.00078548444,0.00052258285,0.0010223303,0.008970965,0.01073334,0.012860515,0.0072683766,0.0007218864],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003637731,0.00063232705,0.033166412,0.0011665728,0.00005788272,0.0012960306,0.63784295,0.002234197,0.009892279,0.076011345,0.022404756,0.21493144],"study_design_scores_gemma":[0.00013959178,0.0006492326,0.015050215,0.004857523,0.00010025694,0.0007334252,0.6105542,0.0120275235,0.026239235,0.10366826,0.22569439,0.00028623955],"about_ca_topic_score_codex":0.007857417,"about_ca_topic_score_gemma":0.014867594,"teacher_disagreement_score":0.7950519,"about_ca_system_score_codex":0.014394716,"about_ca_system_score_gemma":0.02477465,"threshold_uncertainty_score":0.9804405},"labels":[],"label_agreement":null},{"id":"W3102779069","doi":"10.3138/cjpe.69480","title":"Stephanie D. H. Evergreen. (2019). <i>Effective Data Visualization: The Right Chart for the Right Data</i> . Second Edition.","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Visualization; Chart; Data visualization; Computer science; Artificial intelligence; Statistics; Mathematics","score_opus":0.190692075622344,"score_gpt":0.3718316939237039,"score_spread":0.1811396183013599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102779069","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007505646,0.15198183,0.010262037,0.6541784,0.059629627,0.00016454543,0.008521612,0.0029845962,0.11152683],"genre_scores_gemma":[0.013977617,0.22727278,0.030728538,0.18118306,0.012010582,0.0006422521,0.00732013,0.00418941,0.5226757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962584,0.00056381937,0.00022204914,0.0003261739,0.0024303861,0.00019916585],"domain_scores_gemma":[0.9695729,0.006027878,0.0009858143,0.0008207352,0.019605525,0.002987239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060817604,0.0013772098,0.0006775277,0.0034979393,0.0027385226,0.0049593477,0.0014058154,0.0030321404,0.06343172],"category_scores_gemma":[0.032163225,0.0008043254,0.00054661423,0.003388719,0.0018860552,0.00507902,0.0026397903,0.007780831,0.049338594],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057464026,0.0000024865474,0.00007953489,0.00007199577,0.0000016119943,0.000012978476,0.000060739134,0.000009651832,0.000028578599,0.0007545556,0.9726891,0.026283022],"study_design_scores_gemma":[0.0000056171975,0.000004182444,0.0005037364,0.0005374905,0.0000066101793,0.00005413876,0.0002060265,0.000020858542,0.00011981761,0.0014114559,0.99711573,0.0000143081525],"about_ca_topic_score_codex":0.08491581,"about_ca_topic_score_gemma":0.18928203,"teacher_disagreement_score":0.08491581,"about_ca_system_score_codex":0.0030193285,"about_ca_system_score_gemma":0.018732602,"threshold_uncertainty_score":0.21220022},"labels":[],"label_agreement":null},{"id":"W3103082364","doi":"10.3138/cjpe.69230","title":"The Use and Benefits of Evaluation Framework Modules at the Canadian Foundation for Healthcare Improvement: Engaged Capacity Building and Collaborative Program Evaluation Planning","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Public Health; Canadian Foundation for Healthcare Improvement","funders":"","keywords":"Foundation (evidence); Participatory evaluation; Citizen journalism; Health care; Process management; Computer science; Knowledge management; Program evaluation; Capacity building; Engineering management; Management science; Business; Engineering; Sociology; Political science; World Wide Web","score_opus":0.5503134362738925,"score_gpt":0.515309111644216,"score_spread":0.03500432462967651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103082364","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41282004,0.0023711321,0.36637586,0.04602993,0.0004438834,0.041560657,0.0012443664,0.0029847752,0.12616938],"genre_scores_gemma":[0.52838916,0.00041384774,0.4560281,0.0013384431,0.000042816457,0.009250313,0.00057054317,0.00018475913,0.0037820486],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.82425946,0.14918369,0.0036687732,0.003237897,0.0127312895,0.0069188364],"domain_scores_gemma":[0.8302565,0.100702085,0.0074909045,0.011966186,0.035506375,0.014078007],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20026498,0.0010848633,0.00062823977,0.004010244,0.008424186,0.00733691,0.00476846,0.0022451016,0.004414686],"category_scores_gemma":[0.16155705,0.0010280606,0.0010024722,0.0029280349,0.0038463948,0.0056025246,0.010338266,0.003327997,0.00067974604],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090991077,0.0040268837,0.02197468,0.0025776047,0.00018475975,0.0004255547,0.052299604,0.011318744,0.004347983,0.03514341,0.03741247,0.82937825],"study_design_scores_gemma":[0.003556283,0.013082172,0.19904548,0.020214986,0.0008009978,0.0010072262,0.11344254,0.10405359,0.03684149,0.116163895,0.3901703,0.0016211242],"about_ca_topic_score_codex":0.09740346,"about_ca_topic_score_gemma":0.22072715,"teacher_disagreement_score":0.96448463,"about_ca_system_score_codex":0.035515353,"about_ca_system_score_gemma":0.07908502,"threshold_uncertainty_score":0.98621565},"labels":[],"label_agreement":null},{"id":"W3103842672","doi":"10.3138/cjpe.68127","title":"Comparing and Contrasting a Program versus System Approach to Evaluation: The Example of a Cardiac Care System","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Perspective (graphical); Set (abstract data type); Systems theory; Management science; Computer science; Systems thinking; Risk analysis (engineering); Medicine; Artificial intelligence; Engineering; Programming language","score_opus":0.5917953680574175,"score_gpt":0.4872887842568676,"score_spread":0.10450658380054989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103842672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47695923,0.0055423765,0.18763803,0.041964814,0.00056701724,0.0019274392,0.00024406046,0.00027360793,0.2848834],"genre_scores_gemma":[0.94069403,0.00088951015,0.055321615,0.00076570373,0.000053686905,0.0004492394,0.000031372565,0.000027534947,0.0017673454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9230964,0.06672866,0.00095179974,0.0006174859,0.0070649027,0.0015408094],"domain_scores_gemma":[0.92578924,0.06365482,0.0012215645,0.001003394,0.007413571,0.0009173418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03255696,0.0004904493,0.00056185725,0.0039565084,0.0036781295,0.007422939,0.0014152816,0.0019886077,0.003275432],"category_scores_gemma":[0.04242825,0.00024499593,0.0008646465,0.0037562414,0.007631228,0.0041478095,0.004293941,0.0025973779,0.00017134887],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008054229,0.0010711236,0.017260958,0.0020944632,0.00023161757,0.0009332303,0.015734518,0.03074139,0.001311648,0.7844559,0.005811529,0.13954821],"study_design_scores_gemma":[0.0016557095,0.006047803,0.045459285,0.004583758,0.0009779918,0.0010816312,0.073939495,0.26833138,0.013571657,0.4811064,0.1028716,0.00037325706],"about_ca_topic_score_codex":0.02840171,"about_ca_topic_score_gemma":0.037379995,"teacher_disagreement_score":0.03255696,"about_ca_system_score_codex":0.017408025,"about_ca_system_score_gemma":0.012921147,"threshold_uncertainty_score":0.17217976},"labels":[],"label_agreement":null},{"id":"W3105492687","doi":"10.3138/cjpe.69535","title":"Toward Learning from Change Pathways: Reviewing Theory of Change and Its Discontents","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Underpinning; Vagueness; Theory of change; Context (archaeology); Stakeholder; Process (computing); Stakeholder engagement; Epistemology; Management science; Knowledge management; Sociology; Computer science; Political science; Public relations; Economics; Engineering; Artificial intelligence","score_opus":0.918735116591738,"score_gpt":0.5122009043033375,"score_spread":0.4065342122884005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105492687","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023000098,0.87693596,0.019967163,0.09056303,0.0032137744,0.0002031685,0.00006651358,0.00006357135,0.006686924],"genre_scores_gemma":[0.11032146,0.8366564,0.028393421,0.020931022,0.0020695734,0.0007611088,0.00013698901,0.00006657859,0.0006635361],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9423748,0.036280263,0.0056820787,0.0037256768,0.010931102,0.0010060742],"domain_scores_gemma":[0.5903162,0.36532426,0.008294511,0.0050310143,0.028958807,0.0020751946],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10829022,0.0016055591,0.0036065695,0.024720615,0.004183078,0.017990408,0.006761186,0.0077458113,0.002885476],"category_scores_gemma":[0.17111535,0.0009989961,0.0024164107,0.020570789,0.029449878,0.021006042,0.006216215,0.012321097,0.0006602599],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009457614,0.00018105644,0.0022119237,0.07663037,0.0005726552,0.00034505484,0.01599032,0.0048658536,0.00022529098,0.3234645,0.022102972,0.55331546],"study_design_scores_gemma":[0.00004825703,0.00026033,0.003100295,0.2873466,0.000776638,0.00056610355,0.027995635,0.005258761,0.0008548646,0.3572784,0.31634113,0.00017302706],"about_ca_topic_score_codex":0.016129406,"about_ca_topic_score_gemma":0.026406664,"teacher_disagreement_score":0.8917098,"about_ca_system_score_codex":0.029746033,"about_ca_system_score_gemma":0.044166815,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3106401031","doi":"10.3138/cjpe.69099","title":"Missing in Action: Indigenous Knowledge Systems in Evaluation of Comprehensive Community Initiatives","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Island Health; First Nations University of Canada; University of British Columbia","funders":"","keywords":"Indigenous; Action (physics); Sociology; Action research; Traditional knowledge; Public relations; Political science; Pedagogy; Ecology","score_opus":0.352156870763072,"score_gpt":0.47316787646276187,"score_spread":0.12101100569968987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106401031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24233223,0.024672924,0.27265212,0.16936876,0.00251813,0.030819854,0.0009169625,0.0011642544,0.25555477],"genre_scores_gemma":[0.77829164,0.0028363452,0.19888726,0.0043138806,0.00015930564,0.013416332,0.00021207001,0.00009805881,0.0017850347],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.43376452,0.51450557,0.01570143,0.007611846,0.022972966,0.0054436517],"domain_scores_gemma":[0.43723315,0.44968542,0.020652136,0.026648859,0.058059666,0.007720798],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.48640925,0.001230422,0.0023545846,0.010271748,0.015322073,0.028886378,0.006534465,0.0055669043,0.008702017],"category_scores_gemma":[0.4513129,0.0014561692,0.002159623,0.0077426713,0.021267839,0.030157443,0.029968174,0.0076998686,0.00074175466],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082574674,0.0017444346,0.019451777,0.014649877,0.0006259781,0.00045649323,0.27773634,0.0042007486,0.00086959975,0.12647717,0.009288439,0.5436734],"study_design_scores_gemma":[0.0011799226,0.0029006682,0.02438131,0.071358904,0.0018726654,0.00044673303,0.43937892,0.026020441,0.004192047,0.3013158,0.12622437,0.0007283129],"about_ca_topic_score_codex":0.03325058,"about_ca_topic_score_gemma":0.049181536,"teacher_disagreement_score":0.9667494,"about_ca_system_score_codex":0.052236784,"about_ca_system_score_gemma":0.10472501,"threshold_uncertainty_score":0.6333489},"labels":[],"label_agreement":null},{"id":"W310937889","doi":"10.3138/cjpe.0014.008","title":"Building Capacity for School Improvement through Evaluation: Experiences of the Manitoba School Improvement Program Inc.","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Empowerment; Context (archaeology); Capacity building; Perspective (graphical); Program evaluation; Sociology; Pedagogy; Medical education; Political science; Medicine; Public administration; Computer science; Geography","score_opus":0.28399040238513046,"score_gpt":0.49536869734142874,"score_spread":0.21137829495629828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W310937889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85141623,0.003122471,0.0019944857,0.08742819,0.0001858926,0.0007241434,0.0000846634,0.000052828935,0.054991007],"genre_scores_gemma":[0.9684144,0.0023488433,0.0034450868,0.0071765557,0.000041357518,0.00032481292,0.000049384933,0.000045035533,0.018154535],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97805107,0.015765112,0.00016316799,0.0003206792,0.0022272735,0.0034727782],"domain_scores_gemma":[0.98353034,0.0054535535,0.0004541201,0.0003280814,0.004972514,0.0052613765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023177432,0.0004069603,0.00041307032,0.00083399523,0.023212515,0.0056534046,0.0018319468,0.0020827022,0.003089075],"category_scores_gemma":[0.012299008,0.0005819854,0.0002727336,0.0017768084,0.009934838,0.0017318849,0.0073804446,0.0048388336,0.00026608183],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003467923,0.0023450532,0.030691365,0.00046333726,0.000049613234,0.0024737646,0.8231285,0.0008800448,0.0016980667,0.021800382,0.028874021,0.08724909],"study_design_scores_gemma":[0.00012463203,0.0006417004,0.0347175,0.0005698895,0.000042261243,0.0003600255,0.75493604,0.0011608927,0.0020046781,0.0028386877,0.20250331,0.0001002904],"about_ca_topic_score_codex":0.5727548,"about_ca_topic_score_gemma":0.8389304,"teacher_disagreement_score":0.96520394,"about_ca_system_score_codex":0.03479605,"about_ca_system_score_gemma":0.111117825,"threshold_uncertainty_score":0.85952264},"labels":[],"label_agreement":null},{"id":"W3116581541","doi":"10.3138/cjpe.23.009","title":"Une analyse du processus d’évaluation de la politique régionale de santé dans le nord pas-de-calais (France)","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Healthcare Systems and Practices","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Calais; Normative; Political science; Valuation (finance); Humanities; Philosophy; Computer science; Business; Law","score_opus":0.1807888907034327,"score_gpt":0.49808902821960094,"score_spread":0.31730013751616826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116581541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8620368,0.0054575116,0.029814545,0.014626203,0.00015166891,0.002962031,0.0004938755,0.00022378322,0.08423354],"genre_scores_gemma":[0.9811794,0.00069147284,0.0127045745,0.00025183594,0.000029970312,0.00061822176,0.00013179082,0.00003544457,0.0043573505],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8663216,0.106807694,0.0032396654,0.0032571717,0.016836207,0.003537667],"domain_scores_gemma":[0.8319229,0.12152973,0.00917965,0.002918316,0.031386152,0.0030632557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1378037,0.00055529043,0.0009246318,0.006376908,0.0051696165,0.011549904,0.0013738896,0.0016704608,0.0037286617],"category_scores_gemma":[0.10458339,0.0005392802,0.0009143697,0.0072259367,0.005296514,0.0040781554,0.004643373,0.0021396626,0.00022710787],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095542386,0.0012044229,0.08315867,0.0028877906,0.0004098759,0.0012103339,0.2535237,0.020714892,0.0032270167,0.16347979,0.0077286363,0.4614994],"study_design_scores_gemma":[0.00038199913,0.0024541032,0.35990843,0.005270007,0.0003174928,0.00042897125,0.34074965,0.026206419,0.008224075,0.017493462,0.2382516,0.00031376068],"about_ca_topic_score_codex":0.2501547,"about_ca_topic_score_gemma":0.14193387,"teacher_disagreement_score":0.2501547,"about_ca_system_score_codex":0.08356523,"about_ca_system_score_gemma":0.0684993,"threshold_uncertainty_score":0.7287843},"labels":[],"label_agreement":null},{"id":"W3136354237","doi":"10.3138/cjpe.69703","title":"UEval: Bringing Community-Based Experiential Learning to the Evaluation Classroom","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Patient Safety Institute; University of Alberta","funders":"","keywords":"Experiential learning; Curriculum; Citizen journalism; Pedagogy; Psychology; Experiential education; Participatory action research; Engineering ethics; Medical education; Sociology; Political science; Engineering; Medicine","score_opus":0.4370275756617095,"score_gpt":0.5432201279952923,"score_spread":0.10619255233358277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136354237","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25782782,0.002680383,0.3678417,0.02573195,0.0017588761,0.0024598923,0.00021399783,0.0046855393,0.33679995],"genre_scores_gemma":[0.65897983,0.0014113571,0.2905909,0.003522701,0.00027523213,0.0017626375,0.0002544697,0.00041291633,0.042789947],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867191,0.009435653,0.0002476649,0.0006687084,0.0019500931,0.0009787746],"domain_scores_gemma":[0.98097414,0.0098058535,0.00047764304,0.0017142419,0.0021680228,0.0048602135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01776916,0.00056178897,0.0004216153,0.0010127549,0.0029769423,0.007847267,0.0033610046,0.0018040875,0.006796791],"category_scores_gemma":[0.01873977,0.00035177096,0.00040883914,0.0005490745,0.003602461,0.0032528949,0.0116412975,0.0036468117,0.0019369483],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046755985,0.00547055,0.0041021295,0.00069872977,0.000037358084,0.0008864404,0.0530769,0.0028055143,0.0060296603,0.046020027,0.06133261,0.8190725],"study_design_scores_gemma":[0.0003842564,0.0017807572,0.007327276,0.0017865775,0.000033722186,0.0017197698,0.06098057,0.011238296,0.010047375,0.09651721,0.8079672,0.0002170409],"about_ca_topic_score_codex":0.0022129978,"about_ca_topic_score_gemma":0.008233676,"teacher_disagreement_score":0.01776916,"about_ca_system_score_codex":0.0025047662,"about_ca_system_score_gemma":0.008320349,"threshold_uncertainty_score":0.0939734},"labels":[],"label_agreement":null},{"id":"W3136374681","doi":"10.3138/cjpe.70143","title":"Fieldwork Experience as Cultural Immersion: Two International Students and Their Professor Reflect on a Recent Evaluation Practicum","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Science and Policy Research","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Practicum; Interpersonal communication; Psychology; Pedagogy; Cultural competence; Cultural learning; Cultural diversity; Sociology; Social psychology; Anthropology","score_opus":0.39886000680043354,"score_gpt":0.624925970255608,"score_spread":0.2260659634551745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136374681","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8848529,0.001221449,0.014937319,0.052542664,0.0034532568,0.0010341653,0.00011668233,0.00041329756,0.041428313],"genre_scores_gemma":[0.96136546,0.0006467216,0.004657779,0.007296627,0.0006774627,0.00044661615,0.000100984544,0.00028784614,0.024520438],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97117907,0.019230846,0.0006509497,0.0018611714,0.0028763653,0.004201549],"domain_scores_gemma":[0.963619,0.009960537,0.0016910481,0.0023245937,0.006824263,0.01558056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028549466,0.0014882832,0.0010349926,0.0016618354,0.021744767,0.011832563,0.0039114947,0.0075060534,0.005632268],"category_scores_gemma":[0.035435952,0.0011251469,0.0010460991,0.0010987405,0.011031453,0.004778734,0.016659219,0.017944995,0.0019811578],"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":[0.00036587619,0.0034215315,0.007410919,0.00037854305,0.0000562808,0.006038697,0.8639264,0.00047479797,0.0063722013,0.006727264,0.034459334,0.07036819],"study_design_scores_gemma":[0.00007366815,0.0020477725,0.0043421662,0.00037972306,0.0000217949,0.0031878348,0.80941993,0.00045705884,0.0030835883,0.0016369383,0.17519462,0.00015495742],"about_ca_topic_score_codex":0.0026472944,"about_ca_topic_score_gemma":0.0058266046,"teacher_disagreement_score":0.028549466,"about_ca_system_score_codex":0.006429723,"about_ca_system_score_gemma":0.0047728457,"threshold_uncertainty_score":0.15098578},"labels":[],"label_agreement":null},{"id":"W3136555995","doi":"10.3138/cjpe.69601","title":"In Their Own Words: Student Key Learning Experiences in an Introductory Evaluation Course","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Key (lock); Psychology; Taxonomy (biology); Mathematics education; Grounded theory; Pedagogy; Reflective practice; Medical education; Computer science; Qualitative research; Sociology; Medicine","score_opus":0.3004856471172792,"score_gpt":0.5460008305135504,"score_spread":0.2455151833962712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136555995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9444177,0.0005854671,0.0086549735,0.010254127,0.0006818716,0.0003743487,0.00019027971,0.00018439816,0.034656793],"genre_scores_gemma":[0.97783846,0.0004234712,0.003167086,0.0014450266,0.00009912923,0.00014311889,0.00009149709,0.000113931004,0.016678495],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99468756,0.0027758633,0.00021371768,0.00038518172,0.0011291419,0.000808502],"domain_scores_gemma":[0.98323405,0.009272991,0.0010825536,0.0006171947,0.0026049998,0.0031882154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058139204,0.00072828284,0.00051001454,0.00078320404,0.0058520352,0.00653445,0.0014809896,0.002437681,0.0053079864],"category_scores_gemma":[0.029814657,0.00028180776,0.00040316337,0.0005781612,0.0037382815,0.0029360545,0.0050369236,0.004388941,0.001327318],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030887016,0.0010059677,0.012210148,0.00032367234,0.000032221556,0.0028063834,0.8575455,0.0004780835,0.005802987,0.0051850462,0.02392954,0.090371504],"study_design_scores_gemma":[0.000041599258,0.001451736,0.016428374,0.00062572566,0.00004986729,0.0021832515,0.82342124,0.0010369807,0.010418433,0.0028627026,0.14128989,0.00019010658],"about_ca_topic_score_codex":0.004120427,"about_ca_topic_score_gemma":0.008698407,"teacher_disagreement_score":0.00653445,"about_ca_system_score_codex":0.0035238303,"about_ca_system_score_gemma":0.0028191106,"threshold_uncertainty_score":0.030747354},"labels":[],"label_agreement":null},{"id":"W3136672375","doi":"10.3138/cjpe.69698","title":"Praxis Makes Perfect? Transcending Textbooks to Learning Evaluation Experientially and in Cultural Contexts","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Praxis; Transformative learning; Experiential learning; Value (mathematics); White privilege; Sociology; Professional development; Harm; Pedagogy; Psychology; Privilege (computing); Epistemology; Engineering ethics; Racism; Social psychology; Law; Computer science","score_opus":0.3037025959764343,"score_gpt":0.5365116728649787,"score_spread":0.2328090768885444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136672375","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06854765,0.022709467,0.19795261,0.26962888,0.008259231,0.00040421542,0.000108418935,0.0008979391,0.4314916],"genre_scores_gemma":[0.8432249,0.010915277,0.085827425,0.020674594,0.0018503558,0.0006315494,0.00007685311,0.0006718271,0.036127143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9610808,0.03160464,0.0011234322,0.0009990297,0.0043529617,0.0008391144],"domain_scores_gemma":[0.8829892,0.087447256,0.0035903812,0.010478258,0.011970289,0.0035245453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042428873,0.00057621865,0.0007754272,0.0026240044,0.0047661006,0.019977702,0.0021633592,0.0027990323,0.0065650637],"category_scores_gemma":[0.12766387,0.00043875774,0.00039091418,0.0015779239,0.037785105,0.019247193,0.011008373,0.0074477103,0.0016083813],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040928535,0.00014870631,0.0013518492,0.00053329254,0.000012120498,0.00026991332,0.092465356,0.00045752904,0.00039263055,0.68025875,0.027919576,0.19614944],"study_design_scores_gemma":[0.000030798714,0.00015282638,0.0013512095,0.005047262,0.000025260266,0.00048529782,0.06163423,0.0010735567,0.001446315,0.4970422,0.43164206,0.000069064474],"about_ca_topic_score_codex":0.0031529013,"about_ca_topic_score_gemma":0.0067550186,"teacher_disagreement_score":0.042428873,"about_ca_system_score_codex":0.009889236,"about_ca_system_score_gemma":0.010890041,"threshold_uncertainty_score":0.22438794},"labels":[],"label_agreement":null},{"id":"W3137000688","doi":"10.3138/cjpe.69691","title":"Collaborative Evaluation Designs as an Authentic Course Assessment","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Authentic assessment; Computer science; Evaluation methods; Graduate students; Authentic learning; Instructional design; Knowledge management; Psychology; Mathematics education; Pedagogy; Curriculum; Multimedia; Engineering","score_opus":0.36482317151236154,"score_gpt":0.5893866504709884,"score_spread":0.22456347895862683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137000688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048184413,0.0011576568,0.9039151,0.0027149522,0.00065612904,0.014083463,0.00014361227,0.00062424666,0.028520435],"genre_scores_gemma":[0.19734307,0.0003518197,0.78813136,0.0003943382,0.00010693456,0.010974065,0.00007165648,0.00008949026,0.0025371236],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6149786,0.3411847,0.011413343,0.0069251987,0.02399255,0.0015055169],"domain_scores_gemma":[0.59536827,0.2741047,0.020844083,0.047053628,0.057493087,0.0051361625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.22941281,0.0011357204,0.0010512763,0.0028675403,0.003295389,0.0074767694,0.003949089,0.002280707,0.005639892],"category_scores_gemma":[0.31646207,0.00078332087,0.0011719185,0.0013747162,0.0054049133,0.0068122596,0.0074272477,0.003030519,0.0011811564],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011001033,0.00178609,0.006713759,0.0036724252,0.00031019057,0.0002722544,0.026099335,0.0103352,0.004783177,0.1818735,0.0113614425,0.75169253],"study_design_scores_gemma":[0.0036213973,0.013729758,0.010986412,0.00991104,0.00070397014,0.0011162505,0.021654174,0.07528019,0.03983303,0.41628528,0.4061023,0.00077616086],"about_ca_topic_score_codex":0.0006546105,"about_ca_topic_score_gemma":0.0011671942,"teacher_disagreement_score":0.22941281,"about_ca_system_score_codex":0.004629832,"about_ca_system_score_gemma":0.009658656,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3137537988","doi":"10.3138/cjpe.70367","title":"Helping Students Reflect on Their Interpersonal Skills: The Team Performance Scale (TPS)","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Innovations in Medical Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Teamwork; Interpersonal communication; Social skills; Psychology; Scale (ratio); Service-learning; Service (business); Medical education; Team effectiveness; Interpersonal relationship; Knowledge management; Pedagogy; Computer science; Social psychology; Management; Medicine","score_opus":0.06579928805233264,"score_gpt":0.42500836734359604,"score_spread":0.3592090792912634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137537988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95823634,0.00039330678,0.010889058,0.0021936358,0.00033696476,0.0025488469,0.0009170905,0.0006463793,0.023838298],"genre_scores_gemma":[0.9658998,0.00060022564,0.024867555,0.00026223317,0.00008574282,0.0026201955,0.0007582586,0.0001051025,0.0048008207],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99224675,0.0028695988,0.0012104614,0.00028321167,0.002909709,0.00048033943],"domain_scores_gemma":[0.9859213,0.0030599192,0.0030074317,0.00053983746,0.0049845497,0.0024869612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075826254,0.0004576116,0.0006089087,0.001690483,0.0007066261,0.0011119032,0.00057643757,0.0003797866,0.002697891],"category_scores_gemma":[0.022503473,0.0002541043,0.00075427233,0.0008486175,0.00056544784,0.0009659768,0.0022754287,0.0012508008,0.0007014454],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005905476,0.0037471734,0.34269518,0.000729446,0.00026116462,0.00025723016,0.008526949,0.0007361999,0.0057194843,0.0006650517,0.02687809,0.6091935],"study_design_scores_gemma":[0.00020137288,0.004046191,0.9586962,0.00034478316,0.00013334214,0.00040628738,0.0051205796,0.002126955,0.005057748,0.0007542357,0.022979237,0.00013312841],"about_ca_topic_score_codex":0.0015826449,"about_ca_topic_score_gemma":0.0032728391,"teacher_disagreement_score":0.0075826254,"about_ca_system_score_codex":0.00085840316,"about_ca_system_score_gemma":0.0020331426,"threshold_uncertainty_score":0.04010123},"labels":[],"label_agreement":null},{"id":"W3137617126","doi":"10.3138/cjpe.69753","title":"The Role of Evaluative Thinking in the Teaching of Evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Salient; Psychology; Pedagogy; Balance (ability); Professional development; Medical education; Engineering ethics; Mathematics education; Political science; Medicine; Engineering","score_opus":0.2792685004296206,"score_gpt":0.5495539625772053,"score_spread":0.27028546214758475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137617126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037265696,0.020479424,0.48499098,0.21084575,0.0049463953,0.00077923137,0.000043343607,0.0007652915,0.23988383],"genre_scores_gemma":[0.8079251,0.0071850354,0.15926468,0.012312742,0.0014117523,0.0009012195,0.000024718316,0.0005277198,0.0104471035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8547837,0.12749995,0.003077077,0.0029063027,0.0094314385,0.002301413],"domain_scores_gemma":[0.68980986,0.2729781,0.004736535,0.010767686,0.016720809,0.0049869227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10646729,0.00082091097,0.00077841117,0.003583485,0.008360553,0.02454098,0.0029317746,0.0027823125,0.0043221344],"category_scores_gemma":[0.115719214,0.00070632144,0.00072945154,0.0018855849,0.04747445,0.013765153,0.009282039,0.015705138,0.00072377484],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009195503,0.00025671592,0.0015476807,0.0009937908,0.000033472475,0.00027994587,0.15851244,0.0014385957,0.0007847129,0.634097,0.014985537,0.18697818],"study_design_scores_gemma":[0.00006704145,0.00020680769,0.0011519834,0.004539677,0.00003299183,0.00053420983,0.07666662,0.005637053,0.0035376912,0.62132496,0.28617054,0.000130483],"about_ca_topic_score_codex":0.0041993894,"about_ca_topic_score_gemma":0.004984005,"teacher_disagreement_score":0.10646729,"about_ca_system_score_codex":0.014802366,"about_ca_system_score_gemma":0.017315382,"threshold_uncertainty_score":0.56305957},"labels":[],"label_agreement":null},{"id":"W3137926421","doi":"10.3138/cjpe.71156","title":"Establishing and Developing Professional Evaluator Dispositions","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Professional development; Order (exchange); Engineering ethics; Pedagogy; Medical education; Medicine","score_opus":0.36322189242453295,"score_gpt":0.5554788230819199,"score_spread":0.19225693065738692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137926421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79466575,0.0010212606,0.11011852,0.013367808,0.00055937684,0.0031180305,0.00015818952,0.00072237535,0.076268606],"genre_scores_gemma":[0.90979576,0.0004448218,0.08271798,0.0007847653,0.000056950437,0.0011271515,0.00016013386,0.00005302369,0.0048593977],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9611442,0.026531396,0.0024000478,0.0016595229,0.0065059387,0.0017588654],"domain_scores_gemma":[0.84851295,0.055634543,0.016423762,0.015044431,0.051396433,0.012987887],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08967573,0.00026285736,0.00038904307,0.0026750434,0.0033729076,0.005923663,0.0011225545,0.0009140561,0.0028280348],"category_scores_gemma":[0.13436273,0.00049883465,0.00040866988,0.000717069,0.0023696711,0.0034318834,0.0067036985,0.002110263,0.0010311351],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003273986,0.001843762,0.2114976,0.0007513263,0.000065829845,0.000441157,0.074250914,0.0014161353,0.005725055,0.031231172,0.021628058,0.65082157],"study_design_scores_gemma":[0.00036710576,0.004392581,0.41549397,0.0070888773,0.0002596198,0.0016449244,0.1898563,0.018487316,0.033887565,0.07514394,0.25277638,0.00060141727],"about_ca_topic_score_codex":0.0015513528,"about_ca_topic_score_gemma":0.00413949,"teacher_disagreement_score":0.99584204,"about_ca_system_score_codex":0.0041579516,"about_ca_system_score_gemma":0.016920084,"threshold_uncertainty_score":0.47425628},"labels":[],"label_agreement":null},{"id":"W3138644234","doi":"10.3138/cjpe.69751","title":"Offering Graduate Evaluation Degrees Online: Comparing Student Engagement in Two Canadian Programs","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University; University of Victoria","funders":"","keywords":"Certificate; Set (abstract data type); Graduate students; Online learning; Medical education; Tone (literature); Psychology; Mathematics education; Pedagogy; Computer science; Multimedia; Medicine","score_opus":0.7266241610460255,"score_gpt":0.6005049424468304,"score_spread":0.12611921859919506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138644234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96110904,0.0004938905,0.00096076657,0.0037515669,0.0001551572,0.00072717975,0.00044952412,0.00009710008,0.03225581],"genre_scores_gemma":[0.98589236,0.00051683467,0.0019801,0.001176083,0.000042078493,0.00058814,0.0004625896,0.00007386907,0.009267953],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9838254,0.0046019736,0.00046323627,0.0009342886,0.00458337,0.0055917506],"domain_scores_gemma":[0.9477955,0.0071246657,0.0022743684,0.001245784,0.017776001,0.023783715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017996632,0.00050257734,0.0006101746,0.0028131278,0.011950081,0.007247361,0.0026718853,0.0015501486,0.004885767],"category_scores_gemma":[0.03876998,0.00056822837,0.0005247626,0.0041619632,0.0035746591,0.0020565952,0.008902132,0.003224496,0.00077365316],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023082194,0.0056716413,0.19466141,0.00067617407,0.000115581046,0.0005428638,0.4139664,0.00096973084,0.002526002,0.007095904,0.031877827,0.33958822],"study_design_scores_gemma":[0.00021401967,0.0021643161,0.4153022,0.00085579953,0.000073413736,0.00013825516,0.4525928,0.0013618956,0.0024000679,0.0011842966,0.12342268,0.00029028417],"about_ca_topic_score_codex":0.81905746,"about_ca_topic_score_gemma":0.9336818,"teacher_disagreement_score":0.18094254,"about_ca_system_score_codex":0.066554725,"about_ca_system_score_gemma":0.13060594,"threshold_uncertainty_score":0.4828906},"labels":[],"label_agreement":null},{"id":"W3138688726","doi":"10.3138/cjpe.69697","title":"Pinpointing Where to Start: A Reflective Analysis on the Introductory Evaluation Course","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Course (navigation); Reflective practice; Mathematics education; Process (computing); Psychology; Graduate students; Computer science; Course evaluation; Learning theory; Pedagogy; Higher education; Engineering","score_opus":0.33797496032700913,"score_gpt":0.5470026099765712,"score_spread":0.2090276496495621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138688726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6177268,0.000775284,0.2766605,0.027718915,0.0015832324,0.005738309,0.00036740288,0.0011214659,0.06830809],"genre_scores_gemma":[0.79479516,0.00062558823,0.16414148,0.0028408577,0.0002992907,0.002189571,0.0003171945,0.0004944405,0.034296405],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9708939,0.01853825,0.0011084871,0.0016059143,0.0058915266,0.0019619244],"domain_scores_gemma":[0.9259949,0.039074067,0.0031439383,0.0060273213,0.021887673,0.0038721657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028335609,0.00067774946,0.0006453217,0.0029301597,0.00615981,0.007528478,0.00231609,0.0016773527,0.0038682756],"category_scores_gemma":[0.10543664,0.00055298075,0.0005162472,0.0014320455,0.0036871852,0.003865023,0.005352697,0.004725688,0.001455381],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043804295,0.001150914,0.011359893,0.00050720235,0.000032938584,0.0017995327,0.37060454,0.0012028933,0.0176162,0.024484359,0.03334883,0.5374547],"study_design_scores_gemma":[0.000109580564,0.001790236,0.026445268,0.0022863557,0.00008580578,0.0014626287,0.50486666,0.009718806,0.034144837,0.030290358,0.38838056,0.00041883596],"about_ca_topic_score_codex":0.0019602962,"about_ca_topic_score_gemma":0.0030075654,"teacher_disagreement_score":0.028335609,"about_ca_system_score_codex":0.0052779634,"about_ca_system_score_gemma":0.010268166,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3138870977","doi":"10.3138/cjpe.69577","title":"Competency-Based Evaluation Education: Four Essential Things to Know and Do","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Pace; Lifelong learning; Perspective (graphical); Context (archaeology); Psychology; Knowledge management; Pedagogy; Computer science; Medical education; Medicine","score_opus":0.1726522912841817,"score_gpt":0.5158863399418671,"score_spread":0.34323404865768536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138870977","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04540456,0.0064725634,0.295865,0.5252581,0.0023249874,0.003327973,0.00010356817,0.0017448111,0.119498394],"genre_scores_gemma":[0.49385783,0.004778376,0.45316863,0.023750033,0.00062811695,0.001804036,0.00014982937,0.00021127814,0.021651886],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96426845,0.021861786,0.0023464905,0.00082854566,0.008937219,0.0017575525],"domain_scores_gemma":[0.930004,0.0312174,0.0031531868,0.005800079,0.017572744,0.012252507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06587691,0.0007285477,0.00059974386,0.0017533654,0.005267879,0.013190247,0.0020959997,0.0041022897,0.0037220072],"category_scores_gemma":[0.06455199,0.0005932842,0.0005558422,0.000874984,0.012325828,0.010011842,0.009645775,0.011206655,0.0012942158],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013152209,0.0010780949,0.00946945,0.0016941561,0.000038979542,0.00046890258,0.032305416,0.00089271617,0.0024305906,0.21500437,0.074192904,0.66229284],"study_design_scores_gemma":[0.00019283168,0.0010933997,0.023452142,0.009687872,0.00009066672,0.002494993,0.06340746,0.0075200023,0.011283775,0.37978953,0.500557,0.00043023343],"about_ca_topic_score_codex":0.0061093373,"about_ca_topic_score_gemma":0.012256176,"teacher_disagreement_score":0.06587691,"about_ca_system_score_codex":0.007686724,"about_ca_system_score_gemma":0.053615198,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3138888840","doi":"10.3138/cjpe.69576","title":"Using People Styles for Interpersonal Competence: Encouraging Purposeful Reflection on Communication Behaviours","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Communication in Education and Healthcare","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpersonal communication; Psychology; Competence (human resources); Learning styles; Reflection (computer programming); Social skills; Reflective practice; Interpersonal relationship; Context (archaeology); Applied psychology; Medical education; Pedagogy; Social psychology; Computer science; Psychotherapist; Medicine","score_opus":0.4291146031292081,"score_gpt":0.5497583929625408,"score_spread":0.12064378983333268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138888840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74983066,0.00063906744,0.17182451,0.0062742378,0.00046837112,0.0032537032,0.000079992176,0.0011491777,0.066480234],"genre_scores_gemma":[0.8421991,0.00084793346,0.14840063,0.00093265786,0.00006890432,0.0024966872,0.00006318375,0.00014220153,0.0048487396],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9667644,0.025209067,0.0011070074,0.00077088,0.005292177,0.0008565383],"domain_scores_gemma":[0.94960445,0.035436496,0.0034728108,0.004005127,0.0048620338,0.0026190877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028868075,0.00075175613,0.00039636163,0.0012288333,0.0013957941,0.0037143887,0.00091814983,0.00071234524,0.0016559158],"category_scores_gemma":[0.06584114,0.00033663222,0.0006194439,0.00041037038,0.0019947572,0.0024390693,0.0047337264,0.0020522322,0.0006187234],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021300491,0.0026985148,0.027938874,0.0011130758,0.00007105051,0.0002475405,0.17275119,0.0006599783,0.011786651,0.0050849426,0.0076036355,0.76983154],"study_design_scores_gemma":[0.00057009014,0.010558308,0.24572474,0.009731718,0.0004721132,0.0037460981,0.2968631,0.016905783,0.0998664,0.059553456,0.25518346,0.0008248048],"about_ca_topic_score_codex":0.0005754906,"about_ca_topic_score_gemma":0.001523425,"teacher_disagreement_score":0.028868075,"about_ca_system_score_codex":0.0010927957,"about_ca_system_score_gemma":0.00340931,"threshold_uncertainty_score":0.1526708},"labels":[],"label_agreement":null},{"id":"W3138951062","doi":"10.3138/cjpe.71277","title":"Why a Special Issue of Practice Notes about How to Teach Evaluation?: Introducing This Special Issue of The <i>Canadian Journal of Program Evaluation</i>","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Special education; Engineering ethics; Medical education; Psychology; Management science; Library science; Computer science; Mathematics education; Medicine; Engineering","score_opus":0.17232126878233858,"score_gpt":0.4894143158310076,"score_spread":0.31709304704866903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138951062","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002574261,0.034058176,0.0011037362,0.5039063,0.4408544,0.00011273005,0.000113880626,0.00020637152,0.019386938],"genre_scores_gemma":[0.006949963,0.06116824,0.0033019627,0.24547555,0.5671749,0.00027765075,0.00037908438,0.0008340671,0.11443867],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98760843,0.0021596758,0.0010751963,0.0011096859,0.0068302257,0.0012166629],"domain_scores_gemma":[0.9454633,0.015224603,0.0021583259,0.0024821386,0.02347348,0.011198128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015420027,0.0015355839,0.0015884005,0.0051615844,0.00745187,0.01383418,0.0041277655,0.014108737,0.03525206],"category_scores_gemma":[0.050258093,0.0011552343,0.001253206,0.0037688084,0.01295253,0.0099968985,0.0055162334,0.019216837,0.01168026],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032221164,0.000013005306,0.000051461073,0.00008933418,0.0000015962487,0.00002277814,0.00012724864,0.000016767044,0.00004135238,0.0015381596,0.9859561,0.0121389665],"study_design_scores_gemma":[0.0000030011188,0.000007740206,0.00031735582,0.00030940885,0.0000022640652,0.000072918505,0.0002816149,0.000028353403,0.000023643908,0.0010785843,0.9978611,0.000014064211],"about_ca_topic_score_codex":0.11170521,"about_ca_topic_score_gemma":0.27646974,"teacher_disagreement_score":0.11170521,"about_ca_system_score_codex":0.022008933,"about_ca_system_score_gemma":0.030977683,"threshold_uncertainty_score":0.22211003},"labels":[],"label_agreement":null},{"id":"W3139404955","doi":"10.3138/cjpe.71359","title":"Re-Envisioning Evaluation Pedagogy with a Community of Scholar Teachers","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Pedagogy; Sociology; Psychology","score_opus":0.4830094280355481,"score_gpt":0.5808736776311207,"score_spread":0.09786424959557266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139404955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031788517,0.005100841,0.39778456,0.31627885,0.006087188,0.0013787359,0.000054333057,0.0017519878,0.239775],"genre_scores_gemma":[0.6376491,0.0028870632,0.21305081,0.028152961,0.0016352554,0.0011466364,0.000106879015,0.0011140455,0.11425726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.93649083,0.049265586,0.0013376814,0.003526878,0.00750275,0.00187628],"domain_scores_gemma":[0.9231198,0.0321934,0.0029988047,0.01181619,0.018402265,0.011469526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07809066,0.0009248913,0.0010157722,0.0031862902,0.01626325,0.031789377,0.004486785,0.0064989566,0.009155082],"category_scores_gemma":[0.07108867,0.0007176936,0.00081239874,0.0015680597,0.046861395,0.027412685,0.026174573,0.015121949,0.0029718024],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054664284,0.00042704152,0.0018973226,0.0003014023,0.00005478902,0.000462218,0.11994697,0.00074254465,0.0011853089,0.68391067,0.07130006,0.119717054],"study_design_scores_gemma":[0.000083770174,0.0001585019,0.000787169,0.000829131,0.000034401215,0.000507751,0.06084105,0.0021640954,0.0009044759,0.45706618,0.47654313,0.00008029858],"about_ca_topic_score_codex":0.0091234725,"about_ca_topic_score_gemma":0.02474937,"teacher_disagreement_score":0.07809066,"about_ca_system_score_codex":0.011447921,"about_ca_system_score_gemma":0.036950845,"threshold_uncertainty_score":0.41298783},"labels":[],"label_agreement":null},{"id":"W3139438442","doi":"10.3138/cjpe.69696","title":"Teaching Africa-Rooted Evaluation: Using a “Model Client” Innovation to Help Shift the Locus of Knowledge Production","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Economic shortage; Space (punctuation); Sociology; Vulnerability (computing); Knowledge management; Pedagogy; Computer science; Public relations; Psychology; Political science","score_opus":0.5584913811322083,"score_gpt":0.5574010113067539,"score_spread":0.001090369825454407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139438442","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20930347,0.0016061959,0.47904944,0.12740502,0.0011218424,0.0018401548,0.00007701671,0.001256039,0.17834081],"genre_scores_gemma":[0.7885906,0.0012037614,0.18163188,0.0065539596,0.00016517896,0.0010008998,0.00004000382,0.00044612316,0.020367587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93413156,0.05610856,0.0010665242,0.0017395965,0.005004417,0.0019492927],"domain_scores_gemma":[0.9254313,0.04566803,0.0030810747,0.008868491,0.010648652,0.006302406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06414047,0.00069593516,0.00053896155,0.0017603817,0.0092845475,0.016092226,0.0032941941,0.0024762198,0.009560849],"category_scores_gemma":[0.06749608,0.0007684929,0.00048173007,0.001340551,0.012218493,0.015119995,0.0147425635,0.0069857347,0.0020567402],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024056596,0.0014781619,0.009708111,0.00082910486,0.00004498088,0.0010599919,0.34121677,0.0017558136,0.0059083807,0.24076872,0.035966434,0.361023],"study_design_scores_gemma":[0.00020150236,0.00085483585,0.004403181,0.0036783095,0.000102486374,0.002154453,0.27875146,0.015714705,0.02087581,0.1717855,0.50126064,0.00021717897],"about_ca_topic_score_codex":0.003930108,"about_ca_topic_score_gemma":0.009897447,"teacher_disagreement_score":0.06414047,"about_ca_system_score_codex":0.011483815,"about_ca_system_score_gemma":0.02621077,"threshold_uncertainty_score":0.3392113},"labels":[],"label_agreement":null},{"id":"W3139526458","doi":"10.3138/cjpe.69797","title":"If Building Trust Is Important, How Do We Teach Novice Evaluators to Do It?","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Focus (optics); Work (physics); Knowledge management; Key (lock); Psychology; Computer science; Engineering ethics; Pedagogy; Engineering","score_opus":0.2393113993722523,"score_gpt":0.5137830673082322,"score_spread":0.2744716679359799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139526458","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10764997,0.011678892,0.1584254,0.61606735,0.004446734,0.0019311304,0.00012353352,0.00091353775,0.09876354],"genre_scores_gemma":[0.7887649,0.008209102,0.15648785,0.032899812,0.0007951255,0.0018673623,0.0001235189,0.0002848937,0.010567398],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.91847444,0.06384899,0.0028290823,0.0020544715,0.008349392,0.0044435062],"domain_scores_gemma":[0.70014936,0.16765174,0.019311959,0.013682977,0.069310285,0.029893681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12481144,0.00048075456,0.00097178493,0.0015206792,0.006136393,0.014941983,0.0017676321,0.0035970614,0.004827627],"category_scores_gemma":[0.23708259,0.00053433544,0.0006525248,0.00097450096,0.007482563,0.015593167,0.0067458106,0.0071812323,0.0020769206],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027630987,0.0013140148,0.03893055,0.0030014445,0.00014865313,0.0006000064,0.064575754,0.001300492,0.0021800536,0.07013626,0.12302417,0.69451225],"study_design_scores_gemma":[0.00029568307,0.001795087,0.04639325,0.024769256,0.0002847456,0.0014649027,0.19268456,0.007613569,0.013158532,0.25808367,0.4528527,0.0006040595],"about_ca_topic_score_codex":0.0053237826,"about_ca_topic_score_gemma":0.0129696475,"teacher_disagreement_score":0.12481144,"about_ca_system_score_codex":0.0088142,"about_ca_system_score_gemma":0.027336592,"threshold_uncertainty_score":0.6600739},"labels":[],"label_agreement":null},{"id":"W3177752890","doi":"10.3138/cjpe.70235","title":"Étude exploratoire de la pratique évaluative dans le domaine de la santé au Burkina Faso","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Healthcare Systems and Practices","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reflexivity; Psychology; Health sector; Political science; Sociology; Welfare economics; Environmental health; Medicine; Social science; Health services; Economics; Population","score_opus":0.14788876793747835,"score_gpt":0.5256761413084853,"score_spread":0.37778737337100693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177752890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97712654,0.004536089,0.005013014,0.004619124,0.00006397294,0.00037760026,0.000051331444,0.000011064854,0.008201283],"genre_scores_gemma":[0.9945614,0.0014188514,0.0027093706,0.0003273142,0.000012636614,0.00022245216,0.00001069868,0.0000055719074,0.0007317823],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.93288094,0.05913467,0.001810011,0.0009858687,0.0033780986,0.0018104712],"domain_scores_gemma":[0.89039963,0.086179,0.008755249,0.0018903917,0.0110914465,0.0016843295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08568152,0.00040446548,0.00064304576,0.002933222,0.006088714,0.006502929,0.00070845004,0.0010974528,0.0012062151],"category_scores_gemma":[0.07474188,0.000348128,0.0002977066,0.0028907584,0.005219965,0.0035615258,0.0047211535,0.001888884,0.000097816366],"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":[0.00012284306,0.00021031941,0.05219715,0.0010480294,0.000046999907,0.001282147,0.8610298,0.0003131451,0.0019770875,0.0048813834,0.0004424508,0.07644853],"study_design_scores_gemma":[0.000017663253,0.0002478947,0.060547214,0.002679314,0.0000329329,0.0006484793,0.9074495,0.00048452968,0.0012785504,0.0013906793,0.025180677,0.000042609445],"about_ca_topic_score_codex":0.03210898,"about_ca_topic_score_gemma":0.047428038,"teacher_disagreement_score":0.08568152,"about_ca_system_score_codex":0.014273975,"about_ca_system_score_gemma":0.0199859,"threshold_uncertainty_score":0.45313263},"labels":[],"label_agreement":null},{"id":"W320086979","doi":"10.3138/cjpe.24.006","title":"The Downward Trend of Survey Response Rates: Implications and Considerations for Evaluators","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Respondent; Non-response bias; Telephone survey; Current Population Survey; Survey data collection; Psychology; Government (linguistics); Variety (cybernetics); Demographic economics; Population; Response bias; Demography; Econometrics; Social psychology; Statistics; Economics; Political science; Sociology; Business; Marketing; Mathematics","score_opus":0.613190273985666,"score_gpt":0.5602416078357147,"score_spread":0.052948666149951196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W320086979","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20022187,0.008749821,0.16013305,0.5843053,0.0038562894,0.0049913824,0.0016657955,0.0010393816,0.03503721],"genre_scores_gemma":[0.78279215,0.0035287745,0.13786043,0.06029817,0.0014476841,0.008312123,0.0004935209,0.00041601094,0.004851156],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.45180854,0.46103665,0.028324572,0.0063473443,0.04959655,0.0028862697],"domain_scores_gemma":[0.25957373,0.580575,0.03544527,0.021653986,0.099172704,0.0035793895],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5293983,0.0006916925,0.0012600842,0.0047940384,0.0030498581,0.0058841887,0.0036302647,0.0027234682,0.0030505122],"category_scores_gemma":[0.69123614,0.00060658884,0.0009996712,0.006035487,0.0058726524,0.0062763914,0.003106345,0.0046783574,0.0011855926],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011549513,0.00033475028,0.23594548,0.003923222,0.00031808828,0.0009790197,0.04570126,0.0029522332,0.0032669737,0.043698233,0.09094061,0.5707852],"study_design_scores_gemma":[0.0006699917,0.0035191353,0.50910926,0.01741948,0.0005776667,0.003094076,0.08957858,0.031921577,0.014894756,0.07008816,0.25847575,0.0006515463],"about_ca_topic_score_codex":0.015910774,"about_ca_topic_score_gemma":0.019879743,"teacher_disagreement_score":0.47060168,"about_ca_system_score_codex":0.008472195,"about_ca_system_score_gemma":0.011897122,"threshold_uncertainty_score":0.58033574},"labels":[],"label_agreement":null},{"id":"W3205038101","doi":"10.3138/cjpe.69949","title":"Evaluation Advisory Groups: Considerations for Design and Management","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Advisory committee; Resource (disambiguation); Scale (ratio); Political science; Computer science; Public administration; Geography","score_opus":0.5679625182669052,"score_gpt":0.5376190604386261,"score_spread":0.030343457828279186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205038101","genre_codex":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00449222,0.009270862,0.3465315,0.5250461,0.013788958,0.025243698,0.00040640042,0.0025969734,0.072623156],"genre_scores_gemma":[0.12019704,0.0061103688,0.67341167,0.081299834,0.0076920465,0.08567145,0.0004060316,0.0016083736,0.023603184],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.15579289,0.7610909,0.03397039,0.005320617,0.039620377,0.0042048665],"domain_scores_gemma":[0.07767825,0.662416,0.027154218,0.06737406,0.14697546,0.018402003],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7604818,0.0019954361,0.0035572334,0.007348035,0.017366873,0.037428286,0.011757409,0.022521289,0.023001522],"category_scores_gemma":[0.8246855,0.0031413184,0.002529413,0.009628253,0.02122856,0.038188193,0.019367903,0.021087283,0.013540733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091894245,0.0005373446,0.002443277,0.0047874395,0.00017886718,0.00044305722,0.023222001,0.002098235,0.00074799743,0.1873815,0.30288774,0.4743536],"study_design_scores_gemma":[0.0010436028,0.0008586919,0.0024328653,0.020705853,0.00018681528,0.00050832337,0.018717462,0.006069063,0.0009877452,0.20815669,0.7399121,0.0004207563],"about_ca_topic_score_codex":0.005656249,"about_ca_topic_score_gemma":0.007651643,"teacher_disagreement_score":0.23951823,"about_ca_system_score_codex":0.022286851,"about_ca_system_score_gemma":0.08745787,"threshold_uncertainty_score":0.29536867},"labels":[],"label_agreement":null},{"id":"W3205359208","doi":"10.3138/cjpe.72911","title":"Trena M. Paulus and Jessica N. Lester. (2021). <i>Doing Qualitative Research in a Digital World</i> .","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Focus Groups and Qualitative Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Qualitative research; Sociology; Media studies; Library science; Psychology; Social science; Computer science","score_opus":0.45690969009530114,"score_gpt":0.6064682169151608,"score_spread":0.1495585268198597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205359208","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017729906,0.4932942,0.04706949,0.37960124,0.026609719,0.0022398515,0.002327376,0.0015861867,0.045498922],"genre_scores_gemma":[0.024474269,0.56308544,0.147013,0.10097572,0.005042425,0.010915073,0.0026472965,0.0018925717,0.14395417],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98904103,0.005875141,0.00075939676,0.0006102726,0.0034326715,0.0002814926],"domain_scores_gemma":[0.9388618,0.039352164,0.0031449243,0.0010239474,0.013706088,0.0039111758],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03453895,0.0016148237,0.0011168098,0.0042733443,0.0056321607,0.0047116675,0.0022464797,0.00425589,0.025493884],"category_scores_gemma":[0.059459317,0.0028043666,0.00070879684,0.0042056134,0.0036374624,0.009230919,0.0055736657,0.008583043,0.022680702],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003808889,0.000021679887,0.00037301512,0.0020790126,0.000009170462,0.00010993913,0.0068373717,0.000047823673,0.00048272798,0.0026587746,0.7890073,0.19833504],"study_design_scores_gemma":[0.00004239312,0.00005347148,0.0020574878,0.012164165,0.000030912084,0.00049518805,0.008113693,0.00012209968,0.00048114196,0.011641961,0.9647338,0.000063725725],"about_ca_topic_score_codex":0.024016175,"about_ca_topic_score_gemma":0.059682842,"teacher_disagreement_score":0.9654611,"about_ca_system_score_codex":0.0039012288,"about_ca_system_score_gemma":0.017830541,"threshold_uncertainty_score":0.18266165},"labels":[],"label_agreement":null},{"id":"W3205524844","doi":"10.3138/cjpe.72833","title":"Beverly Parsons, Lovely Dhillon, and Matt Keene (Eds.). (2020). <i>Visionary Evaluation for a Sustainable, Equitable Future.</i>","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Environmental ethics; Philosophy","score_opus":0.148458665966718,"score_gpt":0.471744497342231,"score_spread":0.32328583137551303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205524844","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025681776,0.83438975,0.0026890473,0.09796096,0.016268464,0.000044864602,0.0010595182,0.0002913214,0.047039323],"genre_scores_gemma":[0.002694498,0.9056168,0.0029353944,0.0073142066,0.0035305566,0.00006313481,0.0010545554,0.00022262079,0.076568134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971506,0.0005415483,0.00019547774,0.00023778014,0.0017152742,0.00015943462],"domain_scores_gemma":[0.9935368,0.0024624038,0.0004411564,0.000110180335,0.0026058028,0.0008436685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044717244,0.0024949126,0.00161832,0.0027683012,0.0018423796,0.006870633,0.0019351414,0.0037791904,0.040392518],"category_scores_gemma":[0.008567439,0.0014098247,0.0007593293,0.0048820153,0.0012149944,0.008392255,0.0018527075,0.004991578,0.04469284],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015675827,0.000008382348,0.00011767057,0.00040993033,0.0000065818404,0.000013294048,0.00009066051,0.000055126053,0.000035942776,0.00092764234,0.90956366,0.088755436],"study_design_scores_gemma":[0.000010814811,0.000012024531,0.0006514283,0.0015814936,0.00003212541,0.00008004327,0.0003293481,0.00008822722,0.00013403677,0.001775349,0.99528307,0.000022073134],"about_ca_topic_score_codex":0.07961105,"about_ca_topic_score_gemma":0.19676358,"teacher_disagreement_score":0.07961105,"about_ca_system_score_codex":0.0035593587,"about_ca_system_score_gemma":0.0136534,"threshold_uncertainty_score":0.15829533},"labels":[],"label_agreement":null},{"id":"W3206030918","doi":"10.3138/cjpe.70053","title":"Cultivating Cultural Competence","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conceptualization; Cultural competence; Competence (human resources); Cultural diversity; Psychology; Epistemology; Sociology; Engineering ethics; Social psychology; Pedagogy; Anthropology; Computer science; Philosophy","score_opus":0.5646603306791933,"score_gpt":0.585671718843883,"score_spread":0.021011388164689726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206030918","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42127758,0.0025967339,0.06568712,0.03446166,0.00031701723,0.0008362613,0.00007247347,0.0002288338,0.4745223],"genre_scores_gemma":[0.97751355,0.00072277524,0.017691167,0.0012212738,0.000034505654,0.00018560844,0.000022378394,0.000022787843,0.0025859778],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97972775,0.01454976,0.00053702795,0.000953844,0.0030716392,0.0011599814],"domain_scores_gemma":[0.9604805,0.022535373,0.003195857,0.003978023,0.0051612174,0.0046489886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028319275,0.00045418993,0.0004527891,0.0021930616,0.0034137084,0.0082090525,0.0012255907,0.0012672492,0.004696314],"category_scores_gemma":[0.042446777,0.0002521908,0.0004197633,0.0009766165,0.010308971,0.0040013553,0.018981228,0.002504554,0.00064041524],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001009441,0.001815919,0.030228509,0.0013862639,0.000107747815,0.0006693709,0.10262859,0.0018127717,0.0064323614,0.39800307,0.013858843,0.44295555],"study_design_scores_gemma":[0.00018901326,0.0013993714,0.06276729,0.0074074087,0.0002501737,0.0013165745,0.12950696,0.008233656,0.016727118,0.4272925,0.3447048,0.00020513812],"about_ca_topic_score_codex":0.0028659892,"about_ca_topic_score_gemma":0.0044159414,"teacher_disagreement_score":0.028319275,"about_ca_system_score_codex":0.0049649253,"about_ca_system_score_gemma":0.015372896,"threshold_uncertainty_score":0.14976841},"labels":[],"label_agreement":null},{"id":"W3206200039","doi":"10.3138/cjpe.68386","title":"Practice Notes from a Participatory Impact Evaluation of a Leadership Development Program for People Living with HIV","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Pacific AIDS Network","funders":"","keywords":"Participatory evaluation; Citizen journalism; Participatory GIS; Work (physics); Sociology; Participatory development; Participatory action research; Knowledge management; Public relations; Management science; Political science; Computer science; Engineering; Social science","score_opus":0.6469295512114422,"score_gpt":0.5709009173924243,"score_spread":0.07602863381901792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206200039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6494888,0.020885205,0.06676033,0.096508235,0.0029041667,0.05619795,0.0034416504,0.00047573674,0.10333795],"genre_scores_gemma":[0.80505764,0.011138608,0.12388856,0.008656789,0.00039267205,0.03312025,0.0010640708,0.00023184516,0.016449507],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.77177984,0.19772568,0.009551936,0.0027739326,0.015222512,0.002946099],"domain_scores_gemma":[0.620745,0.29883775,0.01009285,0.014996763,0.050696034,0.004631512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23456806,0.0009456934,0.0011098423,0.002978276,0.008527644,0.0032891664,0.0027532747,0.0024250364,0.005034613],"category_scores_gemma":[0.23170958,0.0010511341,0.0016072318,0.0044075367,0.0033641767,0.0029671083,0.007864915,0.0033976228,0.0006043009],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002276642,0.003361068,0.014366671,0.017108671,0.0006661436,0.002301998,0.26242426,0.0027067275,0.0030742008,0.008283934,0.042503946,0.64092577],"study_design_scores_gemma":[0.005262436,0.01754191,0.033744372,0.055838116,0.0021356437,0.0018854991,0.3986527,0.0022066496,0.01676114,0.013934158,0.45144415,0.0005932776],"about_ca_topic_score_codex":0.021393307,"about_ca_topic_score_gemma":0.0645745,"teacher_disagreement_score":0.23456806,"about_ca_system_score_codex":0.015361561,"about_ca_system_score_gemma":0.030460864,"threshold_uncertainty_score":0.9439139},"labels":[],"label_agreement":null},{"id":"W3207991248","doi":"10.3138/cjpe.71575","title":"The Rights of Nature: An Emerging Transformation Opportunity for Evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"David and Lucile Packard Foundation","keywords":"Anthropocene; Generative grammar; Coronavirus disease 2019 (COVID-19); Natural (archaeology); Sociology; Epistemology; Environmental ethics; Law and economics; Political science; Business; Knowledge management; Computer science; Geography","score_opus":0.4074894549911969,"score_gpt":0.5699416873127253,"score_spread":0.16245223232152844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207991248","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011792807,0.019680224,0.0675969,0.65624225,0.0019139872,0.00031018216,0.00014935709,0.00023370991,0.24208061],"genre_scores_gemma":[0.8789356,0.012066994,0.06512589,0.0278518,0.0016163383,0.0006561608,0.00011325679,0.00020757936,0.013426369],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93035036,0.053247668,0.0017406618,0.0020178468,0.008954577,0.0036888996],"domain_scores_gemma":[0.844893,0.11287359,0.0024957103,0.008203682,0.019616922,0.011917001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14209332,0.0006126314,0.0013493366,0.004494672,0.01002778,0.029085018,0.003113685,0.010088525,0.010624074],"category_scores_gemma":[0.062702276,0.00045402348,0.00093105074,0.0038718637,0.06833034,0.025324795,0.01620573,0.0096302265,0.0006436743],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003322923,0.00006399863,0.0005933473,0.00018619254,0.000005984071,0.00013644007,0.0040975944,0.00022294789,0.00012614805,0.93027824,0.009247506,0.05500844],"study_design_scores_gemma":[0.00003463264,0.00008293515,0.00078522024,0.0015409491,0.000012715693,0.00018213633,0.015428943,0.0011825925,0.00044092612,0.7523744,0.22787967,0.000054856326],"about_ca_topic_score_codex":0.016845072,"about_ca_topic_score_gemma":0.02502723,"teacher_disagreement_score":0.14209332,"about_ca_system_score_codex":0.030924585,"about_ca_system_score_gemma":0.054320794,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W3209623811","doi":"10.3138/cjpe.71630","title":"Evaluation in Transition: The Promise and Challenge of South-South Cooperation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Salience (neuroscience); Political science; Narrative; Engineering ethics; International development; Narrative review; Public relations; Sociology; Psychology; Engineering","score_opus":0.37214611116267754,"score_gpt":0.4892118189386274,"score_spread":0.11706570777594988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209623811","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049244385,0.02213929,0.03301077,0.7488096,0.002039265,0.00046921053,0.00007950552,0.00022565016,0.14398237],"genre_scores_gemma":[0.9511169,0.0057064584,0.015690472,0.021431074,0.00046282852,0.0003350617,0.00003989928,0.00008749222,0.005129704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7660972,0.20100054,0.005468497,0.004691394,0.014813663,0.007928692],"domain_scores_gemma":[0.7466571,0.18109864,0.0072259614,0.012926741,0.033110105,0.018981446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1880239,0.0005039469,0.0013340407,0.0035349743,0.010893944,0.023964677,0.0024117117,0.0049678497,0.0060449573],"category_scores_gemma":[0.14101927,0.00042493665,0.0010275705,0.0029397935,0.03386069,0.017871497,0.023878569,0.010142431,0.00067145954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029795236,0.000245872,0.010181705,0.0016732202,0.000105648745,0.00044016683,0.06258026,0.0013001222,0.0004543283,0.6220421,0.025283115,0.27539548],"study_design_scores_gemma":[0.00011176498,0.0003792304,0.011014087,0.009031746,0.000083102874,0.00048885634,0.16665983,0.00189906,0.00079542794,0.55313975,0.25626212,0.00013510596],"about_ca_topic_score_codex":0.024868038,"about_ca_topic_score_gemma":0.02787636,"teacher_disagreement_score":0.1880239,"about_ca_system_score_codex":0.029456606,"about_ca_system_score_gemma":0.09032187,"threshold_uncertainty_score":0.99437726},"labels":[],"label_agreement":null},{"id":"W3209748599","doi":"10.3138/cjpe.72730","title":"Conclusion: Transforming Evaluation Practice for “Business Unusual”","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Key (lock); Business; Business practice; Clinical Practice; Process management; Knowledge management; Psychology; Computer science; Business administration; Medicine; Nursing; Computer security","score_opus":0.4903320513145368,"score_gpt":0.5952244765647577,"score_spread":0.10489242525022097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209748599","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010148688,0.0014336972,0.004878956,0.97924715,0.0075335987,0.00014076204,0.00011017112,0.00014420418,0.005496657],"genre_scores_gemma":[0.081218466,0.0032417288,0.027858082,0.8653024,0.008250955,0.0006332938,0.0003598659,0.00021671326,0.012918473],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95983285,0.022091832,0.0029640857,0.0019027111,0.01124834,0.0019601071],"domain_scores_gemma":[0.82769966,0.070351794,0.007535187,0.0077259643,0.072123885,0.014563477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05018012,0.00071379537,0.00052871194,0.0009664163,0.0025489284,0.00715646,0.0032722482,0.010358087,0.021851318],"category_scores_gemma":[0.20288767,0.00024707874,0.0010216526,0.001021311,0.005875621,0.009960103,0.006379461,0.011234768,0.00763333],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002557873,0.00018641516,0.00344347,0.0019360544,0.00007919652,0.0003372944,0.0025284393,0.00043027554,0.00039067568,0.04394257,0.84827924,0.098190546],"study_design_scores_gemma":[0.00021588113,0.00016970886,0.0062792767,0.009691582,0.00014803823,0.0008726297,0.013904585,0.0011148141,0.0015408647,0.14072892,0.8251987,0.00013500106],"about_ca_topic_score_codex":0.007997817,"about_ca_topic_score_gemma":0.01199146,"teacher_disagreement_score":0.05018012,"about_ca_system_score_codex":0.0066758874,"about_ca_system_score_gemma":0.03706459,"threshold_uncertainty_score":0.26538104},"labels":[],"label_agreement":null},{"id":"W3209866185","doi":"10.3138/cjpe.71527","title":"Catching the Wave: Harnessing Data Science to Support Evaluation’s Capacity for Making a Transformational Contribution to Sustainable Development","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Transformational leadership; Sustainable development; Field (mathematics); Set (abstract data type); Engineering ethics; Key (lock); Politics; Political science; Knowledge management; Data science; Computer science; Sociology; Management science; Public relations; Engineering","score_opus":0.584620824737506,"score_gpt":0.5460516450026884,"score_spread":0.03856917973481755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209866185","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037430964,0.008599939,0.27677685,0.43664354,0.0017987639,0.0018574911,0.00089327234,0.0013169713,0.2346822],"genre_scores_gemma":[0.7503338,0.0052930596,0.22206052,0.013814055,0.00086417125,0.0014626549,0.00042859514,0.00051277294,0.005230416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75388515,0.20096162,0.0061056134,0.005374395,0.028184028,0.0054892506],"domain_scores_gemma":[0.46911523,0.39444226,0.014920923,0.054502267,0.055679604,0.011339776],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29168347,0.00096683024,0.0016113321,0.010751217,0.0071016117,0.03247223,0.0040552625,0.00439639,0.007337917],"category_scores_gemma":[0.3863321,0.0008763666,0.0012865921,0.007354476,0.030315235,0.025495892,0.028255202,0.009085196,0.0012335018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025264506,0.00032034024,0.01445762,0.0016564878,0.00021644765,0.00023302672,0.016271628,0.006796411,0.0010413254,0.50544757,0.03871245,0.41459423],"study_design_scores_gemma":[0.0001667841,0.00029438708,0.00705254,0.007164982,0.00015141109,0.00013934137,0.022254148,0.017871717,0.0028497379,0.7081873,0.23361577,0.00025188885],"about_ca_topic_score_codex":0.035115913,"about_ca_topic_score_gemma":0.040245265,"teacher_disagreement_score":0.70831656,"about_ca_system_score_codex":0.02103991,"about_ca_system_score_gemma":0.085032985,"threshold_uncertainty_score":0.8734804},"labels":[],"label_agreement":null},{"id":"W3210430769","doi":"10.3138/cjpe.71495","title":"<i>kawiyahîtamik kesi wîcehtâsôk</i> : (To Examine in Order to Support/Redirect)","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"PolicyWise for Children & Families; University of Calgary","funders":"","keywords":"Indigenous; Ideology; Order (exchange); Service (business); Sociology; Program evaluation; Computer science; Psychology; Knowledge management; Political science; Business; Public administration; Marketing; Biology; Ecology; Law","score_opus":0.08183295273193161,"score_gpt":0.40178888823650616,"score_spread":0.3199559355045746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210430769","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035986,0.004256758,0.009569578,0.42406422,0.009737815,0.0010302082,0.0019310216,0.0011624944,0.51226187],"genre_scores_gemma":[0.29727829,0.0076301643,0.022654576,0.061691243,0.0018918572,0.0013138807,0.0014802113,0.00085983047,0.6051999],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99905115,0.00024355005,0.000064820415,0.00008998617,0.00036820967,0.00018229145],"domain_scores_gemma":[0.99535,0.0007803201,0.00037745418,0.00019072618,0.0025793696,0.0007221872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032001778,0.00030775275,0.0002466967,0.0008303417,0.005488038,0.0030771582,0.0009711712,0.001330135,0.050605],"category_scores_gemma":[0.008967435,0.00016916926,0.00015449045,0.00085606176,0.0018887294,0.0031686588,0.002695771,0.00249522,0.012392488],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044234086,0.00008651368,0.0063149487,0.00037123912,0.000005868987,0.00054093543,0.012763574,0.00010483821,0.0019055349,0.019282253,0.8625222,0.09605793],"study_design_scores_gemma":[0.0000067316555,0.000031264633,0.009790823,0.0003554272,0.000007034942,0.0004256228,0.011568568,0.00022271165,0.0014193251,0.0024895363,0.9736525,0.000030536925],"about_ca_topic_score_codex":0.08143353,"about_ca_topic_score_gemma":0.17888446,"teacher_disagreement_score":0.91856647,"about_ca_system_score_codex":0.0047262223,"about_ca_system_score_gemma":0.01229595,"threshold_uncertainty_score":0.1692906},"labels":[],"label_agreement":null},{"id":"W3210471454","doi":"10.3138/cjpe.70931","title":"L’apport du journal de bord en évaluation de programmes dans une perspective de pérennisation : le cas du programme HORS-PISTE","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"School Health and Nursing Education","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Logbook; Data collection; Psychology; Sociology; Social science; Biology","score_opus":0.1564193310943564,"score_gpt":0.47815759255214724,"score_spread":0.32173826145779083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210471454","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.154682,0.18688291,0.019160595,0.50999457,0.033360865,0.0025102973,0.00048014795,0.00030227183,0.09262634],"genre_scores_gemma":[0.83630097,0.06508093,0.03607471,0.038520493,0.005200781,0.0035669885,0.00029985092,0.0002934722,0.014661777],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7915039,0.16573215,0.007239679,0.0027950525,0.029139481,0.0035898015],"domain_scores_gemma":[0.7004373,0.21944425,0.012242823,0.0074626636,0.04736809,0.01304487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12578005,0.0007671261,0.0015832674,0.006672505,0.009824131,0.024550457,0.0028156342,0.007101413,0.0040135817],"category_scores_gemma":[0.203883,0.00092038204,0.0010940024,0.007112005,0.012232635,0.013507003,0.008932951,0.005825403,0.00036592546],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011128574,0.0015727726,0.016946716,0.016389264,0.0003317855,0.0021864122,0.20298599,0.0007091807,0.0015801468,0.15200496,0.09812616,0.50605375],"study_design_scores_gemma":[0.0003816333,0.0015418003,0.024587672,0.022050261,0.0003907121,0.0015798043,0.18418287,0.0011212729,0.0023781918,0.012856426,0.74872863,0.00020074444],"about_ca_topic_score_codex":0.042821288,"about_ca_topic_score_gemma":0.07302379,"teacher_disagreement_score":0.12578005,"about_ca_system_score_codex":0.031022687,"about_ca_system_score_gemma":0.07335795,"threshold_uncertainty_score":0.6651964},"labels":[],"label_agreement":null},{"id":"W3211030774","doi":"10.3138/cjpe.70804","title":"Creating Effectiveness Principles for Principles-Focused Developmental Evaluations in Health-Care Initiatives: Lessons Learned from Three Cases in British Columbia","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"","keywords":"Relevance (law); Process (computing); Health care; Management science; Process management; Health care delivery; Psychology; Engineering ethics; Computer science; Political science; Engineering","score_opus":0.7472221985233423,"score_gpt":0.6384194928905885,"score_spread":0.10880270563275374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211030774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77278787,0.0027243474,0.030792922,0.04221984,0.00022849323,0.008183925,0.0002805031,0.0002145337,0.14256759],"genre_scores_gemma":[0.9441199,0.00062047545,0.042028,0.002808769,0.000010805278,0.0030571253,0.00008826774,0.0000692359,0.0071974043],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9169906,0.061288748,0.0032537817,0.0015589,0.009135365,0.0077725244],"domain_scores_gemma":[0.8722233,0.08689081,0.0020069531,0.0041116434,0.027664728,0.007102474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10110379,0.0007559241,0.00088852254,0.002938691,0.02046345,0.009787387,0.0036179847,0.0041893893,0.0032270718],"category_scores_gemma":[0.10525763,0.0008639811,0.0006835642,0.0037696748,0.0094164265,0.0051416107,0.01084005,0.0073544923,0.00028355658],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063042884,0.0043130955,0.048889067,0.0029129141,0.00014596432,0.0092789605,0.3711344,0.008206135,0.0030264622,0.20728187,0.023281371,0.3208994],"study_design_scores_gemma":[0.0011569973,0.0021866015,0.06536146,0.009578037,0.00042613162,0.002254564,0.62225354,0.015471054,0.011834627,0.06591073,0.20282972,0.0007365482],"about_ca_topic_score_codex":0.67561215,"about_ca_topic_score_gemma":0.87433445,"teacher_disagreement_score":0.67561215,"about_ca_system_score_codex":0.10179976,"about_ca_system_score_gemma":0.16186655,"threshold_uncertainty_score":0.7386124},"labels":[],"label_agreement":null},{"id":"W3211253945","doi":"10.3138/cjpe.70502","title":"L’évaluation évolutive, de la théorie à la pratique : perspectives de praticiens québécois","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique; University of Victoria; Université de Sherbrooke","funders":"","keywords":"Summative assessment; Formative assessment; Valuation (finance); Sociology; Business; Knowledge management; Political science; Pedagogy; Computer science; Accounting","score_opus":0.17542502317927477,"score_gpt":0.5004563917657058,"score_spread":0.325031368586431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211253945","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22070085,0.048511524,0.020347299,0.38088575,0.0011546031,0.00030029318,0.00020369723,0.00012945055,0.3277665],"genre_scores_gemma":[0.9570488,0.006059143,0.0043260846,0.0054677106,0.000103303544,0.000118032855,0.000046498702,0.000046992598,0.026783578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98542076,0.009307442,0.00025437985,0.00069059565,0.0026855366,0.0016414234],"domain_scores_gemma":[0.9654717,0.017819269,0.0010678172,0.0008395292,0.012026252,0.0027754263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024703575,0.00056826737,0.0005465153,0.0030605346,0.017406905,0.013241632,0.0025411379,0.003994664,0.0054407096],"category_scores_gemma":[0.02256805,0.0003052849,0.00045642245,0.0030973342,0.036245164,0.006270393,0.0033546027,0.004947387,0.00029482387],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00009509578,0.00017621618,0.008616312,0.00042698465,0.000035897243,0.00093499216,0.2526322,0.0016580815,0.0006825284,0.61662287,0.02918802,0.0889308],"study_design_scores_gemma":[0.000044853987,0.000116974756,0.02297181,0.002496679,0.000044467124,0.00047733594,0.36822587,0.0034590848,0.00092763535,0.09468485,0.50638753,0.00016294324],"about_ca_topic_score_codex":0.9585827,"about_ca_topic_score_gemma":0.955846,"teacher_disagreement_score":0.82672006,"about_ca_system_score_codex":0.17327993,"about_ca_system_score_gemma":0.15509035,"threshold_uncertainty_score":0.9588781},"labels":[],"label_agreement":null},{"id":"W3211298722","doi":"","title":"Strategies for Mentoring and Advising Evaluation Graduate Students of Color","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Honor; Ethnic group; Cultural competence; Psychology; Graduate students; Competence (human resources); Salient; Pedagogy; Women of color; Medical education; Identity (music); People of color; Sociology; Social psychology; Gender studies; Medicine","score_opus":0.6184423513416186,"score_gpt":0.611127572966471,"score_spread":0.007314778375147601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211298722","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15363565,0.00426116,0.25048482,0.39750805,0.003611955,0.01248597,0.000180001,0.0052800346,0.17255239],"genre_scores_gemma":[0.43076038,0.0038463094,0.48843923,0.01958639,0.0012652552,0.007877609,0.00014033716,0.00040483873,0.04767963],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.94597346,0.039990574,0.0024670858,0.0016691507,0.0065080184,0.003391763],"domain_scores_gemma":[0.89473057,0.03702006,0.0090930145,0.008859856,0.02113128,0.029165257],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0710845,0.0011773912,0.00055442046,0.0030105652,0.01021387,0.008609843,0.0046427515,0.0041058213,0.011821112],"category_scores_gemma":[0.10706273,0.0006938044,0.0009193413,0.0016031815,0.003969835,0.0055413386,0.017200755,0.0059019667,0.0036267494],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121734636,0.0015903824,0.008189211,0.00049085566,0.000044003038,0.0017123735,0.09878545,0.000682511,0.0022263979,0.012252017,0.09663271,0.7772724],"study_design_scores_gemma":[0.00028431803,0.0017469808,0.014795472,0.003053035,0.00010345914,0.0036624665,0.37336883,0.0035603282,0.005010598,0.04737437,0.5465591,0.00048105058],"about_ca_topic_score_codex":0.0026643798,"about_ca_topic_score_gemma":0.014172472,"teacher_disagreement_score":0.9289155,"about_ca_system_score_codex":0.004904805,"about_ca_system_score_gemma":0.024654517,"threshold_uncertainty_score":0.37593526},"labels":[],"label_agreement":null},{"id":"W3213734767","doi":"10.3138/cjpe.0027.007","title":"Dissemination and Early Use of the Paris Declaration Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Champion; Declaration; Transparency (behavior); Stakeholder; Corporate governance; Politics; Stakeholder engagement; Evaluation methods; Public relations; Impact evaluation; Political science; Business; Process management; Engineering; Medicine; Law","score_opus":0.4155863677781072,"score_gpt":0.5210278673679903,"score_spread":0.10544149958988314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213734767","genre_codex":"other","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02317495,0.004932984,0.30988735,0.13906907,0.01670392,0.15027249,0.014742683,0.005714628,0.33550194],"genre_scores_gemma":[0.3059461,0.0038435317,0.34917983,0.01982672,0.0020831535,0.24463736,0.00634803,0.0027961808,0.06533908],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.37526727,0.4894977,0.041664544,0.009569067,0.07475533,0.0092462115],"domain_scores_gemma":[0.17475499,0.42375332,0.014726132,0.12638757,0.25233856,0.008039432],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.59851307,0.0016531181,0.0025790082,0.012170319,0.0068750987,0.019724144,0.0050485968,0.005272366,0.031154897],"category_scores_gemma":[0.7608679,0.0021518029,0.0020552464,0.008802763,0.008915558,0.012407776,0.016344337,0.009453599,0.006755393],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011436008,0.00041029524,0.002524755,0.006884947,0.00018979957,0.0003375064,0.0623078,0.0018277573,0.0013831125,0.14137204,0.27602908,0.5055893],"study_design_scores_gemma":[0.0005633742,0.00058411085,0.0060270717,0.0152619695,0.00012185478,0.00007560379,0.017867018,0.0017014181,0.0036541654,0.0373929,0.9164373,0.00031308347],"about_ca_topic_score_codex":0.014082232,"about_ca_topic_score_gemma":0.012932183,"teacher_disagreement_score":0.59851307,"about_ca_system_score_codex":0.030539513,"about_ca_system_score_gemma":0.13259123,"threshold_uncertainty_score":0.4951049},"labels":[],"label_agreement":null},{"id":"W3217770674","doi":"10.3138/cjpe.69191","title":"Toward an Evidence-Based Approach to Building Evaluation Capacity","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Children's Hospital Foundation; Stollery Children’s Hospital Foundation; Women and Children's Health Research Institute; Social Sciences and Humanities Research Council of Canada; Children's Health Research Institute","keywords":"Work (physics); Accountability; Process management; Capacity building; Computer science; Knowledge management; Management science; Risk analysis (engineering); Business; Political science; Engineering","score_opus":0.8095482787308166,"score_gpt":0.5628469968990902,"score_spread":0.24670128183172635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217770674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015994355,0.013402606,0.47377062,0.3556545,0.0013507289,0.0059403344,0.0007032575,0.0007737707,0.13240984],"genre_scores_gemma":[0.30742553,0.0046832403,0.6722683,0.008657883,0.00027362816,0.0040489095,0.00045329725,0.00010132491,0.0020879311],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6291523,0.27541214,0.027809,0.009029886,0.052170083,0.0064265844],"domain_scores_gemma":[0.26248172,0.50705105,0.02502943,0.03166759,0.16026026,0.0135099515],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45350224,0.0022984748,0.0033581199,0.041409187,0.01343477,0.040999543,0.012296349,0.009515404,0.006197182],"category_scores_gemma":[0.5079316,0.0021040516,0.0025270756,0.01865628,0.03492717,0.03437676,0.03540042,0.018550163,0.0011320097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109945904,0.00072668074,0.01442271,0.006121863,0.00045964355,0.00026384727,0.014853979,0.0072030197,0.00040590853,0.63185424,0.030090164,0.29348794],"study_design_scores_gemma":[0.0003071216,0.00033321205,0.0122060655,0.044801846,0.00051773415,0.00021073662,0.03663895,0.019179873,0.0022755377,0.76335484,0.11975632,0.00041770685],"about_ca_topic_score_codex":0.09764801,"about_ca_topic_score_gemma":0.14288,"teacher_disagreement_score":0.9342066,"about_ca_system_score_codex":0.06579341,"about_ca_system_score_gemma":0.24839985,"threshold_uncertainty_score":0.6739291},"labels":[],"label_agreement":null},{"id":"W324559717","doi":"10.3138/cjpe.015.003","title":"The Structure of Stages in the Evaluation Cycle: An Event Sequence Analysis","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canada Mortgage and Housing Corporation","funders":"","keywords":"Similarity (geometry); Event (particle physics); Sequence (biology); Computer science; Data science; Information retrieval; Artificial intelligence; Biology; Genetics","score_opus":0.05386085299474568,"score_gpt":0.3527430781906639,"score_spread":0.2988822251959182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W324559717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34911406,0.00083125866,0.6128988,0.0014792703,0.000092940296,0.006784889,0.0019480938,0.0012830115,0.025567725],"genre_scores_gemma":[0.6606108,0.00019656096,0.33152068,0.000106887295,0.000020810403,0.0019261709,0.0010380081,0.0001613473,0.0044187014],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9815214,0.010947139,0.0011007623,0.0013290276,0.0044409907,0.0006606337],"domain_scores_gemma":[0.9174356,0.052246924,0.0064671743,0.0038358914,0.017755963,0.0022585036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022123376,0.000707614,0.0005873932,0.004133815,0.0014937901,0.0037771212,0.0012824893,0.00074429665,0.0063573173],"category_scores_gemma":[0.07950272,0.0006263004,0.00063435157,0.0039108964,0.0017077944,0.0040472527,0.0020573568,0.001366103,0.00083071843],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021102654,0.0009424407,0.18432632,0.0011636207,0.00019599553,0.00045978042,0.014073842,0.02291917,0.007386432,0.0885256,0.008329035,0.66956747],"study_design_scores_gemma":[0.00040614477,0.0034259828,0.31121176,0.0012490364,0.0004962068,0.00045967972,0.019324683,0.40955308,0.0252015,0.14219095,0.08590894,0.00057203433],"about_ca_topic_score_codex":0.00883507,"about_ca_topic_score_gemma":0.008047495,"teacher_disagreement_score":0.022123376,"about_ca_system_score_codex":0.0035817146,"about_ca_system_score_gemma":0.0055064275,"threshold_uncertainty_score":0.117001},"labels":[],"label_agreement":null},{"id":"W326774523","doi":"10.3138/cjpe.025.003","title":"Constructing and Verifying Program Theory Using Source Documentation","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Documentation; Computer science; A priori and a posteriori; Logic model; Management science; Program Design Language; Software engineering; Programming language; Epistemology; Engineering; Sociology","score_opus":0.31697774328765216,"score_gpt":0.5515263442620003,"score_spread":0.23454860097434815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W326774523","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07365704,0.0002495231,0.8897608,0.0016439379,0.00015437021,0.0030984622,0.0012316924,0.005336986,0.024867257],"genre_scores_gemma":[0.23660538,0.00029692063,0.7568535,0.00013499217,0.000028100661,0.001585213,0.0018379791,0.00065505883,0.002002897],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9132994,0.050932746,0.0080334,0.0031854254,0.023489652,0.0010594587],"domain_scores_gemma":[0.55406123,0.23387717,0.018383482,0.07195572,0.12043304,0.0012893573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08932733,0.0009206587,0.000773494,0.009822683,0.0028806126,0.0075565334,0.002776207,0.0017744604,0.0072092796],"category_scores_gemma":[0.25901818,0.0009752394,0.0010003247,0.0050243502,0.0035078814,0.008023189,0.0052746017,0.0025794832,0.0015870671],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000629308,0.0019403202,0.015787613,0.0031004765,0.00018062329,0.0008872964,0.01594966,0.05448838,0.009299829,0.20007779,0.014342467,0.6833163],"study_design_scores_gemma":[0.0010377176,0.0020515039,0.011178699,0.009289809,0.0004107869,0.0009843486,0.015837833,0.44727087,0.13506734,0.21867858,0.15765703,0.0005354874],"about_ca_topic_score_codex":0.011548359,"about_ca_topic_score_gemma":0.008350936,"teacher_disagreement_score":0.08932733,"about_ca_system_score_codex":0.006622567,"about_ca_system_score_gemma":0.022047393,"threshold_uncertainty_score":0.47241372},"labels":[],"label_agreement":null},{"id":"W327931636","doi":"10.3138/cjpe.018.007","title":"CES Student Essay Award: Student and Professor Perspectives","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Sociology","score_opus":0.26322550767730857,"score_gpt":0.5604918523129583,"score_spread":0.2972663446356497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W327931636","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002558499,0.004856568,0.0002526561,0.89645094,0.021450805,0.00002979241,0.000112082525,0.000029156528,0.074259475],"genre_scores_gemma":[0.14497997,0.02452345,0.0009837177,0.5182969,0.057175703,0.00027046032,0.00044135758,0.00021483461,0.25311366],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9790491,0.0053704553,0.0011995427,0.0010796351,0.008655747,0.004645635],"domain_scores_gemma":[0.9057045,0.0149067165,0.0032144843,0.0012547788,0.04300599,0.03191358],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.030288622,0.0007753175,0.0012301004,0.0025604179,0.012458233,0.02626486,0.00379211,0.021034725,0.04563543],"category_scores_gemma":[0.08178877,0.00036092452,0.00096698647,0.0029919185,0.0051569683,0.0072884425,0.00800783,0.012677376,0.0101038935],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034680248,0.00006463804,0.0008201865,0.000046520512,0.000005280277,0.00017341942,0.00043460482,0.000057456175,0.00002513404,0.028547443,0.956689,0.013101544],"study_design_scores_gemma":[0.000021582511,0.0000520856,0.001668632,0.00026282403,0.000008574946,0.00016588627,0.0040848125,0.00009544635,0.000079271005,0.004800736,0.98873466,0.000025600015],"about_ca_topic_score_codex":0.012174861,"about_ca_topic_score_gemma":0.024292078,"teacher_disagreement_score":0.9899651,"about_ca_system_score_codex":0.010034922,"about_ca_system_score_gemma":0.022953777,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W334332912","doi":"10.3138/cjpe.017.007","title":"Evaluation in the Context of the Social Union Framework Agreement: A Case Study of the National Child Benefit","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Aside; Context (archaeology); Government (linguistics); Attribution; Joint (building); Political science; Program evaluation; Test (biology); Public administration; Public relations; Public economics; Economics; Business; Psychology; Social psychology; Engineering","score_opus":0.4168994987204216,"score_gpt":0.5202938594688366,"score_spread":0.10339436074841496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W334332912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86113685,0.0013683602,0.009141314,0.017552651,0.000104999155,0.0016617422,0.00014876341,0.00005889722,0.108826324],"genre_scores_gemma":[0.9890387,0.00043254337,0.005723679,0.00068338646,0.000021320437,0.0005464759,0.000050034636,0.000020941967,0.0034829949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8839516,0.099172115,0.0015190751,0.0011589194,0.0057368125,0.008461383],"domain_scores_gemma":[0.88997567,0.087869585,0.0031869044,0.0027655966,0.0101560205,0.006046278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.085928425,0.00052527507,0.00072093937,0.00200509,0.019499017,0.008094515,0.002379572,0.005995926,0.0046544624],"category_scores_gemma":[0.08572606,0.00047776435,0.00093260483,0.0040769605,0.0073651834,0.0051151826,0.0074094357,0.006074493,0.00040540853],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025573904,0.0147827435,0.098324515,0.0015905031,0.00029878214,0.021678235,0.22667444,0.029620558,0.001572972,0.34302148,0.023998845,0.23587961],"study_design_scores_gemma":[0.0017656591,0.007550547,0.07726232,0.0027871893,0.00040690447,0.004325872,0.6274647,0.038070332,0.006912163,0.06785945,0.16518655,0.00040838975],"about_ca_topic_score_codex":0.103295185,"about_ca_topic_score_gemma":0.16235432,"teacher_disagreement_score":0.8967048,"about_ca_system_score_codex":0.03634255,"about_ca_system_score_gemma":0.039257932,"threshold_uncertainty_score":0.4544384},"labels":[],"label_agreement":null},{"id":"W338142777","doi":"10.3138/cjpe.0024.006","title":"Evaluating School-Based Tobacco Control Programs and Policies: An Opportunity Gained and Many Opportunities Lost","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Smoking Behavior and Cessation","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Tobacco control; Data collection; Control (management); Psychological intervention; Tobacco use; Domain (mathematical analysis); Business; Public relations; Political science; Medical education; Environmental health; Computer science; Public health; Medicine; Sociology; Nursing; Social science","score_opus":0.2640357120284996,"score_gpt":0.42658321128450744,"score_spread":0.1625474992560078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W338142777","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049139358,0.19546755,0.031855047,0.7007314,0.007768392,0.0009795903,0.0008401417,0.00035523257,0.012863346],"genre_scores_gemma":[0.63510317,0.14089611,0.1473637,0.05218605,0.016147427,0.0026972285,0.0004753029,0.00027649474,0.004854599],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8544975,0.116478756,0.007267821,0.0024706041,0.014754557,0.0045307507],"domain_scores_gemma":[0.6490869,0.26079834,0.007636035,0.016367393,0.049005866,0.017105548],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23814957,0.0019318515,0.003473986,0.0027438095,0.003611532,0.014115306,0.0031380216,0.007678897,0.009019637],"category_scores_gemma":[0.18384549,0.0010793066,0.0017112675,0.0024746645,0.008177171,0.025178801,0.014828116,0.009613547,0.0010779251],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002097424,0.0017371131,0.010915195,0.008874756,0.0008259066,0.0006552193,0.0064217714,0.0029776434,0.0012707592,0.026302043,0.057406995,0.8805152],"study_design_scores_gemma":[0.0039164084,0.019024916,0.05253725,0.054381154,0.001760306,0.0033540004,0.0765438,0.018838378,0.0055135745,0.40347257,0.35942507,0.0012325789],"about_ca_topic_score_codex":0.0060078823,"about_ca_topic_score_gemma":0.010066282,"teacher_disagreement_score":0.9939921,"about_ca_system_score_codex":0.007199566,"about_ca_system_score_gemma":0.022165747,"threshold_uncertainty_score":0.93949723},"labels":[],"label_agreement":null},{"id":"W346291978","doi":"10.3138/cjpe.018.009","title":"CES Case Competition: A Newfoundland and Labrador Chapter Perspective","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Research in Social Sciences","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Perspective (graphical); Competition (biology); Geography; Ecology; Art; Biology","score_opus":0.15284137757036464,"score_gpt":0.4514921157106325,"score_spread":0.2986507381402679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W346291978","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15869722,0.0062398673,0.0012944795,0.12849295,0.00037366274,0.00015272631,0.0006889329,0.00003719469,0.704023],"genre_scores_gemma":[0.763677,0.0051167747,0.0015522259,0.019273398,0.00021674881,0.00012482487,0.00039601978,0.00003178849,0.20961124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99438226,0.0013120493,0.00009188623,0.00025388855,0.0008265464,0.0031333189],"domain_scores_gemma":[0.9925701,0.0028388249,0.00052790326,0.00015499323,0.0018876776,0.002020407],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0039906157,0.0003787787,0.00056170113,0.0032586385,0.011887646,0.01056836,0.003306471,0.0034464628,0.028149655],"category_scores_gemma":[0.007550231,0.00047326685,0.0005697134,0.0035273468,0.0051234225,0.0030522237,0.003927165,0.002838133,0.0007805292],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001894021,0.0005593803,0.025251651,0.0002612335,0.000063690066,0.002637156,0.0124816,0.003992272,0.00046477816,0.735365,0.16608283,0.0526511],"study_design_scores_gemma":[0.000115870986,0.00024822305,0.15492831,0.0013351092,0.00010748319,0.00091017724,0.21548155,0.0049051847,0.0008831636,0.03962608,0.58125633,0.00020256032],"about_ca_topic_score_codex":0.92873627,"about_ca_topic_score_gemma":0.97976047,"teacher_disagreement_score":0.9960094,"about_ca_system_score_codex":0.07425874,"about_ca_system_score_gemma":0.06524972,"threshold_uncertainty_score":0.53878736},"labels":[],"label_agreement":null},{"id":"W346861891","doi":"10.3138/cjpe.15.007","title":"The Effectiveness of a School-Based HIV Education Program: A Longitudinal Comparative Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Adolescent Sexual and Reproductive Health","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Curriculum; Condom; Psychology; Medical education; Peer education; Human immunodeficiency virus (HIV); Peer group; Test (biology); Reproductive health; Intervention (counseling); Health education; Pedagogy; Developmental psychology; Medicine; Family medicine; Population; Public health; Nursing; Syphilis; Environmental health","score_opus":0.34777209146954596,"score_gpt":0.5630643138145887,"score_spread":0.2152922223450427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W346861891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99665207,0.00028097667,0.00011663081,0.000059079863,0.000022841354,0.002084586,0.000260928,0.000016603832,0.0005064166],"genre_scores_gemma":[0.99434316,0.0004831733,0.0010545194,0.000100192374,0.000049284983,0.0029097882,0.0005308883,0.0000046833616,0.0005242926],"study_design_codex":"nonrandomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.99262416,0.004351162,0.0005465103,0.00052498566,0.001035505,0.00091761356],"domain_scores_gemma":[0.99316734,0.0020367005,0.0012273618,0.0005783317,0.0014261897,0.00156403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009874586,0.0008801298,0.0011057783,0.0014903452,0.002098855,0.0008477124,0.001270147,0.0013859002,0.0026338813],"category_scores_gemma":[0.009513351,0.00059708545,0.0014317129,0.0013153276,0.0012625722,0.0014250774,0.0009565294,0.0013455335,0.00031797288],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17168249,0.53753984,0.095857486,0.0020472123,0.0015978335,0.00025311904,0.0031611272,0.0015771381,0.0018445886,0.00027900134,0.0010130426,0.18314703],"study_design_scores_gemma":[0.10324311,0.6477684,0.23972349,0.00035327388,0.001398489,0.00010606841,0.001725032,0.00091654726,0.0028128205,0.00012891849,0.0017503452,0.000073567986],"about_ca_topic_score_codex":0.034032263,"about_ca_topic_score_gemma":0.036587834,"teacher_disagreement_score":0.034032263,"about_ca_system_score_codex":0.0048206933,"about_ca_system_score_gemma":0.009449523,"threshold_uncertainty_score":0.06766832},"labels":[],"label_agreement":null},{"id":"W347468065","doi":"10.3138/cjpe.0023.005","title":"The Road to Evaluation Capacity Building: A Case Study from Israel","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Presentation (obstetrics); Curriculum; Outcome (game theory); Relation (database); Capacity building; Psychology; Political science; Mathematics education; Sociology; Medical education; Pedagogy; Economics; History; Computer science; Medicine; Law; Archaeology","score_opus":0.5869895881998264,"score_gpt":0.5568682661750065,"score_spread":0.030121322024819874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W347468065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95243335,0.00042432154,0.005005562,0.005850092,0.00004747924,0.00061445666,0.000052735675,0.00003538224,0.035536602],"genre_scores_gemma":[0.9917898,0.00026972624,0.0045244326,0.00044062536,0.000015536823,0.00018129127,0.000038449496,0.000024545658,0.00271569],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97433794,0.019190963,0.00067229365,0.0006336879,0.0021279017,0.003037271],"domain_scores_gemma":[0.9653997,0.02276347,0.0017642789,0.0014996049,0.004792566,0.0037803622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028498497,0.0006050135,0.0005858285,0.0019897248,0.014689582,0.0064983773,0.003312706,0.004667499,0.0037132562],"category_scores_gemma":[0.026590504,0.00070410967,0.00058333046,0.0020604734,0.0070003974,0.00372182,0.0063589048,0.0057890243,0.00058410823],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043188126,0.009546266,0.07960134,0.00079747685,0.00008940995,0.031069115,0.6901072,0.0058329077,0.0035572757,0.0560385,0.009987618,0.112940945],"study_design_scores_gemma":[0.0001802674,0.0010492161,0.022321757,0.0010691686,0.00006387132,0.0048692096,0.8838966,0.0071616475,0.0058632134,0.006729799,0.06666825,0.00012707489],"about_ca_topic_score_codex":0.019735629,"about_ca_topic_score_gemma":0.037567858,"teacher_disagreement_score":0.028498497,"about_ca_system_score_codex":0.015811414,"about_ca_system_score_gemma":0.012111654,"threshold_uncertainty_score":0.1507163},"labels":[],"label_agreement":null},{"id":"W4205816780","doi":"10.3138/cjpe.72729","title":"Introduction: Transforming Evaluation Practice for “Business Unusual”","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Entrepreneurship Studies and Influences","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thematic map; Business practice; Thematic analysis; Business; Process management; Knowledge management; Business administration; Sociology; Computer science; Geography; Social science; Qualitative research; Cartography","score_opus":0.09261989750795575,"score_gpt":0.3533748658380606,"score_spread":0.26075496833010486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205816780","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011065992,0.014144121,0.049427792,0.47984257,0.2403497,0.00280111,0.004472447,0.0053553535,0.20250031],"genre_scores_gemma":[0.012971437,0.015640438,0.05488095,0.38858896,0.1071366,0.004985648,0.005195816,0.0045727715,0.40602735],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99055207,0.0030733855,0.0010954173,0.0008227842,0.0038336893,0.00062257453],"domain_scores_gemma":[0.96455824,0.013902982,0.0018617973,0.0015458493,0.014622644,0.003508352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014942894,0.0008897947,0.0007317087,0.0022273255,0.00246118,0.0040345024,0.0022759736,0.007763691,0.104482226],"category_scores_gemma":[0.026409559,0.00062422303,0.0011144457,0.0018374239,0.0026355768,0.006109972,0.005989393,0.009394795,0.05443692],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011588543,0.000025576926,0.000044946435,0.00027043346,0.0000013123121,0.000019063378,0.0002436959,0.000027382603,0.00027187302,0.0037082667,0.96717626,0.02819953],"study_design_scores_gemma":[0.000007391233,0.000025830632,0.00041613216,0.00052201113,0.0000020424584,0.000055505934,0.0002117315,0.000040112252,0.000113677226,0.0022663206,0.9963277,0.000011346748],"about_ca_topic_score_codex":0.003797229,"about_ca_topic_score_gemma":0.009609103,"teacher_disagreement_score":0.104482226,"about_ca_system_score_codex":0.0032313322,"about_ca_system_score_gemma":0.007310449,"threshold_uncertainty_score":0.3495279},"labels":[],"label_agreement":null},{"id":"W4210323099","doi":"10.3138/cjpe.36.2.ed-fr","title":"Un mot de la rédactrice","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Evaluation Society","funders":"","keywords":"Political science","score_opus":0.08961796751011986,"score_gpt":0.36937774345787855,"score_spread":0.2797597759477587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210323099","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008282821,0.0044587846,0.00038273673,0.2792599,0.7106308,0.00003163905,0.00016003408,0.000115049224,0.004878251],"genre_scores_gemma":[0.002697851,0.0046740756,0.0019304398,0.39664415,0.48616818,0.00013895308,0.00020208958,0.0002159887,0.10732828],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888783,0.0020953834,0.001495754,0.001514105,0.0051610866,0.0008555036],"domain_scores_gemma":[0.9347115,0.015258278,0.0029643357,0.0027741806,0.04125735,0.0030342513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011177994,0.0015569156,0.001809427,0.0019733056,0.003670285,0.007064511,0.003936295,0.014254477,0.03440407],"category_scores_gemma":[0.0723147,0.0008557331,0.001910295,0.0017583108,0.0024040902,0.0052954108,0.0029532432,0.01553367,0.029507486],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016296284,0.000005863832,0.00003379516,0.00008295445,0.000005529392,0.000056813857,0.00002472441,0.000014357698,0.00005159884,0.0008549924,0.9938373,0.005015776],"study_design_scores_gemma":[0.000015147252,0.0000095356845,0.00023726895,0.00011956362,0.000010047217,0.00010175957,0.00005245057,0.00007336587,0.00013474165,0.0007237588,0.998505,0.000017353099],"about_ca_topic_score_codex":0.011508616,"about_ca_topic_score_gemma":0.02211744,"teacher_disagreement_score":0.03440407,"about_ca_system_score_codex":0.003194415,"about_ca_system_score_gemma":0.006721417,"threshold_uncertainty_score":0.11509305},"labels":[],"label_agreement":null},{"id":"W4210611449","doi":"10.3138/cjpe.36.2.ed-en","title":"Editor’s Remarks","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.06718062263387857,"score_gpt":0.4319921026209933,"score_spread":0.3648114799871147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210611449","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008930496,0.0012729665,0.00013155515,0.22981764,0.76563823,0.00004373809,0.00014827667,0.000117146024,0.002741156],"genre_scores_gemma":[0.001516507,0.0023119429,0.0011318128,0.48117805,0.47992688,0.00016309327,0.0001290972,0.000110708235,0.03353191],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98629147,0.0012739911,0.002001765,0.0016727925,0.00753767,0.0012224262],"domain_scores_gemma":[0.94474554,0.011842277,0.0035122863,0.0020887288,0.03268453,0.005126753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015513237,0.0026595134,0.0027619018,0.0026463934,0.0037560598,0.0072233058,0.0063988864,0.02744091,0.02180739],"category_scores_gemma":[0.1007282,0.0015521663,0.0042481436,0.0020597775,0.0029507605,0.005173461,0.0023071845,0.029856112,0.023882693],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022023763,0.000009614223,0.00003762236,0.00005519744,0.000008417099,0.00009939472,0.000010444434,0.000019172954,0.000027137525,0.00021898905,0.99706715,0.002424789],"study_design_scores_gemma":[0.00006064208,0.000025475998,0.00048180242,0.00024329858,0.000027837383,0.00022787055,0.000062509214,0.00012256605,0.00018216853,0.00078012963,0.99774075,0.00004487157],"about_ca_topic_score_codex":0.007049512,"about_ca_topic_score_gemma":0.013798155,"teacher_disagreement_score":0.02744091,"about_ca_system_score_codex":0.004541449,"about_ca_system_score_gemma":0.008767191,"threshold_uncertainty_score":0.08204281},"labels":[],"label_agreement":null},{"id":"W4210940283","doi":"10.3138/cjpe.70207","title":"Darlene F. Russ-Eft and Catherine M. Sleezer. (2020). <i>Case Studies in Needs Assessment.</i>","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Sociology","score_opus":0.20023330070450665,"score_gpt":0.5090273898181648,"score_spread":0.30879408911365813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210940283","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011004288,0.17717281,0.011705812,0.64893556,0.058733772,0.00041008153,0.0009318231,0.00113848,0.099871285],"genre_scores_gemma":[0.015358895,0.20227665,0.021996263,0.19045709,0.011544017,0.0012029847,0.0009385806,0.0011119266,0.5551136],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976446,0.00057911145,0.0001899682,0.00022832214,0.0012235338,0.00013448247],"domain_scores_gemma":[0.9849337,0.0047440557,0.0007555843,0.00020624242,0.005724983,0.0036355362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070518157,0.00096305273,0.0004731457,0.002298883,0.0021187197,0.0033406138,0.0015518211,0.004610014,0.055652913],"category_scores_gemma":[0.023985421,0.00076624384,0.0003386256,0.0014146705,0.0013004489,0.005258432,0.002605468,0.0052997475,0.038255163],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057847387,0.000010338783,0.00019781975,0.00010594013,0.0000010199897,0.00004891953,0.00040627253,0.000010901441,0.000039014067,0.00063814817,0.91812974,0.08040608],"study_design_scores_gemma":[0.000010686427,0.000016797798,0.0011761878,0.0012486505,0.000004324515,0.00034317691,0.0012097021,0.00004160045,0.00009853304,0.0019896545,0.9938421,0.000018549632],"about_ca_topic_score_codex":0.016976856,"about_ca_topic_score_gemma":0.06238525,"teacher_disagreement_score":0.055652913,"about_ca_system_score_codex":0.0015516158,"about_ca_system_score_gemma":0.007367998,"threshold_uncertainty_score":0.18617755},"labels":[],"label_agreement":null},{"id":"W4213063025","doi":"10.3138/cjpe.72865.en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Sociology; Psychology; Political science; Medicine; Biology; Ecology","score_opus":0.27978764456850475,"score_gpt":0.5262429699080209,"score_spread":0.24645532533951614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213063025","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038677815,0.020407762,0.02201624,0.5423283,0.003217693,0.00021153396,0.000019460556,0.00020754065,0.37291372],"genre_scores_gemma":[0.89478564,0.0074365833,0.01650894,0.042812504,0.0012964697,0.00022350113,0.000012812803,0.0002144312,0.036709234],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.929325,0.056849588,0.0010534633,0.001814103,0.00817013,0.002787739],"domain_scores_gemma":[0.951072,0.034100834,0.0022901199,0.0028035543,0.004375214,0.00535837],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06342756,0.0003903924,0.00064408843,0.0025068924,0.018774638,0.022891605,0.001597123,0.005594398,0.0073528118],"category_scores_gemma":[0.052785743,0.0004979586,0.0005230448,0.0013340412,0.08629176,0.01893137,0.0253484,0.012435901,0.0007355854],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006034051,0.00013747478,0.00079069636,0.0004092704,0.000031450454,0.00041793345,0.21067046,0.00023041824,0.00073960325,0.6301791,0.036581997,0.119751334],"study_design_scores_gemma":[0.0000401867,0.00013414488,0.0018846178,0.0015458073,0.000043537886,0.00056236103,0.1339264,0.00060055003,0.0011188184,0.3626297,0.49741325,0.00010065227],"about_ca_topic_score_codex":0.011964169,"about_ca_topic_score_gemma":0.03371295,"teacher_disagreement_score":0.98151225,"about_ca_system_score_codex":0.018487748,"about_ca_system_score_gemma":0.025692806,"threshold_uncertainty_score":0.335441},"labels":[],"label_agreement":null},{"id":"W4220680129","doi":"10.3138/cjpe.73686","title":"Michael D. Fetters. (2020). <i>The Mixed Methods Research Workbook: Activities for Designing Implementing, and Publishing Projects</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workbook; Publishing; Management; Library science; Sociology; Political science; Computer science; Economics; Law","score_opus":0.573506722105812,"score_gpt":0.60678165072158,"score_spread":0.033274928615767974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220680129","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008903499,0.13542256,0.01697098,0.5382464,0.08147032,0.0009965922,0.018948095,0.0070794644,0.19997524],"genre_scores_gemma":[0.004897037,0.07867632,0.031446833,0.06426192,0.0073222225,0.0013000988,0.0074016214,0.0023878454,0.80230606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951454,0.0007872047,0.00027947596,0.00032655484,0.0032059087,0.0002554929],"domain_scores_gemma":[0.97916806,0.0029827086,0.001045949,0.00048266063,0.010835932,0.0054847067],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011173757,0.0015913715,0.00063653965,0.0038467883,0.0018740712,0.0041330084,0.0021308032,0.0042150756,0.16725017],"category_scores_gemma":[0.022021601,0.0010773513,0.0006745369,0.0034271588,0.0011556636,0.0035310844,0.0026409356,0.004196372,0.13854198],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001194936,0.000005425452,0.00009130836,0.00010151388,0.0000011783419,0.000009474797,0.000029908248,0.000014805656,0.000050172945,0.00030661435,0.9378603,0.06151725],"study_design_scores_gemma":[0.000008644584,0.000007962997,0.0004319241,0.00042158013,0.000004064596,0.000021946653,0.000077877055,0.000022926575,0.00011424316,0.00042744508,0.99845195,0.000009341445],"about_ca_topic_score_codex":0.06999886,"about_ca_topic_score_gemma":0.15860508,"teacher_disagreement_score":0.9888262,"about_ca_system_score_codex":0.0030280177,"about_ca_system_score_gemma":0.017639449,"threshold_uncertainty_score":0.55950755},"labels":[],"label_agreement":null},{"id":"W4220683166","doi":"10.3138/cjpe.73683","title":"Why a Focus on Integration and Complex Mixed Methods Evaluation Designs?: Introducing this Special Issue of the <i>Canadian Journal of Program Evaluation</i>","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Focus (optics); Management science; Engineering ethics; Program evaluation; Sociology; Computer science; Political science; Engineering; Public administration","score_opus":0.4085758629978245,"score_gpt":0.5421811162476561,"score_spread":0.13360525324983158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220683166","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007842953,0.016246477,0.0011833385,0.21429773,0.7669029,0.000099391305,0.00005764459,0.00009121816,0.0010428331],"genre_scores_gemma":[0.0010773117,0.009387195,0.001894681,0.111444205,0.873961,0.00013430713,0.000032121123,0.00017531979,0.0018939521],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9087495,0.0316225,0.012694346,0.0065130037,0.03802751,0.0023930166],"domain_scores_gemma":[0.49903625,0.29873914,0.01925959,0.010945633,0.15441252,0.017606838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12292809,0.0025450096,0.005485345,0.0052248673,0.0054639573,0.020090038,0.0073146196,0.02691394,0.008769533],"category_scores_gemma":[0.2946037,0.00212583,0.0032883813,0.0036604602,0.01200705,0.008745343,0.004196772,0.031892892,0.0036120622],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039934108,0.000022152739,0.00011294186,0.0006875075,0.000057367462,0.000061840954,0.00009766895,0.000036204987,0.000080206315,0.0013531165,0.98409283,0.013358182],"study_design_scores_gemma":[0.0001400146,0.00008734692,0.0010070322,0.002912715,0.00021295952,0.00034183162,0.000318332,0.00042822346,0.00017893799,0.006300075,0.98796356,0.000108977256],"about_ca_topic_score_codex":0.012920886,"about_ca_topic_score_gemma":0.041684102,"teacher_disagreement_score":0.12292809,"about_ca_system_score_codex":0.010355727,"about_ca_system_score_gemma":0.025404897,"threshold_uncertainty_score":0.65011364},"labels":[],"label_agreement":null},{"id":"W4220735178","doi":"10.3138/cjpe.71488","title":"A Framework to Combine Mixed Methods Integration and Developmental Evaluation to Study Complex Systems","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Stakeholder; Context (archaeology); Scale (ratio); Work (physics); Key (lock); Computer science; Literacy; Data collection; Process management; Management science; Knowledge management; Data science; Sociology; Business; Political science; Public relations; Engineering; Social science; Geography","score_opus":0.5638809926219458,"score_gpt":0.6081958073315192,"score_spread":0.044314814709573436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220735178","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020396993,0.0017852524,0.97177863,0.0039041778,0.0001629227,0.0047393953,0.00012467985,0.00021795751,0.015247401],"genre_scores_gemma":[0.031682856,0.00065217377,0.9562964,0.00050469284,0.000031639953,0.01025004,0.00006903068,0.00004545741,0.00046765304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6399879,0.3372259,0.0059431875,0.0048534856,0.010517171,0.0014723432],"domain_scores_gemma":[0.77880776,0.18787012,0.007107993,0.011097559,0.01263642,0.0024801139],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25620294,0.003911136,0.0038656525,0.01681483,0.005539017,0.011738182,0.0067721335,0.0035671992,0.0053625177],"category_scores_gemma":[0.13023478,0.0018186026,0.0038535914,0.009489679,0.017960364,0.011483061,0.015366119,0.0066445647,0.0008934342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001381883,0.00049368135,0.0029264973,0.0041031833,0.0006732785,0.0003419166,0.015771423,0.013624636,0.00080458797,0.78875774,0.0031237572,0.16924126],"study_design_scores_gemma":[0.00037237702,0.00080899097,0.0020809572,0.009689638,0.0004963742,0.0004139103,0.0127745345,0.04184717,0.0019371836,0.84041935,0.088914976,0.00024448603],"about_ca_topic_score_codex":0.008438845,"about_ca_topic_score_gemma":0.011913169,"teacher_disagreement_score":0.74379706,"about_ca_system_score_codex":0.020356998,"about_ca_system_score_gemma":0.033986434,"threshold_uncertainty_score":0.9172342},"labels":[],"label_agreement":null},{"id":"W4220806961","doi":"10.3138/cjpe.71043","title":"Advancing a Competency-Based Mixed Methods Tool to Assess a Course-Based Service-Learning Model Integrating Real-World Experience","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Service-Learning and Community Engagement","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Course (navigation); Service-learning; Knowledge management; Service (business); Multimethodology; Service model; Psychology; Medical education; Computer science; Process management; Mathematics education; Pedagogy; Engineering; Business; Marketing; Medicine","score_opus":0.15766155554599376,"score_gpt":0.4683620473405492,"score_spread":0.31070049179455544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220806961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06431654,0.00037912495,0.8804028,0.004794401,0.00038442417,0.022569641,0.00085403153,0.0015010056,0.024798116],"genre_scores_gemma":[0.10524352,0.00013742178,0.87002015,0.0008310863,0.00002435952,0.021727702,0.00020945707,0.00010566046,0.0017006878],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.85137224,0.11657201,0.008219739,0.0028675187,0.019660326,0.0013082376],"domain_scores_gemma":[0.72665966,0.1972375,0.011989186,0.0150823165,0.045690525,0.0033408063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17321295,0.0008709564,0.0010431847,0.0059033604,0.0021778408,0.00754372,0.0027807055,0.0018861324,0.006190276],"category_scores_gemma":[0.24489318,0.0006218905,0.0019380455,0.0024342488,0.0021185996,0.0044320817,0.008222613,0.0028048935,0.0010861721],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006326396,0.00234395,0.042881772,0.003570036,0.00041939507,0.00021656285,0.025568834,0.0054617673,0.0067898026,0.044546496,0.01777331,0.8497954],"study_design_scores_gemma":[0.0013618008,0.008519306,0.10233736,0.024092764,0.00113943,0.0017153345,0.06881967,0.18095471,0.08366895,0.17692545,0.34935623,0.0011088664],"about_ca_topic_score_codex":0.0023593397,"about_ca_topic_score_gemma":0.0057961615,"teacher_disagreement_score":0.17321295,"about_ca_system_score_codex":0.005612551,"about_ca_system_score_gemma":0.0123393135,"threshold_uncertainty_score":0.9160485},"labels":[],"label_agreement":null},{"id":"W4220846218","doi":"10.3138/cjpe.36.3.ed-fr","title":"Un mot de la rédactrice","year":2022,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.08457766494705582,"score_gpt":0.359384023416896,"score_spread":0.2748063584698402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220846218","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000111602196,0.0029274346,0.00045625996,0.3869947,0.60555214,0.000028090079,0.00011317376,0.00010770318,0.0037089766],"genre_scores_gemma":[0.003160376,0.0025298675,0.0020639384,0.48627502,0.41815624,0.00013071988,0.00011132186,0.00022087517,0.08735162],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9721344,0.005884608,0.003710505,0.0034133194,0.012643654,0.0022135042],"domain_scores_gemma":[0.8717013,0.027239481,0.005383887,0.00540112,0.085012436,0.0052617732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022413904,0.0019592992,0.0026361695,0.002447707,0.006111249,0.013874546,0.0046922998,0.025927655,0.023228645],"category_scores_gemma":[0.11946014,0.0012071416,0.0027739226,0.002085589,0.0040487484,0.006384221,0.0041237664,0.029878544,0.017726764],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023019287,0.000008740328,0.000053472064,0.00008530294,0.000008711252,0.000070891074,0.000055352637,0.000019962175,0.000078764075,0.0014343922,0.99410015,0.004061315],"study_design_scores_gemma":[0.000024740628,0.000012237994,0.0003068935,0.0001517368,0.000021142292,0.00010660715,0.00011685246,0.00012738426,0.00018828364,0.0009655552,0.9979512,0.000027438578],"about_ca_topic_score_codex":0.020635847,"about_ca_topic_score_gemma":0.03695665,"teacher_disagreement_score":0.025927655,"about_ca_system_score_codex":0.006781428,"about_ca_system_score_gemma":0.014251905,"threshold_uncertainty_score":0.118537486},"labels":[],"label_agreement":null},{"id":"W4220870230","doi":"10.3138/cjpe.36.3.ann-en","title":"Announcement from Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Political science; Social science; Sociology; History; Medicine; Biology; Ecology","score_opus":0.26152087117811373,"score_gpt":0.5024621923116173,"score_spread":0.24094132113350353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220870230","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003978204,0.0017636449,0.0004042488,0.9600205,0.033410925,0.000044632063,0.00004274487,0.00011051958,0.003804894],"genre_scores_gemma":[0.02162351,0.003202568,0.00419405,0.8126089,0.09185922,0.0002982872,0.0001677648,0.0005589697,0.065486684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.92756456,0.031060925,0.0042261956,0.004297043,0.026467048,0.0063842866],"domain_scores_gemma":[0.69146454,0.12074201,0.014399981,0.010878506,0.054258842,0.10825617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11211543,0.0013196216,0.0014742371,0.0017386598,0.0114345895,0.018143425,0.0046445653,0.050908454,0.0376939],"category_scores_gemma":[0.18878216,0.0015736034,0.001572284,0.0017557782,0.010999307,0.013238454,0.014138603,0.052163202,0.008478743],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003436398,0.000040949395,0.0001506988,0.000060135262,0.0000060031975,0.00009537433,0.00034863182,0.000017892453,0.00013633148,0.0020523702,0.9898588,0.0071986145],"study_design_scores_gemma":[0.00011479528,0.00010292705,0.002382658,0.00044108467,0.000027440708,0.0001963544,0.0019593148,0.00021409676,0.00036026884,0.0037301534,0.99036306,0.00010782517],"about_ca_topic_score_codex":0.021626716,"about_ca_topic_score_gemma":0.08004971,"teacher_disagreement_score":0.11211543,"about_ca_system_score_codex":0.013858122,"about_ca_system_score_gemma":0.050319947,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4220885582","doi":"10.3138/cjpe.71259","title":"Integrating Data to Evaluate a Global Health Grand Challenge","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Global Public Health Policies and Epidemiology","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grand Challenges; Global health; Psychology; Data science; Political science; Computer science; Health care","score_opus":0.28118137140633465,"score_gpt":0.45764614250678826,"score_spread":0.1764647711004536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220885582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40022516,0.004555088,0.41877267,0.017028539,0.001991686,0.054780506,0.011187672,0.0004804593,0.09097821],"genre_scores_gemma":[0.61103964,0.00047962068,0.31726742,0.002992558,0.00022476455,0.06420404,0.0019419139,0.00011531466,0.0017346798],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.5326782,0.4235155,0.014036845,0.0062404885,0.020877996,0.002650966],"domain_scores_gemma":[0.6311255,0.2603002,0.025729565,0.034757324,0.044861656,0.0032257182],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24787411,0.0016058014,0.001585827,0.005841016,0.0037251208,0.007887315,0.002602913,0.0023611193,0.0070797224],"category_scores_gemma":[0.29246527,0.00096020283,0.0026444597,0.006455402,0.0045918426,0.006521356,0.009410799,0.0032585443,0.0006938124],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007253781,0.0061920327,0.18273333,0.0070468294,0.005489278,0.00024552087,0.018097913,0.022421759,0.0027845898,0.24645662,0.014490067,0.48678833],"study_design_scores_gemma":[0.0061364886,0.04713791,0.18303002,0.02045626,0.008086399,0.00041631045,0.053904355,0.07073399,0.03527473,0.30766815,0.26600978,0.0011456467],"about_ca_topic_score_codex":0.00684524,"about_ca_topic_score_gemma":0.007913758,"teacher_disagreement_score":0.24787411,"about_ca_system_score_codex":0.009288035,"about_ca_system_score_gemma":0.018970706,"threshold_uncertainty_score":0.92750514},"labels":[],"label_agreement":null},{"id":"W4220996640","doi":"10.3138/cjpe.71288","title":"Leveraging Mixed Methods Designs for Promoting Evaluation and Evaluation Capacity Building","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Capacity building; Evaluation methods; Resource (disambiguation); Business; Process management; Knowledge management; Computer science; Political science; Engineering","score_opus":0.6983590582177419,"score_gpt":0.594212927107646,"score_spread":0.10414613111009596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220996640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01685533,0.0005046035,0.9194721,0.0009869759,0.00039786642,0.05299942,0.00031073517,0.0005042297,0.007968735],"genre_scores_gemma":[0.049909364,0.00015900357,0.86078966,0.00035244538,0.000058107333,0.088068165,0.000052109688,0.00008615302,0.0005249538],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.56395006,0.40186912,0.012215284,0.006889679,0.013544904,0.001530958],"domain_scores_gemma":[0.40144613,0.5039963,0.020258319,0.040161807,0.03206198,0.0020754107],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3439459,0.0023610182,0.0016518498,0.005315552,0.0031630653,0.0064110584,0.003314161,0.0022144585,0.010545314],"category_scores_gemma":[0.3652214,0.0017624383,0.0023461895,0.0042698216,0.0042243986,0.004202136,0.0066154934,0.0035777723,0.0012648285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038915144,0.003993023,0.0092036715,0.01362773,0.0019242818,0.00033290824,0.03379385,0.015008214,0.009283867,0.25384766,0.008146124,0.64694726],"study_design_scores_gemma":[0.009236819,0.019813739,0.015197306,0.013833036,0.0030396162,0.0003500601,0.020655507,0.11908554,0.051010516,0.5806853,0.16629821,0.00079427846],"about_ca_topic_score_codex":0.00118483,"about_ca_topic_score_gemma":0.0032704477,"teacher_disagreement_score":0.3439459,"about_ca_system_score_codex":0.0047495887,"about_ca_system_score_gemma":0.009516982,"threshold_uncertainty_score":0.80903155},"labels":[],"label_agreement":null},{"id":"W4221053267","doi":"10.3138/cjpe.363.423","title":"Peer Reviewers for Volume 36 and Manuscripts Submitted in 2021 / Examinateurs des manuscrits du volume 36 et des manuscrits soumis en 2021","year":2022,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Academic Publishing and Open Access","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Acknowledgement; Volume (thermodynamics); Art; Psychology; Humanities; Computer science; Physics","score_opus":0.19662504947412943,"score_gpt":0.4140292154622942,"score_spread":0.21740416598816478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221053267","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009270409,0.010946226,0.019345751,0.16035415,0.6628152,0.007635644,0.01470467,0.00820269,0.10672527],"genre_scores_gemma":[0.03288975,0.007923107,0.028578984,0.016890239,0.13802789,0.0037015853,0.012122219,0.0068163625,0.75304985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96223414,0.0060789287,0.00432503,0.0029220919,0.02236074,0.002079161],"domain_scores_gemma":[0.47349587,0.016715905,0.012595721,0.011320342,0.45403102,0.031841163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026156547,0.001509875,0.0022254495,0.0081039425,0.0048740134,0.008760597,0.002145064,0.0039121932,0.26241106],"category_scores_gemma":[0.19210967,0.0008482949,0.0016759998,0.005238593,0.0014238437,0.0044364305,0.003669417,0.0034816635,0.2263131],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001513573,0.000026524576,0.00069476303,0.00037121246,0.000012790389,0.00015574039,0.0001586185,0.00002868792,0.00063202844,0.00047634495,0.96317625,0.03411578],"study_design_scores_gemma":[0.00006705355,0.00008098923,0.0023778626,0.00040928542,0.000021441596,0.00032600397,0.00037267696,0.00016866233,0.0006527029,0.0009154437,0.9945615,0.000046390058],"about_ca_topic_score_codex":0.004439616,"about_ca_topic_score_gemma":0.01158275,"teacher_disagreement_score":0.99725145,"about_ca_system_score_codex":0.0027485366,"about_ca_system_score_gemma":0.022272121,"threshold_uncertainty_score":0.87785244},"labels":[],"label_agreement":null},{"id":"W4224228919","doi":"10.3138/cjpe.69932","title":"Examining the Process and Effects of Engaging Patients and Family in Health Service Evaluation: Results from a One-Year Prospective Intervention Study","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Home and Community Care Support Services","funders":"","keywords":"General partnership; Intervention (counseling); Context (archaeology); Nursing; Service (business); Health care; Psychology; Process (computing); Medical education; Medicine; Business; Political science; Computer science","score_opus":0.2617535692198355,"score_gpt":0.49518366530346136,"score_spread":0.23343009608362586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224228919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969247,0.0001248717,0.00041463127,0.00015991344,0.00001777572,0.0015084454,0.000081236656,0.000016368,0.00075201486],"genre_scores_gemma":[0.995093,0.0001527009,0.0013261104,0.00013976028,0.000015852575,0.0027871907,0.000116909025,0.0000044793674,0.00036394052],"study_design_codex":"nonrandomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.98091424,0.012527162,0.0013737392,0.0010154843,0.0015865747,0.002582747],"domain_scores_gemma":[0.9542056,0.023284651,0.006720874,0.003985736,0.0056006536,0.0062025758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031100173,0.00079910335,0.0010212624,0.00161181,0.0059407875,0.0027680567,0.0018689033,0.0019057955,0.0024940914],"category_scores_gemma":[0.048021704,0.0009119744,0.0010730767,0.0013272421,0.0029709549,0.0026028955,0.0038710143,0.0035581647,0.000585365],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011139191,0.3235585,0.30452085,0.0014257844,0.0003819055,0.0007584411,0.13930482,0.00101938,0.0019240463,0.0009359394,0.0024815493,0.21254963],"study_design_scores_gemma":[0.006963534,0.19969928,0.6343685,0.001190382,0.0008135351,0.00041866532,0.14042033,0.0017831704,0.0052013863,0.0010539092,0.007659087,0.0004283287],"about_ca_topic_score_codex":0.013042748,"about_ca_topic_score_gemma":0.020897334,"teacher_disagreement_score":0.031100173,"about_ca_system_score_codex":0.004959971,"about_ca_system_score_gemma":0.012944913,"threshold_uncertainty_score":0.16447538},"labels":[],"label_agreement":null},{"id":"W4224229215","doi":"10.3138/cjpe.71300","title":"Professionalism in Program Evaluators: A Comparison of American and Canadian Evaluators","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Credentialing; Autonomy; Exploratory research; Field (mathematics); Perception; Psychology; Sociology; Medical education; Pedagogy; Social science; Political science; Medicine; Law","score_opus":0.4228532574958362,"score_gpt":0.5923266515598159,"score_spread":0.1694733940639797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224229215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993701,0.00037510818,0.00017511557,0.0007669152,0.000020025915,0.000043786404,0.000043861968,0.000006134587,0.0048681013],"genre_scores_gemma":[0.99828774,0.00032897075,0.00015442548,0.0002051164,0.000004085814,0.000018138482,0.000035148118,0.0000050011913,0.0009614222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9895929,0.0030734986,0.00036472117,0.00054729905,0.00397883,0.0024426186],"domain_scores_gemma":[0.95334864,0.010221671,0.004758782,0.0006765996,0.021841373,0.009153019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014325121,0.00024465442,0.00040379475,0.003884672,0.00781746,0.003987478,0.00095716264,0.00071747025,0.0017333861],"category_scores_gemma":[0.030617243,0.00034995668,0.0002844477,0.0039693993,0.003795539,0.0008623715,0.0027047999,0.0012558176,0.00014831725],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037758244,0.0002535763,0.5302114,0.00020496524,0.000038008595,0.00034468767,0.42179635,0.000116264266,0.0009492318,0.0017448966,0.0031610024,0.040802013],"study_design_scores_gemma":[0.00002364115,0.00017148638,0.5544269,0.0002936497,0.000024223838,0.00020601379,0.4262628,0.00042401842,0.00042960964,0.00023053492,0.017440509,0.000066689136],"about_ca_topic_score_codex":0.88273835,"about_ca_topic_score_gemma":0.93252593,"teacher_disagreement_score":0.9686126,"about_ca_system_score_codex":0.031387374,"about_ca_system_score_gemma":0.058348566,"threshold_uncertainty_score":0.2359044},"labels":[],"label_agreement":null},{"id":"W4224257900","doi":"10.3138/cjpe.70805","title":"Planning the Evaluation of Patient Engagement in the PriCare Research Program","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Perspective (graphical); Logic model; Corporate governance; Key (lock); Health care; Psychology; Process management; Knowledge management; Medical education; Sociology; Medicine; Computer science; Business; Political science; Artificial intelligence","score_opus":0.8350955754394503,"score_gpt":0.6382932925627788,"score_spread":0.19680228287667156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224257900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66492623,0.0010663826,0.061086234,0.03726998,0.0005806725,0.13725798,0.0010459245,0.00065252534,0.09611402],"genre_scores_gemma":[0.79750854,0.00054448633,0.12274322,0.002416207,0.00009273147,0.07223681,0.00047157082,0.00006396968,0.003922499],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.74986756,0.22728471,0.0047415392,0.001897664,0.008894766,0.0073137083],"domain_scores_gemma":[0.8830289,0.06452483,0.009771912,0.008141137,0.020966303,0.013566937],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18285125,0.0006230575,0.00066162745,0.0020539213,0.006773134,0.006912936,0.0029595597,0.0019478098,0.006620465],"category_scores_gemma":[0.14037232,0.0007209346,0.00109457,0.0014055014,0.0030770618,0.0038873355,0.011079749,0.0045633814,0.0010432185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048960787,0.02876933,0.06342753,0.0038272582,0.00035720045,0.0007895648,0.08927254,0.008457854,0.0027164547,0.050894007,0.025320107,0.7212722],"study_design_scores_gemma":[0.00958297,0.085090466,0.1568262,0.014098863,0.0011143317,0.0008544928,0.34949812,0.034560375,0.034437787,0.04772253,0.26552436,0.00068956806],"about_ca_topic_score_codex":0.0039328807,"about_ca_topic_score_gemma":0.010135046,"teacher_disagreement_score":0.9960671,"about_ca_system_score_codex":0.016311802,"about_ca_system_score_gemma":0.06512073,"threshold_uncertainty_score":0.9670214},"labels":[],"label_agreement":null},{"id":"W4224442079","doi":"10.3138/cjpe.72929","title":"Chari Smith. (2021). <i>Nonprofit Program Evaluation Made Simple: Get Your Data. Show Your Impact. Improve Your Programs.</i>","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Disaster Management and Resilience","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Simple (philosophy); Computer science; Library science; Business; Philosophy; Epistemology","score_opus":0.19503504614680237,"score_gpt":0.4377656622489866,"score_spread":0.24273061610218424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224442079","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00087408035,0.022933127,0.0016748894,0.20047076,0.032086637,0.0007500666,0.020535894,0.0030199017,0.71765465],"genre_scores_gemma":[0.003562804,0.009453853,0.002160716,0.017490579,0.0015398904,0.0004799103,0.0070977802,0.0010632226,0.9571512],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961302,0.0005085777,0.00016143579,0.0002455871,0.002490876,0.0004633557],"domain_scores_gemma":[0.97776914,0.0015099614,0.00078390696,0.00044651024,0.013655618,0.0058349073],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003777997,0.0016058062,0.00083349005,0.0025781523,0.0028042253,0.0054818606,0.0013941905,0.0042134845,0.4289438],"category_scores_gemma":[0.015701836,0.0008928537,0.0007416451,0.0033423048,0.000761118,0.003960513,0.0031516983,0.0068228045,0.2944926],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000082943525,0.0000050950093,0.000030322732,0.000030623454,7.851126e-7,0.0000053559106,0.000007114855,0.0000042299052,0.000014775526,0.00012555534,0.9885007,0.011267304],"study_design_scores_gemma":[0.000008647246,0.000009369112,0.0007358734,0.00017599743,0.0000023844946,0.000024752613,0.000092593626,0.000018915804,0.000051476236,0.00019006789,0.99867946,0.0000104531155],"about_ca_topic_score_codex":0.109021306,"about_ca_topic_score_gemma":0.19064756,"teacher_disagreement_score":0.4289438,"about_ca_system_score_codex":0.0070684757,"about_ca_system_score_gemma":0.026066823,"threshold_uncertainty_score":0.81454235},"labels":[],"label_agreement":null},{"id":"W4224451670","doi":"10.3138/cjpe.68284","title":"Assessing Equity in the Provision of Community Based Health Services: A Post-Mortem Analysis","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Equity (law); Data collection; Business; Health services; Health equity; Public relations; Community health; Nursing; Medicine; Public health; Environmental health; Sociology; Political science","score_opus":0.37140681589309704,"score_gpt":0.5865909746940389,"score_spread":0.21518415880094183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224451670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904884,0.0004313915,0.0028574255,0.001197731,0.000030802814,0.00041537147,0.0008580005,0.000018006023,0.0037027146],"genre_scores_gemma":[0.9964876,0.00016452177,0.0017459526,0.0000880425,0.000027077971,0.00007698282,0.0003358722,0.0000067113315,0.0010672545],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9969117,0.0010370179,0.00034077777,0.00024045704,0.0010670578,0.0004029237],"domain_scores_gemma":[0.9775457,0.0071082353,0.0054777893,0.00142949,0.007920445,0.0005182245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012251421,0.00017516372,0.00025928824,0.004955474,0.0014463824,0.0012434124,0.0008916448,0.0004925111,0.0018430926],"category_scores_gemma":[0.029158188,0.0002748435,0.0002721938,0.002470003,0.0007891053,0.0010355109,0.0017848484,0.0008123636,0.00035428398],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017863278,0.000108160006,0.95849335,0.00008569537,0.00004831535,0.00040988612,0.0047430326,0.00013134374,0.00038589645,0.0007301835,0.0018233682,0.032862097],"study_design_scores_gemma":[0.000007863361,0.00023248333,0.9899907,0.000096328906,0.000041487718,0.0002664019,0.0049623456,0.0007403844,0.00086509896,0.00032480233,0.002456099,0.00001587416],"about_ca_topic_score_codex":0.039466023,"about_ca_topic_score_gemma":0.0759361,"teacher_disagreement_score":0.039466023,"about_ca_system_score_codex":0.0023284878,"about_ca_system_score_gemma":0.0028915422,"threshold_uncertainty_score":0.078472614},"labels":[],"label_agreement":null},{"id":"W4224793496","doi":"10.3138/cjpe.71430","title":"Redesigning a University-Based Evaluator Education Program for Scholarship and Practice","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Premise; Curriculum; Process (computing); Medical education; Pedagogy; Engineering ethics; Sociology; Psychology; Computer science; Engineering; Political science; Medicine","score_opus":0.4058180102937288,"score_gpt":0.5556122397401135,"score_spread":0.1497942294463847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224793496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5191848,0.0014976254,0.33064595,0.046942037,0.002260854,0.022187835,0.0005469877,0.00995639,0.06677752],"genre_scores_gemma":[0.5187558,0.0005725155,0.43612963,0.0042320234,0.0004331083,0.0056669298,0.0005178242,0.00064100284,0.03305116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96951586,0.015701579,0.0018166194,0.0031769995,0.0070296684,0.0027592934],"domain_scores_gemma":[0.8967494,0.014977719,0.006231676,0.010212709,0.040526506,0.031301923],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0737377,0.00059333595,0.0004988772,0.003873961,0.005547617,0.0076371557,0.0045897355,0.0014077238,0.010477042],"category_scores_gemma":[0.0500954,0.00077897584,0.00061105605,0.0014193126,0.0021518809,0.0041714543,0.009152085,0.0043833144,0.0027238864],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037746542,0.0068078,0.028182182,0.00058702554,0.00006347825,0.00028569068,0.013567914,0.003974351,0.009234049,0.009222301,0.036312807,0.89138496],"study_design_scores_gemma":[0.000980981,0.01314783,0.18131946,0.0025968817,0.00024417244,0.0012259813,0.029384607,0.023504626,0.04056834,0.015448923,0.69097406,0.00060420576],"about_ca_topic_score_codex":0.008737567,"about_ca_topic_score_gemma":0.02247573,"teacher_disagreement_score":0.98168814,"about_ca_system_score_codex":0.018311886,"about_ca_system_score_gemma":0.07774902,"threshold_uncertainty_score":0.3899669},"labels":[],"label_agreement":null},{"id":"W4224862209","doi":"10.3138/cjpe.71349","title":"Collaborative Evaluation Frameworks for Indigenous-Led Community Health Interventions: A Narrative Review","year":2022,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Indigenous; Psychological intervention; Narrative; Context (archaeology); Participatory action research; Equity (law); Sociology; Traditional knowledge; Citizen journalism; Community-based participatory research; Health equity; Community development; Narrative review; Engineering ethics; Medicine; Political science; Psychology; Geography; Nursing; Public health; Anthropology; Ecology; Engineering; Psychotherapist","score_opus":0.5641203596982542,"score_gpt":0.6521167436229571,"score_spread":0.08799638392470288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224862209","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008354899,0.9611531,0.011222515,0.015691767,0.0014031737,0.00217628,0.00013464373,0.00005066287,0.0073324004],"genre_scores_gemma":[0.04621537,0.8915777,0.043893963,0.005986796,0.0005086952,0.010601684,0.00021777143,0.000056776193,0.00094127294],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.83248645,0.12718831,0.0175445,0.0039025422,0.016976159,0.0019021132],"domain_scores_gemma":[0.69217324,0.26130185,0.011134206,0.0064564934,0.027097903,0.0018363147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16624753,0.0017326717,0.003680421,0.012515657,0.004137729,0.011123503,0.004376135,0.0040131207,0.0031605887],"category_scores_gemma":[0.26714042,0.0011720463,0.0036686114,0.013380834,0.0076711285,0.008020245,0.009498611,0.0066881105,0.00043176854],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015597868,0.00017775259,0.00060417096,0.26430026,0.0009145152,0.00020326154,0.015669534,0.0016033842,0.0002198686,0.17063639,0.023042196,0.5224727],"study_design_scores_gemma":[0.000111727924,0.00014538392,0.00080693356,0.67184067,0.001264181,0.00024235163,0.008482164,0.000696518,0.00037161112,0.024717802,0.29122934,0.000091337715],"about_ca_topic_score_codex":0.015656902,"about_ca_topic_score_gemma":0.024947809,"teacher_disagreement_score":0.16624753,"about_ca_system_score_codex":0.022207813,"about_ca_system_score_gemma":0.07400792,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4224866913","doi":"10.3138/cjpe.72386","title":"Evaluation Utility Metrics (EUMs) in Reflective Practice","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences","keywords":"Quality (philosophy); Negotiation; Computer science; Evaluation methods; Management science; Process management; Risk analysis (engineering); Psychology; Medicine; Business; Reliability engineering; Sociology; Engineering","score_opus":0.5800774051525978,"score_gpt":0.6115541890215195,"score_spread":0.03147678386892172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224866913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0234277,0.009639557,0.91640717,0.007936486,0.00070210744,0.0037307981,0.0003967361,0.0011995932,0.03655981],"genre_scores_gemma":[0.3024221,0.0016844177,0.68803036,0.00072572514,0.00018783358,0.0054515833,0.00025827193,0.00023082101,0.001008905],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.41378182,0.5057175,0.030881489,0.006626687,0.040692985,0.0022995137],"domain_scores_gemma":[0.28042775,0.58466417,0.042339467,0.032718442,0.056292836,0.0035572785],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.34462368,0.0026677141,0.0028916139,0.018689714,0.0028028216,0.016476039,0.0032083536,0.003938661,0.0038658157],"category_scores_gemma":[0.60869586,0.0012993366,0.002912188,0.016911449,0.011004969,0.019446079,0.012502338,0.0051989136,0.0007705696],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062921195,0.000373281,0.014265,0.0057980814,0.00075792056,0.00012283163,0.010965356,0.016420633,0.0006454996,0.41317815,0.0101559125,0.5266881],"study_design_scores_gemma":[0.00042767884,0.0014161684,0.01583153,0.013277808,0.00073021115,0.00056742784,0.008677859,0.08969446,0.004579085,0.7822038,0.08202924,0.0005647986],"about_ca_topic_score_codex":0.0025479693,"about_ca_topic_score_gemma":0.0018183076,"teacher_disagreement_score":0.34462368,"about_ca_system_score_codex":0.012577402,"about_ca_system_score_gemma":0.013156359,"threshold_uncertainty_score":0.8081957},"labels":[],"label_agreement":null},{"id":"W4224935412","doi":"10.3138/cjpe.72398","title":"Évaluer la gouvernance des interventions interministérielles : une nouvelle exigence. Enseignements de l’évaluation de la démarche de transition de l’école à la vie adulte (TÉVA) des jeunes en situation de handicap","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"General partnership; Corporate governance; Valuation (finance); Sociology; Psychological intervention; Political science; Welfare economics; Psychology; Management; Business; Economics; Accounting","score_opus":0.07943805688367402,"score_gpt":0.3940309897984467,"score_spread":0.3145929329147727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224935412","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5030541,0.16934018,0.058531776,0.13068894,0.0051625026,0.04229981,0.004938734,0.0007297643,0.08525418],"genre_scores_gemma":[0.8997657,0.013611272,0.052829884,0.0064343214,0.00042113548,0.020285035,0.0007773999,0.00013205229,0.0057432605],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8044334,0.15932573,0.006749364,0.003967677,0.020398594,0.0051252623],"domain_scores_gemma":[0.7973457,0.122282736,0.018400202,0.0099228695,0.043387067,0.008661416],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19269957,0.0014297487,0.0024739043,0.0018988514,0.0026226568,0.0074009644,0.0026670254,0.0022922046,0.008503862],"category_scores_gemma":[0.24139553,0.00063847145,0.0023473597,0.002640231,0.003342337,0.006442429,0.0049164253,0.003890021,0.0005839218],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0072383257,0.0034131275,0.04011258,0.018971715,0.004820535,0.00015927976,0.017523197,0.007573817,0.0018440381,0.023675155,0.012994924,0.86167336],"study_design_scores_gemma":[0.011281693,0.035316445,0.52421516,0.116953954,0.009412332,0.0002885158,0.033162933,0.019492088,0.008978665,0.02561125,0.21468394,0.0006030261],"about_ca_topic_score_codex":0.15421462,"about_ca_topic_score_gemma":0.27647248,"teacher_disagreement_score":0.9557903,"about_ca_system_score_codex":0.044209722,"about_ca_system_score_gemma":0.07941088,"threshold_uncertainty_score":0.99554515},"labels":[],"label_agreement":null},{"id":"W4224940934","doi":"10.3138/cjpe.71050","title":"Realistic Evaluation and the Process-Tracing Method: A Combined Approach to Scrutinizing Causal Mechanisms","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Scrutiny; Framing (construction); Process tracing; Tracing; Causal model; Computer science; Process (computing); Causal inference; Psychology; Management science; Process management; Epistemology; Econometrics; Political science; Engineering; Economics; Mathematics","score_opus":0.34706621608805643,"score_gpt":0.5365759557097144,"score_spread":0.18950973962165796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224940934","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009688844,0.00075632293,0.97535044,0.0032374826,0.00009799449,0.0014251595,0.00005680309,0.00015539762,0.009231472],"genre_scores_gemma":[0.3177506,0.00042050632,0.67661047,0.00059805514,0.000086090586,0.003518136,0.00006437914,0.00009196995,0.000859758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.44917357,0.5126122,0.009591288,0.010123137,0.017027266,0.0014725039],"domain_scores_gemma":[0.40180412,0.505156,0.022118881,0.05425432,0.014965042,0.0017016842],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30699798,0.002109745,0.0030124134,0.015556883,0.0037360715,0.010573726,0.0054505025,0.004583481,0.0066305925],"category_scores_gemma":[0.3973298,0.0018319224,0.0029305608,0.0060162917,0.02245407,0.021048546,0.012959713,0.006734715,0.00053366413],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032915015,0.00043352396,0.007145108,0.0030062452,0.0005993744,0.00038663458,0.038680736,0.0064115925,0.0019312436,0.7315778,0.001425371,0.20807312],"study_design_scores_gemma":[0.00033780365,0.0007142736,0.0053372663,0.0042646155,0.00041454515,0.00076016004,0.014313508,0.046744168,0.0050821276,0.89383763,0.027876573,0.00031736743],"about_ca_topic_score_codex":0.002534447,"about_ca_topic_score_gemma":0.0028379897,"teacher_disagreement_score":0.693002,"about_ca_system_score_codex":0.009500778,"about_ca_system_score_gemma":0.01402216,"threshold_uncertainty_score":0.8545949},"labels":[],"label_agreement":null},{"id":"W4225597205","doi":"10.3138/cjpe.36.3.ed-en","title":"Editor’s Remarks","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.06340639280039151,"score_gpt":0.42163111870667735,"score_spread":0.35822472590628585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225597205","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007680563,0.0015261127,0.00008547737,0.27010304,0.72575545,0.000034524717,0.00009289078,0.000057200246,0.0022685057],"genre_scores_gemma":[0.0011464908,0.0015830153,0.00054847996,0.51642036,0.4534732,0.00012698288,0.000057659046,0.00007267997,0.02657105],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.973371,0.0030368508,0.0038156558,0.0031176708,0.01356862,0.003090108],"domain_scores_gemma":[0.87642336,0.026883157,0.009813461,0.005081529,0.06876968,0.013028826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029479804,0.0028989068,0.0046416298,0.004349046,0.0067573003,0.013240685,0.007947575,0.05622377,0.025685137],"category_scores_gemma":[0.17316264,0.0022758164,0.0058600167,0.003459665,0.005049864,0.00521553,0.0032582933,0.04640487,0.021994334],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001895061,0.000010597189,0.00004630057,0.00004835093,0.000011210649,0.00011117846,0.000017456305,0.000013323746,0.000015904154,0.00025011503,0.9979755,0.0014811005],"study_design_scores_gemma":[0.00009855416,0.000025452093,0.0005917453,0.00038320658,0.000056274403,0.0002174521,0.00014303421,0.000111635185,0.000107809334,0.00085599633,0.99735606,0.000052770716],"about_ca_topic_score_codex":0.01542564,"about_ca_topic_score_gemma":0.034573276,"teacher_disagreement_score":0.05622377,"about_ca_system_score_codex":0.011074635,"about_ca_system_score_gemma":0.018234015,"threshold_uncertainty_score":0.15590596},"labels":[],"label_agreement":null},{"id":"W4225929430","doi":"10.3138/cjpe.73685","title":"Pat Bazeley. (2018). <i>Integrating Analyses in Mixed Methods Research</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.8220107669184188,"score_gpt":0.7166431773534617,"score_spread":0.10536758956495706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225929430","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005092216,0.19212307,0.05912917,0.63907933,0.042915866,0.0006204325,0.004992595,0.00330384,0.05732648],"genre_scores_gemma":[0.023079036,0.2840405,0.17258584,0.2660419,0.035945974,0.0042619463,0.006766024,0.00647318,0.20080553],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9861215,0.006666121,0.0013257195,0.0007847909,0.004869958,0.00023201681],"domain_scores_gemma":[0.83733577,0.09089379,0.0064803055,0.004537676,0.056159616,0.004592868],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03680838,0.0013276429,0.00108138,0.006189994,0.0030790032,0.006810031,0.0031871551,0.006569444,0.06904118],"category_scores_gemma":[0.1645279,0.0017254453,0.00084717054,0.009452313,0.0042699897,0.008041989,0.004091814,0.012095211,0.05447397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028307331,0.000010095109,0.00022021281,0.00050919194,0.000012226457,0.000027052161,0.0002504639,0.00004150869,0.00007574669,0.0028371292,0.90996224,0.08602585],"study_design_scores_gemma":[0.000045716308,0.000029761364,0.0016807436,0.0034949372,0.000055865657,0.00020655466,0.0004249377,0.00022814727,0.00043991135,0.017458105,0.9758815,0.000053717897],"about_ca_topic_score_codex":0.029615778,"about_ca_topic_score_gemma":0.045454502,"teacher_disagreement_score":0.9631916,"about_ca_system_score_codex":0.0024292092,"about_ca_system_score_gemma":0.013264791,"threshold_uncertainty_score":0.23096573},"labels":[],"label_agreement":null},{"id":"W4225936008","doi":"10.3138/cjpe.73771","title":"Jill Anne Chouinard &amp; Fiona Cram. (2020). <i>Culturally responsive approaches to evaluation: Empirical implications for theory and practice.</i>","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Empirical research; Psychology; Epistemology; Philosophy","score_opus":0.7071106155438179,"score_gpt":0.5753760736915132,"score_spread":0.1317345418523047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225936008","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005420238,0.58308244,0.0042287596,0.20812234,0.02097374,0.0002504915,0.0011939242,0.0008523369,0.18075396],"genre_scores_gemma":[0.0036318456,0.18492082,0.0046639405,0.029953687,0.0022852034,0.00023591907,0.00048733503,0.00049169286,0.7733296],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.998256,0.00021622992,0.00007501674,0.00022141951,0.0011569357,0.00007440896],"domain_scores_gemma":[0.99655724,0.0012554293,0.00022685157,0.000086621934,0.0014283621,0.00044555336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021541817,0.0013744457,0.0008725131,0.0023196517,0.0011504972,0.0035701985,0.0012271194,0.003356781,0.080788605],"category_scores_gemma":[0.0074277427,0.00090248015,0.00039807605,0.0030715754,0.0013262616,0.00544797,0.0016957984,0.0046104034,0.056156363],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047944873,0.000003166555,0.00002993162,0.00014129914,0.0000010375068,0.000014025162,0.000076644086,0.000012635974,0.000039373084,0.0005808594,0.94649607,0.05260021],"study_design_scores_gemma":[0.0000025330282,0.00000410825,0.00024404797,0.00054767815,0.0000022438091,0.00008260789,0.000120990415,0.000025289695,0.000059206577,0.00066033495,0.9982431,0.000007746994],"about_ca_topic_score_codex":0.02314527,"about_ca_topic_score_gemma":0.055942655,"teacher_disagreement_score":0.080788605,"about_ca_system_score_codex":0.0022501305,"about_ca_system_score_gemma":0.003996598,"threshold_uncertainty_score":0.2702648},"labels":[],"label_agreement":null},{"id":"W4226031910","doi":"10.3138/cjpe.36.3.ann-fr","title":"Annonce de la section Nos racines et nos liens : célébrons l’évaluation autochtone","year":2022,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"French Urban and Social Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Section (typography); Philosophy; Humanities; Business","score_opus":0.13440052577727746,"score_gpt":0.3912466028359764,"score_spread":0.25684607705869894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226031910","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003001611,0.0057543414,0.0017751422,0.86338514,0.095189705,0.001022656,0.00019127669,0.0002340232,0.02944601],"genre_scores_gemma":[0.058132906,0.005614126,0.008265853,0.63239753,0.056631494,0.0053205583,0.00059319666,0.0005723637,0.23247206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8367363,0.05645226,0.011764724,0.0057945703,0.07293585,0.016316269],"domain_scores_gemma":[0.6533274,0.12963331,0.013375996,0.018995482,0.12894075,0.055727154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17265679,0.0013096787,0.0018392262,0.003392826,0.010192387,0.015939185,0.0043759416,0.044658244,0.03070244],"category_scores_gemma":[0.32343748,0.0016698542,0.0026686813,0.0014577308,0.007975482,0.009890393,0.014740736,0.030506535,0.008978303],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029693486,0.00033896635,0.0005615082,0.00046260926,0.00003796766,0.00022991741,0.0012307173,0.00015770257,0.0007329554,0.013383341,0.9393236,0.043243784],"study_design_scores_gemma":[0.00027811027,0.0002665086,0.0036050708,0.0013170067,0.000040801453,0.00024250061,0.00097062945,0.0003234062,0.0005526892,0.003886465,0.9883917,0.00012503534],"about_ca_topic_score_codex":0.0324411,"about_ca_topic_score_gemma":0.08647139,"teacher_disagreement_score":0.9768348,"about_ca_system_score_codex":0.023165207,"about_ca_system_score_gemma":0.085245416,"threshold_uncertainty_score":0.9131073},"labels":[],"label_agreement":null},{"id":"W4226083882","doi":"10.3138/cjpe.71482","title":"Learning and Leading: Integrating Mixed Methods in a Collaborative Approach to Educational Evaluation","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta; Western University; Queen's University","funders":"","keywords":"Multimethodology; Perspective (graphical); Context (archaeology); Mental health; Value (mathematics); Collaborative learning; Qualitative property; Qualitative research; Phenomenon; Psychology; Knowledge management; Sociology; Pedagogy; Computer science; Epistemology; Social science","score_opus":0.35869882773020634,"score_gpt":0.6077636009537061,"score_spread":0.24906477322349974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226083882","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024192918,0.0045793676,0.90416074,0.015024134,0.00081839855,0.024183096,0.00016050848,0.00055172964,0.026329223],"genre_scores_gemma":[0.09624141,0.0010529868,0.8811584,0.0012336143,0.00011089312,0.01927415,0.000043104243,0.00008219269,0.0008032415],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.29920912,0.66742235,0.010160154,0.004112893,0.017414428,0.0016809929],"domain_scores_gemma":[0.44491524,0.48628777,0.011250204,0.023956643,0.028333582,0.0052565546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.49723342,0.002088823,0.0029244926,0.01130184,0.008446514,0.02067388,0.0064818147,0.002823613,0.004287007],"category_scores_gemma":[0.35218593,0.0015024644,0.0024162198,0.0057667494,0.010632398,0.009730925,0.020433769,0.0054354714,0.00061973644],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083928474,0.0015160647,0.006560011,0.007327457,0.001259593,0.0004970864,0.09689756,0.0057140053,0.0013627606,0.08625954,0.0055263173,0.78624034],"study_design_scores_gemma":[0.0028428165,0.006052842,0.011039712,0.043845493,0.0020803371,0.0013480224,0.121461414,0.06074937,0.009496211,0.5556785,0.18425196,0.0011532715],"about_ca_topic_score_codex":0.008354929,"about_ca_topic_score_gemma":0.025437005,"teacher_disagreement_score":0.49723342,"about_ca_system_score_codex":0.015440729,"about_ca_system_score_gemma":0.031543545,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4226105250","doi":"10.3138/cjpe.71203","title":"Developing a Comprehensive Mixed Methods Evaluation to Address Contextual Complexities of a MOOC","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.2700693598675374,"score_gpt":0.47357269038458316,"score_spread":0.20350333051704578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226105250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.121285185,0.0074236323,0.7006029,0.0077915387,0.0011353869,0.13237631,0.0008182342,0.0006018624,0.027964976],"genre_scores_gemma":[0.23175193,0.0013075905,0.6750491,0.0020549179,0.000123197,0.08801389,0.0002723425,0.000091734975,0.0013352968],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.5758334,0.36690983,0.018602654,0.0056209676,0.030260587,0.0027725997],"domain_scores_gemma":[0.49844405,0.36780238,0.020428028,0.020683782,0.08821483,0.00442692],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37649307,0.0014861914,0.0017438735,0.0038148349,0.003595577,0.0075504775,0.002920381,0.0026618897,0.0042023696],"category_scores_gemma":[0.36202985,0.0009501676,0.0027203683,0.0023127792,0.0028401387,0.0054113613,0.00630963,0.0023624732,0.00068983727],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023411177,0.003920474,0.024135288,0.01893904,0.001931976,0.00027963668,0.02112451,0.010835589,0.0071562584,0.059079055,0.005729332,0.8445276],"study_design_scores_gemma":[0.00757439,0.075388096,0.082839936,0.11456096,0.008993582,0.001151685,0.054364182,0.09958898,0.07295995,0.17942125,0.3018464,0.0013106095],"about_ca_topic_score_codex":0.0028261906,"about_ca_topic_score_gemma":0.0051916554,"teacher_disagreement_score":0.6235069,"about_ca_system_score_codex":0.012863275,"about_ca_system_score_gemma":0.03579293,"threshold_uncertainty_score":0.76889503},"labels":[],"label_agreement":null},{"id":"W4226119644","doi":"10.3138/cjpe.73687","title":"The Contributions of Innovations in Integration in Complex Mixed Methods Evaluation Designs in This Issue and Beyond","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Closing (real estate); Management science; Psychology; Computer science; Epistemology; Business; Economics; Philosophy","score_opus":0.4642771256930222,"score_gpt":0.5952877465304317,"score_spread":0.1310106208374095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226119644","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007262094,0.009475016,0.00083802576,0.9455511,0.042968493,0.000025798401,0.00006202068,0.000020943091,0.0009859775],"genre_scores_gemma":[0.0033032564,0.0063295932,0.0030151247,0.87136817,0.11412356,0.0001669395,0.00002320947,0.00007987,0.0015902651],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78749263,0.12246426,0.016553868,0.016162936,0.053769372,0.0035567784],"domain_scores_gemma":[0.1539248,0.7616211,0.008466464,0.0083597265,0.06307689,0.004550988],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21781188,0.0014009264,0.0040025054,0.0033405123,0.005749134,0.011344443,0.012902654,0.05700465,0.010088854],"category_scores_gemma":[0.59043497,0.0018900576,0.0035774254,0.003457893,0.026891693,0.012816821,0.0059906025,0.063468486,0.0024808142],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103658545,0.000023971648,0.00024155066,0.0019211733,0.00018626306,0.0001754092,0.0015958088,0.00029763646,0.00008203367,0.05520647,0.9130136,0.02715249],"study_design_scores_gemma":[0.000256572,0.00006260117,0.00084699417,0.013613838,0.00032182966,0.00022286494,0.0011557104,0.00075847574,0.00030491615,0.07756328,0.9047142,0.0001787506],"about_ca_topic_score_codex":0.044319842,"about_ca_topic_score_gemma":0.06400092,"teacher_disagreement_score":0.7821881,"about_ca_system_score_codex":0.020379685,"about_ca_system_score_gemma":0.04121482,"threshold_uncertainty_score":0.9645772},"labels":[],"label_agreement":null},{"id":"W4226263038","doi":"10.3138/cjpe.70920","title":"Responding to the Evaluation Capacity Needs of the Early Childhood Field: Insights from a Mixed Methods Community-based Participatory Design","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Capacity building; Interdependence; Citizen journalism; Knowledge management; Participatory action research; Multimethodology; Resource (disambiguation); Capacity development; Qualitative property; Sociology; Management science; Psychology; Pedagogy; Environmental resource management; Computer science; Engineering; Political science; Social science","score_opus":0.6312424150244843,"score_gpt":0.5375796860218353,"score_spread":0.09366272900264905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226263038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5727454,0.002408005,0.31574193,0.047086902,0.00068642735,0.010407563,0.00046929537,0.00026019415,0.050194323],"genre_scores_gemma":[0.802631,0.0009459355,0.17998108,0.0026239464,0.00008995556,0.009793547,0.000098665136,0.00014645018,0.0036894162],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8039903,0.1816152,0.0022303294,0.0026153617,0.00695828,0.0025904789],"domain_scores_gemma":[0.73804235,0.22943822,0.005211424,0.008048264,0.015184447,0.004075304],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16586296,0.0007211252,0.00080916344,0.0028767611,0.011312122,0.011111707,0.0036730308,0.002395501,0.0026162958],"category_scores_gemma":[0.11531574,0.0009002738,0.00060977,0.002565208,0.016685767,0.005596967,0.011134051,0.0039046544,0.0003332956],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012717425,0.00035414106,0.0058972426,0.0012515187,0.000049769536,0.000657661,0.87711227,0.00074780185,0.0019392667,0.032640558,0.0033090517,0.07591352],"study_design_scores_gemma":[0.000119545286,0.0005278249,0.004613999,0.0024233875,0.000084207415,0.00053476536,0.8351317,0.0026404904,0.004056085,0.053112026,0.09663723,0.000118743104],"about_ca_topic_score_codex":0.0052256603,"about_ca_topic_score_gemma":0.012696017,"teacher_disagreement_score":0.9909197,"about_ca_system_score_codex":0.009080286,"about_ca_system_score_gemma":0.024822185,"threshold_uncertainty_score":0.87717766},"labels":[],"label_agreement":null},{"id":"W4226406422","doi":"10.3138/cjpe.73684","title":"Donna Mertens. (2018). <i>Mixed Methods Design in Evaluation</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.5744650939781201,"score_gpt":0.5931184524350988,"score_spread":0.018653358456978686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226406422","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001285102,0.15089096,0.29293802,0.28162262,0.04788309,0.0056143287,0.029909266,0.010465771,0.17939086],"genre_scores_gemma":[0.024253054,0.081038736,0.5821086,0.05876791,0.0056490395,0.033334102,0.008148946,0.010173582,0.19652599],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96374214,0.023686018,0.0033348207,0.0014122608,0.00746577,0.0003589588],"domain_scores_gemma":[0.7754203,0.14819075,0.008093833,0.010749797,0.053234342,0.0043109045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.064212106,0.0018527877,0.0015545365,0.0045521753,0.0039777523,0.0059816283,0.004139657,0.0069868104,0.12050431],"category_scores_gemma":[0.24886553,0.003146624,0.0019925295,0.0050711227,0.0037336107,0.004337342,0.0042192345,0.010596783,0.049189117],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016629283,0.000026497633,0.00020146587,0.00253724,0.00007039589,0.000056588535,0.0008114979,0.00024527244,0.00032035078,0.010373908,0.8328289,0.15236165],"study_design_scores_gemma":[0.0001726159,0.000043913176,0.0012513548,0.007385811,0.00015700364,0.00010693197,0.00040018346,0.0004948442,0.00072427554,0.017168488,0.97199124,0.000103270846],"about_ca_topic_score_codex":0.053112067,"about_ca_topic_score_gemma":0.09232956,"teacher_disagreement_score":0.12050431,"about_ca_system_score_codex":0.005626366,"about_ca_system_score_gemma":0.02139478,"threshold_uncertainty_score":0.40312713},"labels":[],"label_agreement":null},{"id":"W4226507667","doi":"10.3138/cjpe.71237","title":"A Multi-Stage Approach to Qualitative Sampling within a Mixed Methods Evaluation: Some Reflections on Purpose and Process","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Economic and Social Research Council","keywords":"Randomized controlled trial; Scale (ratio); Sampling (signal processing); Process (computing); Qualitative property; Sample (material); Computer science; Intervention (counseling); Multimethodology; Psychology; Process management; Mathematics education; Business; Machine learning; Geography; Medicine","score_opus":0.8290454090139003,"score_gpt":0.7062106398700911,"score_spread":0.1228347691438092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226507667","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034060415,0.008482467,0.5360229,0.37576443,0.003132742,0.016352143,0.00012908562,0.00047822963,0.025577528],"genre_scores_gemma":[0.36192417,0.003538946,0.55107945,0.04780816,0.00063724665,0.03000616,0.00005164199,0.00060294935,0.0043513305],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.22579761,0.7454118,0.0077214665,0.0035309584,0.01370602,0.003832205],"domain_scores_gemma":[0.3465145,0.5934614,0.007567252,0.017705185,0.030029485,0.0047221393],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.60337216,0.0021957837,0.0023468481,0.0039061923,0.021917991,0.024780223,0.010689561,0.012769973,0.003941567],"category_scores_gemma":[0.39858064,0.0028236695,0.0022502225,0.0031561283,0.06661587,0.020664113,0.022728918,0.023770127,0.0013351369],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020248431,0.00030286683,0.0018887828,0.0030987544,0.00011983237,0.0007228326,0.78407586,0.0008981344,0.001642344,0.13454323,0.007895504,0.06460946],"study_design_scores_gemma":[0.00037666087,0.00092417415,0.0018721722,0.014285004,0.00015907553,0.001359833,0.585735,0.005899338,0.005162136,0.21364613,0.1701836,0.00039685096],"about_ca_topic_score_codex":0.01210148,"about_ca_topic_score_gemma":0.019724485,"teacher_disagreement_score":0.39662784,"about_ca_system_score_codex":0.028259909,"about_ca_system_score_gemma":0.04131182,"threshold_uncertainty_score":0.4891128},"labels":[],"label_agreement":null},{"id":"W4230488502","doi":"10.3138/cjpe.230","title":"Useful Theory of Change Models","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":213,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Causality (physics); Theory of change; Development theory; Intervention (counseling); Epistemology; Computer science; Psychological intervention; Management science; Psychology; Sociology; Economics; Philosophy; Physics","score_opus":0.8815743086593234,"score_gpt":0.5830366120430426,"score_spread":0.2985376966162808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230488502","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009907967,0.0017128161,0.8585519,0.016591322,0.00034147425,0.00048366477,0.00071992,0.00029035014,0.11140054],"genre_scores_gemma":[0.67582065,0.003231082,0.29153016,0.0028019238,0.00038475817,0.0033421838,0.0008921719,0.00015990059,0.021837153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99210453,0.0050600916,0.0002965251,0.00059243606,0.0015280489,0.00041845744],"domain_scores_gemma":[0.9843253,0.0115339,0.00078113715,0.0010232287,0.0019493143,0.00038719465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0094247395,0.0013662896,0.00093863363,0.0023826612,0.001178016,0.00420648,0.0026855948,0.0031311393,0.010362248],"category_scores_gemma":[0.021869104,0.00045312743,0.001447932,0.0022316703,0.0043186005,0.0050286264,0.0022560498,0.004231288,0.0014655838],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008294068,0.000036034555,0.00025682137,0.00007005314,0.000015787406,0.000022671811,0.00019611527,0.014017011,0.000027095453,0.97825694,0.001968609,0.0051245946],"study_design_scores_gemma":[0.000025056339,0.000030612544,0.00012431551,0.00009358687,0.000014511815,0.000020777841,0.00011201919,0.052792028,0.00008422742,0.9344803,0.01221156,0.000011006683],"about_ca_topic_score_codex":0.004107931,"about_ca_topic_score_gemma":0.0036030996,"teacher_disagreement_score":0.010362248,"about_ca_system_score_codex":0.004854846,"about_ca_system_score_gemma":0.0039993473,"threshold_uncertainty_score":0.04984343},"labels":[],"label_agreement":null},{"id":"W4234160001","doi":"10.3138/cjpe.34.3.v","title":"Editor’s Remarks","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.3130698758640696,"score_gpt":0.5203254987844013,"score_spread":0.20725562292033167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234160001","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011897888,0.0015820452,0.00023342078,0.40086737,0.58807343,0.000043609303,0.00019388724,0.00009267516,0.008794662],"genre_scores_gemma":[0.002193362,0.0017013061,0.0009470481,0.65913826,0.24689148,0.00015369711,0.000106309875,0.00012987998,0.08873866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9873685,0.0014800098,0.0014747783,0.0022530865,0.0061911624,0.0012323081],"domain_scores_gemma":[0.9445143,0.013884876,0.0026758935,0.0024198927,0.031901047,0.004603958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017997473,0.0016073197,0.0016713899,0.0027022194,0.0052690534,0.009770556,0.0048116865,0.02684346,0.029474195],"category_scores_gemma":[0.11128567,0.0009277208,0.0026465405,0.0020119739,0.0028396675,0.00531524,0.002526529,0.02588743,0.02050659],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009433921,0.0000066073594,0.000040091698,0.00003038658,0.000004916264,0.00006124931,0.000021218633,0.00002037385,0.000022278604,0.00096960226,0.9968168,0.0019971358],"study_design_scores_gemma":[0.000020086227,0.000008063595,0.00022630952,0.00010875321,0.000013580098,0.00005461721,0.00006521164,0.00006445314,0.00010183141,0.0009291888,0.99838984,0.000018203938],"about_ca_topic_score_codex":0.013315754,"about_ca_topic_score_gemma":0.020156292,"teacher_disagreement_score":0.029474195,"about_ca_system_score_codex":0.0060965447,"about_ca_system_score_gemma":0.011268729,"threshold_uncertainty_score":0.09860104},"labels":[],"label_agreement":null},{"id":"W4234200529","doi":"10.3138/cjpe.32.2.vi","title":"Un mot du rédacteur","year":2017,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.22561917199059764,"score_gpt":0.5001354038874755,"score_spread":0.2745162318968778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234200529","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002980812,0.013086781,0.003015975,0.61464316,0.24115245,0.00022122316,0.0018940999,0.0007299293,0.12227556],"genre_scores_gemma":[0.05138804,0.015803058,0.012065467,0.22760442,0.07483367,0.00061908003,0.0029504956,0.0011978162,0.6135379],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96374696,0.00986124,0.003012315,0.0025824439,0.017749052,0.0030478842],"domain_scores_gemma":[0.8174276,0.031759523,0.006366672,0.010857053,0.11681913,0.016770015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02727915,0.0011518236,0.0012786272,0.0034681996,0.0056081535,0.010704291,0.0030178702,0.0076082167,0.10022205],"category_scores_gemma":[0.14464144,0.0007171934,0.0014316632,0.0029796257,0.003293286,0.008282369,0.0047812564,0.010515191,0.027612535],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011012445,0.000048375965,0.0014913378,0.00044995217,0.000021985414,0.00026583803,0.00051062054,0.00008280103,0.00026989926,0.0152448155,0.8765891,0.104915194],"study_design_scores_gemma":[0.000033256947,0.000033093,0.0015607559,0.0005901741,0.000018138275,0.00046003237,0.00056402496,0.00010248542,0.0003078111,0.002444873,0.9938573,0.00002801293],"about_ca_topic_score_codex":0.074040994,"about_ca_topic_score_gemma":0.084064715,"teacher_disagreement_score":0.10022205,"about_ca_system_score_codex":0.013260542,"about_ca_system_score_gemma":0.044950433,"threshold_uncertainty_score":0.3352762},"labels":[],"label_agreement":null},{"id":"W4234946968","doi":"10.3138/cjpe.30.3.04","title":"Lessons on Decolonizing Evaluation from Kaupapa Māori Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Indigenous; Sociology; Traditional knowledge; Equity (law); Christian ministry; Community development; Cultural competence; Pedagogy; Public relations; Political science; Gender studies","score_opus":0.6218029580620157,"score_gpt":0.5966281862836175,"score_spread":0.02517477177839822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234946968","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11668039,0.029562984,0.026033515,0.64124566,0.0033011185,0.0050255964,0.00016417277,0.0004043184,0.17758219],"genre_scores_gemma":[0.8563464,0.014493084,0.04843249,0.04792348,0.0007756723,0.0066779926,0.00014939274,0.00048651444,0.02471493],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79897374,0.16161866,0.009412055,0.0028400728,0.018061459,0.009094099],"domain_scores_gemma":[0.7042134,0.19576369,0.006761682,0.01287222,0.07081874,0.009570265],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23149009,0.0009680847,0.00120529,0.0036298526,0.015509086,0.021129847,0.0054038214,0.005331295,0.006625647],"category_scores_gemma":[0.20416863,0.0009880979,0.0013229816,0.0032334712,0.019369679,0.017070565,0.01839954,0.0137090115,0.000797773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039945042,0.0006061498,0.00597787,0.005902341,0.00018975849,0.0018008042,0.31203008,0.0014005404,0.0016717524,0.15959087,0.07133732,0.4390931],"study_design_scores_gemma":[0.00039103717,0.00095712015,0.0139993075,0.018325534,0.00021099117,0.0011177091,0.27616063,0.0022258656,0.0028089613,0.077704,0.6056922,0.00040671864],"about_ca_topic_score_codex":0.07866545,"about_ca_topic_score_gemma":0.13644795,"teacher_disagreement_score":0.7685099,"about_ca_system_score_codex":0.05708936,"about_ca_system_score_gemma":0.0903508,"threshold_uncertainty_score":0.94770956},"labels":[],"label_agreement":null},{"id":"W4235459746","doi":"10.3138/cjpe.33.2.vi","title":"Un mot de la rédactrice","year":2018,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.09207310104476685,"score_gpt":0.37894328356865975,"score_spread":0.2868701825238929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235459746","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018920569,0.013418087,0.092315145,0.1643397,0.054786846,0.0009790008,0.0078282235,0.012263412,0.635149],"genre_scores_gemma":[0.11290233,0.008586117,0.06625143,0.021439932,0.014684757,0.0013769607,0.0068845213,0.0066294293,0.76124454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9724851,0.011084457,0.0011842196,0.0023099182,0.01180219,0.0011340831],"domain_scores_gemma":[0.96362966,0.009992888,0.0014676083,0.0034927453,0.019959154,0.001457922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014623268,0.0020595638,0.0015427346,0.0035720211,0.005931755,0.01560749,0.0019182622,0.004643483,0.092633225],"category_scores_gemma":[0.04801931,0.0010265181,0.0018646822,0.0029297932,0.0034353046,0.008988707,0.004354122,0.011279062,0.033787325],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005898941,0.00021705666,0.0018415082,0.0009398877,0.000071958304,0.00065757125,0.003308285,0.0010931733,0.0041785236,0.14199084,0.51289153,0.3322198],"study_design_scores_gemma":[0.00006406114,0.000044968398,0.0011899587,0.00025757717,0.000016253953,0.00038918894,0.00074875605,0.0006200569,0.0015807281,0.0048174765,0.99021727,0.000053686632],"about_ca_topic_score_codex":0.08248943,"about_ca_topic_score_gemma":0.050592273,"teacher_disagreement_score":0.092633225,"about_ca_system_score_codex":0.01057423,"about_ca_system_score_gemma":0.010768235,"threshold_uncertainty_score":0.30988896},"labels":[],"label_agreement":null},{"id":"W4235723298","doi":"10.3138/cjpe.30.3.vi","title":"Un mot du rédacteur","year":2016,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.16177410226179187,"score_gpt":0.46182805204444066,"score_spread":0.30005394978264877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235723298","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031427583,0.013096157,0.003135457,0.6103941,0.2389791,0.00022416371,0.0018717018,0.00073612237,0.12842047],"genre_scores_gemma":[0.05123492,0.01528289,0.011790785,0.22216053,0.07241208,0.00060964964,0.0027884762,0.0011652673,0.6225553],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96455073,0.009730599,0.002919192,0.002546257,0.01727362,0.0029796294],"domain_scores_gemma":[0.82666,0.030849213,0.0063006356,0.010468228,0.10963165,0.016090387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026423318,0.0011572366,0.0012696118,0.0033768837,0.005622086,0.010538296,0.002977826,0.007609992,0.10186391],"category_scores_gemma":[0.14064166,0.00071464956,0.0014359957,0.0029119763,0.003243664,0.00834743,0.0047244616,0.01056156,0.028122181],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011590178,0.00005037673,0.0015455142,0.00046894673,0.000022660624,0.0002913298,0.0005416481,0.00008721485,0.00029139954,0.01598066,0.8720805,0.1085239],"study_design_scores_gemma":[0.000033832075,0.00003477405,0.0015415727,0.0005760412,0.00001815057,0.00048616753,0.0005736772,0.00010487633,0.0003238441,0.0024484026,0.9938304,0.000028380073],"about_ca_topic_score_codex":0.06767864,"about_ca_topic_score_gemma":0.076027334,"teacher_disagreement_score":0.10186391,"about_ca_system_score_codex":0.012499865,"about_ca_system_score_gemma":0.041617054,"threshold_uncertainty_score":0.34076875},"labels":[],"label_agreement":null},{"id":"W4235805954","doi":"10.3138/cjpe.34.1.v","title":"Editor’s Remarks","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.04883348373042004,"score_gpt":0.41588817826090774,"score_spread":0.36705469453048767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235805954","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012506437,0.00186079,0.000121661615,0.41278157,0.58049077,0.000032599673,0.00010785335,0.00007142438,0.004408263],"genre_scores_gemma":[0.0018242829,0.001385375,0.00042470958,0.6923686,0.2601733,0.00008391308,0.000050827515,0.00007130779,0.04361761],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9816788,0.0018356715,0.0019810635,0.0027647614,0.009426596,0.0023131045],"domain_scores_gemma":[0.9340514,0.015898373,0.0048550135,0.0031825472,0.03259416,0.009418585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016111165,0.0017369161,0.0028356346,0.0026800693,0.0054527936,0.010704841,0.005161787,0.04302594,0.031121336],"category_scores_gemma":[0.13044226,0.0012671725,0.0035442226,0.0021123649,0.003805969,0.0036684077,0.0028904537,0.039539922,0.023454491],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015454472,0.0000063389657,0.00004893053,0.000034406217,0.000009267808,0.00009780624,0.000020375017,0.000013268054,0.000026850767,0.00042083696,0.9974369,0.0018695288],"study_design_scores_gemma":[0.000046882993,0.000014157282,0.00045344947,0.00022098246,0.000029248671,0.00017168738,0.00010424575,0.00006929366,0.00011518162,0.0008923689,0.99784696,0.000035591027],"about_ca_topic_score_codex":0.015525863,"about_ca_topic_score_gemma":0.036448892,"teacher_disagreement_score":0.04302594,"about_ca_system_score_codex":0.008305184,"about_ca_system_score_gemma":0.014723211,"threshold_uncertainty_score":0.104111254},"labels":[],"label_agreement":null},{"id":"W4235919605","doi":"10.3138/cjpe.30.3.03","title":"Getting to the Roots of Evaluation Capacity Building in the Global South: Multiple Streams Model to Frame the Agenda Status of Evaluation in Turkey","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Frame (networking); Capacity building; Window of opportunity; Political science; Business; Public administration; Public economics; Economic growth; Economics; Computer science","score_opus":0.44681448485405895,"score_gpt":0.5082014368718829,"score_spread":0.06138695201782396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235919605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44507766,0.002054304,0.16539194,0.05303535,0.00018202415,0.0007472561,0.00024435908,0.00017143198,0.33309573],"genre_scores_gemma":[0.9891137,0.00028096235,0.008618399,0.00032309626,0.000012653578,0.00012051426,0.000018822948,0.000013432233,0.0014983802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.989707,0.007834267,0.00026896733,0.00048411812,0.0007624692,0.00094305776],"domain_scores_gemma":[0.98216003,0.011271821,0.0018735342,0.00080246304,0.0027144707,0.0011777543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013705152,0.0005717632,0.0006970367,0.0044994773,0.0025569312,0.008355443,0.0014390456,0.002255423,0.006061675],"category_scores_gemma":[0.018609801,0.0004556183,0.0007784709,0.0035982274,0.009911849,0.007859071,0.0071410607,0.0036638703,0.00037099337],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017847634,0.00013551424,0.020137979,0.00025807382,0.00005347095,0.0004979606,0.009577863,0.01848175,0.00026527367,0.9190927,0.0020286054,0.029292375],"study_design_scores_gemma":[0.00008122264,0.00015518394,0.012365206,0.00079562643,0.00013473231,0.00023574114,0.03740447,0.087779865,0.0009805954,0.8431431,0.016841,0.000083257175],"about_ca_topic_score_codex":0.01335714,"about_ca_topic_score_gemma":0.016074296,"teacher_disagreement_score":0.01645492,"about_ca_system_score_codex":0.01645492,"about_ca_system_score_gemma":0.013354401,"threshold_uncertainty_score":0.119389355},"labels":[],"label_agreement":null},{"id":"W4236082771","doi":"10.3138/cjpe.29.3.ene","title":"Editor's Remarks","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"History","score_opus":0.11893994916456034,"score_gpt":0.45101198694784933,"score_spread":0.332072037783289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236082771","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013955314,0.0020189527,0.00012769335,0.4283993,0.5646976,0.000034565386,0.000109900124,0.00007968654,0.004392751],"genre_scores_gemma":[0.0018359725,0.0013915158,0.00045642102,0.71909285,0.23374468,0.00008265757,0.000049864848,0.00007533785,0.043270648],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98107636,0.0018742748,0.0020758759,0.002896265,0.0095938975,0.0024832285],"domain_scores_gemma":[0.93275976,0.016266057,0.005097838,0.0033814772,0.033296257,0.009198622],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016912922,0.0017837179,0.003014154,0.002703375,0.0056837318,0.011239806,0.0056770877,0.047639757,0.029821122],"category_scores_gemma":[0.13015257,0.0013196655,0.0036775565,0.0021926414,0.0040689628,0.0039159283,0.0031498473,0.04298138,0.022543509],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016506194,0.0000066809907,0.000052517404,0.000040641018,0.0000101961305,0.00011342319,0.000024855133,0.000014695833,0.00003265292,0.00044240622,0.99718434,0.0020610366],"study_design_scores_gemma":[0.000045073957,0.000014509293,0.0004515741,0.00022633885,0.000032782435,0.00016776164,0.00011779644,0.00006889647,0.00012853694,0.0008677767,0.99784243,0.000036547633],"about_ca_topic_score_codex":0.016152699,"about_ca_topic_score_gemma":0.03736665,"teacher_disagreement_score":0.9701789,"about_ca_system_score_codex":0.008933689,"about_ca_system_score_gemma":0.014993839,"threshold_uncertainty_score":0.099761605},"labels":[],"label_agreement":null},{"id":"W4236552138","doi":"10.3138/cjpe.30.2.vi","title":"Un mot du rédacteur","year":2015,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.27866900293834235,"score_gpt":0.4887029780458749,"score_spread":0.21003397510753258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236552138","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029618423,0.012978499,0.0030277865,0.61081487,0.23903307,0.00022185533,0.0018729571,0.0007130593,0.12837605],"genre_scores_gemma":[0.04962102,0.0153509425,0.011520577,0.22393116,0.0723511,0.0005953028,0.0027951603,0.0011345576,0.6227002],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96457756,0.009528785,0.0028736906,0.0025257133,0.01749392,0.0030002142],"domain_scores_gemma":[0.82523435,0.030906616,0.006190623,0.010253324,0.111316666,0.016098356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026572898,0.0011402641,0.0012590806,0.0033935325,0.005657389,0.0106579745,0.0029913338,0.0076527293,0.10288742],"category_scores_gemma":[0.140623,0.00071184774,0.0014326068,0.0029383656,0.0032699285,0.008196383,0.00467927,0.010472026,0.028275661],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107708925,0.00004686717,0.0014469881,0.00044053738,0.000021222582,0.00026708093,0.0004974383,0.000083273495,0.0002676559,0.015739312,0.8787077,0.10237413],"study_design_scores_gemma":[0.000032381566,0.00003246239,0.0014967232,0.00056242343,0.000017212356,0.00044920752,0.00053999724,0.00010092432,0.0003000015,0.0024086747,0.99403256,0.000027491262],"about_ca_topic_score_codex":0.07464657,"about_ca_topic_score_gemma":0.0838434,"teacher_disagreement_score":0.9869648,"about_ca_system_score_codex":0.013035169,"about_ca_system_score_gemma":0.043434653,"threshold_uncertainty_score":0.34419274},"labels":[],"label_agreement":null},{"id":"W4237364742","doi":"10.3138/cjpe.154","title":"Implementation and Evaluation of an Evidence-Based Treatment of Disruptive Behaviour within a Children's Mental Health Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Multidisciplinary approach; Mental health; Context (archaeology); Psychology; Program evaluation; Medical education; Applied psychology; Process management; Multidisciplinary team; Knowledge management; Nursing; Medicine; Computer science; Business; Psychiatry; Sociology; Political science","score_opus":0.5674638354909648,"score_gpt":0.6170743887808582,"score_spread":0.04961055328989339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237364742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89572215,0.0016986643,0.011650913,0.0073575918,0.00036743132,0.05612152,0.0012986896,0.0003070873,0.025476072],"genre_scores_gemma":[0.88490814,0.0017738105,0.09451172,0.0009377861,0.00010023697,0.013834232,0.00079989847,0.000042253472,0.0030918696],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9495376,0.032559957,0.0032275775,0.0014984185,0.008878458,0.0042980122],"domain_scores_gemma":[0.96705705,0.007927748,0.0039372435,0.0023123391,0.012417623,0.0063479925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043922745,0.0008591518,0.00061331905,0.0013461758,0.0045675836,0.0031219532,0.003751261,0.0013199389,0.0023830521],"category_scores_gemma":[0.03522488,0.0005527346,0.0011417555,0.0012494373,0.0018199049,0.0012695035,0.005537853,0.0023206705,0.0002828268],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009492135,0.06535651,0.04331565,0.00708781,0.0011937439,0.0007708856,0.017922916,0.009332113,0.005644114,0.0046295063,0.009547998,0.82570666],"study_design_scores_gemma":[0.035906214,0.24352036,0.47328657,0.015609311,0.004643927,0.00092773273,0.045333922,0.019502135,0.05054964,0.0040051574,0.10615519,0.00055979943],"about_ca_topic_score_codex":0.22051907,"about_ca_topic_score_gemma":0.42324272,"teacher_disagreement_score":0.22051907,"about_ca_system_score_codex":0.037463862,"about_ca_system_score_gemma":0.11542552,"threshold_uncertainty_score":0.43847102},"labels":[],"label_agreement":null},{"id":"W4238121176","doi":"10.3138/cjpe.32.1.v","title":"Editor’s Remarks","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.0915111373192116,"score_gpt":0.4613580159277985,"score_spread":0.3698468786085869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238121176","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001509312,0.0019621847,0.00013589425,0.46557927,0.5277398,0.00003020951,0.000107576176,0.00007312644,0.0042209113],"genre_scores_gemma":[0.0020870736,0.0013375671,0.0004349356,0.72991693,0.2273829,0.00007495873,0.000048508813,0.00007712149,0.038640015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9816746,0.0018811964,0.002017271,0.0029520772,0.009115548,0.0023592834],"domain_scores_gemma":[0.9321819,0.01675861,0.005245208,0.003316193,0.03354077,0.008957316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015582447,0.001606866,0.0027165622,0.0024429637,0.0054565207,0.01087454,0.0049859826,0.04413806,0.029408986],"category_scores_gemma":[0.13807397,0.0011850359,0.0033004845,0.001947502,0.003925349,0.003848153,0.0029839154,0.041656226,0.021952676],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016618196,0.0000065318604,0.000060367533,0.00003873926,0.000010875285,0.00012364662,0.000027966596,0.0000150845735,0.000035183068,0.0005108102,0.9970644,0.0020898716],"study_design_scores_gemma":[0.0000427351,0.000013622495,0.00046892397,0.00024135884,0.000031634518,0.00019935769,0.0001272198,0.000074104035,0.00014341323,0.0010242144,0.99759465,0.00003876944],"about_ca_topic_score_codex":0.0145595195,"about_ca_topic_score_gemma":0.033341695,"teacher_disagreement_score":0.04413806,"about_ca_system_score_codex":0.008477684,"about_ca_system_score_gemma":0.01434743,"threshold_uncertainty_score":0.09838289},"labels":[],"label_agreement":null},{"id":"W4239798807","doi":"10.3138/cjpe.30.3.v","title":"Editor's Remarks","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.0625892659139386,"score_gpt":0.4241928755318835,"score_spread":0.3616036096179449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239798807","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014423173,0.0020664243,0.00012616834,0.43789703,0.5551167,0.000033890712,0.000108299275,0.000078108365,0.004429145],"genre_scores_gemma":[0.0018604777,0.0013974411,0.00045139558,0.72361225,0.22975965,0.00008119008,0.000048627924,0.00007531052,0.042713717],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98147696,0.0018696707,0.002060356,0.0028730482,0.009265667,0.0024542115],"domain_scores_gemma":[0.93369997,0.016040148,0.0051284707,0.003346767,0.032610785,0.009173798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016528588,0.0017718509,0.0029722503,0.0026433708,0.0056421277,0.011042142,0.0056037093,0.04753104,0.029675424],"category_scores_gemma":[0.12817441,0.0013122645,0.0036383783,0.0021581273,0.004038371,0.0038711852,0.003141402,0.042727914,0.022329751],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016992839,0.0000068145664,0.000055582947,0.000042306892,0.000010525215,0.00012043725,0.000026402136,0.000014725219,0.000033669898,0.00044790417,0.9970937,0.0021308716],"study_design_scores_gemma":[0.00004500034,0.000014643575,0.0004504727,0.00023037568,0.000033166452,0.00017761352,0.000120798795,0.00006693454,0.00012970624,0.0008526974,0.9978423,0.000036178928],"about_ca_topic_score_codex":0.015733846,"about_ca_topic_score_gemma":0.036442135,"teacher_disagreement_score":0.04753104,"about_ca_system_score_codex":0.008773982,"about_ca_system_score_gemma":0.014780269,"threshold_uncertainty_score":0.09927416},"labels":[],"label_agreement":null},{"id":"W4240514370","doi":"10.3138/cjpe.32.3.v","title":"Editor’s Remarks","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.06902451492908086,"score_gpt":0.441705047204782,"score_spread":0.37268053227570114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240514370","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015209067,0.0019981363,0.00013612416,0.49055365,0.50275826,0.000028308345,0.000108842425,0.000071877774,0.0041926675],"genre_scores_gemma":[0.00218194,0.0013448177,0.00044352267,0.7422878,0.21451895,0.00007395955,0.00004786718,0.00007930071,0.039021757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98104215,0.0019996876,0.0020774296,0.00315686,0.009295656,0.0024282213],"domain_scores_gemma":[0.92958826,0.017805522,0.005428935,0.0034774735,0.034335036,0.009364671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015869934,0.0015913395,0.0027091624,0.0024111369,0.005615679,0.011079953,0.0049500945,0.0437737,0.030016297],"category_scores_gemma":[0.14309369,0.0011477361,0.0031578613,0.001970571,0.004069885,0.004030337,0.0030659796,0.042734135,0.021670463],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001678035,0.0000066413563,0.00006197564,0.000039859126,0.000010860359,0.00012354595,0.000032167532,0.000015136032,0.00003568842,0.0005823792,0.9969522,0.0021227922],"study_design_scores_gemma":[0.00004064861,0.000013054475,0.0004570253,0.00024093741,0.000030648644,0.0001942815,0.00013664798,0.00007137423,0.00014229889,0.0010746965,0.99756,0.000038420207],"about_ca_topic_score_codex":0.015013337,"about_ca_topic_score_gemma":0.033357013,"teacher_disagreement_score":0.0437737,"about_ca_system_score_codex":0.0086391615,"about_ca_system_score_gemma":0.014670891,"threshold_uncertainty_score":0.100414515},"labels":[],"label_agreement":null},{"id":"W4240958491","doi":"10.3138/cjpe.31.3.416","title":"Peer Reviewers for Volume 31 and Manuscripts Submitted in 2016 / Examinateurs des manuscrits du volume 31 et des manuscrits soumis en 2016","year":2017,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Earthquake and Disaster Impact Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Art; Humanities; Physics","score_opus":0.18471599997660632,"score_gpt":0.3980687319906649,"score_spread":0.21335273201405858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240958491","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015429718,0.019474968,0.007132044,0.12649629,0.72878546,0.011637286,0.010305576,0.0028595934,0.077878974],"genre_scores_gemma":[0.04390242,0.02303084,0.018563867,0.016811065,0.19279094,0.008340299,0.009935621,0.0037452772,0.6828797],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96014005,0.005634513,0.0062340843,0.0020950234,0.023988811,0.0019075823],"domain_scores_gemma":[0.5309722,0.021716885,0.013896052,0.007497132,0.40104368,0.024873989],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03004062,0.0018235849,0.0029771975,0.014077949,0.0061113387,0.012693094,0.002427795,0.0037290477,0.1336197],"category_scores_gemma":[0.16815813,0.0009807583,0.0020571062,0.007603707,0.0017243704,0.004128534,0.0037351223,0.0029910367,0.06917675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003346409,0.000089505025,0.0016428508,0.0012972164,0.000055759523,0.00021112754,0.0003046497,0.000055244403,0.0006469924,0.00053864304,0.93277025,0.062053],"study_design_scores_gemma":[0.00016091391,0.00017054446,0.0061931,0.0010162075,0.00007493183,0.00019000514,0.0009636029,0.0002034125,0.0008563848,0.0011173679,0.9889938,0.00005976776],"about_ca_topic_score_codex":0.0036919792,"about_ca_topic_score_gemma":0.012338168,"teacher_disagreement_score":0.9967081,"about_ca_system_score_codex":0.0032918921,"about_ca_system_score_gemma":0.027101004,"threshold_uncertainty_score":0.4470024},"labels":[],"label_agreement":null},{"id":"W4241666961","doi":"10.3138/cjpe.29.3.enf","title":"Un mot du rédacteur","year":2015,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.27866900293834235,"score_gpt":0.4887029780458749,"score_spread":0.21003397510753258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241666961","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029618423,0.012978499,0.0030277865,0.61081487,0.23903307,0.00022185533,0.0018729571,0.0007130593,0.12837605],"genre_scores_gemma":[0.04962102,0.0153509425,0.011520577,0.22393116,0.0723511,0.0005953028,0.0027951603,0.0011345576,0.6227002],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96457756,0.009528785,0.0028736906,0.0025257133,0.01749392,0.0030002142],"domain_scores_gemma":[0.82523435,0.030906616,0.006190623,0.010253324,0.111316666,0.016098356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026572898,0.0011402641,0.0012590806,0.0033935325,0.005657389,0.0106579745,0.0029913338,0.0076527293,0.10288742],"category_scores_gemma":[0.140623,0.00071184774,0.0014326068,0.0029383656,0.0032699285,0.008196383,0.00467927,0.010472026,0.028275661],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107708925,0.00004686717,0.0014469881,0.00044053738,0.000021222582,0.00026708093,0.0004974383,0.000083273495,0.0002676559,0.015739312,0.8787077,0.10237413],"study_design_scores_gemma":[0.000032381566,0.00003246239,0.0014967232,0.00056242343,0.000017212356,0.00044920752,0.00053999724,0.00010092432,0.0003000015,0.0024086747,0.99403256,0.000027491262],"about_ca_topic_score_codex":0.07464657,"about_ca_topic_score_gemma":0.0838434,"teacher_disagreement_score":0.10288742,"about_ca_system_score_codex":0.013035169,"about_ca_system_score_gemma":0.043434653,"threshold_uncertainty_score":0.34419274},"labels":[],"label_agreement":null},{"id":"W4243058451","doi":"10.3138/cjpe.30.3.01","title":"Introduction: Decolonizing International Development Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"International Development and Aid","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.12221967907881538,"score_gpt":0.41121142906054287,"score_spread":0.2889917499817275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243058451","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003925838,0.025802147,0.07391692,0.6474432,0.0642898,0.0013280091,0.0010624962,0.001609476,0.1806221],"genre_scores_gemma":[0.09116348,0.021852735,0.10623371,0.42237443,0.038359825,0.0025640188,0.00095046114,0.0018776178,0.3146237],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97632796,0.010976725,0.0019171572,0.0030736052,0.0064988565,0.001205774],"domain_scores_gemma":[0.9315243,0.031056983,0.0027292608,0.0050019585,0.027238382,0.00244912],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034716386,0.0011170614,0.0008822011,0.004540996,0.006669314,0.011833321,0.0027514687,0.007945842,0.021664467],"category_scores_gemma":[0.055808928,0.0009403966,0.0010275445,0.003071047,0.0149304485,0.009850968,0.0064246743,0.013603351,0.00489863],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003275242,0.000060476694,0.00062171574,0.00084673247,0.000014852075,0.000058249232,0.0020066083,0.00028278152,0.0004458568,0.25961897,0.6289854,0.10702559],"study_design_scores_gemma":[0.000028953533,0.0000394621,0.0010942357,0.0013473263,0.000023018654,0.000108664055,0.000882795,0.00043128853,0.00052554195,0.03620407,0.95927,0.000044604487],"about_ca_topic_score_codex":0.03660315,"about_ca_topic_score_gemma":0.06887935,"teacher_disagreement_score":0.987158,"about_ca_system_score_codex":0.012841973,"about_ca_system_score_gemma":0.019894037,"threshold_uncertainty_score":0.18359995},"labels":[],"label_agreement":null},{"id":"W4244221056","doi":"10.3138/cjpe.202","title":"Inspiring Future Program Evaluators through Innovative Curriculum for Undergraduates","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Curriculum; Credentialing; Program evaluation; Medical education; Professionalization; Logic model; Psychology; Computer science; Engineering management; Pedagogy; Engineering; Medicine; Sociology; Political science","score_opus":0.4974043274798436,"score_gpt":0.5733680132125911,"score_spread":0.07596368573274753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244221056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7517629,0.0021800296,0.12403412,0.039760828,0.0018251259,0.0069288732,0.00022713114,0.0020569444,0.07122412],"genre_scores_gemma":[0.702462,0.0016916129,0.25559348,0.0049975836,0.00051756593,0.0031877358,0.00037998275,0.00017358726,0.030996379],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99033153,0.005128705,0.00044016173,0.0005206383,0.0024869554,0.0010920024],"domain_scores_gemma":[0.9688007,0.006285043,0.0028342812,0.0025370074,0.0069226753,0.012620259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025296053,0.0006404701,0.00043154552,0.001363358,0.0022004084,0.0047920053,0.0020017761,0.0010101749,0.006848943],"category_scores_gemma":[0.037500866,0.00042564777,0.00040414385,0.0006286501,0.0016119151,0.002348985,0.0074396175,0.0030416343,0.0014248976],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021092335,0.011259505,0.02775116,0.0007609181,0.00002692054,0.0001964807,0.01825947,0.0013932321,0.0060208673,0.011649316,0.0585375,0.8639338],"study_design_scores_gemma":[0.0006426382,0.010420941,0.15937883,0.0049984343,0.00016011593,0.001991035,0.057197113,0.013380407,0.02706899,0.062202282,0.6622773,0.00028198888],"about_ca_topic_score_codex":0.0008666207,"about_ca_topic_score_gemma":0.004100472,"teacher_disagreement_score":0.025296053,"about_ca_system_score_codex":0.004264003,"about_ca_system_score_gemma":0.01811005,"threshold_uncertainty_score":0.13377988},"labels":[],"label_agreement":null},{"id":"W4245257599","doi":"10.3138/cjpe.33.2.v","title":"Editor’s Remarks","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.06902451492908086,"score_gpt":0.441705047204782,"score_spread":0.37268053227570114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245257599","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015209067,0.0019981363,0.00013612416,0.49055365,0.50275826,0.000028308345,0.000108842425,0.000071877774,0.0041926675],"genre_scores_gemma":[0.00218194,0.0013448177,0.00044352267,0.7422878,0.21451895,0.00007395955,0.00004786718,0.00007930071,0.039021757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98104215,0.0019996876,0.0020774296,0.00315686,0.009295656,0.0024282213],"domain_scores_gemma":[0.92958826,0.017805522,0.005428935,0.0034774735,0.034335036,0.009364671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015869934,0.0015913395,0.0027091624,0.0024111369,0.005615679,0.011079953,0.0049500945,0.0437737,0.030016297],"category_scores_gemma":[0.14309369,0.0011477361,0.0031578613,0.001970571,0.004069885,0.004030337,0.0030659796,0.042734135,0.021670463],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001678035,0.0000066413563,0.00006197564,0.000039859126,0.000010860359,0.00012354595,0.000032167532,0.000015136032,0.00003568842,0.0005823792,0.9969522,0.0021227922],"study_design_scores_gemma":[0.00004064861,0.000013054475,0.0004570253,0.00024093741,0.000030648644,0.0001942815,0.00013664798,0.00007137423,0.00014229889,0.0010746965,0.99756,0.000038420207],"about_ca_topic_score_codex":0.015013337,"about_ca_topic_score_gemma":0.033357013,"teacher_disagreement_score":0.0437737,"about_ca_system_score_codex":0.0086391615,"about_ca_system_score_gemma":0.014670891,"threshold_uncertainty_score":0.100414515},"labels":[],"label_agreement":null},{"id":"W4245842532","doi":"10.3138/cjpe.30.3.08","title":"A Transcultural Global Systems Perspective: In Search of <i>Blue Marble</i> Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Framing (construction); Reflexivity; Indigenous; Sociology; Praxis; Perspective (graphical); Public relations; Engineering ethics; Political science; Social science; Epistemology; Computer science; Engineering","score_opus":0.3034525345500509,"score_gpt":0.5381338373521743,"score_spread":0.23468130280212346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245842532","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03295048,0.02654757,0.036677714,0.5757101,0.0041305195,0.00033993303,0.00006873453,0.00022227001,0.32335255],"genre_scores_gemma":[0.85791844,0.013237586,0.022700844,0.076549925,0.0012928293,0.000529784,0.000064788845,0.0003700332,0.027335847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9330107,0.053759985,0.001164911,0.0020815064,0.0064236424,0.00355926],"domain_scores_gemma":[0.9221698,0.046421338,0.002365655,0.004274462,0.0181699,0.0065988954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07960362,0.0007965986,0.0009749449,0.0046113315,0.011597591,0.030188499,0.0030476088,0.005101815,0.007617096],"category_scores_gemma":[0.0564114,0.00039395885,0.0005254105,0.0049727377,0.05768797,0.016750962,0.014039773,0.010644323,0.000680843],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050424398,0.00011070144,0.004580064,0.0010135534,0.00003952406,0.0003619223,0.16299577,0.0007027575,0.00034125173,0.69193333,0.06097136,0.07689934],"study_design_scores_gemma":[0.000024746301,0.000099153,0.0029722338,0.0030038028,0.000039938062,0.00026010087,0.29622838,0.0010384958,0.00070925313,0.2376444,0.45792985,0.00004964598],"about_ca_topic_score_codex":0.024720902,"about_ca_topic_score_gemma":0.03947703,"teacher_disagreement_score":0.07960362,"about_ca_system_score_codex":0.023797248,"about_ca_system_score_gemma":0.049744587,"threshold_uncertainty_score":0.42098922},"labels":[],"label_agreement":null},{"id":"W4247036941","doi":"10.3138/cjpe.32.1.vi","title":"Un mot du rédacteur","year":2017,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Political science","score_opus":0.22561917199059764,"score_gpt":0.5001354038874755,"score_spread":0.2745162318968778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247036941","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002980812,0.013086781,0.003015975,0.61464316,0.24115245,0.00022122316,0.0018940999,0.0007299293,0.12227556],"genre_scores_gemma":[0.05138804,0.015803058,0.012065467,0.22760442,0.07483367,0.00061908003,0.0029504956,0.0011978162,0.6135379],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96374696,0.00986124,0.003012315,0.0025824439,0.017749052,0.0030478842],"domain_scores_gemma":[0.8174276,0.031759523,0.006366672,0.010857053,0.11681913,0.016770015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02727915,0.0011518236,0.0012786272,0.0034681996,0.0056081535,0.010704291,0.0030178702,0.0076082167,0.10022205],"category_scores_gemma":[0.14464144,0.0007171934,0.0014316632,0.0029796257,0.003293286,0.008282369,0.0047812564,0.010515191,0.027612535],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011012445,0.000048375965,0.0014913378,0.00044995217,0.000021985414,0.00026583803,0.00051062054,0.00008280103,0.00026989926,0.0152448155,0.8765891,0.104915194],"study_design_scores_gemma":[0.000033256947,0.000033093,0.0015607559,0.0005901741,0.000018138275,0.00046003237,0.00056402496,0.00010248542,0.0003078111,0.002444873,0.9938573,0.00002801293],"about_ca_topic_score_codex":0.074040994,"about_ca_topic_score_gemma":0.084064715,"teacher_disagreement_score":0.10022205,"about_ca_system_score_codex":0.013260542,"about_ca_system_score_gemma":0.044950433,"threshold_uncertainty_score":0.3352762},"labels":[],"label_agreement":null},{"id":"W4248375878","doi":"10.3138/cjpe.35.3.intro-fr","title":"Un mot de la rédactrice","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.08961796751011986,"score_gpt":0.36937774345787855,"score_spread":0.2797597759477587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248375878","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03160074,0.007357752,0.09728715,0.17676017,0.039813835,0.0015392974,0.005562701,0.00846843,0.6316099],"genre_scores_gemma":[0.21199375,0.004471453,0.101346165,0.028019894,0.009192473,0.0022347895,0.005152116,0.0067215236,0.6308678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9605861,0.016138416,0.0014741026,0.0023842426,0.017664906,0.0017522421],"domain_scores_gemma":[0.94889045,0.011391266,0.002060145,0.0036924693,0.031153034,0.0028126664],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015945416,0.0015019021,0.0011760808,0.0030122616,0.0051929513,0.011623578,0.0013999809,0.004581132,0.068568915],"category_scores_gemma":[0.05858875,0.0010651215,0.0013737371,0.0019863208,0.0034989284,0.009337333,0.0050305473,0.010375821,0.01808305],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087512756,0.00027364356,0.0027617419,0.001152933,0.00008736253,0.0005680596,0.004685688,0.0015208047,0.0069827866,0.18006071,0.4408704,0.36016077],"study_design_scores_gemma":[0.000109099725,0.00013485076,0.0020213549,0.00040607547,0.000023551576,0.00043468428,0.0013530203,0.0012048653,0.00455809,0.007846286,0.98179895,0.00010922424],"about_ca_topic_score_codex":0.029397601,"about_ca_topic_score_gemma":0.02498636,"teacher_disagreement_score":0.93143106,"about_ca_system_score_codex":0.008557922,"about_ca_system_score_gemma":0.011990843,"threshold_uncertainty_score":0.22938585},"labels":[],"label_agreement":null},{"id":"W4248910069","doi":"10.3138/cjpe.223","title":"Meeting at the Crossroads: Interactivity, Technology, and Evaluation Utilization","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Interactivity; Relevance (law); Creativity; Scholarship; Negotiation; Knowledge management; Computer science; Citizen journalism; Sociology; Psychology; Multimedia; Political science; Social psychology; World Wide Web; Social science","score_opus":0.6056598746697802,"score_gpt":0.5861427794867573,"score_spread":0.019517095183022914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248910069","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1595341,0.18392926,0.13289766,0.15524651,0.0021923047,0.0007762665,0.00020523409,0.00055948144,0.36465922],"genre_scores_gemma":[0.93904173,0.027122516,0.018831942,0.0058700093,0.0011378446,0.00047061773,0.00007755538,0.00019091701,0.007256825],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.808502,0.16211714,0.0060052397,0.0034037302,0.017250285,0.0027216575],"domain_scores_gemma":[0.7666105,0.19420685,0.011380457,0.0074842996,0.01619479,0.004123156],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09693822,0.00075353665,0.001177777,0.008504337,0.0068959016,0.024007443,0.0019687833,0.0032027725,0.009947439],"category_scores_gemma":[0.11724655,0.00059038395,0.0012173263,0.0058774846,0.018954953,0.02124636,0.01581479,0.0036907936,0.0012314152],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003159866,0.0002762011,0.025020724,0.0063862777,0.00045596767,0.0007212414,0.1284071,0.0010830141,0.0009901344,0.23805316,0.01606547,0.5822247],"study_design_scores_gemma":[0.000102487196,0.00054909865,0.038241398,0.025862979,0.00050502963,0.002129945,0.17167749,0.002453585,0.0031272932,0.23340401,0.5215883,0.00035844732],"about_ca_topic_score_codex":0.0038704465,"about_ca_topic_score_gemma":0.0047256546,"teacher_disagreement_score":0.90306175,"about_ca_system_score_codex":0.007844324,"about_ca_system_score_gemma":0.010328922,"threshold_uncertainty_score":0.51266444},"labels":[],"label_agreement":null},{"id":"W4248987738","doi":"10.3138/cjpe.192","title":"Évaluation de la qualité d'un partenariat dans le cadre de la mise en place d'une intervention intersectorielle de type <i>école, famille et communauté</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal","funders":"","keywords":"General partnership; Formative assessment; Valuation (finance); Intervention (counseling); Quality (philosophy); Action (physics); Process (computing); Sociology; Welfare economics; Political science; Psychology; Public relations; Business; Pedagogy; Computer science; Epistemology; Economics; Philosophy; Law; Accounting","score_opus":0.0908543315830593,"score_gpt":0.4024953206089743,"score_spread":0.31164098902591497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248987738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9491846,0.0010265122,0.01812638,0.0024520254,0.00025467883,0.003361634,0.00023290543,0.00020505374,0.025156109],"genre_scores_gemma":[0.98457366,0.00021452317,0.01140584,0.00010055639,0.00001691467,0.0013551611,0.000072109084,0.000026873266,0.002234415],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8523106,0.10546946,0.0071572973,0.004406374,0.026788684,0.0038675657],"domain_scores_gemma":[0.7841927,0.13016945,0.021283474,0.009451882,0.046336714,0.008565775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14989044,0.0007521943,0.0012667008,0.002887584,0.0034106534,0.008070087,0.0018346214,0.0017975835,0.006074291],"category_scores_gemma":[0.21232834,0.0006588908,0.0013944223,0.002052246,0.0041616946,0.0042792144,0.0060780547,0.0019801096,0.00063056423],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007174049,0.0055748257,0.17350425,0.0040704696,0.0009410632,0.0003160987,0.14409234,0.005450091,0.008596483,0.014316013,0.0027590941,0.63320524],"study_design_scores_gemma":[0.0014161489,0.050818257,0.6716784,0.0052776015,0.002275675,0.00051503215,0.15587538,0.015676452,0.043646004,0.008535641,0.043797716,0.00048772243],"about_ca_topic_score_codex":0.00790231,"about_ca_topic_score_gemma":0.010359427,"teacher_disagreement_score":0.14989044,"about_ca_system_score_codex":0.013981148,"about_ca_system_score_gemma":0.017258985,"threshold_uncertainty_score":0.7927059},"labels":[],"label_agreement":null},{"id":"W4249543881","doi":"10.3138/cjpe.69771","title":"Reflective Practice: Moving Intention into Action","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reflective practice; Leverage (statistics); Pillar; Action (physics); Reflection (computer programming); Psychology; Embodied cognition; Engineering ethics; Knowledge management; Pedagogy; Computer science; Artificial intelligence; Engineering","score_opus":0.5098205725321647,"score_gpt":0.6235932080024176,"score_spread":0.11377263547025285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249543881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028313804,0.0034766626,0.65360147,0.05951067,0.0021057792,0.0021097332,0.0001174562,0.0015191005,0.24924539],"genre_scores_gemma":[0.5129797,0.003763126,0.45671237,0.0075897137,0.00039395687,0.0028197377,0.00014763059,0.0004602777,0.015133477],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.92755634,0.057084266,0.002116016,0.0041842656,0.0076766685,0.0013823743],"domain_scores_gemma":[0.85859174,0.10687182,0.0058919545,0.01307802,0.0117282,0.0038381822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054961734,0.0009720641,0.0007081257,0.0031004206,0.003116722,0.0122743035,0.002898102,0.003951586,0.00977844],"category_scores_gemma":[0.12147464,0.000919863,0.0012694873,0.0016519955,0.018919373,0.011043763,0.0081890905,0.006088558,0.0029464175],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018709201,0.00064470083,0.004220283,0.0030607814,0.00017414462,0.00037801752,0.0851341,0.0018272256,0.0016338106,0.43498582,0.028426562,0.43932745],"study_design_scores_gemma":[0.0003919639,0.00064762984,0.0052020485,0.01095725,0.00026203247,0.0008067043,0.03716541,0.009487821,0.005186212,0.63246506,0.29720438,0.0002234892],"about_ca_topic_score_codex":0.0029188653,"about_ca_topic_score_gemma":0.002584362,"teacher_disagreement_score":0.054961734,"about_ca_system_score_codex":0.0055876616,"about_ca_system_score_gemma":0.016577514,"threshold_uncertainty_score":0.29066885},"labels":[],"label_agreement":null},{"id":"W4250786345","doi":"10.3138/cjpe.30.3.06","title":"A Cross-cultural Evaluation Conversation in India: Benefits, Challenges, and Lessons Learned","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Conversation; Cross-cultural; Work (physics); Bridging (networking); Sociology; Principal (computer security); Public relations; Political science; Medical education; Psychology; Medicine; Engineering; Computer science","score_opus":0.5494404661293435,"score_gpt":0.5595244125498549,"score_spread":0.010083946420511358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250786345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82091236,0.0027050334,0.0067553003,0.11091245,0.0011074191,0.00065882807,0.00007745359,0.000103050734,0.056768153],"genre_scores_gemma":[0.9858212,0.0007802983,0.0018252506,0.0072335266,0.000121174584,0.00024575499,0.00002088511,0.000059886428,0.0038921544],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8221505,0.14848506,0.0029595536,0.002982477,0.009256777,0.014165692],"domain_scores_gemma":[0.8331199,0.12592398,0.004062996,0.0036820224,0.021003122,0.0122079495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11073343,0.0010428792,0.001148029,0.0024252695,0.057654507,0.0222533,0.003915999,0.0071264673,0.0022297874],"category_scores_gemma":[0.09065994,0.0011643952,0.0009061568,0.003547899,0.024556948,0.009066041,0.02219671,0.018725565,0.0003392151],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054478136,0.000105323685,0.0015443828,0.00010658197,0.0000123937625,0.001551718,0.9799541,0.00011235677,0.00036092135,0.006625353,0.0024976304,0.007074794],"study_design_scores_gemma":[0.000006370946,0.00003475767,0.00082551397,0.0001608807,0.000009398108,0.00019223413,0.98445016,0.000106821084,0.00028980573,0.00050568016,0.013382826,0.00003553757],"about_ca_topic_score_codex":0.124419875,"about_ca_topic_score_gemma":0.1903097,"teacher_disagreement_score":0.124419875,"about_ca_system_score_codex":0.049728498,"about_ca_system_score_gemma":0.046653282,"threshold_uncertainty_score":0.58562136},"labels":[],"label_agreement":null},{"id":"W4251265234","doi":"10.3138/cjpe.224","title":"Increasing the Utility of AAMC Canadian Graduation Questionnaire Data for Program Evaluation: Subscale Development","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Global Health Workforce Issues","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Graduation (instrument); Medical education; Reliability (semiconductor); Psychology; Applied psychology; Family medicine; Medicine","score_opus":0.5296562765461765,"score_gpt":0.5580537717572522,"score_spread":0.028397495211075707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251265234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7872098,0.0013620501,0.044637263,0.0066786683,0.0012615575,0.026152322,0.03230869,0.0018084785,0.09858109],"genre_scores_gemma":[0.823334,0.00081838365,0.11919618,0.0015406455,0.00015231576,0.027598506,0.01825924,0.0004218807,0.008678913],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9599569,0.013377909,0.0043616774,0.0013799266,0.018426295,0.0024972223],"domain_scores_gemma":[0.82490224,0.022635398,0.008012729,0.0067067873,0.1328006,0.004942286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06093559,0.00079351885,0.00084259256,0.009575698,0.002165957,0.0023844242,0.0022578505,0.0005241847,0.005427178],"category_scores_gemma":[0.12707198,0.00044038772,0.0013750042,0.0075379536,0.0010328504,0.0012105545,0.0035197323,0.0014483788,0.0011054308],"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":[0.0005426136,0.0009946896,0.54470235,0.0010823543,0.00026889823,0.00007304808,0.0056987484,0.0011780361,0.0019754826,0.0029706527,0.062847346,0.3776658],"study_design_scores_gemma":[0.00017251304,0.00054282346,0.9420278,0.00065218005,0.00012690664,0.000038724946,0.003612599,0.0030134623,0.0029678266,0.0006113226,0.04614224,0.00009155732],"about_ca_topic_score_codex":0.35084298,"about_ca_topic_score_gemma":0.53564626,"teacher_disagreement_score":0.35084298,"about_ca_system_score_codex":0.014113474,"about_ca_system_score_gemma":0.038922567,"threshold_uncertainty_score":0.6976017},"labels":[],"label_agreement":null},{"id":"W4251373139","doi":"10.3138/cjpe.34.2.viii","title":"Un mot de la rédactrice","year":2019,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Philosophy; Psychology","score_opus":0.06508585322297354,"score_gpt":0.353867338390934,"score_spread":0.28878148516796043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251373139","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016559094,0.014313094,0.0005055723,0.49251235,0.48618728,0.000025566897,0.0001816688,0.00014133305,0.005967654],"genre_scores_gemma":[0.0061529325,0.008556063,0.001968207,0.473284,0.39596218,0.00009828926,0.00018268528,0.00027391012,0.11352168],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99158454,0.002265556,0.0009920512,0.0013269478,0.0029431765,0.0008876319],"domain_scores_gemma":[0.9600588,0.01129217,0.0016665221,0.0013692132,0.023708498,0.0019048897],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009158408,0.0018141433,0.0019300267,0.0022716755,0.005040904,0.0075443774,0.0030073726,0.016922748,0.024242647],"category_scores_gemma":[0.04276981,0.0006746719,0.0021158473,0.0017613382,0.0028354563,0.0051820823,0.0023675459,0.013655988,0.013740802],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026454067,0.000005723331,0.000057694873,0.000094367584,0.000009258078,0.000101495105,0.000053044063,0.000020900641,0.00006352964,0.0012441104,0.99241054,0.005912856],"study_design_scores_gemma":[0.00001405697,0.000010072388,0.00034173072,0.00013549815,0.0000115073835,0.0001120486,0.00008304674,0.000070337024,0.00013654395,0.0005872576,0.998478,0.000019924108],"about_ca_topic_score_codex":0.046532217,"about_ca_topic_score_gemma":0.066817984,"teacher_disagreement_score":0.97575736,"about_ca_system_score_codex":0.005104727,"about_ca_system_score_gemma":0.00701341,"threshold_uncertainty_score":0.09252274},"labels":[],"label_agreement":null},{"id":"W4252543172","doi":"10.3138/cjpe.35.1.vi","title":"Un mot de la rédactrice","year":2020,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.12225635952327514,"score_gpt":0.36373054832102936,"score_spread":0.24147418879775423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252543172","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015188869,0.0149419885,0.07405989,0.18890865,0.061281946,0.00086029543,0.0066743856,0.010363022,0.62772095],"genre_scores_gemma":[0.095563136,0.008993058,0.05243319,0.024393378,0.01621781,0.0011911514,0.005766303,0.0059246086,0.78951746],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9705631,0.011574441,0.0012307004,0.0024523977,0.012924208,0.0012552337],"domain_scores_gemma":[0.9602754,0.010601266,0.001541567,0.003749836,0.022180753,0.001651073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0153217055,0.0020887095,0.0015852654,0.00370128,0.0064796717,0.016570045,0.0020287065,0.0050833905,0.096288994],"category_scores_gemma":[0.04945642,0.0010513654,0.0019186228,0.0030981852,0.0037427687,0.009397951,0.004520322,0.011935305,0.03665668],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050515006,0.00019365358,0.0016141009,0.00083202013,0.00006305055,0.0006102269,0.0028444054,0.00092095614,0.0034810458,0.13948105,0.55003643,0.29941788],"study_design_scores_gemma":[0.00005361663,0.000037739268,0.0010089305,0.00023073018,0.00001390022,0.0003609384,0.0006441787,0.00048760732,0.0012495897,0.004523731,0.99134153,0.000047550653],"about_ca_topic_score_codex":0.09233086,"about_ca_topic_score_gemma":0.056521468,"teacher_disagreement_score":0.096288994,"about_ca_system_score_codex":0.011584262,"about_ca_system_score_gemma":0.01218094,"threshold_uncertainty_score":0.32211876},"labels":[],"label_agreement":null},{"id":"W4253176475","doi":"10.3138/cjpe.31.3.v","title":"Editor’s Remarks","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.0915111373192116,"score_gpt":0.4613580159277985,"score_spread":0.3698468786085869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253176475","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001509312,0.0019621847,0.00013589425,0.46557927,0.5277398,0.00003020951,0.000107576176,0.00007312644,0.0042209113],"genre_scores_gemma":[0.0020870736,0.0013375671,0.0004349356,0.72991693,0.2273829,0.00007495873,0.000048508813,0.00007712149,0.038640015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9816746,0.0018811964,0.002017271,0.0029520772,0.009115548,0.0023592834],"domain_scores_gemma":[0.9321819,0.01675861,0.005245208,0.003316193,0.03354077,0.008957316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015582447,0.001606866,0.0027165622,0.0024429637,0.0054565207,0.01087454,0.0049859826,0.04413806,0.029408986],"category_scores_gemma":[0.13807397,0.0011850359,0.0033004845,0.001947502,0.003925349,0.003848153,0.0029839154,0.041656226,0.021952676],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016618196,0.0000065318604,0.000060367533,0.00003873926,0.000010875285,0.00012364662,0.000027966596,0.0000150845735,0.000035183068,0.0005108102,0.9970644,0.0020898716],"study_design_scores_gemma":[0.0000427351,0.000013622495,0.00046892397,0.00024135884,0.000031634518,0.00019935769,0.0001272198,0.000074104035,0.00014341323,0.0010242144,0.99759465,0.00003876944],"about_ca_topic_score_codex":0.0145595195,"about_ca_topic_score_gemma":0.033341695,"teacher_disagreement_score":0.04413806,"about_ca_system_score_codex":0.008477684,"about_ca_system_score_gemma":0.01434743,"threshold_uncertainty_score":0.09838289},"labels":[],"label_agreement":null},{"id":"W4253688856","doi":"10.3138/cjpe.33.1.v","title":"Editor’s Remarks","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.06902451492908086,"score_gpt":0.441705047204782,"score_spread":0.37268053227570114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253688856","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015209067,0.0019981363,0.00013612416,0.49055365,0.50275826,0.000028308345,0.000108842425,0.000071877774,0.0041926675],"genre_scores_gemma":[0.00218194,0.0013448177,0.00044352267,0.7422878,0.21451895,0.00007395955,0.00004786718,0.00007930071,0.039021757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98104215,0.0019996876,0.0020774296,0.00315686,0.009295656,0.0024282213],"domain_scores_gemma":[0.92958826,0.017805522,0.005428935,0.0034774735,0.034335036,0.009364671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015869934,0.0015913395,0.0027091624,0.0024111369,0.005615679,0.011079953,0.0049500945,0.0437737,0.030016297],"category_scores_gemma":[0.14309369,0.0011477361,0.0031578613,0.001970571,0.004069885,0.004030337,0.0030659796,0.042734135,0.021670463],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001678035,0.0000066413563,0.00006197564,0.000039859126,0.000010860359,0.00012354595,0.000032167532,0.000015136032,0.00003568842,0.0005823792,0.9969522,0.0021227922],"study_design_scores_gemma":[0.00004064861,0.000013054475,0.0004570253,0.00024093741,0.000030648644,0.0001942815,0.00013664798,0.00007137423,0.00014229889,0.0010746965,0.99756,0.000038420207],"about_ca_topic_score_codex":0.015013337,"about_ca_topic_score_gemma":0.033357013,"teacher_disagreement_score":0.0437737,"about_ca_system_score_codex":0.0086391615,"about_ca_system_score_gemma":0.014670891,"threshold_uncertainty_score":0.100414515},"labels":[],"label_agreement":null},{"id":"W4254498193","doi":"10.3138/cjpe.31.2.vi","title":"Un mot du rédacteur","year":2016,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.16177410226179187,"score_gpt":0.46182805204444066,"score_spread":0.30005394978264877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254498193","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031427583,0.013096157,0.003135457,0.6103941,0.2389791,0.00022416371,0.0018717018,0.00073612237,0.12842047],"genre_scores_gemma":[0.05123492,0.01528289,0.011790785,0.22216053,0.07241208,0.00060964964,0.0027884762,0.0011652673,0.6225553],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96455073,0.009730599,0.002919192,0.002546257,0.01727362,0.0029796294],"domain_scores_gemma":[0.82666,0.030849213,0.0063006356,0.010468228,0.10963165,0.016090387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026423318,0.0011572366,0.0012696118,0.0033768837,0.005622086,0.010538296,0.002977826,0.007609992,0.10186391],"category_scores_gemma":[0.14064166,0.00071464956,0.0014359957,0.0029119763,0.003243664,0.00834743,0.0047244616,0.01056156,0.028122181],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011590178,0.00005037673,0.0015455142,0.00046894673,0.000022660624,0.0002913298,0.0005416481,0.00008721485,0.00029139954,0.01598066,0.8720805,0.1085239],"study_design_scores_gemma":[0.000033832075,0.00003477405,0.0015415727,0.0005760412,0.00001815057,0.00048616753,0.0005736772,0.00010487633,0.0003238441,0.0024484026,0.9938304,0.000028380073],"about_ca_topic_score_codex":0.06767864,"about_ca_topic_score_gemma":0.076027334,"teacher_disagreement_score":0.98750013,"about_ca_system_score_codex":0.012499865,"about_ca_system_score_gemma":0.041617054,"threshold_uncertainty_score":0.34076875},"labels":[],"label_agreement":null},{"id":"W4254530337","doi":"10.3138/cjpe.32.2.v","title":"Editor’s Remarks","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.0915111373192116,"score_gpt":0.4613580159277985,"score_spread":0.3698468786085869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254530337","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001509312,0.0019621847,0.00013589425,0.46557927,0.5277398,0.00003020951,0.000107576176,0.00007312644,0.0042209113],"genre_scores_gemma":[0.0020870736,0.0013375671,0.0004349356,0.72991693,0.2273829,0.00007495873,0.000048508813,0.00007712149,0.038640015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9816746,0.0018811964,0.002017271,0.0029520772,0.009115548,0.0023592834],"domain_scores_gemma":[0.9321819,0.01675861,0.005245208,0.003316193,0.03354077,0.008957316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015582447,0.001606866,0.0027165622,0.0024429637,0.0054565207,0.01087454,0.0049859826,0.04413806,0.029408986],"category_scores_gemma":[0.13807397,0.0011850359,0.0033004845,0.001947502,0.003925349,0.003848153,0.0029839154,0.041656226,0.021952676],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016618196,0.0000065318604,0.000060367533,0.00003873926,0.000010875285,0.00012364662,0.000027966596,0.0000150845735,0.000035183068,0.0005108102,0.9970644,0.0020898716],"study_design_scores_gemma":[0.0000427351,0.000013622495,0.00046892397,0.00024135884,0.000031634518,0.00019935769,0.0001272198,0.000074104035,0.00014341323,0.0010242144,0.99759465,0.00003876944],"about_ca_topic_score_codex":0.0145595195,"about_ca_topic_score_gemma":0.033341695,"teacher_disagreement_score":0.04413806,"about_ca_system_score_codex":0.008477684,"about_ca_system_score_gemma":0.01434743,"threshold_uncertainty_score":0.09838289},"labels":[],"label_agreement":null},{"id":"W4255004666","doi":"10.3138/cjpe.30.3.05","title":"Decolonizing and Indigenizing Evaluation Practice in Africa: Toward African Relational Evaluation Approaches","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenization; Decolonization; Sociology; African culture; Metaphor; Epistemology; African philosophy; Political science; Gender studies; Anthropology; Linguistics; Philosophy","score_opus":0.6556148384806202,"score_gpt":0.5116189627666728,"score_spread":0.14399587571394734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255004666","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14498842,0.012413984,0.31282339,0.12870573,0.0005786783,0.00065535767,0.00004573797,0.00015132569,0.39963743],"genre_scores_gemma":[0.9542293,0.0024303573,0.036226917,0.0024492883,0.00006750049,0.00029409764,0.000010356592,0.00004629045,0.0042459997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9534067,0.039169002,0.0011096464,0.0014065214,0.0032365255,0.0016715461],"domain_scores_gemma":[0.96173704,0.026747296,0.0030330871,0.0024203474,0.0049030473,0.0011592051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.063421294,0.00069144496,0.00063578604,0.005040349,0.008657922,0.017203609,0.0019135097,0.002848372,0.0031394898],"category_scores_gemma":[0.039438255,0.0005077822,0.00046138393,0.0033179575,0.048504166,0.017228635,0.015462501,0.0062043993,0.00028870825],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002049405,0.000031069732,0.00079346116,0.00016358202,0.000007773087,0.000086374064,0.04340147,0.00032908618,0.00017367507,0.93450207,0.0008001955,0.019690793],"study_design_scores_gemma":[0.000048211292,0.00008828009,0.001706736,0.0030178244,0.000048672802,0.0003855015,0.137583,0.0045519318,0.0017334064,0.7534108,0.09737368,0.00005194541],"about_ca_topic_score_codex":0.00528395,"about_ca_topic_score_gemma":0.0063741803,"teacher_disagreement_score":0.063421294,"about_ca_system_score_codex":0.014795622,"about_ca_system_score_gemma":0.015916165,"threshold_uncertainty_score":0.33540785},"labels":[],"label_agreement":null},{"id":"W4255130301","doi":"10.3138/cjpe.33.1.vi","title":"Un mot de la rédactrice","year":2018,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.09207310104476685,"score_gpt":0.37894328356865975,"score_spread":0.2868701825238929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255130301","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018920569,0.013418087,0.092315145,0.1643397,0.054786846,0.0009790008,0.0078282235,0.012263412,0.635149],"genre_scores_gemma":[0.11290233,0.008586117,0.06625143,0.021439932,0.014684757,0.0013769607,0.0068845213,0.0066294293,0.76124454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9724851,0.011084457,0.0011842196,0.0023099182,0.01180219,0.0011340831],"domain_scores_gemma":[0.96362966,0.009992888,0.0014676083,0.0034927453,0.019959154,0.001457922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014623268,0.0020595638,0.0015427346,0.0035720211,0.005931755,0.01560749,0.0019182622,0.004643483,0.092633225],"category_scores_gemma":[0.04801931,0.0010265181,0.0018646822,0.0029297932,0.0034353046,0.008988707,0.004354122,0.011279062,0.033787325],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005898941,0.00021705666,0.0018415082,0.0009398877,0.000071958304,0.00065757125,0.003308285,0.0010931733,0.0041785236,0.14199084,0.51289153,0.3322198],"study_design_scores_gemma":[0.00006406114,0.000044968398,0.0011899587,0.00025757717,0.000016253953,0.00038918894,0.00074875605,0.0006200569,0.0015807281,0.0048174765,0.99021727,0.000053686632],"about_ca_topic_score_codex":0.08248943,"about_ca_topic_score_gemma":0.050592273,"teacher_disagreement_score":0.092633225,"about_ca_system_score_codex":0.01057423,"about_ca_system_score_gemma":0.010768235,"threshold_uncertainty_score":0.30988896},"labels":[],"label_agreement":null},{"id":"W4255851291","doi":"10.3138/cjpe.209","title":"Challenges in Evaluating a Prototype Project in a Large Health Authority: Lessons Learned","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Fraser Health; Centre for Advancing Health Outcomes","funders":"","keywords":"Pace; Health care; Bureaucracy; Bridge (graph theory); Process (computing); Process management; Business; Program evaluation; Test (biology); Public relations; Public sector; Nursing; Knowledge management; Medicine; Computer science; Political science; Public administration","score_opus":0.8786268415298759,"score_gpt":0.6676318817317606,"score_spread":0.21099495979811533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255851291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8175352,0.0015692109,0.07589044,0.02933972,0.00078909314,0.04609401,0.0005537929,0.00075653597,0.027472002],"genre_scores_gemma":[0.8285161,0.0006091969,0.14905633,0.0018405366,0.000113135255,0.016516855,0.0003372776,0.00020866367,0.0028019515],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.62522286,0.32045275,0.012627042,0.004041854,0.02732638,0.010329126],"domain_scores_gemma":[0.55107707,0.28068474,0.010555962,0.028001856,0.10875308,0.020927235],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.34144175,0.0013776887,0.0015722585,0.0015572425,0.007664184,0.011489511,0.00998159,0.0042579314,0.0048885085],"category_scores_gemma":[0.37289605,0.0015077752,0.0012852884,0.0016257694,0.005457147,0.008984932,0.007464928,0.0067562503,0.0009883911],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00563074,0.052957352,0.058272112,0.008224814,0.0005451003,0.005344516,0.17943949,0.026687177,0.0120648155,0.022489639,0.02612405,0.6022203],"study_design_scores_gemma":[0.009465878,0.13207628,0.077771336,0.015643131,0.0007363808,0.003296119,0.46426755,0.049483504,0.031352226,0.02088416,0.19373907,0.0012843811],"about_ca_topic_score_codex":0.020185366,"about_ca_topic_score_gemma":0.032229457,"teacher_disagreement_score":0.34144175,"about_ca_system_score_codex":0.024011713,"about_ca_system_score_gemma":0.053463686,"threshold_uncertainty_score":0.8121196},"labels":[],"label_agreement":null},{"id":"W4255897202","doi":"10.3138/cjpe.31.2.v","title":"Editor’s Remarks","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.06275224776942365,"score_gpt":0.42328038584787103,"score_spread":0.3605281380784474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255897202","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015917534,0.0020174535,0.00014426983,0.45651585,0.53633356,0.00003251408,0.00011433686,0.00007918614,0.004603695],"genre_scores_gemma":[0.0021990447,0.0013609015,0.00047022264,0.7207895,0.23138367,0.00007923309,0.000051126728,0.00008068555,0.043585684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.982087,0.0018346739,0.001975072,0.0029156816,0.008889948,0.002297702],"domain_scores_gemma":[0.93484426,0.016021868,0.0051279487,0.0033279501,0.03196265,0.008715434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0153150745,0.0016189042,0.0026886323,0.0024454123,0.0053413003,0.010625187,0.0049562613,0.043056462,0.030230198],"category_scores_gemma":[0.13238455,0.0011909459,0.0033027001,0.0019476616,0.0037881252,0.0037634538,0.0029231205,0.039609008,0.022507848],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017587625,0.000006735332,0.00006003394,0.000040343682,0.0000109295315,0.00012516673,0.00002765674,0.00001558314,0.00003821711,0.00050762185,0.9969907,0.0021594234],"study_design_scores_gemma":[0.000042440337,0.00001394777,0.00047437163,0.00022625168,0.00003109292,0.00019263872,0.00011704438,0.00007331872,0.00014717731,0.0009664919,0.99767786,0.000037344613],"about_ca_topic_score_codex":0.014171693,"about_ca_topic_score_gemma":0.032135215,"teacher_disagreement_score":0.043056462,"about_ca_system_score_codex":0.008160964,"about_ca_system_score_gemma":0.013462189,"threshold_uncertainty_score":0.10113007},"labels":[],"label_agreement":null},{"id":"W4256354490","doi":"10.3138/cjpe.35.1.v","title":"Editor’s Remarks","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.09183389973985367,"score_gpt":0.4261636144090774,"score_spread":0.33432971466922373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256354490","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016844849,0.0019669016,0.00017187373,0.308899,0.67154783,0.00007219291,0.00020956818,0.00013708211,0.016827099],"genre_scores_gemma":[0.002367013,0.0020621752,0.0007089231,0.68285733,0.1970351,0.00025077406,0.00012592768,0.00013911142,0.1144536],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9821878,0.0017716298,0.002066344,0.0023780323,0.009431138,0.0021650146],"domain_scores_gemma":[0.92543477,0.012583552,0.0035992137,0.0038751988,0.046770222,0.00773702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01690907,0.0014538836,0.0027665498,0.0025870071,0.006091234,0.009418594,0.0052347104,0.03323756,0.048448674],"category_scores_gemma":[0.110669896,0.0011366123,0.0031427941,0.0018349261,0.0030554424,0.0039539835,0.002199779,0.02911325,0.041728783],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020251322,0.000007759332,0.0000427201,0.00005247411,0.0000067196715,0.000068094094,0.000011197247,0.000009530717,0.000026568605,0.0004001429,0.9966304,0.002724069],"study_design_scores_gemma":[0.00005482006,0.000011846605,0.0004099256,0.0003396272,0.000022886445,0.00011998126,0.0000742263,0.00006357079,0.00010722995,0.00088514976,0.9978855,0.000025203222],"about_ca_topic_score_codex":0.018977154,"about_ca_topic_score_gemma":0.044617016,"teacher_disagreement_score":0.048448674,"about_ca_system_score_codex":0.00759099,"about_ca_system_score_gemma":0.015693828,"threshold_uncertainty_score":0.16207701},"labels":[],"label_agreement":null},{"id":"W4256514482","doi":"10.3138/cjpe.30.2.v","title":"Editor's Remarks","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.11893994916456034,"score_gpt":0.45101198694784933,"score_spread":0.332072037783289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256514482","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013955314,0.0020189527,0.00012769335,0.4283993,0.5646976,0.000034565386,0.000109900124,0.00007968654,0.004392751],"genre_scores_gemma":[0.0018359725,0.0013915158,0.00045642102,0.71909285,0.23374468,0.00008265757,0.000049864848,0.00007533785,0.043270648],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98107636,0.0018742748,0.0020758759,0.002896265,0.0095938975,0.0024832285],"domain_scores_gemma":[0.93275976,0.016266057,0.005097838,0.0033814772,0.033296257,0.009198622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016912922,0.0017837179,0.003014154,0.002703375,0.0056837318,0.011239806,0.0056770877,0.047639757,0.029821122],"category_scores_gemma":[0.13015257,0.0013196655,0.0036775565,0.0021926414,0.0040689628,0.0039159283,0.0031498473,0.04298138,0.022543509],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016506194,0.0000066809907,0.000052517404,0.000040641018,0.0000101961305,0.00011342319,0.000024855133,0.000014695833,0.00003265292,0.00044240622,0.99718434,0.0020610366],"study_design_scores_gemma":[0.000045073957,0.000014509293,0.0004515741,0.00022633885,0.000032782435,0.00016776164,0.00011779644,0.00006889647,0.00012853694,0.0008677767,0.99784243,0.000036547633],"about_ca_topic_score_codex":0.016152699,"about_ca_topic_score_gemma":0.03736665,"teacher_disagreement_score":0.047639757,"about_ca_system_score_codex":0.008933689,"about_ca_system_score_gemma":0.014993839,"threshold_uncertainty_score":0.099761605},"labels":[],"label_agreement":null},{"id":"W4285480071","doi":"10.3138/cjpe.35.3.intro-eng","title":"Editor’s Remarks","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.06718062263387857,"score_gpt":0.4319921026209933,"score_spread":0.3648114799871147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285480071","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000075890406,0.0015164012,0.00008295582,0.2681321,0.72773004,0.00003441292,0.00009324181,0.000055927296,0.002279003],"genre_scores_gemma":[0.0011478013,0.001619822,0.00054440513,0.510921,0.45835274,0.00012780413,0.000059164402,0.000073018164,0.02715413],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97341925,0.0030232458,0.003813789,0.0030858922,0.01358141,0.0030764567],"domain_scores_gemma":[0.87584865,0.026690837,0.009683089,0.0050231563,0.06971881,0.013035452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029577134,0.0029199228,0.0046489937,0.0044334074,0.0068339547,0.013158625,0.007963261,0.05552709,0.025476316],"category_scores_gemma":[0.17254643,0.0022699945,0.005803693,0.0035401091,0.005052991,0.0052271974,0.0032279708,0.04603916,0.02180508],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018802593,0.000010512763,0.000045960223,0.000048273145,0.000010845615,0.0001079724,0.000017239936,0.000013169646,0.00001540168,0.00024843164,0.9979867,0.0014767208],"study_design_scores_gemma":[0.00009717271,0.000025222635,0.0005934503,0.0003791922,0.00005489772,0.00021139368,0.00014234646,0.000110556735,0.000104909355,0.0008385176,0.9973902,0.00005223187],"about_ca_topic_score_codex":0.016244981,"about_ca_topic_score_gemma":0.03649604,"teacher_disagreement_score":0.05552709,"about_ca_system_score_codex":0.011300449,"about_ca_system_score_gemma":0.018604502,"threshold_uncertainty_score":0.15642071},"labels":[],"label_agreement":null},{"id":"W4317356924","doi":"10.3138/cjpe.74693","title":"Listening with the Heart: A Reflection on Relationality and Ceremony","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Ceremony; Active listening; Reflection (computer programming); Sociology; Process (computing); Psychology; History; Computer science; Communication; Archaeology; Ecology","score_opus":0.4173002021624416,"score_gpt":0.531349183556716,"score_spread":0.11404898139427438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317356924","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25450456,0.011235306,0.04041796,0.46671918,0.015467656,0.00078288344,0.00012041167,0.00034048458,0.21041152],"genre_scores_gemma":[0.9095602,0.0064299065,0.012543683,0.029856158,0.001321168,0.00037263072,0.00002990231,0.00040370933,0.039482538],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9452253,0.04456087,0.00072811206,0.0017334566,0.0042063366,0.003545928],"domain_scores_gemma":[0.9556104,0.0317087,0.0017249839,0.0019915013,0.0037541334,0.0052102474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04269386,0.00092436053,0.00092275895,0.0012285396,0.023612954,0.012757812,0.0039379783,0.005924862,0.0055740387],"category_scores_gemma":[0.06161285,0.0006182607,0.0010592898,0.0009214433,0.03562654,0.009444637,0.011714946,0.0243219,0.0008950317],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048392434,0.00016498295,0.00036156172,0.00016283564,0.00001278367,0.0010638526,0.92925674,0.00011039036,0.00078610354,0.02669873,0.020397002,0.020936543],"study_design_scores_gemma":[0.000015299724,0.0001226816,0.0005961592,0.0008309427,0.000014020026,0.00084759586,0.7004475,0.00025183073,0.00077740505,0.0054743206,0.29056394,0.00005836371],"about_ca_topic_score_codex":0.01753066,"about_ca_topic_score_gemma":0.026063573,"teacher_disagreement_score":0.04269386,"about_ca_system_score_codex":0.011523337,"about_ca_system_score_gemma":0.014343062,"threshold_uncertainty_score":0.22578943},"labels":[],"label_agreement":null},{"id":"W4317356959","doi":"10.3138/cjpe.70523","title":"Challenges Evaluating an Equity-Focused Community Coalition Initiative","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Community Health and Development","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Equity (law); Health equity; Public relations; Psychology; Political science; Public economics; Economic growth; Economics; Health care","score_opus":0.81037546813697,"score_gpt":0.6217158535728178,"score_spread":0.18865961456415226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317356959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83216,0.0012058563,0.0074061453,0.107106656,0.00096841727,0.0042871227,0.00016507324,0.00015893058,0.04654187],"genre_scores_gemma":[0.9763455,0.00040351404,0.010458885,0.006628137,0.00008173105,0.0022366035,0.00006741946,0.000062221116,0.003716043],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8153495,0.14850757,0.0050046165,0.003210159,0.013113877,0.014814296],"domain_scores_gemma":[0.84867126,0.08661832,0.006189392,0.00488732,0.030921819,0.022711849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1464011,0.0006609758,0.0008359708,0.0010193873,0.026622718,0.015348706,0.006072558,0.0064674835,0.0051514986],"category_scores_gemma":[0.13618593,0.0009200129,0.0007105996,0.0013398291,0.010258493,0.0071326043,0.024981499,0.007968766,0.0004915164],"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":[0.0006742686,0.008186269,0.04034979,0.0023832591,0.00023036859,0.0036110897,0.64419293,0.0026891457,0.0027078295,0.039544936,0.037912894,0.21751724],"study_design_scores_gemma":[0.00030968484,0.0028039787,0.009032237,0.0012645129,0.00006718734,0.0003957558,0.9050337,0.0011731471,0.0018954892,0.007443041,0.07045957,0.000121793826],"about_ca_topic_score_codex":0.039888766,"about_ca_topic_score_gemma":0.091833524,"teacher_disagreement_score":0.1464011,"about_ca_system_score_codex":0.030349122,"about_ca_system_score_gemma":0.09438164,"threshold_uncertainty_score":0.7742523},"labels":[],"label_agreement":null},{"id":"W4317381160","doi":"10.3138/cjpe.66908","title":"Making Relationships Count: Measuring Trust in Relationships Between a Catholic Development Agency and Māori Communities","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Indigenous; Centrality; Agency (philosophy); Foundation (evidence); Sociology; Affect (linguistics); Cultural values; Public relations; Social psychology; Psychology; Political science; Social science; Gender studies","score_opus":0.7823290008155973,"score_gpt":0.5171308822180672,"score_spread":0.26519811859753006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906194,0.00008876873,0.0016493748,0.0002458751,0.0000115770445,0.00020366469,0.00008130796,0.000006011845,0.0070941267],"genre_scores_gemma":[0.9977508,0.00005233768,0.0016843274,0.000017621005,0.000002886305,0.00013935182,0.000049277904,0.0000014030674,0.0003019504],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9927856,0.0042525963,0.0007405482,0.00027648316,0.0014223884,0.00052241154],"domain_scores_gemma":[0.9659792,0.011704934,0.010717527,0.0017636957,0.0072160023,0.0026185873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011911682,0.00024557894,0.00027454496,0.0019684106,0.0025268414,0.002260701,0.000703185,0.00050947233,0.0016900791],"category_scores_gemma":[0.03842799,0.00024789284,0.00050801074,0.0013574641,0.0013856179,0.0016861222,0.0040115183,0.0010329477,0.00018177566],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018008654,0.00028487487,0.8912671,0.00020526067,0.0001400106,0.00019150086,0.048780847,0.00035758072,0.0006464208,0.001487221,0.00094506657,0.055514053],"study_design_scores_gemma":[0.00002403598,0.0005771929,0.86197174,0.0003181468,0.0001516939,0.00032997402,0.12605357,0.0036441537,0.0010815831,0.0013763446,0.004411695,0.000059867925],"about_ca_topic_score_codex":0.015041872,"about_ca_topic_score_gemma":0.025968265,"teacher_disagreement_score":0.015041872,"about_ca_system_score_codex":0.0031673638,"about_ca_system_score_gemma":0.002836832,"threshold_uncertainty_score":0.06299573},"labels":[],"label_agreement":null},{"id":"W4317381167","doi":"10.3138/cjpe.37.2.ed","title":"Editor's Remarks / Un mot de la rédactrice","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Posthumanist Ethics and Activism","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Philosophy","score_opus":0.07644955342865889,"score_gpt":0.40930361675832305,"score_spread":0.33285406332966416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381167","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009788371,0.0018979071,0.00014988717,0.5469738,0.4485557,0.00002896109,0.0001001889,0.000045089175,0.0021505193],"genre_scores_gemma":[0.0015911531,0.0018530488,0.0007564842,0.7087007,0.2630308,0.000112217065,0.000041007523,0.000063281164,0.023851324],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9737961,0.004114324,0.004207633,0.0032838122,0.0120661305,0.002531946],"domain_scores_gemma":[0.84998643,0.04156421,0.0072211977,0.005737925,0.084343426,0.011146806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028839339,0.0022077027,0.0032258204,0.0025365767,0.0075189383,0.012864843,0.006533861,0.04680722,0.012361758],"category_scores_gemma":[0.15517388,0.001533682,0.003388358,0.002710201,0.00614642,0.0054986253,0.0032559482,0.05404196,0.009402125],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016317332,0.000009662887,0.000067279376,0.00007474229,0.000010422824,0.00006473984,0.00004434068,0.0000146381335,0.00003555817,0.00070548675,0.99675167,0.0022053043],"study_design_scores_gemma":[0.000053153297,0.000015790105,0.00068832433,0.00039325867,0.00004851844,0.00017755757,0.00025509493,0.0001584635,0.00016441902,0.0014568178,0.9965371,0.00005156606],"about_ca_topic_score_codex":0.040258083,"about_ca_topic_score_gemma":0.074918106,"teacher_disagreement_score":0.04680722,"about_ca_system_score_codex":0.010791279,"about_ca_system_score_gemma":0.024989177,"threshold_uncertainty_score":0.15251881},"labels":[],"label_agreement":null},{"id":"W4317381171","doi":"10.3138/cjpe.74487","title":"New Insights for Tracking and Reporting Milestones","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tracking (education); Reflection (computer programming); Process (computing); Metric (unit); Developmental Milestone; Key (lock); Critical reflection; Psychology; Computer science; Operations management; Pedagogy; Engineering; Computer security; Developmental psychology","score_opus":0.6188240831545975,"score_gpt":0.573439920067952,"score_spread":0.0453841630866455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028417677,0.0056547117,0.5400279,0.34603798,0.0026737049,0.0015963117,0.00077627663,0.001592773,0.07322272],"genre_scores_gemma":[0.36508223,0.0038721443,0.61307174,0.008830765,0.000567477,0.0014048152,0.00047779156,0.00045653037,0.006236479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.73767203,0.20519689,0.018934967,0.007146046,0.026622055,0.0044280346],"domain_scores_gemma":[0.47869483,0.31990692,0.03143166,0.028960083,0.13294497,0.008061513],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21514508,0.0017004091,0.0012516155,0.014613384,0.0076881493,0.03237232,0.0055171223,0.006088333,0.0070284787],"category_scores_gemma":[0.40965113,0.0014118038,0.0012788379,0.0100530945,0.018953532,0.035644446,0.015096148,0.013791551,0.0019367298],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001713302,0.0002896315,0.009670857,0.0020677636,0.000058266265,0.00056207186,0.08756912,0.0039182925,0.0009795655,0.5447936,0.058749504,0.29117],"study_design_scores_gemma":[0.00009692136,0.00034188514,0.0063145123,0.01018832,0.000118090546,0.0007232474,0.09194895,0.017313108,0.0043115616,0.44885007,0.41932312,0.00047018912],"about_ca_topic_score_codex":0.032885216,"about_ca_topic_score_gemma":0.051173907,"teacher_disagreement_score":0.21514508,"about_ca_system_score_codex":0.031090688,"about_ca_system_score_gemma":0.05603034,"threshold_uncertainty_score":0.9678658},"labels":[],"label_agreement":null},{"id":"W4317381178","doi":"10.3138/cjpe.75648","title":"Jean M. Breny and Shannon L. McMorrow. (2021). <i>Photovoice for Social Justice: Visual Representation in Action</i> . Thousand Oaks, CA: SAGE. VitalSource, 101 pages. (ISBN 978-1-5443-5551-1)","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Participatory Visual Research Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Evaluation Society","funders":"","keywords":"Photovoice; Action (physics); Sociology; Representation (politics); Social justice; Economic Justice; Social science; Political science; Art; Visual arts; Law; Physics","score_opus":0.4291454653615963,"score_gpt":0.5903200076307625,"score_spread":0.16117454226916622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381178","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011417224,0.6048918,0.008976951,0.22717662,0.022442032,0.00024341475,0.0026835713,0.0009019416,0.13154186],"genre_scores_gemma":[0.014712932,0.40356317,0.012838263,0.026249524,0.004045815,0.00049024937,0.0016026776,0.000789302,0.53570807],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988925,0.00019955995,0.000063804364,0.000107798965,0.0006656313,0.000070682465],"domain_scores_gemma":[0.9969202,0.00073843286,0.00020375916,0.00006374084,0.0015166013,0.00055729185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032526706,0.0010569823,0.00038613373,0.0021579333,0.0017019244,0.0029223491,0.000991709,0.0024750673,0.076615565],"category_scores_gemma":[0.008012475,0.00064469525,0.00031994915,0.0016299798,0.00096291915,0.0042862804,0.0018993139,0.0028479062,0.03988683],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014791241,0.0000055501437,0.00018304336,0.0002065706,0.0000017036006,0.000023100429,0.00027405572,0.000018805822,0.00008406559,0.0010335571,0.82657224,0.17158248],"study_design_scores_gemma":[0.000005331035,0.0000061219093,0.0009070958,0.00090698677,0.0000043128093,0.00007824813,0.0005750308,0.00001931439,0.00010599185,0.00096779666,0.9964139,0.0000097774955],"about_ca_topic_score_codex":0.097418346,"about_ca_topic_score_gemma":0.21061799,"teacher_disagreement_score":0.097418346,"about_ca_system_score_codex":0.0019381053,"about_ca_system_score_gemma":0.0059870575,"threshold_uncertainty_score":0.25630462},"labels":[],"label_agreement":null},{"id":"W4317381207","doi":"10.3138/cjpe.73987","title":"Involving Youth in Empowerment Evaluation: Evaluators’ Perspectives","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Winnipeg","funders":"","keywords":"Youth empowerment; Empowerment; Positive Youth Development; Psychology; Applied psychology; Developmental psychology; Political science","score_opus":0.41873982061622445,"score_gpt":0.5321663351437933,"score_spread":0.11342651452756886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42376813,0.02578278,0.049046215,0.36098865,0.0042798873,0.0019266373,0.00028062676,0.0003139436,0.13361317],"genre_scores_gemma":[0.9598207,0.004107917,0.010128149,0.020171365,0.00065411616,0.000840558,0.00006910486,0.00013992608,0.0040681325],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.492577,0.46455333,0.010069376,0.003951197,0.01735891,0.011490099],"domain_scores_gemma":[0.5950233,0.29609773,0.014801503,0.0057957955,0.070101336,0.018180419],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.29959643,0.00088340987,0.0010227141,0.0039020737,0.015487281,0.022357067,0.0029392052,0.0057388623,0.0038399345],"category_scores_gemma":[0.25221506,0.0010483769,0.0011924999,0.0027038725,0.017773554,0.011211184,0.014991565,0.010798178,0.00041707596],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003479548,0.0005221674,0.018957067,0.0016772532,0.00017651418,0.0016440406,0.8356609,0.0006000423,0.0012838606,0.03584149,0.023092512,0.08019618],"study_design_scores_gemma":[0.00015474191,0.00042638462,0.005188383,0.0055592135,0.00016383252,0.0009783965,0.7858433,0.0010783413,0.0022698317,0.010701312,0.18745238,0.00018387013],"about_ca_topic_score_codex":0.009097512,"about_ca_topic_score_gemma":0.011684966,"teacher_disagreement_score":0.29959643,"about_ca_system_score_codex":0.015847964,"about_ca_system_score_gemma":0.031947765,"threshold_uncertainty_score":0.8637223},"labels":[],"label_agreement":null},{"id":"W4317381228","doi":"10.3138/cjpe.72343","title":"The Evaluation Marketplace in Canada: What Qualifications Do Employers Demand?","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Business; Profit (economics); Public relations; Marketing; Private sector; Political science; Economics; Economic growth","score_opus":0.37366454585497816,"score_gpt":0.5216791308618242,"score_spread":0.148014585006846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86027545,0.0029712773,0.000874621,0.048745785,0.00021214166,0.00015888813,0.0011183713,0.00008354287,0.085559815],"genre_scores_gemma":[0.99198055,0.00078117097,0.00041374852,0.0019373058,0.00003321216,0.00002451145,0.00018122724,0.000022102095,0.004626176],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9900113,0.0014671413,0.00030362798,0.0005761495,0.005260954,0.0023808377],"domain_scores_gemma":[0.9410085,0.014973904,0.004874495,0.00081491825,0.025511168,0.012816938],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010714911,0.00015468664,0.00036627412,0.0022855818,0.007997318,0.007713725,0.0010880154,0.0012102391,0.009675387],"category_scores_gemma":[0.032771967,0.00027648616,0.00019839482,0.0034474798,0.003048048,0.002147174,0.0016913016,0.0012276846,0.0005628845],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008505937,0.0006516309,0.50987977,0.0008646896,0.000044604505,0.00129449,0.064703256,0.00067568896,0.0037228288,0.028222863,0.09375943,0.2953302],"study_design_scores_gemma":[0.000055294833,0.00010790601,0.7702861,0.0007078501,0.000023271059,0.00019325948,0.12116214,0.0014521801,0.0010159633,0.0019127033,0.102957,0.00012631092],"about_ca_topic_score_codex":0.93597054,"about_ca_topic_score_gemma":0.9755755,"teacher_disagreement_score":0.9892851,"about_ca_system_score_codex":0.07861433,"about_ca_system_score_gemma":0.11532085,"threshold_uncertainty_score":0.57038957},"labels":[],"label_agreement":null},{"id":"W4317381693","doi":"10.3138/cjpe.75739","title":"John Creswell and Johanna Creswell Báez. (2020). <i>30 Essential Skills for the Qualitative Researcher</i> , 2nd edition. Thousand Oaks, CA: Sage. eBook, 338 pages. (ISBN 978-1-5443-5570-2)","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Research Methods and Applications","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes","funders":"","keywords":"Sociology; Library science; Computer science","score_opus":0.1736379202955411,"score_gpt":0.5233968733509051,"score_spread":0.34975895305536403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381693","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00076846976,0.68394375,0.017002119,0.20158204,0.022884076,0.0005758721,0.0031845002,0.0012378863,0.06882126],"genre_scores_gemma":[0.010058586,0.6364945,0.04340335,0.037350506,0.002727475,0.0021318449,0.0034002324,0.001822809,0.26261076],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952545,0.0014009106,0.00042583025,0.00039838903,0.0022593224,0.00026101104],"domain_scores_gemma":[0.97634625,0.00898271,0.0015573727,0.00071916205,0.009958145,0.002436314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015502977,0.0020867079,0.0009231001,0.0037082445,0.002835489,0.0045513995,0.002330569,0.003709982,0.051656935],"category_scores_gemma":[0.031102449,0.0019957446,0.00056469865,0.00459808,0.0024435122,0.008018098,0.0038613165,0.0066160196,0.040951744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020864882,0.000011497435,0.00014007706,0.0009285896,0.00000405657,0.00006357155,0.00074077124,0.000031022537,0.00017477367,0.0015075222,0.7938189,0.20255847],"study_design_scores_gemma":[0.000012486612,0.000010546184,0.0008015264,0.004895124,0.000011328904,0.00017489807,0.0012790991,0.00003086955,0.00018367133,0.0019676455,0.99060214,0.000030729796],"about_ca_topic_score_codex":0.09642058,"about_ca_topic_score_gemma":0.18422455,"teacher_disagreement_score":0.09642058,"about_ca_system_score_codex":0.0035795844,"about_ca_system_score_gemma":0.021216495,"threshold_uncertainty_score":0.1917187},"labels":[],"label_agreement":null},{"id":"W4317381695","doi":"10.3138/cjpe.74582","title":"Fostering an Evaluative Culture by Addressing a Breakdown in the Policy Development Cycle","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Accountability; Corporate governance; Function (biology); Process (computing); Citizen journalism; Participatory evaluation; Process management; Political science; Public relations; Public administration; Business; Management; Economics; Computer science; Law","score_opus":0.4732297645571751,"score_gpt":0.5733556647379928,"score_spread":0.10012590018081774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22160962,0.002065096,0.4251997,0.25635687,0.0019963174,0.0058737006,0.00013318488,0.0015220705,0.08524345],"genre_scores_gemma":[0.8264133,0.0005141149,0.15459691,0.008673601,0.00022253396,0.0027435964,0.00006904057,0.0002511172,0.006515843],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6699256,0.23952326,0.01902771,0.011496938,0.047883764,0.012142832],"domain_scores_gemma":[0.5513486,0.21414846,0.039967675,0.04669974,0.114501595,0.03333395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.31407213,0.0010889014,0.0014829922,0.0061252913,0.020612443,0.043774217,0.004462949,0.0062998817,0.003180353],"category_scores_gemma":[0.27446193,0.0019475428,0.00096492865,0.0036986787,0.02637524,0.020893652,0.030881096,0.018456882,0.0009678855],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045440852,0.0024230222,0.026439613,0.0018002723,0.000254824,0.0009450161,0.28488368,0.0065611294,0.008436377,0.298672,0.024240116,0.34488955],"study_design_scores_gemma":[0.00044569987,0.001710303,0.02950138,0.006275257,0.00022528907,0.00092343055,0.25049323,0.023047693,0.015921121,0.29782814,0.37270838,0.0009200879],"about_ca_topic_score_codex":0.009505465,"about_ca_topic_score_gemma":0.010282103,"teacher_disagreement_score":0.31407213,"about_ca_system_score_codex":0.047410045,"about_ca_system_score_gemma":0.124786414,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4317381706","doi":"10.3138/cjpe.73451","title":"Validation du questionnaire sur la capacité évaluative des organisations et ses déterminants (QCEOD)","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Internal consistency; Confirmatory factor analysis; Psychology; Reliability (semiconductor); Applied psychology; Consistency (knowledge bases); Social psychology; Structural equation modeling; Psychometrics; Statistics; Clinical psychology; Computer science; Mathematics","score_opus":0.3059432813083428,"score_gpt":0.5062255374256022,"score_spread":0.20028225611725936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93094206,0.00037672993,0.040484123,0.001494688,0.00021517031,0.0124791935,0.0029427973,0.00015025206,0.010914868],"genre_scores_gemma":[0.90135634,0.00039884806,0.07042037,0.0007427758,0.000049151116,0.019713104,0.0027000976,0.00006583793,0.004553518],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98066425,0.011527486,0.0021707346,0.0006569808,0.003969007,0.0010116094],"domain_scores_gemma":[0.9358846,0.03631314,0.003652011,0.002888772,0.019198973,0.0020624911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035627726,0.00036452644,0.0005132826,0.0019098213,0.0007236655,0.0010082028,0.0007943211,0.00072569493,0.003430222],"category_scores_gemma":[0.051910568,0.0003610197,0.000611135,0.001095617,0.00096605264,0.000987045,0.0016947963,0.0011975168,0.00073690765],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011280465,0.0031869202,0.5417677,0.0020504785,0.00020187868,0.00038293295,0.025982393,0.0045946985,0.011636427,0.007983506,0.012896581,0.38818845],"study_design_scores_gemma":[0.00043061477,0.0026481694,0.87183625,0.0010724672,0.00009705723,0.00040486592,0.014458646,0.008348764,0.0133104045,0.0025132045,0.08473009,0.0001494863],"about_ca_topic_score_codex":0.005040775,"about_ca_topic_score_gemma":0.004032225,"teacher_disagreement_score":0.035627726,"about_ca_system_score_codex":0.00205503,"about_ca_system_score_gemma":0.00615756,"threshold_uncertainty_score":0.18841964},"labels":[],"label_agreement":null},{"id":"W4353046979","doi":"10.3138/cjpe.37.3.fm","title":"Front Matter","year":2023,"lang":"en","type":"paratext","venue":"Canadian Journal of Program Evaluation","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Front (military); Geology; Oceanography","score_opus":0.15093772260935273,"score_gpt":0.4029056971675459,"score_spread":0.25196797455819314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353046979","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002877198,0.0002655021,0.00012272895,0.0029476122,0.0013344329,0.00005086486,0.0013415805,0.0002698393,0.9933797],"genre_scores_gemma":[0.00074628653,0.00016849885,0.00009526279,0.00067011017,0.00009326215,0.000013250211,0.00024122125,0.000060411683,0.99791163],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987035,0.000089345776,0.000052186246,0.00017630187,0.00069431396,0.00028438773],"domain_scores_gemma":[0.99362236,0.00081231643,0.00017310199,0.00021836716,0.0028084647,0.002365481],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012602445,0.0012409964,0.00074365933,0.0026127447,0.0028195705,0.005941548,0.0011412194,0.0042783464,0.9297402],"category_scores_gemma":[0.005522635,0.00060074276,0.0005156509,0.0019443164,0.0013394138,0.0020510617,0.0017404477,0.0018329436,0.8444447],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021504482,0.00003323803,0.00025380668,0.00006691204,0.0000023122386,0.000041721854,0.000028168295,0.000032191725,0.0000776556,0.0031807127,0.92097664,0.07528506],"study_design_scores_gemma":[0.000013582176,0.0000091115135,0.00081359176,0.00013459864,0.0000021604374,0.00005388052,0.00009204277,0.00005339676,0.000046434492,0.00047066744,0.9983045,0.000006147515],"about_ca_topic_score_codex":0.1000059,"about_ca_topic_score_gemma":0.16660213,"teacher_disagreement_score":0.1000059,"about_ca_system_score_codex":0.0038206524,"about_ca_system_score_gemma":0.012600561,"threshold_uncertainty_score":0.19884759},"labels":[],"label_agreement":null},{"id":"W4353048394","doi":"10.3138/cjpe.37.3.bm","title":"Back Matter","year":2023,"lang":"en","type":"paratext","venue":"Canadian Journal of Program Evaluation","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Psychology","score_opus":0.17849221185712547,"score_gpt":0.4109888864651381,"score_spread":0.23249667460801263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353048394","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017556778,0.00024432683,0.00010165029,0.0039816373,0.0023306757,0.00007652789,0.0020675494,0.00041756677,0.99060446],"genre_scores_gemma":[0.00035126664,0.000098430595,0.00004318921,0.0005064725,0.000059342026,0.0000107538335,0.0002893196,0.00005609166,0.9985851],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984499,0.00009115722,0.000051881005,0.00017148585,0.00089765276,0.0003378717],"domain_scores_gemma":[0.99457526,0.00041886434,0.0000882534,0.00031443674,0.0030563602,0.0015469387],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001234732,0.0009519314,0.0009110881,0.002894003,0.00428474,0.009001752,0.0014739768,0.004138916,0.93606484],"category_scores_gemma":[0.007730536,0.000655177,0.00091811875,0.0022316352,0.001638066,0.0017381103,0.0023261174,0.0025669837,0.86266065],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016707463,0.000021970409,0.00009333689,0.000048970345,0.0000019005797,0.000019432171,0.00001660265,0.00001898447,0.000038413444,0.0024887286,0.9656165,0.031618524],"study_design_scores_gemma":[0.0000082594615,0.000004995328,0.00032432209,0.0000784867,0.0000019183422,0.000020368763,0.00004815935,0.000026458521,0.000043335127,0.00048673,0.9989525,0.0000046180953],"about_ca_topic_score_codex":0.15985455,"about_ca_topic_score_gemma":0.24938054,"teacher_disagreement_score":0.15985455,"about_ca_system_score_codex":0.005882452,"about_ca_system_score_gemma":0.01854291,"threshold_uncertainty_score":0.31784815},"labels":[],"label_agreement":null},{"id":"W4353055378","doi":"10.3138/cjpe.75448","title":"John Mayne and Rules of Thumb for Contribution Analysis: A Comparison With Two Related Approaches","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rule of thumb; Manifesto; Thumb; Epistemology; Work (physics); Sociology; Computer science; Political science; Law; Philosophy; Medicine; Engineering; Algorithm; Surgery","score_opus":0.4678585488688824,"score_gpt":0.5302059008889366,"score_spread":0.0623473520200542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055378","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060264138,0.0068747476,0.9279911,0.016352162,0.000733753,0.00056226505,0.00011636128,0.00030804414,0.04103513],"genre_scores_gemma":[0.15673883,0.0028278695,0.83084655,0.00341723,0.0005160713,0.0015498291,0.00009630544,0.000366473,0.0036409493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.653915,0.25023705,0.014963601,0.011622847,0.067123726,0.0021378004],"domain_scores_gemma":[0.46693215,0.4622339,0.010127047,0.031901423,0.026405577,0.002400011],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22645576,0.0018144923,0.0035710335,0.014334746,0.0059158397,0.018661618,0.00501718,0.0052103936,0.004983868],"category_scores_gemma":[0.43687937,0.0014712415,0.002357844,0.010465802,0.025812566,0.018924976,0.009481705,0.0071857073,0.001498435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009646376,0.00004369361,0.00084954844,0.00057148666,0.00012271553,0.000045665958,0.002422386,0.0032085984,0.000081568156,0.91017395,0.004198945,0.07818496],"study_design_scores_gemma":[0.000071324386,0.000042099455,0.0004767094,0.0006988881,0.000055866298,0.000078905694,0.0007300045,0.008435436,0.00028982214,0.96703213,0.022020638,0.000068291745],"about_ca_topic_score_codex":0.006490996,"about_ca_topic_score_gemma":0.0071603684,"teacher_disagreement_score":0.22645576,"about_ca_system_score_codex":0.009366127,"about_ca_system_score_gemma":0.01538838,"threshold_uncertainty_score":0.95391774},"labels":[],"label_agreement":null},{"id":"W4353055383","doi":"10.3138/cjpe.37.3.ed-fr","title":"Un mot de la rédactrice","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.11514319283525193,"score_gpt":0.38527159884555906,"score_spread":0.27012840601030713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055383","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006297023,0.011809436,0.010173813,0.2858389,0.050899617,0.00037099447,0.0006160971,0.0007664407,0.6332277],"genre_scores_gemma":[0.06661892,0.008022419,0.011686352,0.055104535,0.008808392,0.00049641257,0.0006592486,0.00093183044,0.8476719],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9789513,0.007541744,0.0007920302,0.0020497045,0.008999923,0.0016653013],"domain_scores_gemma":[0.9660773,0.007939211,0.0018022002,0.0033397595,0.016562598,0.0042788154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012012284,0.0011417374,0.00079734216,0.0025731397,0.010377007,0.016524473,0.0019120931,0.00506521,0.08435402],"category_scores_gemma":[0.044352375,0.0007554222,0.0009848595,0.003071815,0.0075299847,0.015272053,0.009750568,0.012694373,0.031524424],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083814324,0.0000571655,0.0011134122,0.0005304938,0.000014516848,0.00025103864,0.01014744,0.0001185688,0.0007046692,0.20106721,0.66081405,0.12509762],"study_design_scores_gemma":[0.000006663394,0.00002146208,0.00058171415,0.00027477668,0.000004940616,0.00014596118,0.002232629,0.000063877844,0.00027380622,0.00627397,0.99009764,0.000022581864],"about_ca_topic_score_codex":0.01803591,"about_ca_topic_score_gemma":0.025140382,"teacher_disagreement_score":0.08435402,"about_ca_system_score_codex":0.01023161,"about_ca_system_score_gemma":0.018693643,"threshold_uncertainty_score":0.2821923},"labels":[],"label_agreement":null},{"id":"W4353055384","doi":"10.3138/cjpe.75515","title":"Remembering John Mayne—A Practical Thinker and a Thinking Practitioner","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Stroke Network","funders":"","keywords":"Psychoanalysis; Psychology; Epistemology; Philosophy","score_opus":0.4904664904135886,"score_gpt":0.5735784858630458,"score_spread":0.08311199544945724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055384","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007059947,0.012038519,0.0043493086,0.9438353,0.034469616,0.000022426217,0.000021857173,0.00008809416,0.004468929],"genre_scores_gemma":[0.039231163,0.014417873,0.016328067,0.84916204,0.025858575,0.00013782561,0.00003892751,0.00032851435,0.054497063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9718685,0.012455787,0.0017204818,0.0031636646,0.009404968,0.0013867182],"domain_scores_gemma":[0.8341937,0.055746544,0.0047925613,0.0043214536,0.058417745,0.042527888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02520031,0.001293774,0.0015350999,0.0024774498,0.009532416,0.018292336,0.0036663238,0.011882085,0.0093594],"category_scores_gemma":[0.12950365,0.0007338406,0.0009110052,0.0013210865,0.020430405,0.013495598,0.005035987,0.031758323,0.0039311554],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005072766,0.00010211681,0.00053569995,0.00017638516,0.000042327552,0.00047358812,0.006799443,0.00012052788,0.00022250651,0.02370593,0.9501665,0.017604308],"study_design_scores_gemma":[0.00006783365,0.00009125483,0.00045245365,0.0011828245,0.000042528274,0.001549124,0.022714058,0.0004584865,0.00049347844,0.07225844,0.9005332,0.0001562444],"about_ca_topic_score_codex":0.024166334,"about_ca_topic_score_gemma":0.036941633,"teacher_disagreement_score":0.02520031,"about_ca_system_score_codex":0.00890471,"about_ca_system_score_gemma":0.026274012,"threshold_uncertainty_score":0.13327354},"labels":[],"label_agreement":null},{"id":"W4353055391","doi":"10.3138/cjpe.75444","title":"Using Evaluative Information Sensibly: The Enduring Contributions of John Mayne","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Stroke Network","funders":"MetroWest Health Foundation; Hartford Foundation for Public Giving","keywords":"Causation; Audit; Accountability; Discipline; Bridge (graph theory); Work (physics); Knowledge management; Sociology; Engineering ethics; Epistemology; Computer science; Political science; Social science; Accounting; Engineering; Medicine; Business; Law","score_opus":0.47197470653963447,"score_gpt":0.5711621102531929,"score_spread":0.09918740371355839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055391","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040442147,0.022949936,0.015931621,0.9202468,0.015462028,0.000055101093,0.000022488726,0.000091658716,0.021196144],"genre_scores_gemma":[0.3233591,0.08983839,0.07467245,0.39620382,0.050262343,0.00039547498,0.00006386271,0.0011017594,0.06410273],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9430804,0.03504947,0.0016499731,0.0029123381,0.01608863,0.0012192202],"domain_scores_gemma":[0.815581,0.1262437,0.0024642542,0.0055187964,0.038455334,0.0117368745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05205446,0.0005571715,0.0009011415,0.002978041,0.008112633,0.017175116,0.0019369232,0.0034821087,0.0017598228],"category_scores_gemma":[0.113227144,0.0007011607,0.000439195,0.0018585125,0.02497478,0.018960822,0.0066480716,0.016452814,0.0005679579],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068561356,0.0001357234,0.0016604417,0.00069618435,0.00004962858,0.00054686726,0.058345526,0.0006238467,0.0005395957,0.25498658,0.5430612,0.13928585],"study_design_scores_gemma":[0.000012733945,0.000036636477,0.00057479535,0.0010934388,0.000026162816,0.00052824523,0.020360911,0.00072643766,0.0009151699,0.12610133,0.8494915,0.00013263166],"about_ca_topic_score_codex":0.009491105,"about_ca_topic_score_gemma":0.016518189,"teacher_disagreement_score":0.05205446,"about_ca_system_score_codex":0.0072080167,"about_ca_system_score_gemma":0.01535089,"threshold_uncertainty_score":0.2752936},"labels":[],"label_agreement":null},{"id":"W4353055426","doi":"10.3138/cjpe.75451","title":"John Mayne and the Origins of Evaluation in the Public Sector in Canada: A Shaping of Both Evaluation and the Evaluator","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Test (biology); Public sector; Public administration; Political science; Sociology; Management; Public relations; Economics; Law; Philosophy; Geology","score_opus":0.37158747526533276,"score_gpt":0.48774464836179726,"score_spread":0.1161571730964645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055426","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037798267,0.035775628,0.0034292706,0.905927,0.0031250094,0.00008011125,0.000046683086,0.000054414708,0.04778199],"genre_scores_gemma":[0.45001948,0.09805603,0.018099695,0.33845264,0.0038547376,0.00024293043,0.000078544756,0.0005699876,0.09062596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92726964,0.02629374,0.0023977074,0.00435086,0.032822434,0.0068656337],"domain_scores_gemma":[0.84809166,0.066081755,0.0026111288,0.0026503126,0.058744326,0.02182082],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.04798846,0.0005893155,0.0014377129,0.005207923,0.03881333,0.03220757,0.0033533801,0.008896652,0.0033420653],"category_scores_gemma":[0.099647745,0.0011036947,0.000665161,0.006582069,0.08856794,0.011084436,0.0058703204,0.026638892,0.0004433898],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000065583714,0.00009799252,0.0025050866,0.00032019868,0.00004066318,0.000433588,0.031551555,0.0009435705,0.00022505857,0.6097425,0.30349636,0.050577827],"study_design_scores_gemma":[0.000031554806,0.000028238026,0.0025722461,0.0016245091,0.000025162388,0.00016361233,0.022644693,0.000798192,0.00032697947,0.09543485,0.8761123,0.00023756626],"about_ca_topic_score_codex":0.9650465,"about_ca_topic_score_gemma":0.979162,"teacher_disagreement_score":0.96118665,"about_ca_system_score_codex":0.24311756,"about_ca_system_score_gemma":0.38482332,"threshold_uncertainty_score":0.87787634},"labels":[],"label_agreement":null},{"id":"W4353055431","doi":"10.3138/cjpe.75432","title":"John Mayne’s Contribution to Results-Based Management Thinking: A Leadership Legacy","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Accounting and Organizational Management","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":true,"route_about_ca":false,"ca_institutions":"Ontario Stroke Network","funders":"","keywords":"Salient; Task (project management); Key (lock); Knowledge management; Management; Sociology; Psychology; Engineering ethics; Computer science; Engineering; Artificial intelligence","score_opus":0.11887089476737892,"score_gpt":0.3153735980637159,"score_spread":0.19650270329633698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055431","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041378946,0.037428737,0.016326003,0.8497028,0.018663488,0.00003107287,0.000039631457,0.00013476526,0.07353578],"genre_scores_gemma":[0.31688824,0.07901488,0.040963676,0.34709784,0.041874763,0.00017573635,0.000070920265,0.00063118106,0.1732828],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98389554,0.007075239,0.00059924606,0.0013369081,0.006286319,0.0008067456],"domain_scores_gemma":[0.9515555,0.027594931,0.0011955426,0.0018937169,0.010764857,0.0069953264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01651571,0.0005294878,0.0004728337,0.0022728657,0.0054838494,0.010045514,0.0011631221,0.0030827746,0.0048021195],"category_scores_gemma":[0.031047577,0.00045637813,0.0003498776,0.0012926352,0.014745943,0.009824858,0.0033697148,0.012189642,0.001373055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036193553,0.00015471288,0.00083432655,0.00021868739,0.000024690828,0.00034267645,0.009859537,0.00028654537,0.0002429898,0.34945282,0.5452991,0.09324766],"study_design_scores_gemma":[0.000011165347,0.000038281836,0.000327873,0.00038797178,0.000007238292,0.0004772758,0.0017353548,0.0003263058,0.00028424143,0.09457401,0.9017954,0.00003497655],"about_ca_topic_score_codex":0.005489668,"about_ca_topic_score_gemma":0.008698391,"teacher_disagreement_score":0.01651571,"about_ca_system_score_codex":0.005770781,"about_ca_system_score_gemma":0.010961764,"threshold_uncertainty_score":0.08734453},"labels":[],"label_agreement":null},{"id":"W4353055441","doi":"10.3138/cjpe.37.3.ed-en","title":"Editor’s Remarks","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.3016607384097375,"score_gpt":0.5419447489581198,"score_spread":0.24028401054838233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055441","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019325914,0.0015964787,0.00026613538,0.5484891,0.4429849,0.000038568945,0.00017838369,0.00020407932,0.0060490645],"genre_scores_gemma":[0.0033875913,0.0017716276,0.0010948505,0.70151347,0.2373176,0.000121738434,0.00012226013,0.00018324106,0.054487653],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9869446,0.0011456308,0.0011464745,0.0025494106,0.006962715,0.0012511433],"domain_scores_gemma":[0.947793,0.010852068,0.002420006,0.0022110492,0.031177519,0.005546324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012304888,0.0016213716,0.0018207384,0.0018592312,0.004965354,0.010235266,0.0049102586,0.02267303,0.026112597],"category_scores_gemma":[0.09679381,0.00084378006,0.002662956,0.0016011815,0.0034098965,0.005850587,0.003152073,0.026675982,0.022777406],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011365107,0.000006455436,0.00004870229,0.000025012692,0.0000038684757,0.00006491964,0.000029838851,0.000015401189,0.000030193058,0.00057232595,0.9966529,0.0025390866],"study_design_scores_gemma":[0.000015769709,0.000010932569,0.0002556201,0.000115325296,0.000008021646,0.000102163685,0.000109923865,0.0000707058,0.00013567081,0.0008579628,0.9982936,0.000024284685],"about_ca_topic_score_codex":0.009010021,"about_ca_topic_score_gemma":0.017166335,"teacher_disagreement_score":0.026112597,"about_ca_system_score_codex":0.005206063,"about_ca_system_score_gemma":0.011127049,"threshold_uncertainty_score":0.087355316},"labels":[],"label_agreement":null},{"id":"W4353055504","doi":"10.3138/cjpe.75430","title":"Causality and Complexity in Evaluating Equity Interventions: Conceptual Issues That Need to Be Addressed in Theory-Driven Evaluation Approaches","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Causality (physics); Variety (cybernetics); Psychological intervention; Equity (law); Management science; Causal model; Conceptual framework; Risk analysis (engineering); Positive economics; Psychology; Computer science; Sociology; Economics; Political science; Business; Medicine; Social science","score_opus":0.921309918994153,"score_gpt":0.6511159997897381,"score_spread":0.27019391920441493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055504","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018834956,0.011397459,0.8521821,0.082259566,0.001510965,0.0049364455,0.00040369114,0.00020440774,0.028270384],"genre_scores_gemma":[0.46771204,0.0059484933,0.5053768,0.0071832114,0.00069688034,0.011237845,0.00018779798,0.00014531554,0.0015116393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6325803,0.31223416,0.013725385,0.0075204694,0.031254932,0.0026847813],"domain_scores_gemma":[0.26269838,0.6934296,0.014510321,0.014462625,0.01269311,0.0022060745],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.35270166,0.0027991042,0.006449667,0.008008849,0.0041445624,0.015607256,0.006588077,0.006213282,0.010281088],"category_scores_gemma":[0.5485412,0.0017786167,0.0048858067,0.0053417585,0.027512131,0.030768653,0.011996455,0.0128682405,0.000506555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021903109,0.00021793907,0.0038269109,0.0036659772,0.0006938029,0.00008944892,0.002413507,0.015237608,0.00017331133,0.9188044,0.001133184,0.05352477],"study_design_scores_gemma":[0.000113291826,0.00014666855,0.0006609552,0.0015568834,0.00021150606,0.000034048862,0.0007267662,0.012115889,0.00031839087,0.9811739,0.0028926716,0.000049113944],"about_ca_topic_score_codex":0.006895921,"about_ca_topic_score_gemma":0.008587788,"teacher_disagreement_score":0.35270166,"about_ca_system_score_codex":0.017400937,"about_ca_system_score_gemma":0.0256892,"threshold_uncertainty_score":0.7982341},"labels":[],"label_agreement":null},{"id":"W4353055508","doi":"10.3138/cjpe.75467","title":"John Mayne’s Contribution to Performance Audit","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Audit; Government (linguistics); Service (business); Public service; Business; Accounting; Public administration; Political science; Philosophy; Marketing","score_opus":0.3441610320995043,"score_gpt":0.528996299099539,"score_spread":0.18483526700003472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055508","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026547597,0.040476758,0.023306925,0.7666357,0.032792263,0.00010777303,0.00016632624,0.00041209662,0.13344744],"genre_scores_gemma":[0.23687823,0.07727305,0.041876532,0.20352432,0.041310616,0.00023253102,0.00023635151,0.0009095575,0.39775878],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.954162,0.013367827,0.0019047436,0.0032717744,0.025460107,0.0018334413],"domain_scores_gemma":[0.87990445,0.039861348,0.0034270484,0.007314583,0.054474972,0.0150174685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021584146,0.00048768157,0.0005900009,0.0034337186,0.005378391,0.010790047,0.001347239,0.0030525734,0.0083686765],"category_scores_gemma":[0.10097003,0.00065853173,0.0004567648,0.0034463513,0.008072489,0.0054047597,0.0042216415,0.011627605,0.0022430995],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003663243,0.00004175535,0.0012590033,0.00017993512,0.00002641128,0.00014417946,0.0023870708,0.00050262903,0.00018758193,0.10881312,0.7333803,0.1530413],"study_design_scores_gemma":[0.000004097235,0.0000096211925,0.00058862776,0.00019294095,0.000006438495,0.00020146201,0.00034779136,0.00027359376,0.00021713755,0.022048663,0.97608167,0.000027886743],"about_ca_topic_score_codex":0.05621977,"about_ca_topic_score_gemma":0.0696487,"teacher_disagreement_score":0.05621977,"about_ca_system_score_codex":0.014379768,"about_ca_system_score_gemma":0.03326118,"threshold_uncertainty_score":0.11414921},"labels":[],"label_agreement":null},{"id":"W4353055537","doi":"10.3138/cjpe.75431","title":"Building Evaluation Culture—The Missing Link","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Sociology; Knowledge management; Psychology; Epistemology; Computer science; Philosophy","score_opus":0.5208539717794183,"score_gpt":0.5865932421472865,"score_spread":0.0657392703678682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055537","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0150910355,0.011502968,0.07013273,0.8501688,0.0050225244,0.00021749751,0.000026895688,0.00035936543,0.047478154],"genre_scores_gemma":[0.6917383,0.010009854,0.10285664,0.17993434,0.002857637,0.0007799099,0.000056885907,0.00067456765,0.0110919075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7042643,0.23050542,0.010529533,0.009733361,0.03782759,0.007139797],"domain_scores_gemma":[0.58183527,0.21066543,0.014330405,0.035275485,0.12052434,0.037369095],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25932518,0.0007290085,0.0014270106,0.00461187,0.017065894,0.03547212,0.0033480166,0.0064333794,0.0033423796],"category_scores_gemma":[0.24930933,0.0014005416,0.0009999741,0.0028591824,0.04913774,0.042507578,0.023319313,0.024109675,0.0014196843],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009928498,0.0004712599,0.0053553698,0.0010733387,0.00018819861,0.00027753762,0.055862173,0.00085297815,0.0008748914,0.5815994,0.101972476,0.25137308],"study_design_scores_gemma":[0.000090102716,0.00031340614,0.003831166,0.006250379,0.00009389415,0.0004460206,0.08537016,0.002332917,0.001965479,0.44311392,0.4558392,0.0003533305],"about_ca_topic_score_codex":0.010759791,"about_ca_topic_score_gemma":0.0076345685,"teacher_disagreement_score":0.25932518,"about_ca_system_score_codex":0.020545831,"about_ca_system_score_gemma":0.0532133,"threshold_uncertainty_score":0.9133839},"labels":[],"label_agreement":null},{"id":"W4353055544","doi":"10.3138/cjpe.37.3.494","title":"Peer Reviewers for Volume 37 and Manuscripts Submitted in 2022 / Examinateurs des manuscrits du volume 37 et des manuscrits soumis en 2022","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Medical Research and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Art; Psychology; Physics","score_opus":0.17585770840817205,"score_gpt":0.4106271554059882,"score_spread":0.23476944699781616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055544","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012401769,0.017513916,0.0065606604,0.11904578,0.6712126,0.008788005,0.012498376,0.0038455452,0.14813331],"genre_scores_gemma":[0.026659438,0.013392512,0.0137884775,0.016486268,0.12528521,0.0040090634,0.008138077,0.0035664826,0.7886745],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.973463,0.0038371312,0.0033532958,0.0015290632,0.01602641,0.001791133],"domain_scores_gemma":[0.712695,0.013480624,0.0069878446,0.005931646,0.23828466,0.022620246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020848468,0.0020028567,0.0027776305,0.012021534,0.005618824,0.0117976,0.0022664214,0.004725152,0.2290644],"category_scores_gemma":[0.101233765,0.0009532569,0.0020635359,0.005673307,0.0013847967,0.0032828643,0.0031154882,0.0030466164,0.14172454],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002683977,0.00006317502,0.0011230949,0.00060262054,0.000040352854,0.00019460557,0.00012961931,0.00004236778,0.00057905086,0.00054032466,0.9529153,0.043501057],"study_design_scores_gemma":[0.00014113153,0.000118203214,0.0041656108,0.0005170749,0.00004980698,0.00020962443,0.0004010117,0.00018018579,0.0008182136,0.0008911214,0.99246585,0.000042174037],"about_ca_topic_score_codex":0.006829212,"about_ca_topic_score_gemma":0.019044636,"teacher_disagreement_score":0.2290644,"about_ca_system_score_codex":0.003312621,"about_ca_system_score_gemma":0.027999006,"threshold_uncertainty_score":0.76629674},"labels":[],"label_agreement":null},{"id":"W4353055566","doi":"10.3138/cjpe.75441","title":"Mapping the Contributions of John Mayne: Bridging the Gaps Between Evaluation, Auditing, and Performance Monitoring","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Citation; Bridging (networking); Field (mathematics); Library science; Data science; Computer science; Accounting; Business","score_opus":0.36971123944452877,"score_gpt":0.5041761856590817,"score_spread":0.13446494621455296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055566","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28618127,0.0970635,0.046357065,0.3554298,0.0054979473,0.00062488765,0.00043996744,0.0005873648,0.2078182],"genre_scores_gemma":[0.88987315,0.0383862,0.035159037,0.008881591,0.0016664026,0.00025957817,0.000302564,0.00028699875,0.02518455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9532326,0.020966774,0.002240902,0.0021896032,0.018732497,0.0026376343],"domain_scores_gemma":[0.7641327,0.12694134,0.012284916,0.0067856433,0.07609986,0.013755632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048242103,0.0004457926,0.0005697689,0.012987674,0.004913827,0.018791063,0.0012895241,0.0016616746,0.0027631118],"category_scores_gemma":[0.19517563,0.0004485849,0.00029350657,0.013190955,0.0068604564,0.009898082,0.005720372,0.0031800414,0.0007054194],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025026198,0.00018600517,0.040514152,0.0019273543,0.0000848158,0.00065755466,0.03842974,0.0013674824,0.00150716,0.06941918,0.06137065,0.78428566],"study_design_scores_gemma":[0.000041173575,0.00035753893,0.09699975,0.008495308,0.00015462984,0.0010408739,0.073886834,0.0036456732,0.007108514,0.05512058,0.752825,0.00032407558],"about_ca_topic_score_codex":0.031375453,"about_ca_topic_score_gemma":0.052305557,"teacher_disagreement_score":0.048242103,"about_ca_system_score_codex":0.017335663,"about_ca_system_score_gemma":0.04482345,"threshold_uncertainty_score":0.25513172},"labels":[],"label_agreement":null},{"id":"W4353055592","doi":"10.3138/cjpe.37.3.addendum-fr","title":"Addendum","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Addendum; Philosophy; Linguistics","score_opus":0.642089777734816,"score_gpt":0.5990496877794452,"score_spread":0.043040089955370786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055592","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077743334,0.0055779843,0.0038925477,0.014021747,0.031974338,0.0006572913,0.0123110395,0.0053945347,0.9253931],"genre_scores_gemma":[0.0030644129,0.0035393944,0.0026028152,0.006565761,0.0033156676,0.0002867179,0.008097679,0.0019620818,0.97056544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971842,0.00036766464,0.00022742852,0.00048268653,0.0014839936,0.000254032],"domain_scores_gemma":[0.9929268,0.0007152853,0.00030364576,0.0010202107,0.0035763138,0.0014577471],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018924826,0.0015488724,0.0012999586,0.0032172028,0.0029175917,0.009669673,0.003954179,0.0038037247,0.8438274],"category_scores_gemma":[0.012478712,0.0007010274,0.0012929394,0.0029162713,0.0010354009,0.0057110847,0.00661964,0.0029635925,0.7594328],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058053873,0.00003831839,0.00012455789,0.00048176412,0.0000072084345,0.00013436384,0.000104093255,0.00004870919,0.00034472908,0.0032483668,0.8869196,0.10849016],"study_design_scores_gemma":[0.000007489941,0.000014210577,0.000104774284,0.00012151654,0.0000047981493,0.00011020599,0.00006012769,0.000015893705,0.00010006246,0.0008786693,0.99857616,0.000006114703],"about_ca_topic_score_codex":0.003677487,"about_ca_topic_score_gemma":0.008250557,"teacher_disagreement_score":0.15617257,"about_ca_system_score_codex":0.0022756811,"about_ca_system_score_gemma":0.006587815,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4353055595","doi":"10.3138/cjpe.37.3.addendum-en","title":"Addendum","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Addendum; Philosophy; Linguistics","score_opus":0.642089777734816,"score_gpt":0.5990496877794452,"score_spread":0.043040089955370786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055595","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001071554,0.006336146,0.005646136,0.09644614,0.5349613,0.0015375749,0.034634985,0.004543561,0.31482267],"genre_scores_gemma":[0.00614548,0.00723117,0.007139404,0.049174227,0.08665504,0.0011689056,0.029684603,0.0032406899,0.8095605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99379385,0.00082795403,0.0006313332,0.0007251661,0.003567038,0.00045464686],"domain_scores_gemma":[0.91524494,0.011205545,0.0022494104,0.0049975673,0.0587476,0.0075548366],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004050314,0.001498047,0.0013930809,0.0037020713,0.0025154694,0.006505977,0.0038401058,0.0029213503,0.695728],"category_scores_gemma":[0.07181855,0.0007024803,0.001259468,0.0027851928,0.0009956226,0.0033778772,0.0038279823,0.003759144,0.4598952],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003847559,0.000016850392,0.000053850537,0.00017684615,0.0000031750446,0.0000563174,0.000022483637,0.00001845727,0.00008029095,0.00047111168,0.9782762,0.020785807],"study_design_scores_gemma":[0.000019740666,0.000031868316,0.00022508598,0.00017468169,0.000007039772,0.00022989782,0.000049133836,0.000030435825,0.00012969521,0.00080970157,0.99828184,0.000010971901],"about_ca_topic_score_codex":0.0043900413,"about_ca_topic_score_gemma":0.01053671,"teacher_disagreement_score":0.304272,"about_ca_system_score_codex":0.0027705596,"about_ca_system_score_gemma":0.009760666,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4353055654","doi":"10.3138/cjpe.75428","title":"Causal Claims in Contribution Analysis","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Counterfactual thinking; Causality (physics); Causation; Relevance (law); Epistemology; Causal analysis; Counterfactual conditional; Generative grammar; Probabilistic logic; Computer science; Positive economics; Psychology; Sociology; Econometrics; Philosophy; Artificial intelligence; Economics; Political science; Law","score_opus":0.4173134303158473,"score_gpt":0.5774615920977317,"score_spread":0.16014816178188446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055654","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009075671,0.0057734293,0.8671819,0.023811683,0.0012230838,0.00045876886,0.00023345211,0.0002309247,0.09201103],"genre_scores_gemma":[0.61202246,0.004339723,0.3602875,0.0051088147,0.0025189468,0.0019501265,0.0003098307,0.00034485964,0.013117698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8767645,0.09488531,0.004196111,0.007236667,0.015021501,0.0018959396],"domain_scores_gemma":[0.6949682,0.26443443,0.007143975,0.018755876,0.013022428,0.0016750839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11056996,0.0017346184,0.0023489268,0.009452751,0.0065154363,0.009799355,0.0038133452,0.0060074185,0.013771674],"category_scores_gemma":[0.21440455,0.0011030093,0.0029813687,0.007240245,0.03506328,0.023552971,0.010232768,0.009175946,0.0014575225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013042044,0.000015369336,0.0003461567,0.00010237916,0.00003473927,0.00004214836,0.00064941344,0.0008646497,0.000023831886,0.9895167,0.00094882806,0.0074427472],"study_design_scores_gemma":[0.000009288323,0.0000071265767,0.00007695397,0.00010339924,0.000014143213,0.00002990645,0.00014542286,0.0019103038,0.000076229306,0.9916781,0.005939038,0.000010132367],"about_ca_topic_score_codex":0.003129998,"about_ca_topic_score_gemma":0.0019434172,"teacher_disagreement_score":0.11056996,"about_ca_system_score_codex":0.008375866,"about_ca_system_score_gemma":0.006817175,"threshold_uncertainty_score":0.58475685},"labels":[],"label_agreement":null},{"id":"W4353055688","doi":"10.3138/cjpe.75457","title":"Bridging Evaluation Theory and Practice: The Contributions of John Mayne to Canadian Federal Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bridging (networking); Thematic analysis; Function (biology); Government (linguistics); Conceptual framework; Sociology; Qualitative research; Computer science; Social science; Philosophy","score_opus":0.3228660608706075,"score_gpt":0.5747000820470364,"score_spread":0.2518340211764289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055688","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006413299,0.084770836,0.014177744,0.80094075,0.0063625164,0.000096247706,0.00007556104,0.000105606254,0.08705747],"genre_scores_gemma":[0.6239874,0.14021821,0.03846673,0.13542154,0.004349751,0.00027835643,0.0001167691,0.00052697427,0.05663438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9214914,0.032729793,0.0025998063,0.003585993,0.034250055,0.0053429613],"domain_scores_gemma":[0.7802609,0.09609828,0.0026759943,0.005650932,0.09777786,0.017535936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07577963,0.00062545517,0.00112563,0.009455103,0.024562448,0.023422955,0.0036303885,0.0053263716,0.0031604804],"category_scores_gemma":[0.1354606,0.0008084378,0.00059317675,0.012029676,0.046059053,0.0094134435,0.0077542383,0.011377949,0.0004890829],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000052127867,0.00006569827,0.0022898465,0.00067441136,0.00003661391,0.00023448293,0.03520521,0.0010653569,0.00017517465,0.63158286,0.20662294,0.1219952],"study_design_scores_gemma":[0.000009479981,0.00001752404,0.0022966308,0.0016664541,0.000023577802,0.0001138851,0.014632589,0.0007867453,0.00032862075,0.062251873,0.9177636,0.00010896984],"about_ca_topic_score_codex":0.922461,"about_ca_topic_score_gemma":0.9451082,"teacher_disagreement_score":0.922461,"about_ca_system_score_codex":0.20652553,"about_ca_system_score_gemma":0.3085327,"threshold_uncertainty_score":0.9203179},"labels":[],"label_agreement":null},{"id":"W4353055711","doi":"10.3138/cjpe.75429","title":"Enduring Themes in John Mayne’s Work: Implications for Evaluation Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Sophistication; Checklist; Work (physics); Elaboration; Accountability; Field (mathematics); Causality (physics); Sociology; Psychology; Engineering ethics; Political science; Social science; Engineering; Cognitive psychology","score_opus":0.5854453128611484,"score_gpt":0.6102911840352087,"score_spread":0.02484587117406023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055711","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023795722,0.015392708,0.12061098,0.80992424,0.0039955974,0.00038657617,0.00002810208,0.0001961588,0.02566993],"genre_scores_gemma":[0.6754308,0.014804501,0.19911996,0.09436904,0.002889481,0.0022830477,0.000038340288,0.00047314257,0.010591702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.60776675,0.32639366,0.013508838,0.011829979,0.034309193,0.006191589],"domain_scores_gemma":[0.4125699,0.4986364,0.009215788,0.013137988,0.053807136,0.012632697],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.33780456,0.00093699625,0.0017372626,0.008633319,0.017323839,0.030510938,0.008227175,0.010908685,0.0030066979],"category_scores_gemma":[0.36633798,0.0013492672,0.00129101,0.0075975955,0.08137706,0.037265696,0.019446151,0.024871489,0.0005978833],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001283225,0.00025074993,0.0024696307,0.0013785948,0.00006558555,0.00084838155,0.30057606,0.00073340023,0.00031774104,0.56784534,0.03407208,0.09131415],"study_design_scores_gemma":[0.000081542275,0.00014448566,0.0014987176,0.005403568,0.000042409367,0.0008790221,0.25269085,0.002116539,0.0008042387,0.49247092,0.2436549,0.00021268014],"about_ca_topic_score_codex":0.00929612,"about_ca_topic_score_gemma":0.017006373,"teacher_disagreement_score":0.33780456,"about_ca_system_score_codex":0.027135465,"about_ca_system_score_gemma":0.03437176,"threshold_uncertainty_score":0.81660485},"labels":[],"label_agreement":null},{"id":"W4362681378","doi":"10.3138/cjpe.18.001","title":"Evaluation and Research: Differences and Similarities","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Generalization; Similarity (geometry); Relevance (law); Causality (physics); Psychology; Management science; Computer science; Knowledge management; Epistemology; Artificial intelligence; Political science","score_opus":0.7713106731453503,"score_gpt":0.617815743068949,"score_spread":0.15349493007640125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362681378","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05236108,0.369868,0.16833471,0.12362511,0.0043699853,0.000952032,0.00016296034,0.0005296073,0.27979645],"genre_scores_gemma":[0.83474743,0.05263366,0.088347346,0.011847383,0.0028571207,0.0015618344,0.0001193724,0.0002777705,0.00760809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7925403,0.14698376,0.014032544,0.006481189,0.037384573,0.002577648],"domain_scores_gemma":[0.7568157,0.1918096,0.007609081,0.014760763,0.024842069,0.004162726],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.123062566,0.0006308706,0.002239551,0.013205047,0.0030140164,0.026801215,0.0021406729,0.00512289,0.0023200435],"category_scores_gemma":[0.134208,0.000998002,0.0009227682,0.010839574,0.055265427,0.02114664,0.011952315,0.0060090018,0.0007117789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010542877,0.0000955439,0.004842022,0.0019204539,0.00015133347,0.0002119237,0.030281678,0.00051451044,0.00030770633,0.7832203,0.0033687826,0.1749803],"study_design_scores_gemma":[0.000094765346,0.00025169476,0.01385329,0.006699387,0.00011452575,0.0011842789,0.03246838,0.001955837,0.00059362897,0.78927094,0.15337248,0.00014081817],"about_ca_topic_score_codex":0.002903111,"about_ca_topic_score_gemma":0.0022779817,"teacher_disagreement_score":0.87693745,"about_ca_system_score_codex":0.012311549,"about_ca_system_score_gemma":0.010362009,"threshold_uncertainty_score":0.65082484},"labels":[],"label_agreement":null},{"id":"W4362683297","doi":"10.3138/cjpe.18.006","title":"Creating Logic Models Using Grounded Theory: A Case Example Demonstrating a Unique Approach to Logic Model Development","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Saskatchewan Health; University of Regina; York University","funders":"","keywords":"Grounded theory; Logic model; Parallels; Computer science; Process (computing); Context (archaeology); Theory; Management science; Sociology; Qualitative research; Engineering; Programming language","score_opus":0.7082610594770602,"score_gpt":0.5253019207443822,"score_spread":0.182959138732678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14117575,0.00038628673,0.77547646,0.008634736,0.00017697281,0.004048949,0.0004228838,0.0008690014,0.06880899],"genre_scores_gemma":[0.24778642,0.00032202998,0.7461309,0.00036689785,0.000011956925,0.0011598066,0.00021474193,0.00012319519,0.0038841083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9813138,0.0141666,0.0005903524,0.00045157023,0.0029408908,0.00053664506],"domain_scores_gemma":[0.9606468,0.03389973,0.0006340655,0.0018777784,0.0024037466,0.00053786626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020176357,0.0008346762,0.0005711994,0.0023853658,0.004575332,0.0055410736,0.0026904356,0.0032781917,0.0054367217],"category_scores_gemma":[0.026640076,0.0005654506,0.001384138,0.0023423813,0.0040810383,0.005801058,0.0041467813,0.0037885427,0.00088112615],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004396576,0.0020260627,0.006152837,0.0017763994,0.00009656278,0.008121204,0.11914855,0.052957628,0.00584684,0.5145769,0.013309283,0.27554804],"study_design_scores_gemma":[0.0008050884,0.001179096,0.0021686193,0.0030556237,0.00020576915,0.0034710998,0.07692303,0.27703962,0.021672666,0.32383013,0.28927952,0.00036980477],"about_ca_topic_score_codex":0.0075833034,"about_ca_topic_score_gemma":0.013974404,"teacher_disagreement_score":0.020176357,"about_ca_system_score_codex":0.0060204417,"about_ca_system_score_gemma":0.008619748,"threshold_uncertainty_score":0.106704},"labels":[],"label_agreement":null},{"id":"W4362683298","doi":"10.3138/cjpe.18.005","title":"Theory-Driven Approach for Facilitation of Planning Health Promotion or Other Programs","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Theory of change; Promotion (chess); Computer science; Process management; Management science; Chen; Development theory; Facilitation; Program Design Language; Program evaluation; Knowledge management; Business; Political science; Software engineering; Management; Engineering; Economic growth; Economics","score_opus":0.6171863065840855,"score_gpt":0.5681104673795182,"score_spread":0.04907583920456726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008849455,0.00056346983,0.8988245,0.012198047,0.00026887425,0.0033754858,0.00016289395,0.00034443894,0.0754129],"genre_scores_gemma":[0.11483887,0.00041635794,0.8769212,0.0009598857,0.000038435654,0.003314116,0.0001553715,0.000044186883,0.0033115807],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95621955,0.035464272,0.00084864604,0.0012536693,0.0055727875,0.00064114534],"domain_scores_gemma":[0.9638103,0.025317488,0.0012239164,0.0031704467,0.0052890414,0.001188773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03994108,0.0017162355,0.0008029447,0.005711266,0.0027956339,0.004967142,0.004031329,0.0025241731,0.013548747],"category_scores_gemma":[0.033323567,0.00076350436,0.0014118805,0.002710567,0.0061662965,0.0039272048,0.005303507,0.0034649444,0.0017022751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015576869,0.0011057022,0.001929952,0.0021008311,0.0001349343,0.00046101626,0.010861064,0.023973886,0.001644802,0.74967444,0.012673051,0.19528459],"study_design_scores_gemma":[0.0005790837,0.0004939245,0.001483972,0.003065926,0.000114349044,0.00041826465,0.010263829,0.07441197,0.004593095,0.71620905,0.18823676,0.00012977145],"about_ca_topic_score_codex":0.0058116857,"about_ca_topic_score_gemma":0.01102204,"teacher_disagreement_score":0.03994108,"about_ca_system_score_codex":0.013176724,"about_ca_system_score_gemma":0.029112704,"threshold_uncertainty_score":0.21123117},"labels":[],"label_agreement":null},{"id":"W4362683301","doi":"10.3138/cjpe.18.002","title":"The Language of Evaluation Theory: Insights Gained from an Empirical Study of Evaluation Theory and Practice","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Terminology; Ambiguity; Confusion; Epistemology; Field (mathematics); Vernacular; Empirical research; Psychology; Linguistics; Sociology; Computer science; Philosophy","score_opus":0.28713025319252194,"score_gpt":0.573348207363572,"score_spread":0.28621795417105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7939139,0.0047317394,0.070011355,0.031430535,0.00017147866,0.0006976783,0.00008038101,0.000053735388,0.09890927],"genre_scores_gemma":[0.9942773,0.00052192126,0.004178576,0.00040706113,0.000015485943,0.00018361774,0.000013819758,0.000019547431,0.00038256013],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.81336135,0.15832564,0.0050665345,0.00291291,0.0175133,0.002820197],"domain_scores_gemma":[0.32132828,0.6346717,0.012962935,0.006425544,0.022536464,0.0020750784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15877683,0.00043520055,0.0011943261,0.006175108,0.0073646125,0.018921798,0.002082191,0.0027592897,0.003974317],"category_scores_gemma":[0.3476903,0.0007378128,0.00053318666,0.008225615,0.03621741,0.030651083,0.008654378,0.0073628384,0.0003907696],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001555991,0.00064484816,0.029242799,0.0010042235,0.00003916336,0.00047395236,0.5975813,0.0010752098,0.00040996863,0.30548447,0.0017544904,0.06213391],"study_design_scores_gemma":[0.000098904704,0.00037515778,0.025789592,0.004432948,0.000060020146,0.0004179041,0.7691315,0.009867581,0.0011817665,0.16889247,0.019653527,0.000098677265],"about_ca_topic_score_codex":0.00785162,"about_ca_topic_score_gemma":0.0072190505,"teacher_disagreement_score":0.15877683,"about_ca_system_score_codex":0.017216818,"about_ca_system_score_gemma":0.014890513,"threshold_uncertainty_score":0.8397022},"labels":[],"label_agreement":null},{"id":"W4362683305","doi":"10.3138/cjpe.18.003","title":"Évaluation de l’implantation et des effets d’un programme de soutien intensif offert à des familles afin d’éviter un placement en milieu substitut","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Family and Disability Support Research","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Intervention (counseling); Valuation (finance); Psychology; Business; Psychiatry; Accounting","score_opus":0.1623021320775699,"score_gpt":0.4070604209747124,"score_spread":0.2447582888971425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99391794,0.0004421361,0.00048416428,0.00029055635,0.00006456127,0.0024255242,0.00008775728,0.0000319585,0.0022553361],"genre_scores_gemma":[0.9863987,0.0010206118,0.0050705066,0.00014942502,0.0001128143,0.004567836,0.00018582169,0.00001040317,0.0024838753],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99602026,0.0024443557,0.00019646765,0.00030370592,0.00048541793,0.00054983137],"domain_scores_gemma":[0.9931144,0.003932737,0.00075722416,0.00028393278,0.00046796582,0.0014437337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048913737,0.00084946613,0.00065189076,0.00094431534,0.0013238146,0.0005541378,0.0011199504,0.0013602847,0.008781241],"category_scores_gemma":[0.009775139,0.00042882957,0.0008696889,0.0006221309,0.0010036578,0.0005268699,0.0010948187,0.0012366793,0.00037044397],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12727346,0.22565708,0.02278446,0.0041614347,0.00075583224,0.00078738865,0.008765495,0.003598534,0.0067957044,0.0011780704,0.001787923,0.5964546],"study_design_scores_gemma":[0.06869621,0.72284096,0.17627326,0.0013460591,0.0012182437,0.00032214125,0.0040024924,0.0029761305,0.011997827,0.00060413097,0.009607984,0.000114621216],"about_ca_topic_score_codex":0.015136421,"about_ca_topic_score_gemma":0.020950636,"teacher_disagreement_score":0.015136421,"about_ca_system_score_codex":0.0023889998,"about_ca_system_score_gemma":0.003861063,"threshold_uncertainty_score":0.03009665},"labels":[],"label_agreement":null},{"id":"W4362683309","doi":"10.3138/cjpe.18.004","title":"User-Friendly Evaluation in Community-Based Projects","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); User Friendly; Evaluation methods; Program evaluation; Process management; User group; Computer science; Psychology; Knowledge management; Management science; Business; Political science; Multimedia; Engineering","score_opus":0.4381303297538949,"score_gpt":0.5384420399654519,"score_spread":0.10031171021155705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5736324,0.002772765,0.26936597,0.008618257,0.0005612325,0.027554879,0.0003490241,0.0031902536,0.113955304],"genre_scores_gemma":[0.7947211,0.00068198063,0.18409751,0.0008362569,0.0001471238,0.01364723,0.00021347654,0.00028056803,0.00537476],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.48478484,0.4848086,0.0072437315,0.0024914853,0.017414037,0.0032572865],"domain_scores_gemma":[0.51669514,0.3918759,0.01526204,0.024066288,0.04208059,0.010020097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.29656377,0.0017182825,0.0013610033,0.003968962,0.004446851,0.009297197,0.003804805,0.0037889404,0.006544229],"category_scores_gemma":[0.31040108,0.00082838966,0.00094605837,0.0036983148,0.0038563474,0.0064286566,0.009180677,0.002951166,0.0016303151],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052058017,0.012622309,0.03235882,0.0059185955,0.00031706513,0.0028657739,0.14315733,0.010941585,0.0044801384,0.03385312,0.033392973,0.7148865],"study_design_scores_gemma":[0.010058207,0.045229547,0.10258288,0.017119208,0.00082623435,0.0058531943,0.12114919,0.06267625,0.039041117,0.11122268,0.48273873,0.0015027587],"about_ca_topic_score_codex":0.0024198624,"about_ca_topic_score_gemma":0.0038289968,"teacher_disagreement_score":0.29656377,"about_ca_system_score_codex":0.0055044484,"about_ca_system_score_gemma":0.0075681787,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4362683351","doi":"10.3138/cjpe.18.007","title":"Développement d’un cadre de classement des résultats de la réadaptation pour documenter la progression des clientèles","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre de réadaptation Lethbridge-Layton-Mackay","funders":"","keywords":"Psychology; Adaptation (eye)","score_opus":0.06244379687016339,"score_gpt":0.4040100609250905,"score_spread":0.3415662640549271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683351","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8630312,0.0023021898,0.07140374,0.0032548297,0.0005251624,0.0038337954,0.0059587006,0.0042499653,0.045440402],"genre_scores_gemma":[0.8817503,0.0010129833,0.094358094,0.00017448084,0.00012217523,0.0028029727,0.00295524,0.00028234144,0.016541485],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993359,0.002065113,0.0009234435,0.00058089587,0.0027310336,0.00034050195],"domain_scores_gemma":[0.9569574,0.014053964,0.005429104,0.0029567366,0.019536333,0.0010664883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019668175,0.0008232739,0.00072706974,0.005980163,0.0010387666,0.002925452,0.0015217186,0.00085564464,0.0073198713],"category_scores_gemma":[0.046972077,0.00036062457,0.0008441001,0.0018631057,0.0005778097,0.0027746074,0.0010646462,0.00071505865,0.0019092625],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007441295,0.0009814971,0.15924421,0.00091734057,0.00013941966,0.00017560307,0.009079057,0.0017953258,0.004139783,0.0012377066,0.010995565,0.8105504],"study_design_scores_gemma":[0.0003692959,0.0030385102,0.8685274,0.00162796,0.00057428784,0.0005314608,0.007129866,0.023232536,0.028760081,0.0012691546,0.06466213,0.00027735016],"about_ca_topic_score_codex":0.03489475,"about_ca_topic_score_gemma":0.031076107,"teacher_disagreement_score":0.03489475,"about_ca_system_score_codex":0.0039604246,"about_ca_system_score_gemma":0.0039228667,"threshold_uncertainty_score":0.10401648},"labels":[],"label_agreement":null},{"id":"W4362688850","doi":"10.3138/cjpe.015.007","title":"Lessons Learned from Establishing a Research and Evaluation Unit for a Regional Health Authority","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba; Winnipeg Regional Health Authority","funders":"","keywords":"Unit (ring theory); Service (business); Health authority; Health services; Health care; Business; Service delivery framework; Community service; Local authority; Public relations; Nursing; Environmental planning; Political science; Public administration; Medicine; Environmental health; Psychology; Geography; Marketing","score_opus":0.7824261501085263,"score_gpt":0.6474805479731992,"score_spread":0.13494560213532714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362688850","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019795071,0.006863557,0.018193558,0.92789173,0.0056388774,0.003169291,0.0001436734,0.00034111057,0.01796314],"genre_scores_gemma":[0.49335954,0.011366007,0.2553384,0.19554898,0.0059652226,0.007472973,0.0006138274,0.00037618654,0.029958837],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.83063924,0.11111126,0.012139916,0.00581442,0.022789234,0.017505905],"domain_scores_gemma":[0.572844,0.11532875,0.012220099,0.0228427,0.14086692,0.13589738],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2587361,0.0011942459,0.0011184908,0.002934695,0.01499062,0.017971536,0.010575327,0.014006623,0.006950898],"category_scores_gemma":[0.21044187,0.0015618518,0.0018923997,0.0027085957,0.011226031,0.015898094,0.0127388425,0.02178984,0.0015589524],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000725948,0.004714044,0.037661627,0.0051250868,0.00026780303,0.008210781,0.041921835,0.005309258,0.0029337176,0.13891397,0.33859277,0.41562313],"study_design_scores_gemma":[0.0017083626,0.0041473843,0.050309274,0.013336712,0.0003459042,0.004250578,0.09474301,0.0072282976,0.0032757171,0.031971034,0.7878746,0.0008090965],"about_ca_topic_score_codex":0.28392652,"about_ca_topic_score_gemma":0.45708352,"teacher_disagreement_score":0.9591398,"about_ca_system_score_codex":0.040860176,"about_ca_system_score_gemma":0.30618003,"threshold_uncertainty_score":0.91411036},"labels":[],"label_agreement":null},{"id":"W4362688871","doi":"10.3138/cjpe.015.001","title":"Answering the <i>Why</i> Question in Evaluation: The Causal-Model Approach","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Casual; Terminology; Causal model; Outcome (game theory); Test (biology); Intervention (counseling); Contrast (vision); Computer science; Psychology; Management science; Artificial intelligence; Economics; Political science; Linguistics; Medicine; Microeconomics","score_opus":0.38287591332918275,"score_gpt":0.5196684715095707,"score_spread":0.136792558180388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362688871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026389156,0.020134034,0.56177133,0.33306313,0.0017759681,0.0019427047,0.00033174973,0.00029922312,0.054292705],"genre_scores_gemma":[0.80327225,0.00681331,0.16904363,0.015713014,0.0010386427,0.0025988491,0.00008285723,0.00006435136,0.001373157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80026406,0.17981037,0.0034690297,0.0031627065,0.0118036745,0.0014902015],"domain_scores_gemma":[0.5308201,0.44149646,0.0074055027,0.008129973,0.010574037,0.0015739417],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17708892,0.0012370675,0.0020828866,0.0058477484,0.0036421884,0.009686875,0.0033280854,0.009642573,0.0053707617],"category_scores_gemma":[0.31656626,0.00083587767,0.0015642756,0.0046113776,0.032734346,0.018068545,0.0043844446,0.008258863,0.00048839895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022189479,0.00029411566,0.0027232985,0.0017473687,0.00019718385,0.00013890259,0.002115453,0.0079652015,0.000111610716,0.9087936,0.0068872254,0.06880413],"study_design_scores_gemma":[0.00015393355,0.000114049704,0.0006343093,0.0010774361,0.0000832559,0.000058789556,0.0012570709,0.012815644,0.0002700992,0.97865,0.004845407,0.00004001876],"about_ca_topic_score_codex":0.00710231,"about_ca_topic_score_gemma":0.0054213894,"teacher_disagreement_score":0.8229111,"about_ca_system_score_codex":0.013068398,"about_ca_system_score_gemma":0.013755019,"threshold_uncertainty_score":0.9365469},"labels":[],"label_agreement":null},{"id":"W4362688961","doi":"10.3138/cjpe.015.002","title":"Towards Sustainability of Human Services: Assessing Community Self-Determination and Self-Reliance","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sustainability; Negotiation; Dependency (UML); Process (computing); Accountability; Process management; Relevance (law); Knowledge management; Human resources; Environmental resource management; Business; Psychology; Computer science; Political science; Ecology; Economics","score_opus":0.21373330538929033,"score_gpt":0.5275247607142796,"score_spread":0.3137914553249892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362688961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9765069,0.00014765117,0.0068526696,0.00046741616,0.000012303999,0.00050577807,0.00011054386,0.00004350846,0.015353226],"genre_scores_gemma":[0.9952034,0.00006318058,0.0042377026,0.000028669123,0.0000025682846,0.00016319579,0.000062039326,0.0000029071243,0.00023627272],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98684305,0.0067950576,0.0009310939,0.00034118365,0.0045480398,0.0005416353],"domain_scores_gemma":[0.9601855,0.013531902,0.007611511,0.0016020177,0.013687757,0.0033812467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020852624,0.0003458625,0.00036423226,0.0048078103,0.002132011,0.0033129754,0.0007061616,0.00070643926,0.0010317443],"category_scores_gemma":[0.045349576,0.0002488208,0.0006355894,0.0025906428,0.0024657182,0.0025239259,0.004165336,0.0010713827,0.00016335439],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009790303,0.00058338494,0.86631316,0.00028522496,0.00016367239,0.0000748021,0.018607164,0.0033669595,0.00048150602,0.0060136737,0.0009678601,0.103044786],"study_design_scores_gemma":[0.000030987387,0.0012207475,0.8695447,0.00060225243,0.00012791074,0.00025095657,0.07319398,0.024023084,0.0034844193,0.017591607,0.009777078,0.00015216047],"about_ca_topic_score_codex":0.011056899,"about_ca_topic_score_gemma":0.017946297,"teacher_disagreement_score":0.020852624,"about_ca_system_score_codex":0.005032762,"about_ca_system_score_gemma":0.0075012073,"threshold_uncertainty_score":0.110280514},"labels":[],"label_agreement":null},{"id":"W4362689123","doi":"10.3138/cjpe.015.005","title":"The Redesign of Advanced Patrol Training for Police Constables in Ontario: Making Use of Evaluation to Maximize Organizational Effectiveness and Efficiency","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Nipissing University","funders":"","keywords":"Training (meteorology); Curriculum; Operations management; Business; Medical education; Engineering management; Psychology; Engineering; Medicine; Pedagogy","score_opus":0.31680565738729644,"score_gpt":0.48073747035389924,"score_spread":0.1639318129666028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94510627,0.002057357,0.013809386,0.004489256,0.00007757907,0.011307621,0.00035186825,0.00029827972,0.02250235],"genre_scores_gemma":[0.9704077,0.00078676024,0.024291825,0.00024106783,0.00002311603,0.0012134283,0.00022784676,0.000018490691,0.0027897274],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9780189,0.009857359,0.0010728417,0.0007231081,0.008648102,0.0016796308],"domain_scores_gemma":[0.9639287,0.00971283,0.0064543015,0.0015311622,0.015054154,0.0033188174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01893004,0.00054500566,0.00042146543,0.0020729918,0.002813156,0.002279877,0.0015492995,0.0005068419,0.0016263911],"category_scores_gemma":[0.04542879,0.00047696233,0.00041767696,0.0016315705,0.0013779032,0.0013547938,0.0018134442,0.0008994841,0.00014312893],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023857276,0.0023092225,0.084412895,0.002428159,0.00016140245,0.0003389627,0.0071351556,0.020036057,0.0067936713,0.0022993982,0.00626992,0.8654294],"study_design_scores_gemma":[0.002245762,0.009413543,0.85757655,0.0016885925,0.0003609237,0.000288959,0.015040777,0.045011196,0.020015305,0.0024030781,0.04565539,0.00029992018],"about_ca_topic_score_codex":0.5871513,"about_ca_topic_score_gemma":0.7140253,"teacher_disagreement_score":0.4128487,"about_ca_system_score_codex":0.05604041,"about_ca_system_score_gemma":0.09482853,"threshold_uncertainty_score":0.8305601},"labels":[],"label_agreement":null},{"id":"W4362689189","doi":"10.3138/cjpe.16.007","title":"Modelling Success: Articulating Program Impact Theory","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Geriatric Care and Nursing Homes","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Process (computing); Service delivery framework; Program evaluation; Service (business); Health care delivery; Psychology; Nursing; Health services; Health care; Primary care; Process management; Business; Public relations; Marketing; Medicine; Computer science; Family medicine; Economic growth; Political science; Environmental health; Economics","score_opus":0.19285734359323395,"score_gpt":0.4991095940645385,"score_spread":0.30625225047130455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689189","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20487037,0.00036720542,0.6189771,0.0078942645,0.00009637642,0.00071798166,0.0003139551,0.00022494562,0.16653772],"genre_scores_gemma":[0.95552236,0.00018466785,0.04172433,0.00011548628,0.000025003234,0.00038346153,0.00009052441,0.00004807848,0.0019059682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915035,0.0058584283,0.00023617776,0.0005104247,0.0010754988,0.0008160209],"domain_scores_gemma":[0.9548757,0.03942498,0.0016936294,0.0011685396,0.0018748557,0.000962178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011411489,0.0010516765,0.00070035626,0.0029664594,0.0011812296,0.004427091,0.0029413034,0.0020830708,0.010163133],"category_scores_gemma":[0.05678187,0.0005441658,0.0010571778,0.001901426,0.0053383796,0.0063245604,0.0049946434,0.0025767316,0.00054267095],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006032371,0.00031691484,0.014452891,0.0002103381,0.000083161416,0.00016737405,0.003136428,0.19266254,0.0001097358,0.7633564,0.0012466244,0.024197323],"study_design_scores_gemma":[0.00005934259,0.00021544597,0.0027575337,0.00024528033,0.000062880994,0.00007685876,0.003583644,0.5302449,0.0002598061,0.45692137,0.005540894,0.000032166063],"about_ca_topic_score_codex":0.00882633,"about_ca_topic_score_gemma":0.0051272255,"teacher_disagreement_score":0.011411489,"about_ca_system_score_codex":0.0045213825,"about_ca_system_score_gemma":0.003918827,"threshold_uncertainty_score":0.060350418},"labels":[],"label_agreement":null},{"id":"W4362689217","doi":"10.3138/cjpe.16.002","title":"Methodological Challenges in Evaluating Mobile Crisis Psychiatric Programs","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychiatric care and mental health services","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Psychological intervention; Psychology; Politics; Service delivery framework; Service (business); Psychiatry; Public relations; Political science; Business; Marketing","score_opus":0.5990355893588402,"score_gpt":0.5543964611722118,"score_spread":0.04463912818662841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689217","genre_codex":"methods","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18669464,0.025482837,0.52079374,0.030397449,0.007826338,0.1678721,0.00352627,0.00041437722,0.05699227],"genre_scores_gemma":[0.38217106,0.0022835615,0.36037928,0.006002651,0.0010275071,0.2456891,0.000747815,0.0001141176,0.001584863],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.15671073,0.7352041,0.056666587,0.0061068307,0.043782137,0.0015296196],"domain_scores_gemma":[0.1909415,0.6470674,0.04195408,0.032852296,0.08456226,0.002622488],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6125932,0.0020135764,0.0030681898,0.006937239,0.004771638,0.00816888,0.0076040234,0.0031222159,0.0039853826],"category_scores_gemma":[0.7794129,0.0016994916,0.0029121866,0.008832702,0.009503143,0.0047488855,0.008705749,0.0038893174,0.0006531264],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009390344,0.005686031,0.12320237,0.039812505,0.007995822,0.0009816511,0.0474883,0.01591706,0.0022581283,0.13905941,0.02327868,0.5849297],"study_design_scores_gemma":[0.016390787,0.02771954,0.1795987,0.059706677,0.009929897,0.0018765087,0.072616704,0.06051982,0.01745425,0.3483966,0.20422888,0.0015617154],"about_ca_topic_score_codex":0.012729154,"about_ca_topic_score_gemma":0.018482395,"teacher_disagreement_score":0.6125932,"about_ca_system_score_codex":0.012169838,"about_ca_system_score_gemma":0.021162665,"threshold_uncertainty_score":0.47774166},"labels":[],"label_agreement":null},{"id":"W4362689219","doi":"10.3138/cjpe.16.005","title":"Insurance Claimants Working While on Claim","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Employment and Welfare Studies","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Employment and Social Development Canada","funders":"","keywords":"Unemployment; Work (physics); Actuarial science; Business; Labour economics; Insurance policy; Economics; Economic growth","score_opus":0.3355999945586563,"score_gpt":0.4889647120288136,"score_spread":0.15336471747015729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956501,0.00014987742,0.000053942695,0.00013857098,0.000020327989,0.000064281536,0.0007035608,0.0000049029245,0.0032145167],"genre_scores_gemma":[0.9955402,0.0001465177,0.00008664196,0.00007460575,0.000018090337,0.000057573543,0.0008761793,0.0000015811382,0.003198596],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990183,0.00012939503,0.00007347284,0.000073623785,0.0003045504,0.0004006333],"domain_scores_gemma":[0.99606687,0.00058970693,0.0013729833,0.00016246307,0.0007791499,0.0010287928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012941504,0.00023002655,0.0003490374,0.0012878806,0.0018059657,0.0009607335,0.0005357264,0.00047757901,0.0073330486],"category_scores_gemma":[0.0047791624,0.00012418699,0.00046058066,0.000759185,0.000399479,0.0003976799,0.0010209968,0.0007165328,0.0011579446],"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":[0.0009586141,0.0011780342,0.9480318,0.000178909,0.00008008634,0.0003650262,0.0050935964,0.0001410022,0.0016706598,0.00043885183,0.002933545,0.03892995],"study_design_scores_gemma":[0.000028360004,0.00066051015,0.9873104,0.00007437542,0.000065071465,0.00021046694,0.00626633,0.00018591061,0.00083237677,0.0000876722,0.0042670555,0.000011493521],"about_ca_topic_score_codex":0.06085821,"about_ca_topic_score_gemma":0.0727415,"teacher_disagreement_score":0.06085821,"about_ca_system_score_codex":0.0009167468,"about_ca_system_score_gemma":0.0018798,"threshold_uncertainty_score":0.12100798},"labels":[],"label_agreement":null},{"id":"W4362689223","doi":"10.3138/cjpe.015.008","title":"Focusing on Inputs, Outputs, and Outcomes: Are International Approaches to Performance Management Really so Different?","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Logic model; Process (computing); Service (business); Focus (optics); Key (lock); Performance measurement; Process management; Performance management; Business; Public relations; Knowledge management; Computer science; Political science; Public administration; Marketing; Computer security","score_opus":0.45225536612016,"score_gpt":0.4616739906963755,"score_spread":0.009418624576215506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689223","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01926709,0.0713657,0.06995678,0.34937456,0.0035568047,0.00015386139,0.00054953515,0.0003036582,0.48547196],"genre_scores_gemma":[0.85554415,0.05017244,0.054452427,0.02642848,0.002181736,0.0004976882,0.00050189736,0.0005444985,0.009676696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.928378,0.04081659,0.00430479,0.00409946,0.018266171,0.004135046],"domain_scores_gemma":[0.8940941,0.04313762,0.0056174025,0.0077384617,0.045773845,0.0036385776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07402938,0.0014043876,0.0018745745,0.012765076,0.0058376472,0.02587156,0.0030525548,0.0027498088,0.004899557],"category_scores_gemma":[0.089371055,0.00049490057,0.0010052157,0.020451367,0.036182288,0.018051784,0.006229768,0.010067056,0.0008307671],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007456103,0.000066697394,0.0055800034,0.001164378,0.000119768505,0.00004467861,0.009969717,0.0012107155,0.00027758876,0.7994596,0.01996934,0.16206294],"study_design_scores_gemma":[0.00006413359,0.00024066927,0.041872486,0.016059719,0.00060542725,0.00022848036,0.060728047,0.0040859636,0.0028314355,0.588431,0.28444928,0.00040331625],"about_ca_topic_score_codex":0.22106037,"about_ca_topic_score_gemma":0.2238961,"teacher_disagreement_score":0.22106037,"about_ca_system_score_codex":0.05174086,"about_ca_system_score_gemma":0.0429977,"threshold_uncertainty_score":0.4395473},"labels":[],"label_agreement":null},{"id":"W4362689327","doi":"10.3138/cjpe.16.001","title":"Using the Right Tools to Answer the Right Questions: The Importance of Evaluative Research Techniques for Health Services Evaluation Research in the 21st Century","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Rubric; Causal inference; Affect (linguistics); Accountability; Health care; Psychology; Causal model; Inference; Health policy; Health services research; Applied psychology; Public relations; Social psychology; Management science; Political science; Computer science; Medicine; Economics; Mathematics education; Econometrics","score_opus":0.6435564373162587,"score_gpt":0.6614983899363868,"score_spread":0.0179419526201281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689327","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004673389,0.016342215,0.84689665,0.10721523,0.0030014624,0.0032230576,0.00026210732,0.00059335347,0.017792586],"genre_scores_gemma":[0.122722246,0.0057902443,0.8514787,0.009589751,0.0013050366,0.008115089,0.00007763425,0.0003033314,0.0006179843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.23773749,0.7040275,0.020787634,0.005820031,0.030186782,0.0014404963],"domain_scores_gemma":[0.08340097,0.8443094,0.01327344,0.03185972,0.025330221,0.0018262742],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.66071457,0.002614674,0.0072372304,0.013751676,0.0059331614,0.032953672,0.0063835615,0.008490528,0.0057382393],"category_scores_gemma":[0.75164026,0.002133241,0.0032781654,0.010439071,0.047986675,0.03792615,0.012121111,0.025167923,0.001459647],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022700202,0.00056208996,0.0026077502,0.0063548773,0.00069515366,0.0001333747,0.016958302,0.004001474,0.00042310084,0.692769,0.019755151,0.2555128],"study_design_scores_gemma":[0.00032745607,0.00018993801,0.0011934523,0.010318747,0.00014800177,0.00011331618,0.00624336,0.010096753,0.0007830879,0.94180506,0.028563062,0.00021773466],"about_ca_topic_score_codex":0.003002815,"about_ca_topic_score_gemma":0.0025018954,"teacher_disagreement_score":0.66071457,"about_ca_system_score_codex":0.01191866,"about_ca_system_score_gemma":0.028044097,"threshold_uncertainty_score":0.4183994},"labels":[],"label_agreement":null},{"id":"W4362689335","doi":"10.3138/cjpe.16.004","title":"Accountability, Rationality, and New Structures of Governance: Making Room for Political Rationality","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Accountability; Rationality; Agency (philosophy); Politics; Bureaucracy; Law and economics; Corporate governance; Technocracy; Parliament; Mandate; Political science; Sociology; Economics; Public relations; Public administration; Positive economics; Law; Social science; Finance","score_opus":0.518764035540208,"score_gpt":0.5838040393902938,"score_spread":0.06504000385008579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689335","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08665797,0.005520474,0.19331232,0.24500985,0.0010302012,0.0001621408,0.00007126332,0.00023723514,0.4679986],"genre_scores_gemma":[0.9777002,0.0008349152,0.012795431,0.002767219,0.0003087234,0.000112357135,0.00002165725,0.000048177415,0.005411368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9700228,0.019362174,0.00072375726,0.0023463303,0.004828784,0.002716112],"domain_scores_gemma":[0.95267284,0.02885438,0.0040297406,0.0070081274,0.0045875995,0.002847359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03860897,0.0004157771,0.0006170739,0.001974634,0.00559973,0.015046579,0.0018794226,0.0040171957,0.003516693],"category_scores_gemma":[0.03204595,0.00045272175,0.00069354265,0.0014421921,0.07787363,0.016274361,0.007643233,0.0073672268,0.0004635491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070119545,0.000007384857,0.00022132102,0.0000135228065,0.000004667028,0.000013391672,0.0011443467,0.0005350917,0.00003432557,0.99465203,0.0006498049,0.0027170484],"study_design_scores_gemma":[0.000022712815,0.000009750018,0.00031465926,0.00006397009,0.0000058404366,0.000010466948,0.00064124557,0.0009405048,0.00009014529,0.9817231,0.016166223,0.000011486915],"about_ca_topic_score_codex":0.008445866,"about_ca_topic_score_gemma":0.008006617,"teacher_disagreement_score":0.03860897,"about_ca_system_score_codex":0.013311012,"about_ca_system_score_gemma":0.016219862,"threshold_uncertainty_score":0.2041862},"labels":[],"label_agreement":null},{"id":"W4362689338","doi":"10.3138/cjpe.015.006","title":"Contributions of Evaluation Research to the Development of Community Policing in a Canadian City","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Windsor; Service (business); Community service; Population; Sociology; Political science; Business; Demography; Public relations; Marketing","score_opus":0.6536296981549493,"score_gpt":0.636219151212957,"score_spread":0.01741054694199229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41901508,0.20595405,0.02552005,0.0558854,0.001125393,0.0045111924,0.001041434,0.0001848884,0.28676257],"genre_scores_gemma":[0.9600518,0.023594497,0.012954673,0.0011204414,0.00012945953,0.00069260073,0.00014716081,0.000025867495,0.0012836512],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.88144964,0.0793822,0.0061763152,0.0022965702,0.027386913,0.0033083814],"domain_scores_gemma":[0.6347789,0.19941281,0.020425696,0.0094315605,0.12820175,0.0077492427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1422812,0.00069873664,0.0015592664,0.015491716,0.0060877907,0.012023352,0.0029045038,0.001009964,0.0017118892],"category_scores_gemma":[0.21346238,0.00060099154,0.0005863433,0.02040997,0.010307361,0.0043585626,0.004351165,0.0022988084,0.000093716495],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039102748,0.0007074377,0.108698286,0.008984902,0.0005810484,0.0002376103,0.050773896,0.0038168044,0.00027431527,0.06400208,0.008920151,0.7526124],"study_design_scores_gemma":[0.00037156764,0.001208224,0.56590164,0.03742224,0.0009158473,0.0003735264,0.13949317,0.012690263,0.0029372561,0.042724088,0.19540837,0.0005539025],"about_ca_topic_score_codex":0.817817,"about_ca_topic_score_gemma":0.82373494,"teacher_disagreement_score":0.18218303,"about_ca_system_score_codex":0.1166715,"about_ca_system_score_gemma":0.20409213,"threshold_uncertainty_score":0.84651494},"labels":[],"label_agreement":null},{"id":"W4366382532","doi":"10.3138/cjpe.31132","title":"Moving Beyond the Buzzword: A Framework for Teaching Culturally Responsive Approaches to Evaluation","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conceptual framework; Competence (human resources); Cultural competence; Sociology; Domain (mathematical analysis); Knowledge management; Computer science; Engineering ethics; Psychology; Pedagogy; Social psychology; Social science; Engineering","score_opus":0.6407724104552023,"score_gpt":0.5597165071488638,"score_spread":0.0810559033063385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366382532","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068024104,0.0026137577,0.8158563,0.06487997,0.000704396,0.0011627574,0.000078947836,0.00069188926,0.10720955],"genre_scores_gemma":[0.18533695,0.0022649097,0.7975312,0.00393203,0.00015702438,0.0019117768,0.00009172709,0.0003028673,0.008471456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9295334,0.060570523,0.0019803573,0.0013807394,0.004870213,0.0016647807],"domain_scores_gemma":[0.93010575,0.04954509,0.0015892719,0.0038595195,0.010377136,0.0045232307],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07858788,0.0014792884,0.001024814,0.0059077917,0.008998682,0.014829419,0.0046965107,0.0047757546,0.0051193265],"category_scores_gemma":[0.05447143,0.0009083378,0.0012390988,0.0036218832,0.035574775,0.013672595,0.008342273,0.010645579,0.0014041261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019985597,0.00012943229,0.0005295515,0.00029462087,0.000007910486,0.00013509841,0.031436276,0.0010978141,0.0004015137,0.91158235,0.009194953,0.04517048],"study_design_scores_gemma":[0.000053200827,0.000081366576,0.00056754914,0.002731179,0.00002495852,0.000235442,0.026874837,0.007203903,0.0012489833,0.71830285,0.24258947,0.000086152024],"about_ca_topic_score_codex":0.048736982,"about_ca_topic_score_gemma":0.07509736,"teacher_disagreement_score":0.9680924,"about_ca_system_score_codex":0.031907625,"about_ca_system_score_gemma":0.046898596,"threshold_uncertainty_score":0.4156174},"labels":[],"label_agreement":null},{"id":"W4366382683","doi":"10.3138/cjpe.20.005","title":"Evaluator Competencies and Performance Development","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reflection (computer programming); Human resources; Knowledge management; Foundation (evidence); Resource (disambiguation); Context (archaeology); Computer science; Process management; Professional development; Engineering ethics; Management science; Psychology; Business; Management; Engineering; Political science; Pedagogy","score_opus":0.10252947695831835,"score_gpt":0.36862357064743084,"score_spread":0.2660940936891125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366382683","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1706699,0.003470651,0.10950842,0.0319564,0.00037685028,0.00074546866,0.00026357837,0.00084252213,0.6821662],"genre_scores_gemma":[0.9483946,0.0011401715,0.035062466,0.0010847787,0.00006372048,0.00038423657,0.00012458541,0.000108894594,0.013636414],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95498353,0.03410564,0.0014671874,0.00130949,0.00653484,0.0015993549],"domain_scores_gemma":[0.9040763,0.054209378,0.0068134163,0.0039292253,0.02260883,0.008362996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036800385,0.0004166315,0.00032093283,0.002977019,0.0029090205,0.0075760186,0.0008262663,0.00101827,0.010225672],"category_scores_gemma":[0.09289801,0.0003015481,0.00018802588,0.0013901792,0.0051749996,0.0043838914,0.006319078,0.0022235075,0.0014468865],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021759786,0.0007367724,0.07631443,0.00086583965,0.000066821805,0.0002549913,0.042350452,0.0029168546,0.0010090393,0.39492297,0.035539668,0.44480464],"study_design_scores_gemma":[0.00022868894,0.0012207938,0.14453377,0.0065833847,0.0001299584,0.0014505978,0.056646243,0.020671338,0.014027164,0.27757007,0.47664946,0.00028856684],"about_ca_topic_score_codex":0.004780315,"about_ca_topic_score_gemma":0.0037225822,"teacher_disagreement_score":0.036800385,"about_ca_system_score_codex":0.007065083,"about_ca_system_score_gemma":0.018435635,"threshold_uncertainty_score":0.19462138},"labels":[],"label_agreement":null},{"id":"W4366382770","doi":"10.3138/cjpe.20.004","title":"Editor’s Introduction","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Posthumanist Ethics and Activism","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Psychology","score_opus":0.08470903683142299,"score_gpt":0.4034651812112244,"score_spread":0.3187561443798014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366382770","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006343901,0.0021238464,0.000101095065,0.081962526,0.9120394,0.000037736314,0.00013374248,0.000048319693,0.0034899577],"genre_scores_gemma":[0.0016872665,0.002945481,0.00042178202,0.20069452,0.72585404,0.0001396266,0.0001364014,0.00008354081,0.06803732],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918568,0.0011463499,0.0009165321,0.0010522096,0.004214285,0.0008137968],"domain_scores_gemma":[0.9530787,0.010562338,0.003377122,0.0022237974,0.0251928,0.005565204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010284554,0.002131805,0.0022278416,0.004021886,0.003130818,0.0057921237,0.0038500342,0.014910656,0.05652111],"category_scores_gemma":[0.0588133,0.00092398626,0.0027060413,0.0018582748,0.0019303132,0.002825798,0.0019532533,0.012140792,0.02279903],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017217279,0.0000064607234,0.000033791774,0.0000952627,0.0000075313046,0.000060328948,0.0000075681464,0.000010982035,0.000025910214,0.0001810698,0.99605656,0.003497207],"study_design_scores_gemma":[0.00003777631,0.00001706047,0.0004906755,0.0003181386,0.000031592677,0.00013515605,0.00004440482,0.000055313732,0.00010669284,0.00045506758,0.99829155,0.000016610888],"about_ca_topic_score_codex":0.0044222586,"about_ca_topic_score_gemma":0.010169673,"teacher_disagreement_score":0.05652111,"about_ca_system_score_codex":0.004041715,"about_ca_system_score_gemma":0.006436166,"threshold_uncertainty_score":0.18908197},"labels":[],"label_agreement":null},{"id":"W4366383281","doi":"10.3138/cjpe.20.003","title":"Réflexions autour d’une typologie des dispositifs institutionnels d’évaluation","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Institutionalisation; Typology; Openness to experience; Valuation (finance); Sociology; Ideal (ethics); Institutionalism; Political science; Epistemology; Philosophy; Economics; Psychology; Accounting; Law; Social psychology","score_opus":0.19847712031970613,"score_gpt":0.42835684704099247,"score_spread":0.22987972672128634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22256866,0.0071638376,0.44714314,0.046097215,0.0006527928,0.000760158,0.00071603915,0.0010611892,0.27383712],"genre_scores_gemma":[0.94481385,0.0009367116,0.049493134,0.000531841,0.00013936049,0.00051806605,0.000120597935,0.00017393251,0.0032724428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8312267,0.10976239,0.011983877,0.00897301,0.033345453,0.0047086035],"domain_scores_gemma":[0.6968721,0.20104451,0.019075124,0.03897955,0.040348593,0.0036800352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.107565664,0.0009561609,0.0009978128,0.010820444,0.0063492437,0.029213374,0.0020942092,0.004894132,0.007842625],"category_scores_gemma":[0.18856573,0.0010645523,0.0017358523,0.009455636,0.033187333,0.02945076,0.008464363,0.005652681,0.0009110885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058391834,0.000047709542,0.008579111,0.00023732781,0.00005717856,0.00015419097,0.01864336,0.0017073286,0.00037635167,0.92388034,0.0023345498,0.043924227],"study_design_scores_gemma":[0.00014156304,0.00010483547,0.014863007,0.0017750167,0.000098755416,0.0014285612,0.043049835,0.015666679,0.004141827,0.74816364,0.17033723,0.00022911449],"about_ca_topic_score_codex":0.015367507,"about_ca_topic_score_gemma":0.008352046,"teacher_disagreement_score":0.107565664,"about_ca_system_score_codex":0.018853277,"about_ca_system_score_gemma":0.012908036,"threshold_uncertainty_score":0.5688684},"labels":[],"label_agreement":null},{"id":"W4366383480","doi":"10.3138/cjpe.20.008","title":"Certification, Credentialing, Licensure, Competencies, and the Like: Issues Confronting the Field of Evaluation","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credentialing; Accreditation; Licensure; Certification; Competence (human resources); Engineering ethics; Medical education; Professional certification (computer technology); Framing (construction); Certification and Accreditation; Professional association; Psychology; Political science; Medicine; Public relations; Engineering; Law; Social psychology","score_opus":0.2723915791832564,"score_gpt":0.5250140899096121,"score_spread":0.25262251072635566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383480","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035549959,0.38400698,0.008705455,0.5512236,0.009897004,0.000047661353,0.000040893272,0.000038327078,0.042485144],"genre_scores_gemma":[0.34759802,0.39673385,0.021402933,0.1751209,0.040699363,0.00025388505,0.00009506118,0.00017921561,0.017916743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.95274895,0.03183836,0.0026526304,0.0012174795,0.010399295,0.0011433596],"domain_scores_gemma":[0.7239303,0.23864685,0.0046540378,0.0025344815,0.026999721,0.0032346162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059267018,0.00039928523,0.0015740336,0.0055929557,0.0063283225,0.021509908,0.00212296,0.009989798,0.0040074755],"category_scores_gemma":[0.10887345,0.00036404168,0.0005304155,0.0072250124,0.030413931,0.013333376,0.003962767,0.013044993,0.00053493347],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010659716,0.00007845281,0.0017739225,0.0022104608,0.000036522622,0.00019662747,0.0037086504,0.00040427918,0.00021339986,0.64928186,0.080307946,0.26168123],"study_design_scores_gemma":[0.000031564014,0.00015865156,0.0055395514,0.015214743,0.000054374337,0.00061046483,0.019972261,0.0011121298,0.00043224002,0.413378,0.5433765,0.000119521435],"about_ca_topic_score_codex":0.020637106,"about_ca_topic_score_gemma":0.04753363,"teacher_disagreement_score":0.059267018,"about_ca_system_score_codex":0.018391246,"about_ca_system_score_gemma":0.021419898,"threshold_uncertainty_score":0.3134377},"labels":[],"label_agreement":null},{"id":"W4366383700","doi":"10.3138/cjpe.0022.007","title":"Évaluations à grande échelle de l’écriture: lien entre le score holistique et les composantes de l’écriture","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Rimouski; Université Laval","funders":"","keywords":"Psychology; Context (archaeology); Scale (ratio); Humanities; Social psychology; Art; History; Cartography; Geography","score_opus":0.13733066775635627,"score_gpt":0.39924317265965886,"score_spread":0.2619125049033026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912053,0.00022590304,0.000617125,0.000090898255,0.000010442801,0.000029147406,0.0001029525,0.000016884418,0.007701424],"genre_scores_gemma":[0.9981647,0.000075451324,0.0005674936,0.000009645794,0.000004243819,0.000012270779,0.00008247318,0.0000056086733,0.0010781827],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99633634,0.00058398984,0.00023341345,0.0002598804,0.0022805382,0.000305869],"domain_scores_gemma":[0.9816684,0.005016353,0.002554813,0.00060444314,0.008622845,0.0015331159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053943573,0.00041471954,0.00029886232,0.0023959295,0.000854666,0.0018811782,0.0005204327,0.00033804838,0.0019752486],"category_scores_gemma":[0.026614655,0.00017256761,0.00029916165,0.0013310702,0.0012781054,0.0009557519,0.0016177539,0.0006390038,0.00024538446],"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":[0.000354498,0.000098448996,0.8929347,0.000106912776,0.00020455387,0.00013209181,0.009093582,0.0005836093,0.0030333681,0.00067193166,0.00080895255,0.091977306],"study_design_scores_gemma":[0.0000052738774,0.00009782208,0.99493426,0.000029759141,0.000023655339,0.000062308005,0.002308459,0.0005270474,0.00097356417,0.00016273194,0.00086107815,0.000014096074],"about_ca_topic_score_codex":0.115394525,"about_ca_topic_score_gemma":0.19230238,"teacher_disagreement_score":0.115394525,"about_ca_system_score_codex":0.0024768442,"about_ca_system_score_gemma":0.0030104178,"threshold_uncertainty_score":0.2294457},"labels":[],"label_agreement":null},{"id":"W4366383857","doi":"10.3138/cjpe.021.003","title":"Making Cost-Benefit Analysis a Practical Tool for Evaluation","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Treasury; Probabilistic logic; Cost–benefit analysis; Risk analysis (engineering); Cost analysis; Watson; Operations research; Reliability engineering; Business; Engineering; Artificial intelligence","score_opus":0.3939906214401624,"score_gpt":0.5438817132129423,"score_spread":0.14989109177277993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383857","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008732044,0.004306728,0.87115127,0.045688145,0.0014888232,0.0020506482,0.0010524802,0.0010235963,0.064506315],"genre_scores_gemma":[0.27949634,0.0045573,0.70029247,0.0043726033,0.0014463207,0.0036599697,0.0005591468,0.0005099713,0.0051059225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9401618,0.04540735,0.0024023433,0.001301879,0.010024982,0.0007016502],"domain_scores_gemma":[0.8146755,0.15185705,0.0052448274,0.009205091,0.017649401,0.0013680782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07208817,0.0030719582,0.0024949294,0.0061872113,0.0015683979,0.011159557,0.0027073554,0.0051369104,0.020316161],"category_scores_gemma":[0.21695647,0.0013010423,0.0018624292,0.0040529133,0.004204116,0.013204959,0.0052649337,0.0074948585,0.00409237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045804784,0.00045255042,0.0023288538,0.003100254,0.00090160227,0.0003502903,0.00069718773,0.07480276,0.0008280589,0.5359366,0.066079244,0.31406456],"study_design_scores_gemma":[0.0003772073,0.00043726983,0.0013043665,0.003661366,0.000498307,0.0002594677,0.0007648303,0.08340844,0.0013911418,0.82270753,0.085031025,0.00015905233],"about_ca_topic_score_codex":0.0022781033,"about_ca_topic_score_gemma":0.0013717061,"teacher_disagreement_score":0.07208817,"about_ca_system_score_codex":0.007146557,"about_ca_system_score_gemma":0.008407426,"threshold_uncertainty_score":0.38124323},"labels":[],"label_agreement":null},{"id":"W4366383873","doi":"10.3138/cjpe.023.001","title":"Editor’s Remarks","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.08668835489651817,"score_gpt":0.4221565138758071,"score_spread":0.33546815897928894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383873","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018349658,0.0020364877,0.00015634207,0.42966306,0.5624495,0.00003703466,0.00012750257,0.00009299463,0.0052535883],"genre_scores_gemma":[0.0023151913,0.0014012468,0.0005077894,0.69974136,0.243678,0.00008494027,0.000057515685,0.00008494344,0.05212898],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98530966,0.0014803843,0.0016699348,0.0024000243,0.0072058016,0.001934237],"domain_scores_gemma":[0.94726133,0.013563974,0.004213946,0.0028189938,0.02560078,0.00654105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013711688,0.0016493544,0.0027062832,0.0025603496,0.0051163426,0.009132854,0.004915683,0.040454403,0.030101435],"category_scores_gemma":[0.10760184,0.0012196457,0.0033920184,0.0020094335,0.00322395,0.0034896038,0.0026190882,0.034624767,0.022067234],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002099196,0.000007536852,0.00006171045,0.00004186419,0.0000111605,0.0001383568,0.00002468252,0.000017751316,0.00004575386,0.0004655893,0.9969433,0.00222121],"study_design_scores_gemma":[0.000047070844,0.00001573044,0.0005808104,0.00019138506,0.000035339224,0.00019737611,0.000101361955,0.000085013475,0.00017111823,0.0008291057,0.9977081,0.000037566104],"about_ca_topic_score_codex":0.01385003,"about_ca_topic_score_gemma":0.029992364,"teacher_disagreement_score":0.040454403,"about_ca_system_score_codex":0.0072394744,"about_ca_system_score_gemma":0.010227785,"threshold_uncertainty_score":0.100699365},"labels":[],"label_agreement":null},{"id":"W4366383875","doi":"10.3138/cjpe.023.009","title":"A Theory-Based Evaluation Framework for Primary Care: Setting the Stage to Evaluate the “Comparison of Models of Primary Health Care in Ontario” Project","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Élisabeth Bruyère Hospital; University of Ottawa","funders":"","keywords":"Primary care; Primary health care; Process management; Management science; Program evaluation; Health care; Computer science; Medicine; Business; Engineering; Political science; Family medicine; Public administration","score_opus":0.2433163457514083,"score_gpt":0.5134295400375312,"score_spread":0.2701131942861229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383875","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045151602,0.0038308413,0.7751476,0.06756835,0.00096232374,0.043653745,0.0007514029,0.00053929654,0.06239482],"genre_scores_gemma":[0.30280104,0.0005480803,0.66298795,0.0019577513,0.00007014096,0.03066126,0.00020833395,0.000049293838,0.00071615796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3679734,0.5880712,0.009511941,0.003487795,0.028125064,0.0028306008],"domain_scores_gemma":[0.64829546,0.2541293,0.016011026,0.01610133,0.058902457,0.006560458],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4646394,0.0025797396,0.0032556031,0.010736571,0.013244709,0.015992893,0.007876946,0.004468191,0.0039789067],"category_scores_gemma":[0.34001818,0.0014850243,0.0028952719,0.006535372,0.029065792,0.0094689,0.011997053,0.0073161433,0.00033755228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000630528,0.0015421045,0.008923591,0.00812913,0.0008643158,0.0003204164,0.039099056,0.018208522,0.0008578398,0.77134514,0.01661407,0.13346522],"study_design_scores_gemma":[0.0064257775,0.005769601,0.016247446,0.02902817,0.0015337681,0.00039109276,0.06941184,0.1246851,0.004307561,0.66691566,0.07469689,0.0005872121],"about_ca_topic_score_codex":0.10892309,"about_ca_topic_score_gemma":0.12830073,"teacher_disagreement_score":0.8910769,"about_ca_system_score_codex":0.10850172,"about_ca_system_score_gemma":0.16970512,"threshold_uncertainty_score":0.7872387},"labels":[],"label_agreement":null},{"id":"W4366383880","doi":"10.3138/cjpe.026.005","title":"Evaluation-Capacity Building: The Three Sides of the Coin","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Gautama Buddha; Metaphor; Context (archaeology); Field (mathematics); Intervention (counseling); Process (computing); Computer science; Psychology; Linguistics; Mathematics; History; Philosophy; Buddhism; Archaeology","score_opus":0.6801887921330342,"score_gpt":0.5042779477622058,"score_spread":0.17591084437082838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383880","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0184759,0.021436706,0.040976375,0.71019405,0.0021247643,0.000444185,0.000057231147,0.00028646702,0.20600428],"genre_scores_gemma":[0.914181,0.009550297,0.027141983,0.036046457,0.00061320054,0.0005183718,0.000031911102,0.00028296013,0.011633834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8925642,0.07092739,0.0028277184,0.0032239337,0.021637565,0.008819172],"domain_scores_gemma":[0.89584094,0.06300464,0.0037218162,0.0038746556,0.022401532,0.011156353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09699455,0.0013528463,0.0017331848,0.005439301,0.019402796,0.04089967,0.0040228907,0.00928574,0.008007508],"category_scores_gemma":[0.10484587,0.00075761596,0.000854121,0.0055784727,0.118943214,0.026275266,0.020964859,0.015939327,0.0008999187],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009124759,0.00013049763,0.0018812971,0.00087392254,0.00007174958,0.00023908225,0.047721673,0.0016567685,0.00028456777,0.84648657,0.036498826,0.06406386],"study_design_scores_gemma":[0.00007785969,0.00009339225,0.0041221865,0.005541742,0.00006118479,0.00020911104,0.08921511,0.0035145725,0.0012709142,0.6475223,0.2480953,0.0002764573],"about_ca_topic_score_codex":0.20988105,"about_ca_topic_score_gemma":0.20888996,"teacher_disagreement_score":0.20988105,"about_ca_system_score_codex":0.06259954,"about_ca_system_score_gemma":0.1142117,"threshold_uncertainty_score":0.51296234},"labels":[],"label_agreement":null},{"id":"W4366383893","doi":"10.3138/cjpe.26.003","title":"Commentaires sur l’article de Robert P. Shepherd «In Search of a Balanced Canadian Federal Evaluation Function: Getting to Relevance»","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Political Systems and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Relevance (law); Function (biology); Political science; Biology; Law; Cell biology","score_opus":0.1260836186315575,"score_gpt":0.37966284717466436,"score_spread":0.2535792285431069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383893","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002943009,0.0014387927,0.00024230704,0.9791829,0.016476031,0.000016029324,0.000094623036,0.000039697938,0.0022154192],"genre_scores_gemma":[0.0043726717,0.001385361,0.00049581623,0.97208875,0.012957343,0.00004463033,0.000040093146,0.0000884792,0.008526793],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96148306,0.009217243,0.0033713586,0.004559554,0.018213939,0.0031549297],"domain_scores_gemma":[0.8585479,0.08327591,0.0056845667,0.002247387,0.045471698,0.0047725355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02354824,0.0013532548,0.0013955542,0.001835942,0.0122030275,0.011785287,0.00526216,0.039281644,0.007102126],"category_scores_gemma":[0.18443412,0.0013211697,0.0021339403,0.0037494972,0.009345466,0.00951097,0.0032854977,0.053548604,0.0042470484],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022193442,0.00000714099,0.00015812753,0.000058096626,0.000007595233,0.000101592464,0.0006451842,0.000054776076,0.00008122941,0.00461261,0.9923664,0.0018851135],"study_design_scores_gemma":[0.000023864322,0.000013746879,0.0014278565,0.00024827413,0.000019727451,0.00021149224,0.001665336,0.00018280608,0.0004891164,0.0046510794,0.99094665,0.000120028315],"about_ca_topic_score_codex":0.4091741,"about_ca_topic_score_gemma":0.5123753,"teacher_disagreement_score":0.9796425,"about_ca_system_score_codex":0.02035752,"about_ca_system_score_gemma":0.029309854,"threshold_uncertainty_score":0.8135849},"labels":[],"label_agreement":null},{"id":"W4366383969","doi":"10.3138/cjpe.0024.002","title":"Monitoring Tobacco Control Outcomes: The Unintended Consequences of Target Selection","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Census and Population Estimation","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Tobacco Research Unit; University of Toronto","funders":"","keywords":"Unintended consequences; Context (archaeology); Stakeholder; Key (lock); Control (management); Selection (genetic algorithm); Tobacco control; Quality (philosophy); Business; Public relations; Risk analysis (engineering); Political science; Computer science; Medicine; Computer security; Public health","score_opus":0.14249974523663317,"score_gpt":0.41185999594715544,"score_spread":0.2693602507105223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54434323,0.004995674,0.30127826,0.07448988,0.0007333769,0.0023033842,0.0015529906,0.00026797352,0.0700352],"genre_scores_gemma":[0.9686614,0.00046013357,0.02690305,0.0022998506,0.000082765146,0.00065781636,0.000086939945,0.000028587025,0.00081942376],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7006375,0.24087474,0.009313477,0.008090084,0.038378496,0.002705689],"domain_scores_gemma":[0.5455727,0.34640187,0.047290277,0.027583547,0.031339254,0.0018123313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23997071,0.00052597723,0.0011053202,0.0013693712,0.0032828315,0.004798561,0.0025433577,0.0024804343,0.0015880413],"category_scores_gemma":[0.38034335,0.0004137095,0.0005490939,0.0021797805,0.006346916,0.0042456514,0.0045509674,0.0035588834,0.00029939733],"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":[0.0012667577,0.0005405199,0.4424389,0.0026103817,0.00084279943,0.00072474545,0.040265273,0.02006431,0.002369341,0.11709728,0.012515842,0.35926384],"study_design_scores_gemma":[0.00031793342,0.0033125505,0.5270612,0.0054922206,0.00089757965,0.0014554672,0.02591247,0.06963331,0.022163851,0.27952933,0.06373168,0.0004924432],"about_ca_topic_score_codex":0.024335418,"about_ca_topic_score_gemma":0.027269406,"teacher_disagreement_score":0.23997071,"about_ca_system_score_codex":0.006728892,"about_ca_system_score_gemma":0.009417939,"threshold_uncertainty_score":0.93725145},"labels":[],"label_agreement":null},{"id":"W4366383979","doi":"10.3138/cjpe.23.001","title":"Guest Editor’s Introduction","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Posthumanist Ethics and Activism","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.13615640400303158,"score_gpt":0.3976857622421535,"score_spread":0.26152935823912193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383979","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009926367,0.0014496769,0.00013395862,0.072154135,0.92103994,0.00003178593,0.00009057129,0.000063168256,0.004937555],"genre_scores_gemma":[0.0028150075,0.0023384318,0.0003958506,0.1156231,0.79129493,0.00010644238,0.00011963541,0.000117379765,0.08718915],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99525625,0.000631241,0.00048565795,0.00067200547,0.0023890086,0.00056592503],"domain_scores_gemma":[0.96573544,0.0067843394,0.0021221433,0.0015365022,0.018892093,0.004929582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068278345,0.001320718,0.0014644482,0.002469896,0.0022981227,0.005067845,0.0024845093,0.009742891,0.060361274],"category_scores_gemma":[0.044037536,0.00064439577,0.0016791823,0.0010054968,0.0011983847,0.0021735304,0.0018409183,0.010159895,0.021721218],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001632185,0.0000058985543,0.00004117829,0.00006739724,0.0000041537937,0.00008419129,0.000008362254,0.000010309643,0.00003655135,0.0002261219,0.99509746,0.0044020796],"study_design_scores_gemma":[0.0000308223,0.000020346724,0.0005069337,0.00022691561,0.000020798823,0.00020661631,0.000055340315,0.000077551056,0.00014856349,0.00050616346,0.99818474,0.00001521895],"about_ca_topic_score_codex":0.0024316576,"about_ca_topic_score_gemma":0.005801929,"teacher_disagreement_score":0.060361274,"about_ca_system_score_codex":0.002323598,"about_ca_system_score_gemma":0.0041863387,"threshold_uncertainty_score":0.20192856},"labels":[],"label_agreement":null},{"id":"W4366384040","doi":"10.3138/cjpe.0024.004","title":"Utilité de l’évaluation de l’évaluabilité des politiques gouvernementales de lutte contre le tabagisme : l’expérience québécoise des centres d’abandon du tabagisme","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Government (linguistics); Welfare economics; Political science; Humanities; Psychology; Economics; Philosophy; Accounting","score_opus":0.14670026669426978,"score_gpt":0.4436251216368626,"score_spread":0.2969248549425928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8503391,0.00219993,0.011618783,0.014662872,0.00013205496,0.0011162523,0.00025375636,0.00014942969,0.119527735],"genre_scores_gemma":[0.98694056,0.0003748871,0.0052058967,0.0003053516,0.000018888035,0.00025640283,0.0000770755,0.00002555166,0.0067953467],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95670724,0.032110523,0.00068608177,0.000809044,0.0072246934,0.002462401],"domain_scores_gemma":[0.9507432,0.030937146,0.0018949006,0.0011699208,0.013054118,0.0022007932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05166192,0.000694691,0.0005609323,0.0020748905,0.006395874,0.006641739,0.0012535302,0.0014803369,0.0061237565],"category_scores_gemma":[0.045926705,0.0002756339,0.0007025824,0.002015162,0.0050743017,0.0020748186,0.0022967,0.0023578405,0.00042160542],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022069684,0.0034921772,0.0933639,0.0018324218,0.00039094794,0.0009520578,0.2099529,0.02706485,0.004633678,0.057214167,0.027496632,0.57139933],"study_design_scores_gemma":[0.001262875,0.006533144,0.400292,0.0031549947,0.0004996244,0.0004484868,0.18414362,0.080848135,0.012555149,0.019780071,0.2898604,0.00062153774],"about_ca_topic_score_codex":0.686123,"about_ca_topic_score_gemma":0.714624,"teacher_disagreement_score":0.313877,"about_ca_system_score_codex":0.07561025,"about_ca_system_score_gemma":0.047574967,"threshold_uncertainty_score":0.6314509},"labels":[],"label_agreement":null},{"id":"W4366384047","doi":"10.3138/cjpe.0021.018","title":"<i>Empowerment</i> et évaluation : quelques réflexions","year":2007,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Empowerment; Valuation (finance); Economics; Sociology; Economic growth; Finance","score_opus":0.15879051058389487,"score_gpt":0.45288202876960393,"score_spread":0.29409151818570906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384047","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001240745,0.10459219,0.004716832,0.864441,0.008431438,0.00003498754,0.00007784825,0.00004567694,0.016419351],"genre_scores_gemma":[0.2429729,0.13057484,0.018613707,0.5642144,0.028989518,0.00071499514,0.00012617094,0.00026562568,0.0135277705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90431935,0.06555832,0.0044789724,0.0074368548,0.014432937,0.003773538],"domain_scores_gemma":[0.62904,0.3209322,0.006887844,0.0102686435,0.028236676,0.0046347408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1477262,0.0017760188,0.00366492,0.0053083464,0.009900803,0.030755304,0.0062392335,0.032560803,0.009791048],"category_scores_gemma":[0.15855418,0.0009875251,0.0016227097,0.008880786,0.09174725,0.042394873,0.009049036,0.028418234,0.0012851505],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093913644,0.00008111025,0.00043404734,0.0015104616,0.00008557053,0.000115398165,0.007994297,0.00022385988,0.00008684052,0.8787357,0.073922895,0.036715902],"study_design_scores_gemma":[0.00017355935,0.00003832077,0.0012815816,0.008919433,0.00009469109,0.00027662568,0.020707207,0.00067060353,0.00028257514,0.6136423,0.35377425,0.00013883968],"about_ca_topic_score_codex":0.104713,"about_ca_topic_score_gemma":0.13027084,"teacher_disagreement_score":0.1477262,"about_ca_system_score_codex":0.038237922,"about_ca_system_score_gemma":0.043757983,"threshold_uncertainty_score":0.78126013},"labels":[],"label_agreement":null},{"id":"W4366384048","doi":"10.3138/cjpe.0021.014","title":"Collectif pour un Québec sans pauvreté : un processus d’évaluation continue des « fruits » obtenus et des « chemins » parcourus","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Obligation; Valuation (finance); Poverty; Welfare economics; Process (computing); Sociology; Political science; Computer science; Business; Economics; Law; Accounting","score_opus":0.11536424300092411,"score_gpt":0.3937034130125219,"score_spread":0.27833917001159775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8547599,0.0028409048,0.037301034,0.018689867,0.00029876613,0.017409284,0.0013410631,0.00031872836,0.06704056],"genre_scores_gemma":[0.91183305,0.0009847053,0.060744584,0.0009485437,0.000033331566,0.0033757405,0.0006196189,0.00008236215,0.021378096],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97562134,0.015995938,0.0004948677,0.00087659736,0.005846538,0.0011646533],"domain_scores_gemma":[0.9545217,0.009834375,0.0016146455,0.0013606712,0.027998434,0.0046701115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06492337,0.0007296886,0.00052606675,0.0023816198,0.009002067,0.005152779,0.001427434,0.001240507,0.0028586944],"category_scores_gemma":[0.033614263,0.00046341168,0.00037961645,0.0023373798,0.0022872319,0.0014523987,0.0026114178,0.001822227,0.00021561365],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014220508,0.0049549835,0.09070717,0.0017943331,0.0003348707,0.0023238806,0.18141198,0.008140705,0.013299386,0.028297996,0.061642487,0.60567015],"study_design_scores_gemma":[0.00064420153,0.0062752906,0.36437285,0.0036551715,0.000286034,0.00043529912,0.22020479,0.019563712,0.020949926,0.006000083,0.35703108,0.00058151886],"about_ca_topic_score_codex":0.81267977,"about_ca_topic_score_gemma":0.8711657,"teacher_disagreement_score":0.18732023,"about_ca_system_score_codex":0.04672226,"about_ca_system_score_gemma":0.13174431,"threshold_uncertainty_score":0.3768468},"labels":[],"label_agreement":null},{"id":"W4366384053","doi":"10.3138/cjpe.022.002","title":"Quand une république s’expose au regard de citoyens-évaluateurs","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Parliament; Political science; Government (linguistics); Unemployment; Relevance (law); Commission; Social security; Intervention (counseling); Public administration; Business; Public relations; Public economics; Economic growth; Psychology; Economics; Politics; Law","score_opus":0.1666996929325435,"score_gpt":0.4240010299556528,"score_spread":0.2573013370231093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384053","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008968282,0.041374274,0.011004306,0.8051078,0.039431818,0.0001394124,0.0003218714,0.00028175348,0.093370415],"genre_scores_gemma":[0.38400868,0.030495286,0.0143635925,0.21238822,0.0298365,0.0011342947,0.0006879648,0.0010850277,0.32600048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9569899,0.025808156,0.0016868232,0.0028217216,0.00999212,0.0027012576],"domain_scores_gemma":[0.9568835,0.021766946,0.0025735763,0.0035696698,0.013311744,0.0018946163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034631096,0.0009897801,0.0009723628,0.002153204,0.009445653,0.018481432,0.002217703,0.011233449,0.024576413],"category_scores_gemma":[0.07401081,0.00056166743,0.0012010484,0.0028370412,0.01224481,0.016774146,0.0067964853,0.012330198,0.0039862553],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031717852,0.00011701408,0.00209521,0.0009954785,0.000053984277,0.00062690856,0.022103056,0.00020937638,0.0013831912,0.5868316,0.32546893,0.059798017],"study_design_scores_gemma":[0.000027502732,0.000039973864,0.0014633982,0.00092605327,0.000011617979,0.0002311698,0.0066684675,0.00015499518,0.00071393186,0.017101258,0.9726281,0.000033639993],"about_ca_topic_score_codex":0.033259243,"about_ca_topic_score_gemma":0.031510968,"teacher_disagreement_score":0.034631096,"about_ca_system_score_codex":0.015610303,"about_ca_system_score_gemma":0.01374777,"threshold_uncertainty_score":0.18314886},"labels":[],"label_agreement":null},{"id":"W4366384054","doi":"10.3138/cjpe.0021.005","title":"Evaluation Can Cross the Boundaries: The Case of Transport Canada","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Transport Canada","funders":"","keywords":"Champion; Coaching; Unit (ring theory); Work (physics); Service (business); Function (biology); Resource (disambiguation); Government (linguistics); Independence (probability theory); Computer science; Process management; Operations management; Business; Public relations; Psychology; Political science; Management; Marketing; Engineering; Economics; Mathematics education","score_opus":0.29431312733175025,"score_gpt":0.5310447804049384,"score_spread":0.23673165307318816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384054","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30937752,0.0074796337,0.009293631,0.22456567,0.0008195826,0.000694085,0.00036064663,0.00019397825,0.44721526],"genre_scores_gemma":[0.9522599,0.0013619213,0.003349856,0.011638486,0.0000735516,0.00012861645,0.000083043145,0.000089972265,0.031014705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"case_report","domain_scores_codex":[0.9633363,0.010728722,0.00077733095,0.0015271669,0.007612989,0.016017513],"domain_scores_gemma":[0.95445484,0.01291086,0.0011236763,0.0015436116,0.017773671,0.012193344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021376686,0.00052390003,0.0006678798,0.0023945794,0.04822576,0.019078486,0.003658313,0.007590089,0.010015654],"category_scores_gemma":[0.038158458,0.0007075048,0.0009978318,0.0061297314,0.013283928,0.006642695,0.010873402,0.009684163,0.0005669351],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00038144787,0.0005759644,0.057725366,0.00049904024,0.00017776492,0.015915796,0.08414686,0.009859061,0.0007176413,0.64884,0.07954172,0.101619415],"study_design_scores_gemma":[0.00027311093,0.00020873945,0.05357627,0.002060719,0.00024240286,0.0022893033,0.2623076,0.012266387,0.0012828615,0.09020158,0.57489103,0.00040006696],"about_ca_topic_score_codex":0.983429,"about_ca_topic_score_gemma":0.9886656,"teacher_disagreement_score":0.7839619,"about_ca_system_score_codex":0.21603812,"about_ca_system_score_gemma":0.354462,"threshold_uncertainty_score":0.90928465},"labels":[],"label_agreement":null},{"id":"W4366384055","doi":"10.3138/cjpe.27.001","title":"Current Evaluation Practices Involving Resource Allocation Processes in Canadian Healthcare Organizations: A Survey of Senior Managers","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; University of British Columbia; Centre for Advancing Health Outcomes","funders":"","keywords":"Resource allocation; Function (biology); Health care; Resource (disambiguation); Business; Process (computing); Senior management; Key (lock); Knowledge management; Survey data collection; Resource management (computing); Healthcare system; Process management; Public relations; Management; Computer science; Political science; Economics; Economic growth","score_opus":0.5278696771232352,"score_gpt":0.502401097060437,"score_spread":0.025468580062798174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96626484,0.005223368,0.0009166261,0.01357602,0.000058827318,0.0003983596,0.0009462754,0.00004644778,0.012569208],"genre_scores_gemma":[0.9955498,0.0016931825,0.0011074635,0.000830115,0.000011031879,0.00007581127,0.00019177207,0.000009050747,0.00053180684],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95613235,0.013028428,0.0051134406,0.0015656038,0.019141942,0.0050183074],"domain_scores_gemma":[0.83005595,0.04289157,0.026115876,0.0027367624,0.07729307,0.020906683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04190762,0.00032424444,0.00061055215,0.0042579537,0.005320002,0.0045293756,0.0023379526,0.0009104872,0.001998443],"category_scores_gemma":[0.11761135,0.0005383393,0.00044167734,0.0082319975,0.003026537,0.0015258306,0.0025637678,0.0013782294,0.00015090719],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004598945,0.0004018196,0.7821553,0.0010293523,0.00013647795,0.00019147394,0.059815858,0.000600969,0.0005744741,0.0029577161,0.014715243,0.13696146],"study_design_scores_gemma":[0.000037541635,0.000194724,0.91513973,0.0009517593,0.00004054352,0.000098985285,0.06305521,0.0012394591,0.00034513164,0.0006251506,0.018140249,0.00013160074],"about_ca_topic_score_codex":0.9361922,"about_ca_topic_score_gemma":0.94439644,"teacher_disagreement_score":0.9113135,"about_ca_system_score_codex":0.0886865,"about_ca_system_score_gemma":0.13221917,"threshold_uncertainty_score":0.6434686},"labels":[],"label_agreement":null},{"id":"W4366384065","doi":"10.3138/cjpe.0026.002","title":"En quoi la complexité a-t-elle des répercussions sur l’évaluation? Introduction au numéro spécial","year":2012,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université de Sherbrooke; Université du Québec à Montréal; McGill University; École Nationale d'Administration Publique; York University","funders":"","keywords":"Chemistry; Philosophy","score_opus":0.20381500239583542,"score_gpt":0.41903984082732565,"score_spread":0.21522483843149023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384065","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012192082,0.046075452,0.035236474,0.69268876,0.011221443,0.00018716583,0.00020941318,0.00022627419,0.20196299],"genre_scores_gemma":[0.6653262,0.038169943,0.06772061,0.0928024,0.014407862,0.0010314039,0.0002233511,0.00061142346,0.1197069],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.93084615,0.036918297,0.0044718017,0.0040737307,0.021042753,0.0026472623],"domain_scores_gemma":[0.8506424,0.097269155,0.0055194944,0.0068316488,0.035127677,0.004609615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06344556,0.0007078174,0.0015437294,0.004413831,0.0051750904,0.024312548,0.0024474044,0.008902893,0.009014493],"category_scores_gemma":[0.1567031,0.00061252574,0.00087604515,0.0051133656,0.023709,0.019313486,0.006127199,0.0068615098,0.00093199423],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008255435,0.00006580306,0.0021007387,0.0008870546,0.000041864205,0.00007770069,0.0044568167,0.0008950339,0.000347771,0.8152335,0.05907269,0.11673844],"study_design_scores_gemma":[0.000060816164,0.00012286796,0.0076982654,0.0044913585,0.00007217974,0.0003625295,0.00704464,0.003188614,0.000767225,0.39339617,0.58265775,0.00013750498],"about_ca_topic_score_codex":0.081231795,"about_ca_topic_score_gemma":0.110394605,"teacher_disagreement_score":0.081231795,"about_ca_system_score_codex":0.027378624,"about_ca_system_score_gemma":0.033233102,"threshold_uncertainty_score":0.33553618},"labels":[],"label_agreement":null},{"id":"W4366384066","doi":"10.3138/cjpe.022.004","title":"Conceptualizing Research Impact: The Case of Education Research","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Social Sciences and Humanities Research Council; University of Ottawa","funders":"","keywords":"Interdependence; Educational research; Conceptual framework; Task (project management); Field (mathematics); Subject (documents); Sociology; Process (computing); Qualitative research; Grounded theory; Research methodology; Management science; Psychology; Epistemology; Computer science; Pedagogy; Social science; Management","score_opus":0.8198728471732565,"score_gpt":0.7382456792202653,"score_spread":0.08162716795299119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1516031,0.007921119,0.4234115,0.080646716,0.0007493836,0.0034363067,0.00021061585,0.00033000138,0.33169124],"genre_scores_gemma":[0.9098697,0.0021656624,0.081491396,0.0017291822,0.00013632055,0.0014118761,0.00009747288,0.000095573094,0.0030028601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8299057,0.13851042,0.004866718,0.0035479849,0.01730375,0.005865452],"domain_scores_gemma":[0.7664269,0.19027485,0.009282489,0.012898933,0.016440326,0.004676458],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12005572,0.0013992651,0.0011928083,0.014403521,0.014951003,0.026118381,0.004850885,0.0077847484,0.0036509354],"category_scores_gemma":[0.12636858,0.001343708,0.0016006373,0.0120747,0.08787927,0.04915483,0.018944472,0.011677249,0.00053358934],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031899635,0.00008208353,0.0021334894,0.00048506615,0.00001737888,0.0010021162,0.24087563,0.00072157045,0.00031247892,0.73841697,0.00085137563,0.015069981],"study_design_scores_gemma":[0.000052026622,0.00015306071,0.0029195955,0.0026916396,0.000074203,0.0022394017,0.43829873,0.004129803,0.0016162765,0.41256258,0.13516028,0.00010242417],"about_ca_topic_score_codex":0.007322255,"about_ca_topic_score_gemma":0.00447234,"teacher_disagreement_score":0.87994426,"about_ca_system_score_codex":0.02327156,"about_ca_system_score_gemma":0.019953256,"threshold_uncertainty_score":0.6349229},"labels":[],"label_agreement":null},{"id":"W4366384067","doi":"10.3138/cjpe.0021.015","title":"Du carré à la spirale : réflexions sur quelques années de participation du comité <i>AVEC</i> du Collectif pour un Québec sans pauvreté","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Sociology; Political science; Variety (cybernetics); Carr; Humanities; Philosophy","score_opus":0.06281950440542908,"score_gpt":0.36430665968614745,"score_spread":0.30148715528071834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384067","genre_codex":"empirical","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88007027,0.0013764866,0.004849035,0.06326831,0.0006656089,0.00043434143,0.00013250558,0.00007378254,0.049129702],"genre_scores_gemma":[0.98593706,0.0004431183,0.0009903089,0.0021582954,0.00005162367,0.00017422157,0.00003822435,0.000040623225,0.010166627],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9621732,0.025713813,0.000568729,0.0015962704,0.0054370244,0.0045110686],"domain_scores_gemma":[0.92237526,0.035537276,0.005717231,0.0026035425,0.022764169,0.01100252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04624336,0.00081862404,0.00060845737,0.0029863038,0.038016308,0.014283598,0.0033133451,0.004830137,0.003762256],"category_scores_gemma":[0.08222267,0.00096910953,0.00043491338,0.002574659,0.026543422,0.006247082,0.010697648,0.011036958,0.00043378284],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003314378,0.00003189371,0.0045855846,0.000038707418,0.0000039306906,0.000263099,0.9825136,0.00003213438,0.00015987405,0.0043165684,0.0022484348,0.0057730214],"study_design_scores_gemma":[0.0000034076238,0.000032025666,0.0054135523,0.00015769388,0.000003316857,0.000061149665,0.9718104,0.000074342344,0.00018164967,0.00056613144,0.021674419,0.000021839627],"about_ca_topic_score_codex":0.62476903,"about_ca_topic_score_gemma":0.71059865,"teacher_disagreement_score":0.37523097,"about_ca_system_score_codex":0.050481822,"about_ca_system_score_gemma":0.058729015,"threshold_uncertainty_score":0.75488156},"labels":[],"label_agreement":null},{"id":"W4366384075","doi":"10.3138/cjpe.021.005","title":"Discours qui résistent à l’objectivation : que peut-on en tirer pour l’évaluation?","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Meaning (existential); Sympathy; Politics; Political science; Context (archaeology); Sociology; Welfare economics; Social psychology; Psychology; Public relations; Epistemology; Philosophy; Law; Economics; Geography","score_opus":0.2866063764522911,"score_gpt":0.5192156027950292,"score_spread":0.23260922634273812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384075","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09760371,0.01627671,0.0855184,0.66588455,0.0068490035,0.0020784405,0.00021097099,0.00039074983,0.1251874],"genre_scores_gemma":[0.8858237,0.007866113,0.053163294,0.026400851,0.0017279979,0.0035309533,0.00012648024,0.00036752486,0.020993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.582725,0.35034055,0.013661397,0.0037687507,0.04361277,0.00589156],"domain_scores_gemma":[0.64980507,0.24208876,0.018562708,0.012912407,0.07086478,0.0057663047],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23185703,0.0010998102,0.001314426,0.0021070554,0.009115308,0.026136253,0.0025470427,0.0069660773,0.0065813554],"category_scores_gemma":[0.38389015,0.0007069181,0.0009666152,0.0028109644,0.024444697,0.02140926,0.006824226,0.012759962,0.0016988185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006990002,0.0005725098,0.009329514,0.0044327616,0.00024409071,0.0013333467,0.32963133,0.0009341358,0.0049807015,0.33258146,0.07262436,0.24263681],"study_design_scores_gemma":[0.00019870438,0.00036028682,0.006498012,0.010288866,0.00015920274,0.0008701531,0.32854968,0.0027216983,0.0074804565,0.07296982,0.56959146,0.00031158942],"about_ca_topic_score_codex":0.012129348,"about_ca_topic_score_gemma":0.012630758,"teacher_disagreement_score":0.23185703,"about_ca_system_score_codex":0.016111195,"about_ca_system_score_gemma":0.025132762,"threshold_uncertainty_score":0.94725704},"labels":[],"label_agreement":null},{"id":"W4366384079","doi":"10.3138/cjpe.021.007","title":"Participatory Needs Assessment","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Credibility; Participatory evaluation; Citizen journalism; Needs assessment; Relevance (law); Quality (philosophy); Process (computing); Process management; Business; Program evaluation; Knowledge management; Computer science; Sociology; Political science","score_opus":0.497564820203374,"score_gpt":0.5742346745312081,"score_spread":0.07666985432783413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06490901,0.0013023099,0.52922004,0.03195895,0.0008720084,0.051571112,0.0027388989,0.0009972039,0.3164304],"genre_scores_gemma":[0.420819,0.00094590423,0.48908022,0.0031787227,0.00019974897,0.044060368,0.0017147498,0.00022889017,0.03977238],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86392313,0.10874876,0.004947471,0.0048147882,0.014474667,0.0030912217],"domain_scores_gemma":[0.89593536,0.04969297,0.0052214507,0.010582915,0.035291344,0.0032760152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10470312,0.0014309462,0.00096013653,0.0064737406,0.008878045,0.005840401,0.0038447855,0.002344322,0.023906497],"category_scores_gemma":[0.113255225,0.0007522,0.0008779111,0.0040832697,0.0047874954,0.006482487,0.015405656,0.0030954576,0.0045168907],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036890776,0.00067504443,0.008958698,0.0036932013,0.000118420714,0.0006982869,0.12719277,0.0036658589,0.0042592324,0.17162134,0.059619464,0.61912876],"study_design_scores_gemma":[0.0002738989,0.00073978317,0.008044377,0.0048689325,0.000114200375,0.0007029115,0.11066094,0.009232208,0.008132917,0.23516493,0.6218414,0.00022359347],"about_ca_topic_score_codex":0.0055210586,"about_ca_topic_score_gemma":0.0077940244,"teacher_disagreement_score":0.10470312,"about_ca_system_score_codex":0.010124786,"about_ca_system_score_gemma":0.034352947,"threshold_uncertainty_score":0.55372965},"labels":[],"label_agreement":null},{"id":"W4366384147","doi":"10.3138/cjpe.26.005","title":"Using Evaluation to Shape and Direct Comprehensive Community Initiatives: Evaluation, Reflective Practice, and Interventions Dealing with Complexity","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Regional Municipality of Waterloo; Wilfrid Laurier University; Centre for Community Based Research","funders":"","keywords":"Citizen journalism; Participatory action research; Experiential learning; Experiential knowledge; Psychological intervention; Value (mathematics); Reflective practice; Action (physics); Sociology; Engineering ethics; Knowledge management; Psychology; Computer science; Pedagogy; Epistemology; Engineering","score_opus":0.8567416364459937,"score_gpt":0.631227536497771,"score_spread":0.2255140999482227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29807574,0.009463581,0.34168717,0.099393345,0.00129665,0.011225907,0.000076878576,0.0010921684,0.23768863],"genre_scores_gemma":[0.8838538,0.0017938194,0.10612451,0.0018946056,0.000089250425,0.0034330685,0.000028988197,0.00008533237,0.0026965886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.71756506,0.2557055,0.0046500955,0.0039461483,0.01380665,0.004326647],"domain_scores_gemma":[0.71411616,0.23578697,0.010341018,0.015411387,0.01684986,0.007494603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18208636,0.0010052109,0.0011874331,0.0034731238,0.009796745,0.01233983,0.003312476,0.003131866,0.0034224538],"category_scores_gemma":[0.23236744,0.0006535362,0.0008100287,0.0027439818,0.018964317,0.010939922,0.01503426,0.0044326833,0.00036540933],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003666412,0.0022884621,0.010956674,0.0032358705,0.00017562682,0.0004962352,0.14611045,0.0037486334,0.0013090268,0.124729,0.0082944175,0.6982889],"study_design_scores_gemma":[0.0010157774,0.0038281444,0.021491,0.019333344,0.00041640594,0.00090620643,0.28742164,0.017265506,0.012570276,0.40679353,0.2283494,0.0006089087],"about_ca_topic_score_codex":0.006482002,"about_ca_topic_score_gemma":0.00973941,"teacher_disagreement_score":0.18208636,"about_ca_system_score_codex":0.015694955,"about_ca_system_score_gemma":0.045566544,"threshold_uncertainty_score":0.9629762},"labels":[],"label_agreement":null},{"id":"W4366384151","doi":"10.3138/cjpe.0024.007","title":"Can Tobacco Control Advocacy Work be Evaluated?","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Tobacco Research Unit; York University; Women's Health In Women's Hands","funders":"","keywords":"Midstream; Tobacco control; Context (archaeology); Work (physics); Control (management); Public relations; Political science; Tobacco industry; Engineering ethics; Sociology; Management; Public health; Medicine; Engineering; Nursing; Law; Economics","score_opus":0.6089075430715206,"score_gpt":0.6661379147441598,"score_spread":0.057230371672639224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384151","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2807496,0.023231937,0.018395873,0.35989574,0.007045832,0.01891212,0.0020467173,0.00052560057,0.2891966],"genre_scores_gemma":[0.94098043,0.0047850744,0.026021797,0.009791208,0.00044468412,0.012581636,0.00040037243,0.000069385846,0.0049254796],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75675595,0.18866394,0.006068133,0.002750101,0.03871718,0.007044711],"domain_scores_gemma":[0.6593751,0.18659964,0.026062928,0.01012109,0.10204211,0.015799105],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24967736,0.0010761152,0.0017090344,0.004460238,0.009816989,0.014885568,0.0035782414,0.004102913,0.009405279],"category_scores_gemma":[0.41721496,0.00072106515,0.0011974422,0.0057403236,0.0068983026,0.0111424,0.0074530165,0.0035931075,0.0008549808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032725765,0.0046879593,0.09856254,0.010134025,0.0010187286,0.00031822748,0.04522173,0.0033275087,0.00051358406,0.10250549,0.056830604,0.67360705],"study_design_scores_gemma":[0.009839175,0.012702205,0.22236586,0.067314856,0.004434118,0.00023639757,0.16401684,0.02003307,0.007393461,0.16949034,0.32134086,0.0008328228],"about_ca_topic_score_codex":0.17920738,"about_ca_topic_score_gemma":0.2915828,"teacher_disagreement_score":0.24967736,"about_ca_system_score_codex":0.08594236,"about_ca_system_score_gemma":0.17413019,"threshold_uncertainty_score":0.9252814},"labels":[],"label_agreement":null},{"id":"W4366384160","doi":"10.3138/cjpe.22.004","title":"Using Public Databases to Study Relative Program Impact","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Impact assessment; Database; Computer science; Control (management); Impact evaluation; Statistics; Political science; Artificial intelligence; Mathematics","score_opus":0.7796421792303019,"score_gpt":0.6674537745782021,"score_spread":0.11218840465209978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384160","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6071491,0.00721719,0.11733204,0.007663191,0.00047410457,0.0074510016,0.20810431,0.0011969687,0.043412056],"genre_scores_gemma":[0.8375343,0.0015773252,0.07873173,0.00049210817,0.00017672408,0.0093417205,0.07126604,0.00014000277,0.00074003084],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.7948192,0.1382796,0.021878494,0.0067420173,0.03640224,0.0018785362],"domain_scores_gemma":[0.3959359,0.42674437,0.065810345,0.058094252,0.050581343,0.002833815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13582814,0.0007629352,0.0016120232,0.022289906,0.0017127483,0.005167927,0.0031636711,0.0016183725,0.00429649],"category_scores_gemma":[0.40939793,0.00073890435,0.0013592046,0.04539038,0.0013985683,0.005904757,0.004137615,0.0016867531,0.00058770453],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037369179,0.0021020705,0.6225036,0.0063045886,0.006113406,0.0002812121,0.0029630943,0.021648547,0.000493855,0.05721881,0.029734617,0.2468993],"study_design_scores_gemma":[0.004094995,0.0027231683,0.69989103,0.0059733163,0.0073419674,0.0010091292,0.011531677,0.08274887,0.008757305,0.06302207,0.11232553,0.0005810625],"about_ca_topic_score_codex":0.036140125,"about_ca_topic_score_gemma":0.024031837,"teacher_disagreement_score":0.13582814,"about_ca_system_score_codex":0.0065254136,"about_ca_system_score_gemma":0.013284753,"threshold_uncertainty_score":0.71833646},"labels":[],"label_agreement":null},{"id":"W4366384164","doi":"10.3138/cjpe.027.008","title":"DeMars, C. (2010). <i>Item Response Theory.</i> Oxford, UK: Oxford University Press. 137 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Item response theory; Media studies; Political science; Economic history; Library science; Economics; Sociology; Computer science; Law","score_opus":0.29078747149008427,"score_gpt":0.43684040231959376,"score_spread":0.1460529308295095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384164","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007866156,0.6391927,0.15605383,0.09247004,0.021561194,0.0027680008,0.022414172,0.0030891742,0.054584634],"genre_scores_gemma":[0.10675965,0.4857678,0.32575142,0.013884526,0.0068078944,0.008301915,0.021633515,0.0022011243,0.02889218],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9753955,0.013456445,0.0035359475,0.00089080626,0.006456602,0.0002647551],"domain_scores_gemma":[0.7768481,0.16901529,0.007954167,0.006682684,0.03822521,0.0012745651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059194922,0.0033799023,0.0029527885,0.014213123,0.0029041837,0.0055477675,0.0054934644,0.003628844,0.02310231],"category_scores_gemma":[0.20297639,0.0037891907,0.0024843994,0.016963787,0.0064305514,0.0105788605,0.0033396343,0.012019303,0.019130196],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023771025,0.000107186206,0.004726475,0.0034840442,0.00030014396,0.000097602344,0.0020786389,0.0009096494,0.00052744563,0.008214064,0.52190495,0.45741206],"study_design_scores_gemma":[0.00040758666,0.00048444458,0.063412614,0.030381233,0.001583751,0.001663526,0.004690334,0.002455316,0.003305581,0.074847825,0.8160446,0.0007231947],"about_ca_topic_score_codex":0.02273084,"about_ca_topic_score_gemma":0.036893133,"teacher_disagreement_score":0.059194922,"about_ca_system_score_codex":0.0046991794,"about_ca_system_score_gemma":0.0057320753,"threshold_uncertainty_score":0.3130564},"labels":[],"label_agreement":null},{"id":"W4366384165","doi":"10.3138/cjpe.21.001","title":"Suggestions d’améliorations d’un cadre conceptuel de l’évaluation participative","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Participatory evaluation; Empowerment; Stakeholder; Citizen journalism; Relevance (law); Valuation (finance); Sociology; Knowledge management; Management science; Process management; Business; Political science; Computer science; Public relations; Social science; Engineering; Accounting","score_opus":0.3522063354619847,"score_gpt":0.5249077562850959,"score_spread":0.17270142082311118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009620108,0.011494019,0.7234622,0.22104904,0.004438373,0.0062939753,0.00016495869,0.0009918385,0.022485452],"genre_scores_gemma":[0.10335739,0.005423062,0.8620447,0.00950015,0.00092189095,0.012140956,0.00023166559,0.00025355074,0.006126661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5686244,0.36095563,0.020982165,0.0070971563,0.03861604,0.0037246153],"domain_scores_gemma":[0.59627444,0.23637351,0.013991804,0.024144944,0.12189274,0.0073225372],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38477072,0.004243354,0.002821813,0.013245676,0.0083729755,0.031984862,0.009666139,0.013635123,0.007060355],"category_scores_gemma":[0.29334787,0.0020385387,0.004210293,0.008134787,0.034932185,0.04194219,0.012098926,0.017363342,0.0025990175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036430647,0.0007190278,0.0026878088,0.0059146425,0.0001672831,0.00054827373,0.03083374,0.004291665,0.0022991856,0.71412194,0.025881192,0.21217103],"study_design_scores_gemma":[0.00083676295,0.0007830011,0.004424693,0.021349812,0.0003215668,0.0014768357,0.045337,0.026592446,0.0053299326,0.39217746,0.50066626,0.00070432277],"about_ca_topic_score_codex":0.014679041,"about_ca_topic_score_gemma":0.015873538,"teacher_disagreement_score":0.38477072,"about_ca_system_score_codex":0.022951864,"about_ca_system_score_gemma":0.053018246,"threshold_uncertainty_score":0.75868726},"labels":[],"label_agreement":null},{"id":"W4366384168","doi":"10.3138/cjpe.27.006","title":"Wyatt Knowlton, L., &amp; Phillips, C. C. (2013). <i>The Logic Model Guidebook: Better Strategies for Great Results</i> (2nd ed.). Thousand Oaks, CA: Sage. 170 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Philosophy; Cognitive science; Psychology; Physics; Nuclear physics","score_opus":0.11702970430923154,"score_gpt":0.34224199700042734,"score_spread":0.2252122926911958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384168","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032830504,0.43712458,0.07808373,0.07336272,0.008755832,0.00050299487,0.008901629,0.003481013,0.38650438],"genre_scores_gemma":[0.03366796,0.49183172,0.07100178,0.013842443,0.0016144811,0.0007286641,0.0044755316,0.0019142458,0.38092315],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991375,0.00015194801,0.00010065954,0.00008778894,0.00047500452,0.00004702105],"domain_scores_gemma":[0.99370474,0.002575422,0.0004060701,0.00030906152,0.0026505827,0.000354107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032631909,0.0010730503,0.0006262264,0.0041341074,0.0021195353,0.0046158973,0.0017102789,0.00229118,0.077649005],"category_scores_gemma":[0.011360959,0.001351276,0.00059580273,0.0036230606,0.0020611912,0.0077036917,0.0014740322,0.003907846,0.039752737],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022837065,0.00003750931,0.00046924487,0.0005454165,0.000008925707,0.000032491153,0.00045000252,0.000111414665,0.0003399756,0.004875623,0.6974687,0.2956379],"study_design_scores_gemma":[0.000012114235,0.00003332103,0.0034721328,0.002170678,0.000041209045,0.00014525295,0.0005275839,0.00013847927,0.0009924809,0.014165193,0.9782694,0.000032171192],"about_ca_topic_score_codex":0.035434347,"about_ca_topic_score_gemma":0.10099669,"teacher_disagreement_score":0.077649005,"about_ca_system_score_codex":0.0022184416,"about_ca_system_score_gemma":0.005378284,"threshold_uncertainty_score":0.25976175},"labels":[],"label_agreement":null},{"id":"W4366384172","doi":"10.3138/cjpe.0024.005","title":"Rigour and Feasibility in Tobacco Control Evaluation: Toward a Successful Reconciliation","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Communications and Information Technology Ontario; Heart and Stroke Foundation; University of Waterloo; Public Health Ontario; University of Toronto","funders":"","keywords":"Rigour; Stakeholder; Relevance (law); Context (archaeology); Tobacco control; Control (management); Plan (archaeology); Management science; Program evaluation; Process management; Political science; Engineering ethics; Public relations; Computer science; Business; Public administration; Engineering; Medicine; Public health; Epistemology; Nursing; Law; Geography","score_opus":0.37313234694188385,"score_gpt":0.5320879190308285,"score_spread":0.15895557208894467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384172","genre_codex":"methods","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029872678,0.020406784,0.65828234,0.23288369,0.0024445069,0.009525017,0.0001514187,0.0005725681,0.04586096],"genre_scores_gemma":[0.4675425,0.0033303439,0.5080053,0.009958536,0.0011299566,0.007989422,0.00010021831,0.00022819666,0.0017155203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.056632116,0.8443934,0.030708393,0.0067243897,0.059464097,0.002077758],"domain_scores_gemma":[0.08857952,0.7135817,0.041596197,0.0735992,0.078546084,0.004097336],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.85428953,0.0024554888,0.0053001675,0.016311174,0.011894235,0.038366985,0.00957213,0.012723169,0.0026669544],"category_scores_gemma":[0.8375267,0.003585883,0.0038192316,0.009978873,0.054453082,0.03452598,0.039634626,0.017342536,0.00063556276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009924883,0.0007521068,0.010936908,0.008974115,0.0013194939,0.00048590632,0.04142318,0.00923504,0.0014006613,0.4841944,0.009823225,0.4304625],"study_design_scores_gemma":[0.0012011983,0.0021713492,0.011459658,0.025826868,0.0008343076,0.0007119417,0.013535291,0.020374542,0.0051525594,0.8231656,0.09478112,0.0007855067],"about_ca_topic_score_codex":0.004479147,"about_ca_topic_score_gemma":0.004681074,"teacher_disagreement_score":0.85428953,"about_ca_system_score_codex":0.034016695,"about_ca_system_score_gemma":0.08559014,"threshold_uncertainty_score":0.2468096},"labels":[],"label_agreement":null},{"id":"W4366384175","doi":"10.3138/cjpe.23.017","title":"R. Pawson. (2006). <i>Evidence-based Policy: A Realist Perspective.</i> Thousand Oaks, CA: Sage. 209 pages.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); SAGE; Sociology; Philosophy; Political science; Epistemology; Regional science; Art; Physics; Visual arts; Quantum mechanics","score_opus":0.3443396687424581,"score_gpt":0.4951481816256015,"score_spread":0.1508085128831434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384175","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005982614,0.77933085,0.024334706,0.14636798,0.009735936,0.00017439848,0.0026297357,0.00047011042,0.036358003],"genre_scores_gemma":[0.024618773,0.8592781,0.047667414,0.025859533,0.004981661,0.00050497556,0.0013237788,0.00054853485,0.035217233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962198,0.0016397316,0.0005837149,0.00020361212,0.0012394577,0.00011371067],"domain_scores_gemma":[0.9498587,0.03455071,0.0037562458,0.0009903773,0.009663407,0.0011804445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013747628,0.0017632877,0.0012628705,0.0055794334,0.0013756263,0.004198913,0.0021595038,0.0039426307,0.023870623],"category_scores_gemma":[0.043084126,0.0016351381,0.00085168035,0.007679006,0.0024294842,0.0069908476,0.0016341505,0.007272916,0.01618344],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098708166,0.000029595734,0.0005359522,0.0025545426,0.000054565506,0.00009818737,0.00029953226,0.00035649602,0.00014020725,0.017591974,0.7415391,0.2367011],"study_design_scores_gemma":[0.00011579198,0.00010592403,0.005607372,0.018967984,0.0002623491,0.0008283124,0.00066154305,0.0007480832,0.00093589263,0.10388215,0.8677451,0.00013954185],"about_ca_topic_score_codex":0.013798277,"about_ca_topic_score_gemma":0.026519192,"teacher_disagreement_score":0.023870623,"about_ca_system_score_codex":0.002196768,"about_ca_system_score_gemma":0.0065971273,"threshold_uncertainty_score":0.079855144},"labels":[],"label_agreement":null},{"id":"W4366384176","doi":"10.3138/cjpe.21.002","title":"Challenges of Participatory Evaluation within a Community-Based Health Promotion Partnership: Mujer Sana, Comunidad Sana—Healthy Women, Healthy Communities","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"General partnership; Citizen journalism; Participatory action research; Community-based participatory research; Participatory evaluation; Promotion (chess); Sociology; Public relations; Nursing; Medicine; Political science; Social science","score_opus":0.7114160732550165,"score_gpt":0.5663836151296869,"score_spread":0.1450324581253296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384176","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4253618,0.011452066,0.05200597,0.43229944,0.0019926433,0.011658623,0.00013016257,0.00023805846,0.06486128],"genre_scores_gemma":[0.9534406,0.0015126186,0.03132602,0.005816479,0.00015627529,0.0055960543,0.000032869422,0.000047214704,0.0020718744],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.4504746,0.50718516,0.0072745928,0.004579244,0.021782048,0.008704356],"domain_scores_gemma":[0.5545055,0.34099033,0.013756819,0.013122677,0.05346692,0.024157796],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.43739492,0.000877498,0.0014061374,0.0018008249,0.031048752,0.020885034,0.0059744394,0.0059390333,0.003415263],"category_scores_gemma":[0.31519786,0.001056637,0.0009177786,0.0022728248,0.019789126,0.011034527,0.017043136,0.007573728,0.00033627648],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008423651,0.0020989364,0.021220522,0.004428713,0.00027114566,0.0022933565,0.559488,0.0036317972,0.001712424,0.099792846,0.021012586,0.2832073],"study_design_scores_gemma":[0.00064805243,0.0016281551,0.010185019,0.007416705,0.00016302036,0.0010360668,0.78831816,0.0056669763,0.0024789423,0.06398937,0.11816719,0.00030220833],"about_ca_topic_score_codex":0.039167486,"about_ca_topic_score_gemma":0.052268554,"teacher_disagreement_score":0.43739492,"about_ca_system_score_codex":0.032122966,"about_ca_system_score_gemma":0.12838002,"threshold_uncertainty_score":0.6937922},"labels":[],"label_agreement":null},{"id":"W4366384224","doi":"10.3138/cjpe.0022.011","title":"Bouchamma, Y., &amp; Long, M. J. (2007). <i>Porte d’entrée dans la réussite en écriture. Outil de supervision des enseignants basé sur le Programme d’Indicateurs du Rendement Scolaire</i> (PIRS). Lévis, Québec: Éditions de la francophonie. 112 pages + 1 cédérom.","year":2008,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"French Language Learning Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Art","score_opus":0.07293822846507657,"score_gpt":0.3205586306788727,"score_spread":0.2476204022137961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384224","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13580455,0.3070036,0.15918434,0.09968147,0.0069095744,0.0015830648,0.010399602,0.0033402543,0.27609348],"genre_scores_gemma":[0.48682493,0.120000824,0.14361487,0.004656781,0.0005705292,0.0012469023,0.0036024132,0.0008585503,0.23862413],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99798524,0.00059239316,0.00009819076,0.00014440142,0.0010477962,0.00013203488],"domain_scores_gemma":[0.99032193,0.0041919067,0.00065898005,0.00033277596,0.003971485,0.0005229158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006487098,0.0006352714,0.00057895854,0.0019716253,0.0027332534,0.0041052634,0.0013964268,0.0011643997,0.023248654],"category_scores_gemma":[0.022104455,0.00048976653,0.000365378,0.0019722427,0.0018023778,0.0035188026,0.0012948834,0.0014335458,0.006960542],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037734225,0.00014329047,0.011773059,0.0011345479,0.000059387745,0.00014398017,0.005055529,0.00053929427,0.002765589,0.005758748,0.2025497,0.76969945],"study_design_scores_gemma":[0.00016019365,0.00034951724,0.14817058,0.002836376,0.00032253927,0.0005295087,0.007897614,0.003181435,0.009157204,0.0081217,0.81910896,0.00016431283],"about_ca_topic_score_codex":0.375605,"about_ca_topic_score_gemma":0.46671727,"teacher_disagreement_score":0.624395,"about_ca_system_score_codex":0.00562491,"about_ca_system_score_gemma":0.009587313,"threshold_uncertainty_score":0.74683744},"labels":[],"label_agreement":null},{"id":"W4366384235","doi":"10.3138/cjpe.21.008","title":"Performance Studies: The Missing Link?","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Accounting and Organizational Management","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Performance measurement; Set (abstract data type); Computer science; Performance management; Link (geometry); Risk analysis (engineering); Data mining; Business; Marketing","score_opus":0.07347803825364241,"score_gpt":0.30301303658925033,"score_spread":0.22953499833560792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384235","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012420501,0.2771666,0.004193741,0.6958496,0.015656248,0.000030940184,0.0004959412,0.0001153347,0.0052496158],"genre_scores_gemma":[0.13217847,0.5348632,0.013063324,0.24318205,0.07120072,0.00030331776,0.0011833564,0.00029650624,0.0037291383],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9172416,0.05156093,0.009876507,0.0040641795,0.015857672,0.0013992086],"domain_scores_gemma":[0.2891028,0.5979329,0.025756784,0.01675605,0.060760144,0.009691367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.122687824,0.0013637209,0.0033981365,0.010993706,0.002628358,0.019285481,0.0045921546,0.012344312,0.02789053],"category_scores_gemma":[0.47961256,0.0011616555,0.0009872458,0.017207632,0.014043165,0.04363909,0.0069555035,0.01920765,0.0067314515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041521573,0.0002856449,0.00693481,0.015297604,0.00048828023,0.0002863045,0.0009799988,0.0004671883,0.000088674395,0.168631,0.42032805,0.38579726],"study_design_scores_gemma":[0.00027806478,0.00019138817,0.0095573785,0.055343997,0.00048621895,0.0010984258,0.008567633,0.0017565152,0.0002389691,0.58379346,0.3383917,0.00029615455],"about_ca_topic_score_codex":0.007990224,"about_ca_topic_score_gemma":0.0052735214,"teacher_disagreement_score":0.122687824,"about_ca_system_score_codex":0.006865777,"about_ca_system_score_gemma":0.01367904,"threshold_uncertainty_score":0.648843},"labels":[],"label_agreement":null},{"id":"W4366384241","doi":"10.3138/cjpe.21.006","title":"Development of a Framework for Comprehensive Evaluation of Client Outcomes in Community Mental Health Services","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University; Riverview Hospital; University of British Columbia","funders":"","keywords":"Operationalization; Assertive community treatment; Mental health; Conceptualization; Stakeholder; Psychology; Inclusion (mineral); Mental illness; Applied psychology; Process management; Psychiatry; Public relations; Social psychology; Business; Computer science","score_opus":0.46199264417842795,"score_gpt":0.5765774015422332,"score_spread":0.1145847573638053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384241","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015245883,0.001831743,0.9298493,0.011236088,0.00015763205,0.01661417,0.0008956222,0.00071452296,0.023454957],"genre_scores_gemma":[0.11049445,0.00042656003,0.87404466,0.0004802855,0.000033394073,0.013507869,0.00058782316,0.00003785784,0.00038703703],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.69460446,0.24882779,0.02136827,0.00554729,0.026694972,0.0029572023],"domain_scores_gemma":[0.83619404,0.10738709,0.009833679,0.0061645135,0.036816437,0.0036043671],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25966123,0.0029428531,0.0031703704,0.012277091,0.004122999,0.011646829,0.0052339607,0.0037196458,0.002528373],"category_scores_gemma":[0.1742519,0.0011637566,0.0043261526,0.008378762,0.008632029,0.009412399,0.007581614,0.0050959755,0.0006045768],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028683795,0.0013396604,0.019025207,0.003759588,0.0006354081,0.00039378094,0.013062814,0.036332034,0.0012381376,0.62628984,0.0106551,0.2869817],"study_design_scores_gemma":[0.0008083613,0.0024852557,0.01969249,0.018499158,0.0011509791,0.0005896715,0.016019715,0.19244574,0.0049388153,0.6766936,0.06621879,0.00045741655],"about_ca_topic_score_codex":0.024670143,"about_ca_topic_score_gemma":0.021276472,"teacher_disagreement_score":0.25966123,"about_ca_system_score_codex":0.03203842,"about_ca_system_score_gemma":0.050733685,"threshold_uncertainty_score":0.9129695},"labels":[],"label_agreement":null},{"id":"W4366384242","doi":"10.3138/cjpe.0023.008","title":"Insights into Evaluation Capacity Building: Motivations, Strategies, Outcomes, and Lessons Learned","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Capacity building; Accountability; Face (sociological concept); Public relations; Business; Psychology; Process management; Knowledge management; Political science; Sociology; Computer science","score_opus":0.536890060585536,"score_gpt":0.5401212105282374,"score_spread":0.00323114994270135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8884088,0.0012316424,0.022754394,0.035402533,0.00006909833,0.00056691683,0.00005766102,0.00012831022,0.051380727],"genre_scores_gemma":[0.9935714,0.0003087676,0.0047706435,0.00038206513,0.000010380011,0.000103592494,0.0000140683915,0.000014279827,0.0008247052],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9630778,0.028327504,0.0008742556,0.00065986137,0.003665907,0.003394587],"domain_scores_gemma":[0.8884618,0.0873106,0.0053766523,0.002501184,0.008393232,0.007956474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044865698,0.00045851563,0.00035153577,0.0025408657,0.0040684566,0.008686027,0.0016757709,0.0016135029,0.0021360575],"category_scores_gemma":[0.06958214,0.000457893,0.0003145345,0.0018504469,0.0065693106,0.0059287646,0.0052838847,0.0034551125,0.00024754164],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017159042,0.0016974456,0.083954334,0.001091387,0.00004558303,0.002109223,0.5711557,0.0012182578,0.0024680663,0.07529641,0.0069066877,0.25388533],"study_design_scores_gemma":[0.000051999526,0.0002672499,0.047492485,0.0016707868,0.000031263742,0.0009946779,0.8443321,0.005308205,0.0039025005,0.056851815,0.038971838,0.00012515172],"about_ca_topic_score_codex":0.004128863,"about_ca_topic_score_gemma":0.0070888256,"teacher_disagreement_score":0.044865698,"about_ca_system_score_codex":0.008676663,"about_ca_system_score_gemma":0.013279779,"threshold_uncertainty_score":0.2372753},"labels":[],"label_agreement":null},{"id":"W4366384248","doi":"10.3138/cjpe.026.006","title":"J. Fitzpatrick, C. Christie, &amp; M. M. Mark. (2009). <i>Evaluation in Action: Interviews with Expert Evaluators</i> . Thousand Oaks, CA: Sage. xiv + 456 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Action (physics); Psychology; Sociology; Physics","score_opus":0.3641684196792167,"score_gpt":0.47772110415375324,"score_spread":0.11355268447453654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384248","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010098,0.38537884,0.052930765,0.2881183,0.008600447,0.00076090224,0.0036828185,0.0009922115,0.24943767],"genre_scores_gemma":[0.11391478,0.5169319,0.09280069,0.030702364,0.0012857453,0.0007158182,0.0015377676,0.00070891995,0.2414021],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988403,0.00030961557,0.000095392556,0.00010170844,0.00059125974,0.000061759456],"domain_scores_gemma":[0.99066895,0.005437575,0.0005637508,0.00017429593,0.0026661581,0.0004892397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046154987,0.00058926776,0.00031816238,0.0023527986,0.0021669278,0.0035098153,0.0010668794,0.0018154236,0.025242306],"category_scores_gemma":[0.017569277,0.00073894736,0.00029193537,0.002288796,0.0013549326,0.005849029,0.001081756,0.002208268,0.011190134],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050103983,0.000058781803,0.0014793262,0.000761866,0.000011712292,0.000087134824,0.0014432059,0.00010577305,0.00029407247,0.0026532444,0.60888547,0.38416922],"study_design_scores_gemma":[0.000044111315,0.00009070643,0.019714544,0.004854448,0.00007349597,0.0006836523,0.0055092312,0.0002978194,0.0015241395,0.015310897,0.95182014,0.000076852884],"about_ca_topic_score_codex":0.024577368,"about_ca_topic_score_gemma":0.10378164,"teacher_disagreement_score":0.025242306,"about_ca_system_score_codex":0.0014014842,"about_ca_system_score_gemma":0.0039053687,"threshold_uncertainty_score":0.08444393},"labels":[],"label_agreement":null},{"id":"W4366384250","doi":"10.3138/cjpe.27.005","title":"The Key Functions of Collaborative Logic Modelling: Insights from the British Columbia Early Childhood Dental Programs","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Documentation; General partnership; Key (lock); Logic model; Government (linguistics); Knowledge management; Computer science; Process management; Public relations; Political science; Psychology; Business; Public administration","score_opus":0.21203274369979694,"score_gpt":0.40990725897507363,"score_spread":0.1978745152752767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68113416,0.00057366677,0.07950834,0.023381084,0.000037795333,0.0007148582,0.00034111197,0.00019072295,0.21411829],"genre_scores_gemma":[0.96834105,0.00019479576,0.027801637,0.00032616462,0.0000047519034,0.00012332418,0.00010192732,0.00003626419,0.0030700073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9817394,0.014925487,0.00031074294,0.0004706092,0.0015675324,0.0009861687],"domain_scores_gemma":[0.9363941,0.054336995,0.0014477981,0.0015991207,0.004949168,0.0012727848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016264448,0.00048780785,0.0003741382,0.0017385159,0.0059428997,0.010447438,0.0022286272,0.0014898728,0.0038352609],"category_scores_gemma":[0.03997668,0.00041132275,0.00052752317,0.0024253677,0.00712247,0.0041307183,0.0035476326,0.0025728703,0.00026843857],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042805658,0.00086260395,0.04022264,0.000506082,0.0000963781,0.0021142066,0.14853838,0.09688661,0.0013973204,0.59260815,0.007137608,0.109201975],"study_design_scores_gemma":[0.00021791145,0.00024114296,0.017005317,0.0009019607,0.00013870391,0.0004906233,0.24379468,0.41487667,0.0022511494,0.25574964,0.06414935,0.00018281469],"about_ca_topic_score_codex":0.56017035,"about_ca_topic_score_gemma":0.59267473,"teacher_disagreement_score":0.43982965,"about_ca_system_score_codex":0.031927325,"about_ca_system_score_gemma":0.039262842,"threshold_uncertainty_score":0.8848398},"labels":[],"label_agreement":null},{"id":"W4366384274","doi":"10.3138/cjpe.21.004","title":"Using Community-Based Participatory Research for an Online Dementia Care Program","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Participatory action research; Community-based participatory research; Dementia; Citizen journalism; Health care; Participatory evaluation; Work (physics); Plan (archaeology); Participatory design; Medical education; Process (computing); Psychology; Nursing; Sociology; Medicine; Computer science; Political science; Engineering; World Wide Web","score_opus":0.9407376859961307,"score_gpt":0.6744158388136409,"score_spread":0.26632184718248986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384274","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79570454,0.0009548103,0.11028335,0.01763735,0.0005550157,0.037179347,0.00020149442,0.00028365882,0.03720037],"genre_scores_gemma":[0.8849482,0.00038752152,0.08907926,0.001770622,0.000085151536,0.020679181,0.00007242973,0.000036505287,0.0029410613],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.842893,0.1456182,0.0014090225,0.0025762615,0.003762119,0.00374139],"domain_scores_gemma":[0.91879684,0.06019704,0.0031213698,0.0053211786,0.0055415602,0.007022008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11629511,0.00095426606,0.0006853218,0.002661529,0.017434388,0.0070831627,0.0036900507,0.0028860755,0.0050266176],"category_scores_gemma":[0.07204445,0.00070239196,0.0007319591,0.0016105605,0.0085702175,0.0052817897,0.011764181,0.0038669896,0.00057400955],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005440153,0.009596637,0.011709793,0.0013399601,0.00008229037,0.0030542712,0.7370218,0.0015684607,0.003175075,0.018523017,0.005406225,0.20797858],"study_design_scores_gemma":[0.0012724147,0.0042592175,0.0060767047,0.0019378215,0.00009522354,0.0012938026,0.87578696,0.0046144184,0.0033139545,0.02571681,0.07544288,0.00018980369],"about_ca_topic_score_codex":0.004165453,"about_ca_topic_score_gemma":0.011338689,"teacher_disagreement_score":0.11629511,"about_ca_system_score_codex":0.0055349045,"about_ca_system_score_gemma":0.021094598,"threshold_uncertainty_score":0.6150347},"labels":[],"label_agreement":null},{"id":"W4366384275","doi":"10.3138/cjpe.027.006","title":"Ryan, K. E., &amp; Cousins, J. B. (Eds.). (2009). <i>The Sage International Handbook of Educational Evaluation.</i> Thousand Oaks, CA: Sage. 608 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Sociology; Psychology; Gerontology; Library science; Medicine; Computer science; Physics","score_opus":0.17755472847929304,"score_gpt":0.4727750580837578,"score_spread":0.29522032960446476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384275","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001631786,0.8769675,0.014824546,0.026941746,0.0031918625,0.00017705717,0.0023446558,0.0005785821,0.07334219],"genre_scores_gemma":[0.00858249,0.9328973,0.015539724,0.0009929847,0.00057543966,0.00011676515,0.00094100373,0.0001996981,0.040154494],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842876,0.00032599695,0.00017623152,0.00012060818,0.000873499,0.00007478191],"domain_scores_gemma":[0.9940631,0.0030550617,0.0005105666,0.00018016674,0.0018416421,0.00034946293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039622234,0.0014036782,0.0010953174,0.0034996935,0.0011317045,0.0039429264,0.0014917672,0.0016306071,0.028217364],"category_scores_gemma":[0.009146737,0.0011550714,0.0007565377,0.004154129,0.0012089158,0.0049283532,0.0010520578,0.002816971,0.025296552],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003489283,0.000041195868,0.00076563976,0.0015767418,0.00002021527,0.000053882195,0.0005956198,0.0002727693,0.00022253142,0.00258045,0.40044853,0.59338754],"study_design_scores_gemma":[0.000016198923,0.000057242014,0.0049245544,0.005659291,0.00007685878,0.00057989307,0.0011592389,0.00022505994,0.00065864925,0.0073723835,0.97921205,0.000058551876],"about_ca_topic_score_codex":0.03276519,"about_ca_topic_score_gemma":0.07735658,"teacher_disagreement_score":0.03276519,"about_ca_system_score_codex":0.002062039,"about_ca_system_score_gemma":0.007884875,"threshold_uncertainty_score":0.09439653},"labels":[],"label_agreement":null},{"id":"W4366384282","doi":"10.3138/cjpe.26.010","title":"D. Kahneman. (2011). <i>Thinking, Fast and Slow.</i> New York, NY: Farrar, Straus and Giroux. 499 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Critical Realism in Sociology","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Sociology; Criminology; Psychoanalysis","score_opus":0.22289122525737154,"score_gpt":0.3813127202992037,"score_spread":0.15842149504183217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384282","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001856814,0.5771763,0.065933734,0.15097024,0.011299365,0.00020965977,0.004167561,0.0011941309,0.18719229],"genre_scores_gemma":[0.08945033,0.66664547,0.08987501,0.018985473,0.0041035474,0.0011826854,0.0024639172,0.001202986,0.12609054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99854124,0.0004787743,0.00020429028,0.00014479554,0.00058106316,0.000049989154],"domain_scores_gemma":[0.9854004,0.009583919,0.000625643,0.00046736296,0.0036332356,0.00028952525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005494296,0.0015031863,0.00081587926,0.004233123,0.002519162,0.0030349556,0.0013134431,0.0028003396,0.03875881],"category_scores_gemma":[0.01759809,0.0014738524,0.0008139027,0.0035635298,0.0027360155,0.007906738,0.0012657192,0.0056866296,0.017734263],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006504501,0.00003926711,0.0005762226,0.00097139354,0.000027509343,0.000094553136,0.0013923306,0.00047591282,0.0001732951,0.07931013,0.70468605,0.21218838],"study_design_scores_gemma":[0.00006295256,0.00002964203,0.003797409,0.0028804664,0.0000996986,0.00037102416,0.0011801743,0.00057488744,0.0005776992,0.23895249,0.7513828,0.00009069856],"about_ca_topic_score_codex":0.025556037,"about_ca_topic_score_gemma":0.05179691,"teacher_disagreement_score":0.03875881,"about_ca_system_score_codex":0.0036573207,"about_ca_system_score_gemma":0.0043848404,"threshold_uncertainty_score":0.12966114},"labels":[],"label_agreement":null},{"id":"W4366384285","doi":"10.3138/cjpe.021.fm","title":"Editor’s Remarks","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.04557215191313067,"score_gpt":0.40773021983105295,"score_spread":0.36215806791792227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384285","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019584817,0.002100445,0.00015981735,0.4192388,0.57255,0.000038509923,0.00013502104,0.00009814525,0.0054833875],"genre_scores_gemma":[0.00242317,0.0014468664,0.0005354711,0.6906473,0.24950041,0.000088153334,0.000061879226,0.00008776889,0.05520894],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9859093,0.0014019986,0.0016398006,0.0022932652,0.0068736835,0.0018820065],"domain_scores_gemma":[0.94945836,0.012913154,0.0040876754,0.002767984,0.024587534,0.0061852224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013402311,0.0016833049,0.0027183741,0.0026552912,0.005106016,0.008830253,0.0049194517,0.03987717,0.030240754],"category_scores_gemma":[0.101881735,0.0012257845,0.0034668634,0.002101693,0.0031072043,0.0034195208,0.002548492,0.032939877,0.021962242],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023099663,0.000008101988,0.00006606419,0.000044451346,0.0000118807,0.00014837025,0.000024748026,0.000019061885,0.00004952483,0.0004695508,0.9968246,0.0023105391],"study_design_scores_gemma":[0.000049514383,0.00001653721,0.00062742207,0.00018600267,0.000037544112,0.00020176846,0.00009836243,0.0000878678,0.00018018027,0.0008043787,0.99767274,0.000037701335],"about_ca_topic_score_codex":0.013789554,"about_ca_topic_score_gemma":0.029784596,"teacher_disagreement_score":0.03987717,"about_ca_system_score_codex":0.0070825526,"about_ca_system_score_gemma":0.009447023,"threshold_uncertainty_score":0.101165354},"labels":[],"label_agreement":null},{"id":"W4366384291","doi":"10.3138/cjpe.0027.008","title":"Meta-evaluation: Evaluating the Evaluation of the Paris Declaration","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Evaluation methods; Meta-analysis; Strengths and weaknesses; Quality (philosophy); Psychology; Computer science; Management science; Political science; Medicine; Engineering; Social psychology; Law; Reliability engineering","score_opus":0.7957816232407139,"score_gpt":0.5870236538267359,"score_spread":0.20875796941397795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384291","genre_codex":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025178177,0.64227706,0.18998672,0.029565709,0.01696799,0.06784783,0.0104388995,0.002357204,0.0153803965],"genre_scores_gemma":[0.3841808,0.089818805,0.38352862,0.008918387,0.0024611673,0.12419115,0.0038406716,0.0008679447,0.0021924286],"study_design_codex":"meta_analysis","study_design_gemma":"qualitative","domain_scores_codex":[0.24525215,0.6534663,0.055706967,0.011114732,0.033023138,0.001436695],"domain_scores_gemma":[0.2137147,0.6713465,0.040806673,0.039967068,0.032048285,0.0021168482],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5605815,0.0065931156,0.022414906,0.01828751,0.0029705185,0.012880186,0.008840191,0.009127746,0.0073047457],"category_scores_gemma":[0.7187894,0.004439696,0.04626917,0.014352146,0.0063521597,0.009593047,0.007657841,0.008368249,0.00075028394],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010218103,0.00016766715,0.0042633624,0.33935347,0.5570449,0.00031189254,0.0013611089,0.005262394,0.00062718336,0.011824605,0.008868886,0.06069645],"study_design_scores_gemma":[0.008853332,0.0032378074,0.006272707,0.16967058,0.7379692,0.00022097761,0.00077166094,0.0074445037,0.002761218,0.02343993,0.03884091,0.00051723263],"about_ca_topic_score_codex":0.0072464305,"about_ca_topic_score_gemma":0.008389569,"teacher_disagreement_score":0.4394185,"about_ca_system_score_codex":0.022731338,"about_ca_system_score_gemma":0.020412836,"threshold_uncertainty_score":0.54188126},"labels":[],"label_agreement":null},{"id":"W4366384295","doi":"10.3138/cjpe.28.009","title":"Aldrick, J. O., &amp; Rodriguez, H. M. (2013). <i>Building SPSS Graphs to Understand Data.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics; Sociology; Statistics; Combinatorics","score_opus":0.1823983063883564,"score_gpt":0.3739319899069526,"score_spread":0.19153368351859618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384295","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018462986,0.05617537,0.6229767,0.1291332,0.0072080432,0.0013926427,0.01644432,0.0077882884,0.14041847],"genre_scores_gemma":[0.14476901,0.08118999,0.6823034,0.016169166,0.002300751,0.0019118642,0.00920749,0.0033005236,0.058847815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963225,0.0013594114,0.00034525082,0.00018368092,0.0017070142,0.000082158855],"domain_scores_gemma":[0.91535133,0.06348648,0.0041556843,0.002236193,0.0139147565,0.0008555954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011339428,0.0007230038,0.0005161675,0.008247463,0.0014492052,0.004112928,0.0015632838,0.0009644924,0.016657367],"category_scores_gemma":[0.101836085,0.0006107756,0.00071377534,0.008338155,0.002173287,0.004157667,0.0013819081,0.0027081617,0.008382142],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011766795,0.00007963171,0.0074341493,0.0015241908,0.00009239176,0.0001415791,0.002781312,0.0006479096,0.0012975528,0.015722249,0.43047854,0.5396828],"study_design_scores_gemma":[0.00008200234,0.00019284531,0.033451855,0.0031848247,0.0004443934,0.00055793603,0.005036926,0.0033869548,0.006090335,0.06851832,0.8788881,0.00016548033],"about_ca_topic_score_codex":0.018097369,"about_ca_topic_score_gemma":0.045373585,"teacher_disagreement_score":0.018097369,"about_ca_system_score_codex":0.0017902972,"about_ca_system_score_gemma":0.0037884095,"threshold_uncertainty_score":0.059969306},"labels":[],"label_agreement":null},{"id":"W4366384337","doi":"10.3138/cjpe.0026.009","title":"Creating a Dialogue between the Concepts of Complexity Paradigms and the Pragmatic Approaches Proposed for Evaluating Complex Interventions","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Complex Systems and Decision Making","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Psychology; Epistemology; Management science; Cognitive science; Computer science; Philosophy; Engineering","score_opus":0.7754094270046622,"score_gpt":0.5491954043938461,"score_spread":0.22621402261081613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384337","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004504159,0.006317611,0.43086073,0.532833,0.0029138431,0.0008564997,0.00010034531,0.00012154596,0.021492232],"genre_scores_gemma":[0.25984836,0.0055178963,0.6648194,0.059441082,0.0026239993,0.005437882,0.00008058703,0.00031579696,0.0019150394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5893615,0.35518155,0.014745661,0.006742768,0.030903896,0.0030646606],"domain_scores_gemma":[0.33166167,0.62286794,0.008606527,0.011920166,0.019383792,0.005559908],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39298752,0.0023249316,0.006394992,0.008427899,0.011137883,0.0382432,0.011755709,0.022336364,0.0051696287],"category_scores_gemma":[0.38717014,0.0027334902,0.0033095698,0.0043326374,0.10452688,0.047204033,0.022701958,0.048023157,0.0006691358],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028835464,0.00004812816,0.00014251651,0.0007213926,0.00007836603,0.00006759041,0.013911087,0.001303309,0.0001309862,0.9677912,0.004324883,0.011451781],"study_design_scores_gemma":[0.000081269114,0.000040111336,0.000105467065,0.0012968718,0.00003790396,0.00005509841,0.0037781273,0.0018433724,0.00016494874,0.9669688,0.025565755,0.00006218777],"about_ca_topic_score_codex":0.010229007,"about_ca_topic_score_gemma":0.015079403,"teacher_disagreement_score":0.6070125,"about_ca_system_score_codex":0.03241143,"about_ca_system_score_gemma":0.056728594,"threshold_uncertainty_score":0.74855447},"labels":[],"label_agreement":null},{"id":"W4366384338","doi":"10.3138/cjpe.0025.011","title":"Je me souviens … de t’avoir trop longtemps cherché","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Logic program; Set (abstract data type); Computer science; Process (computing); Expression (computer science); Epistemology; Artificial intelligence; Programming language; Philosophy; Logic programming","score_opus":0.6896710628632848,"score_gpt":0.5555406698966722,"score_spread":0.13413039296661267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384338","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104435235,0.011662257,0.06262589,0.2963946,0.008467258,0.00079847645,0.0012803794,0.0016720456,0.5126639],"genre_scores_gemma":[0.6101758,0.009912703,0.063293956,0.03130382,0.0011995962,0.0006463848,0.0005712171,0.001061424,0.2818351],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921876,0.0035466175,0.00017997711,0.00063357264,0.0026803182,0.0007719198],"domain_scores_gemma":[0.9854483,0.0054237833,0.001044123,0.0010244513,0.004975134,0.0020842238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0108747855,0.000736425,0.0006121872,0.00091830123,0.0052462546,0.006139483,0.0012589103,0.002359206,0.05179239],"category_scores_gemma":[0.03703518,0.0002917011,0.0006552032,0.001213818,0.0051976386,0.006539869,0.0025964219,0.006069471,0.008085007],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072343444,0.0008041572,0.015353809,0.0011545889,0.00020752978,0.0014900365,0.01603697,0.002140437,0.0051361253,0.2725843,0.35484874,0.32951993],"study_design_scores_gemma":[0.000081291335,0.0005462992,0.009917348,0.0017005897,0.00011205982,0.001079353,0.014336566,0.0011706583,0.0051041096,0.053008623,0.9127585,0.0001845543],"about_ca_topic_score_codex":0.027602883,"about_ca_topic_score_gemma":0.041837938,"teacher_disagreement_score":0.05179239,"about_ca_system_score_codex":0.0060777063,"about_ca_system_score_gemma":0.0103777805,"threshold_uncertainty_score":0.17326277},"labels":[],"label_agreement":null},{"id":"W4366384352","doi":"10.3138/cjpe.024.008","title":"Valéry Ridde &amp; Christian Dagenais (Éds.). (2009). <i>Approches et pratiques en évaluation de programme.</i> Montréal : Les Presses de l’Université de Montréal. 358 pages.","year":2009,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Art; Sociology","score_opus":0.14445123495851397,"score_gpt":0.4024079413428465,"score_spread":0.25795670638433255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384352","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001137338,0.9154152,0.0093242545,0.03434037,0.0041916748,0.00006511968,0.0014666223,0.0003417125,0.033717662],"genre_scores_gemma":[0.009355267,0.93545586,0.008671648,0.0016528411,0.0010566809,0.000058567624,0.0006960609,0.00012571077,0.042927317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984775,0.00044504827,0.00011495977,0.0001815731,0.00069409335,0.00008685542],"domain_scores_gemma":[0.99489355,0.0024096176,0.00029732013,0.00013976159,0.0019342147,0.00032545908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035563041,0.0016151614,0.0010699593,0.0028039266,0.00091511454,0.0042512813,0.0013935162,0.002137548,0.027050842],"category_scores_gemma":[0.0073691946,0.0010200216,0.00043622294,0.0046285116,0.0010574295,0.0051023304,0.001031792,0.0021433858,0.01819072],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005744723,0.000029096682,0.0007689129,0.0016228495,0.000026949325,0.000046546942,0.0005456414,0.00047673594,0.00017311102,0.002856027,0.5894893,0.4039074],"study_design_scores_gemma":[0.000026915583,0.000037529622,0.0032370691,0.0036986067,0.00008022905,0.00021104969,0.0009386429,0.00032398052,0.0008103264,0.005244094,0.9853495,0.000042052594],"about_ca_topic_score_codex":0.06428203,"about_ca_topic_score_gemma":0.14759018,"teacher_disagreement_score":0.06428203,"about_ca_system_score_codex":0.002757591,"about_ca_system_score_gemma":0.0072442014,"threshold_uncertainty_score":0.12781572},"labels":[],"label_agreement":null},{"id":"W4366384395","doi":"10.3138/cjpe.024.006","title":"Evaluating the Early Implementation of a Community Crisis Bed Program for People Experiencing a Psychiatric Emergency Using Key Component Scaling","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Emergency and Acute Care Studies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Key (lock); Component (thermodynamics); Stakeholder; Qualitative property; Psychology; Process management; Multidimensional scaling; Program evaluation; Public relations; Computer science; Applied psychology; Medical education; Business; Medicine; Political science; Computer security; Public administration","score_opus":0.18630967376502514,"score_gpt":0.49501469280625454,"score_spread":0.3087050190412294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9773586,0.000109411354,0.0019618024,0.00030900043,0.000048914055,0.01691522,0.00011828203,0.00007474574,0.0031040662],"genre_scores_gemma":[0.9585552,0.00031932245,0.0214502,0.00023064336,0.000027845705,0.018423548,0.00021647441,0.00001852673,0.00075812906],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97730106,0.016355842,0.0012207731,0.00044368193,0.002791087,0.001887586],"domain_scores_gemma":[0.980514,0.008930788,0.0019357234,0.0010101852,0.0053233514,0.0022859406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018008782,0.0009172619,0.00092384627,0.001416199,0.0027303072,0.0014299428,0.0019452948,0.00069112383,0.0026201783],"category_scores_gemma":[0.033707645,0.0006697557,0.0010599514,0.0012336728,0.0010017935,0.0014737044,0.002911853,0.0019316135,0.00021948956],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012583252,0.16661014,0.060005236,0.0073013413,0.0006152047,0.00081106095,0.046261583,0.0067699174,0.006845197,0.0020306527,0.0036126047,0.6865537],"study_design_scores_gemma":[0.015329622,0.4258566,0.38975865,0.0035374137,0.0015040884,0.0004537918,0.09793685,0.011284623,0.032046393,0.0017698661,0.020053156,0.0004690325],"about_ca_topic_score_codex":0.0165717,"about_ca_topic_score_gemma":0.027861161,"teacher_disagreement_score":0.018008782,"about_ca_system_score_codex":0.0067659304,"about_ca_system_score_gemma":0.01766402,"threshold_uncertainty_score":0.09524071},"labels":[],"label_agreement":null},{"id":"W4366384398","doi":"10.3138/cjpe.0025.004","title":"L’influence de l’évaluation sur les suites des projets d’expérimentation : l’exemple des projets d’informatisation au Québec","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université Laval","funders":"","keywords":"Formative assessment; Valuation (finance); Political science; Action plan; Knowledge management; Business; Sociology; Pedagogy; Management; Computer science; Economics; Accounting","score_opus":0.3539878063192124,"score_gpt":0.47094040675696225,"score_spread":0.11695260043774985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81185305,0.0021353217,0.026601056,0.015633931,0.00023323447,0.0013557412,0.00040411568,0.00062215317,0.14116137],"genre_scores_gemma":[0.979388,0.00039491543,0.009912152,0.00049016025,0.000033534692,0.00037899317,0.000118937074,0.00007973521,0.009203564],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9180002,0.053743783,0.0024443294,0.002082518,0.020048527,0.0036806234],"domain_scores_gemma":[0.7768592,0.15442881,0.0059432895,0.0068827937,0.05014703,0.0057388814],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.057618354,0.0007671224,0.0005572413,0.002455872,0.007221262,0.008110403,0.0015499198,0.0023407638,0.004910282],"category_scores_gemma":[0.10174118,0.0005142152,0.00068967696,0.002409832,0.0048728525,0.0024966425,0.0032676186,0.0024468922,0.00061715505],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002507118,0.0035644907,0.10648521,0.0031789613,0.0005021795,0.002707517,0.08049993,0.03229525,0.028100519,0.041132607,0.022667287,0.676359],"study_design_scores_gemma":[0.0011722189,0.008397176,0.5133616,0.0035846715,0.00066841044,0.0009389591,0.06875515,0.045249544,0.060848527,0.012507986,0.2835401,0.00097560725],"about_ca_topic_score_codex":0.5848097,"about_ca_topic_score_gemma":0.5856932,"teacher_disagreement_score":0.9600584,"about_ca_system_score_codex":0.039941594,"about_ca_system_score_gemma":0.043524638,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W4366384407","doi":"10.3138/cjpe.0025.015","title":"Réflexions autour des 25 ans de la <i>Revue canadienne d’évaluation de programme</i> : l’évaluation au passé, au présent, et au futur","year":2011,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Economics; Humanities; Philosophy","score_opus":0.3511264130259222,"score_gpt":0.4670286099850321,"score_spread":0.11590219695910992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384407","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021454824,0.27471104,0.004868824,0.5680349,0.08189624,0.00059926236,0.0022097402,0.00027935347,0.04594585],"genre_scores_gemma":[0.3638857,0.22583319,0.021493828,0.2134878,0.03330845,0.0027316045,0.0038919067,0.0006882611,0.1346793],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9285316,0.023293925,0.009728003,0.0033585143,0.030549286,0.0045386255],"domain_scores_gemma":[0.7839078,0.063842654,0.015907228,0.006953795,0.11660831,0.012780349],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10877324,0.0011938467,0.0014027507,0.006306199,0.0032867081,0.011884683,0.0028470655,0.008692045,0.0069882027],"category_scores_gemma":[0.17910767,0.0007671926,0.0019731536,0.0067068934,0.005062959,0.0038223441,0.005100145,0.010868858,0.0019064641],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014139793,0.00039108988,0.0084616635,0.008210481,0.00042350098,0.00076000724,0.0198163,0.0012251217,0.005453448,0.038118813,0.6021819,0.31354377],"study_design_scores_gemma":[0.000067453555,0.00013664993,0.0133402245,0.0058569214,0.00013287949,0.00011348455,0.002550831,0.0001165991,0.0017663194,0.0016236167,0.9742138,0.00008130193],"about_ca_topic_score_codex":0.22992335,"about_ca_topic_score_gemma":0.26410633,"teacher_disagreement_score":0.9626744,"about_ca_system_score_codex":0.037325602,"about_ca_system_score_gemma":0.08860423,"threshold_uncertainty_score":0.57525474},"labels":[],"label_agreement":null},{"id":"W4366384488","doi":"10.3138/cjpe.0025.006","title":"Chronique d’une évaluation ratée","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Charter; Confusion; Transparency (behavior); Pluralism (philosophy); Valuation (finance); Management science; Engineering ethics; Political science; Arbitration; Public relations; Sociology; Law and economics; Epistemology; Business; Psychology; Law; Accounting; Economics; Engineering","score_opus":0.6502887605764812,"score_gpt":0.5430176093994878,"score_spread":0.10727115117699337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384488","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080807894,0.019391375,0.17680924,0.03321411,0.027815225,0.013682728,0.02303982,0.008087579,0.6171521],"genre_scores_gemma":[0.39308587,0.015077216,0.20955239,0.0034941877,0.004255692,0.023936236,0.012789364,0.0038848934,0.3339241],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9482058,0.01745829,0.0075622494,0.0034004918,0.020811316,0.0025618123],"domain_scores_gemma":[0.86031747,0.033732813,0.0058630346,0.009372525,0.086637095,0.0040771156],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03903316,0.0015089134,0.0014043922,0.009309327,0.004886231,0.0090657575,0.0018930221,0.0019318279,0.080548525],"category_scores_gemma":[0.1003389,0.00086447847,0.001406657,0.0050154193,0.0022209045,0.0057236976,0.004741706,0.005061343,0.029518165],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021430673,0.00030366099,0.012002124,0.002739342,0.00009327125,0.0007676321,0.0058450885,0.0010997962,0.010167626,0.08051061,0.23722301,0.64710474],"study_design_scores_gemma":[0.00012852497,0.0004270073,0.015005251,0.0014510967,0.000040121144,0.0009476738,0.0036687162,0.0016765617,0.011206236,0.005492732,0.9597936,0.00016240263],"about_ca_topic_score_codex":0.012988829,"about_ca_topic_score_gemma":0.007327744,"teacher_disagreement_score":0.9609668,"about_ca_system_score_codex":0.008643104,"about_ca_system_score_gemma":0.009410789,"threshold_uncertainty_score":0.26946163},"labels":[],"label_agreement":null},{"id":"W4366384492","doi":"10.3138/cjpe.0025.001","title":"Guest Editor’s Remarks: As I Recall—or How to take Advantage of Less-Than-Successful Evaluation Experiences","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Recall; Psychology; Cognitive psychology","score_opus":0.3693533046613303,"score_gpt":0.5143513771140032,"score_spread":0.14499807245267293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384492","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020257624,0.0008544832,0.00030059155,0.7560992,0.24171141,0.000014404019,0.0000560181,0.000043931137,0.0007173723],"genre_scores_gemma":[0.0032138852,0.0011834166,0.0010627104,0.8014431,0.18441027,0.000047629645,0.000027476372,0.00007468204,0.008536814],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98531437,0.002485628,0.0031972213,0.0021516222,0.0055113817,0.0013397697],"domain_scores_gemma":[0.87862736,0.04040028,0.00818009,0.0037825939,0.059220105,0.009789491],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022458509,0.0011897116,0.0020288406,0.0010032654,0.0047460604,0.008776648,0.003897532,0.02777386,0.006994546],"category_scores_gemma":[0.15238777,0.0009434187,0.0019312376,0.0014006484,0.004488702,0.0055731614,0.003018796,0.050292153,0.0055841208],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002604281,0.000011205894,0.00018325615,0.00005995901,0.000012722026,0.00015784084,0.0001281339,0.000025388266,0.00005372098,0.00066158146,0.9962174,0.0024626849],"study_design_scores_gemma":[0.00006302376,0.000041686046,0.0013149957,0.00053518417,0.000072553674,0.0006093728,0.0011389161,0.0003611236,0.0004768489,0.0033394701,0.9919098,0.00013701674],"about_ca_topic_score_codex":0.00795879,"about_ca_topic_score_gemma":0.016794322,"teacher_disagreement_score":0.9775415,"about_ca_system_score_codex":0.004164551,"about_ca_system_score_gemma":0.009609121,"threshold_uncertainty_score":0.11877334},"labels":[],"label_agreement":null},{"id":"W4366384497","doi":"10.3138/cjpe.0025.017","title":"Succès mitigés","year":2011,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business","score_opus":0.27528837891174407,"score_gpt":0.3623561457995736,"score_spread":0.08706776688782952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384497","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01788477,0.002264632,0.01341328,0.017359419,0.0027622895,0.00047918945,0.001378511,0.00076027313,0.9436977],"genre_scores_gemma":[0.1756736,0.002471838,0.009179232,0.010499812,0.0010071041,0.00052001484,0.0013800906,0.000520793,0.7987475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912231,0.0021262842,0.00032841155,0.0010365335,0.0038210368,0.0014647028],"domain_scores_gemma":[0.98576134,0.002284196,0.0010085745,0.0031426577,0.0060614715,0.0017416878],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067397305,0.0011848577,0.00076878176,0.0034734542,0.0041193296,0.00588028,0.0015490412,0.0022140394,0.10704199],"category_scores_gemma":[0.022722956,0.00037966494,0.0012941209,0.0013948041,0.0024278285,0.0035165325,0.0050509945,0.004052388,0.02203024],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024975443,0.0003396738,0.009106406,0.00041723312,0.0001241141,0.00084446743,0.001942123,0.0009545776,0.0015343471,0.41055822,0.25166148,0.3222675],"study_design_scores_gemma":[0.000023338738,0.00009594633,0.0031923542,0.00035828596,0.000058639285,0.00051115453,0.0012226963,0.00058404723,0.0011337242,0.03882651,0.95397085,0.000022419592],"about_ca_topic_score_codex":0.013281909,"about_ca_topic_score_gemma":0.024182474,"teacher_disagreement_score":0.99326026,"about_ca_system_score_codex":0.0037390173,"about_ca_system_score_gemma":0.008167772,"threshold_uncertainty_score":0.35809112},"labels":[],"label_agreement":null},{"id":"W4366384499","doi":"10.3138/cjpe.0025.013","title":"Learning from Evaluation Misadventures: The Importance of Good Communication","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Relevance (law); Key (lock); Order (exchange); Quality (philosophy); Government (linguistics); Knowledge management; Process management; Management science; Computer science; Business; Psychology; Risk analysis (engineering); Engineering ethics; Political science; Engineering; Epistemology; Artificial intelligence; Computer security","score_opus":0.48907842534633805,"score_gpt":0.5126845869829371,"score_spread":0.02360616163659901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384499","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27239677,0.013677155,0.10701197,0.35899815,0.0020507558,0.00074605265,0.000105359344,0.00087409373,0.24413976],"genre_scores_gemma":[0.9635128,0.003070448,0.017043183,0.010281767,0.0005116174,0.00023554775,0.00004074524,0.00016935091,0.005134731],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7629034,0.18716301,0.0056029484,0.0025818124,0.03759671,0.0041521452],"domain_scores_gemma":[0.6346002,0.27669862,0.019291548,0.016900824,0.041683793,0.0108250445],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1080659,0.0006719336,0.00082823663,0.0022831813,0.008539323,0.0182383,0.001968287,0.005425428,0.0045195003],"category_scores_gemma":[0.28937492,0.00061160635,0.00055820425,0.0011730789,0.014125547,0.014323776,0.011466245,0.008659351,0.0011010934],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004003011,0.00076065795,0.030993892,0.002152093,0.00024854526,0.0027705908,0.23851646,0.0021149165,0.002615201,0.07905122,0.05729309,0.58308303],"study_design_scores_gemma":[0.00021986377,0.001515726,0.03845779,0.011782215,0.0003085365,0.007862164,0.28901526,0.006814487,0.013092779,0.29697463,0.33328333,0.00067315024],"about_ca_topic_score_codex":0.002764856,"about_ca_topic_score_gemma":0.0032100938,"teacher_disagreement_score":0.8919341,"about_ca_system_score_codex":0.006700238,"about_ca_system_score_gemma":0.011281131,"threshold_uncertainty_score":0.57151395},"labels":[],"label_agreement":null},{"id":"W4366384503","doi":"10.3138/cjpe.0025.012","title":"Management Challenges in M&amp;E: Thoughts from South Africa","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Land Rights and Reforms","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Narrative; Set (abstract data type); Politics; Key (lock); Government (linguistics); Political science; Unit (ring theory); Public relations; Environmental resource management; Sociology; Economic growth; Process management; Business; Psychology; Computer science; Economics; Mathematics education; Computer security; Linguistics","score_opus":0.2722744450041827,"score_gpt":0.28963756497649307,"score_spread":0.01736311997231038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384503","genre_codex":"empirical","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8020481,0.0033393032,0.0024023836,0.13271329,0.00040329815,0.00020935194,0.00006793727,0.000019863193,0.05879653],"genre_scores_gemma":[0.9900332,0.0011288367,0.00049467204,0.0039217332,0.000046752066,0.00007265444,0.0000081502885,0.000021063986,0.0042729983],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.98701596,0.009226011,0.00023796757,0.00039229993,0.00076418143,0.0023636622],"domain_scores_gemma":[0.9897591,0.0071428795,0.0007981798,0.00015934226,0.000794456,0.0013461472],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014894654,0.0007618407,0.0005359197,0.0012976805,0.032167386,0.011258486,0.0015030826,0.0046654944,0.0041469387],"category_scores_gemma":[0.01605284,0.0005902903,0.00033397056,0.0014714068,0.023128133,0.006857414,0.010709554,0.009100879,0.0002971389],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001727157,0.000018022265,0.0006979969,0.00007751557,0.0000028100706,0.001358049,0.98433685,0.000049219623,0.00032990918,0.010192428,0.0012671491,0.0016527496],"study_design_scores_gemma":[0.0000022660704,0.0000122334495,0.0003800749,0.000132336,0.0000017473684,0.00019535233,0.98097813,0.00003518343,0.00016297752,0.0007383532,0.017353915,0.0000074208397],"about_ca_topic_score_codex":0.034237,"about_ca_topic_score_gemma":0.044062726,"teacher_disagreement_score":0.98510534,"about_ca_system_score_codex":0.01359888,"about_ca_system_score_gemma":0.008841098,"threshold_uncertainty_score":0.098667264},"labels":[],"label_agreement":null},{"id":"W4366384617","doi":"10.3138/cjpe.0025.003","title":"Evaluation, Valuation, Negotiation: Some Reflections Towards a Culture of Evaluation","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Negotiation; Valuation (finance); Consolidation (business); Contingent valuation; Program evaluation; Management science; Political science; Process management; Business; Knowledge management; Computer science; Economics; Public administration; Willingness to pay; Accounting","score_opus":0.6159822124301794,"score_gpt":0.5735759694267458,"score_spread":0.04240624300343354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384617","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04864324,0.017272495,0.09471501,0.7133722,0.0019766544,0.0005866474,0.000038695915,0.00012504376,0.12327016],"genre_scores_gemma":[0.9358225,0.003963969,0.029519476,0.02648015,0.0005941353,0.00051038375,0.000016539714,0.00017704909,0.0029157521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.6287852,0.33212945,0.0061753695,0.0052202586,0.02112908,0.0065606856],"domain_scores_gemma":[0.6564512,0.2802008,0.010632851,0.011955998,0.03332828,0.007430883],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2813388,0.0011968612,0.0019927267,0.0053325896,0.023931775,0.060404424,0.0071983594,0.016373862,0.0020497504],"category_scores_gemma":[0.16680953,0.0013325125,0.0014174667,0.005810956,0.2204433,0.03328304,0.023791045,0.036356363,0.0003083672],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043725227,0.00008411501,0.00077163725,0.0002601276,0.000031201726,0.00035216263,0.2111118,0.00060429913,0.00018720215,0.7700631,0.0039017468,0.012588851],"study_design_scores_gemma":[0.00012511195,0.00012487319,0.000817602,0.0021119874,0.000033052274,0.00058951415,0.3103488,0.0027147175,0.00074173155,0.5346395,0.14757816,0.00017496862],"about_ca_topic_score_codex":0.022409875,"about_ca_topic_score_gemma":0.01075391,"teacher_disagreement_score":0.7186612,"about_ca_system_score_codex":0.050644543,"about_ca_system_score_gemma":0.04717123,"threshold_uncertainty_score":0.8862372},"labels":[],"label_agreement":null},{"id":"W4366384628","doi":"10.3138/cjpe.0025.002","title":"Un mot de la rédactrice invitée: « Je me souviens » ou comment tirer profit d’expériences d’évaluation qu’on ne peut qualifier de succès","year":2011,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Valuation (finance); Political science; Humanities; Economics; Philosophy","score_opus":0.5043602781342642,"score_gpt":0.522399082584033,"score_spread":0.018038804449768797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384628","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045744744,0.003173621,0.003269286,0.9515749,0.016606983,0.00009560847,0.00011153676,0.0001457338,0.020447735],"genre_scores_gemma":[0.16359155,0.0035696356,0.012372678,0.6952833,0.007406596,0.000824428,0.00019233063,0.00071748276,0.11604211],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8974508,0.06589087,0.005087074,0.0039128093,0.023245027,0.00441335],"domain_scores_gemma":[0.78545946,0.10662972,0.0102654165,0.011746723,0.07027999,0.01561881],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07339956,0.000978029,0.0010602075,0.0014125307,0.01304001,0.01698648,0.002837485,0.019768214,0.012767456],"category_scores_gemma":[0.27076155,0.0007352645,0.00137436,0.0016527646,0.017388882,0.014936965,0.009664898,0.033909425,0.004082157],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029906642,0.00017450281,0.002613217,0.0010571011,0.0000771245,0.00049953954,0.061670016,0.00017389096,0.0017687731,0.12063254,0.7490415,0.061992656],"study_design_scores_gemma":[0.00007669177,0.00009575617,0.0016432154,0.0013884035,0.00005108082,0.00060581026,0.025647601,0.00023345379,0.0013252983,0.015505247,0.9533077,0.00011984473],"about_ca_topic_score_codex":0.028299548,"about_ca_topic_score_gemma":0.05071961,"teacher_disagreement_score":0.92660046,"about_ca_system_score_codex":0.012892905,"about_ca_system_score_gemma":0.03632976,"threshold_uncertainty_score":0.3881786},"labels":[],"label_agreement":null},{"id":"W4366384635","doi":"10.3138/cjpe.0025.014","title":"Reflections Over 25 Years: Evaluation Then, Now, and Into the Future","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Political science","score_opus":0.390329876993874,"score_gpt":0.5523569994362977,"score_spread":0.16202712244242368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384635","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089936316,0.099405356,0.0070351767,0.7463313,0.018041797,0.00054373307,0.00075119716,0.00041699462,0.037538163],"genre_scores_gemma":[0.8284143,0.045956206,0.015189126,0.070438355,0.0029000272,0.00088368804,0.0009151359,0.0003216939,0.03498151],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9176175,0.049046088,0.0043194206,0.0024331629,0.017178627,0.009405205],"domain_scores_gemma":[0.84847814,0.035316754,0.009583428,0.005762397,0.05665063,0.04420864],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.115402,0.0009275298,0.0010932991,0.0020439045,0.0062077753,0.01774278,0.0033545725,0.0044471193,0.007511135],"category_scores_gemma":[0.18074769,0.00048461804,0.0011993463,0.0030057158,0.00604977,0.012476697,0.010425021,0.012097558,0.0013614589],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009547692,0.0011685689,0.01813171,0.0015151118,0.0001829585,0.00066884805,0.044347517,0.0007238952,0.0013721647,0.039326172,0.17511734,0.716491],"study_design_scores_gemma":[0.00014047045,0.001610656,0.03894117,0.0062334435,0.00021302803,0.00055733806,0.16577159,0.00054566393,0.0024004634,0.021818342,0.7614441,0.0003237271],"about_ca_topic_score_codex":0.04032911,"about_ca_topic_score_gemma":0.080328,"teacher_disagreement_score":0.9808179,"about_ca_system_score_codex":0.019182075,"about_ca_system_score_gemma":0.08079951,"threshold_uncertainty_score":0.6103114},"labels":[],"label_agreement":null},{"id":"W4366384695","doi":"10.3138/cjpe.24.010","title":"D. L. Streiner &amp; S. Sidani (Eds.). (2010). <i>When Research Goes Off the Rails: Why It Happens and What You Can Do About It.</i> New York, NY: Guilford. 398 Pages.","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Interdisciplinary Research and Collaboration","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Sociology; Media studies","score_opus":0.40580709701726325,"score_gpt":0.48228736315699644,"score_spread":0.07648026613973319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384695","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00094284024,0.9065682,0.0058755414,0.04223673,0.0044917427,0.000047355552,0.0011296903,0.00040939203,0.038298514],"genre_scores_gemma":[0.006653764,0.9458585,0.0072489944,0.0017856272,0.0012378042,0.000042800606,0.0006420419,0.00013066993,0.036399778],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989961,0.00023874402,0.00010763899,0.00010126686,0.0004914642,0.000064772226],"domain_scores_gemma":[0.9965185,0.0017088136,0.0003215846,0.00008137752,0.00094322686,0.00042651704],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0028697704,0.0020241346,0.0011317832,0.0029424322,0.001129289,0.00474048,0.0014629617,0.0023840873,0.03212147],"category_scores_gemma":[0.0045743897,0.0011792476,0.0004401722,0.0049209436,0.0011789668,0.0055055995,0.001191646,0.0026127049,0.02939784],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036801448,0.000021496578,0.00047749656,0.00093530497,0.000013862342,0.00004132178,0.00034562976,0.00022259189,0.00011225687,0.0018782921,0.6005671,0.3953478],"study_design_scores_gemma":[0.000022922059,0.000043579308,0.0034545504,0.0039786114,0.00007876599,0.00032686727,0.0013471001,0.0003843162,0.0006804662,0.007235278,0.98239917,0.000048324462],"about_ca_topic_score_codex":0.039974563,"about_ca_topic_score_gemma":0.12094926,"teacher_disagreement_score":0.99761593,"about_ca_system_score_codex":0.0026315188,"about_ca_system_score_gemma":0.006530309,"threshold_uncertainty_score":0.10745704},"labels":[],"label_agreement":null},{"id":"W4366384698","doi":"10.3138/cjpe.0025.005","title":"Successful Evaluation Management: Engaging Mind and Spirit","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outcome (game theory); Quality (philosophy); Affect (linguistics); Psychology; Key (lock); Evaluation methods; Engineering ethics; Business; Process management; Public relations; Computer science; Political science; Epistemology; Engineering; Philosophy; Economics","score_opus":0.5238099666472505,"score_gpt":0.5252574195694363,"score_spread":0.0014474529221857324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384698","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15379876,0.0051578926,0.20179833,0.2598564,0.0024118358,0.0021769896,0.000039491268,0.0011417727,0.37361857],"genre_scores_gemma":[0.90028733,0.0014301633,0.06907823,0.012625655,0.0006558445,0.0008484211,0.00003288395,0.00018523129,0.014856204],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88442945,0.09089446,0.0023985824,0.0015593264,0.017398957,0.0033192204],"domain_scores_gemma":[0.89302915,0.054008644,0.00832499,0.0054766955,0.016786937,0.022373555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08290006,0.00055301125,0.0005980583,0.0020562322,0.007868476,0.019676616,0.001692952,0.00333467,0.0027910753],"category_scores_gemma":[0.11287352,0.0005278536,0.0005388848,0.0009015507,0.0128065385,0.0063367714,0.015866397,0.0067785294,0.0011369891],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018752296,0.0015654323,0.017616985,0.0011388339,0.0002312305,0.0014429818,0.14828894,0.0018376596,0.0039420095,0.24166958,0.10960292,0.4724759],"study_design_scores_gemma":[0.00026365634,0.0009441081,0.024703933,0.0035902462,0.00011875307,0.002494254,0.12684749,0.009034522,0.004577732,0.41117194,0.41595197,0.0003014765],"about_ca_topic_score_codex":0.0008829373,"about_ca_topic_score_gemma":0.0012541577,"teacher_disagreement_score":0.91709995,"about_ca_system_score_codex":0.00674492,"about_ca_system_score_gemma":0.02261755,"threshold_uncertainty_score":0.43842268},"labels":[],"label_agreement":null},{"id":"W4366384703","doi":"10.3138/cjpe.0025.016","title":"Incomplete Successes","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Legal principles and applications","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Political science","score_opus":0.33232416739307524,"score_gpt":0.43096074881282304,"score_spread":0.09863658141974779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384703","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19815676,0.0015180436,0.066068076,0.006236182,0.00053273,0.0011108331,0.016191904,0.0009780292,0.70920753],"genre_scores_gemma":[0.8459242,0.00091058615,0.017343063,0.0008396708,0.00022243768,0.0013211432,0.008264878,0.00046928087,0.12470476],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97476,0.0059998604,0.0018274402,0.0029444029,0.01147332,0.0029950289],"domain_scores_gemma":[0.91017455,0.036491565,0.007777606,0.020371959,0.022006486,0.0031779222],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01603734,0.0009670804,0.001959288,0.005595324,0.003147231,0.0047308784,0.0021812753,0.001433905,0.046318296],"category_scores_gemma":[0.09961239,0.0005595237,0.0010813407,0.0047559086,0.004081188,0.0082680825,0.0063122166,0.002990272,0.006561762],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004475658,0.0002644532,0.038006887,0.0009578869,0.00020909918,0.00039733082,0.007442806,0.0032743192,0.00058619044,0.65336776,0.05016799,0.2448778],"study_design_scores_gemma":[0.000081083715,0.00034177228,0.04888079,0.001263419,0.00033151556,0.00090773735,0.0094131995,0.008249747,0.003154729,0.5458057,0.3814515,0.000118856515],"about_ca_topic_score_codex":0.008263079,"about_ca_topic_score_gemma":0.01156894,"teacher_disagreement_score":0.98396266,"about_ca_system_score_codex":0.0035707313,"about_ca_system_score_gemma":0.005576407,"threshold_uncertainty_score":0.15495014},"labels":[],"label_agreement":null},{"id":"W4366384728","doi":"10.3138/cjpe.0025.009","title":"Navigating Expectations, Values and Context: A Canadian Evaluator Abroad","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Politics; Political science; Psychology; Public relations; Sociology; History; Law; Archaeology","score_opus":0.3205900033941147,"score_gpt":0.530989583284331,"score_spread":0.2103995798902163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384728","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7514963,0.0019949449,0.00411264,0.12276025,0.0010778785,0.00040234497,0.00012557102,0.00012947222,0.1179006],"genre_scores_gemma":[0.97019494,0.00070181047,0.0020505877,0.00672133,0.000037060945,0.000070890106,0.00005136235,0.00008364598,0.020088414],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.96092457,0.01956055,0.000651796,0.00184542,0.0071965386,0.009821148],"domain_scores_gemma":[0.9597682,0.006826143,0.0012361159,0.00080549985,0.018277172,0.0130868405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033956867,0.00066841656,0.00062514225,0.0017422887,0.062271778,0.017836973,0.0033658398,0.0051611313,0.00416262],"category_scores_gemma":[0.031915337,0.00067251304,0.00059309084,0.0019140189,0.01742392,0.004162744,0.008619846,0.010775846,0.00064786547],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017297255,0.00040138027,0.015292489,0.000097087395,0.000028476348,0.003007609,0.88802487,0.0007498288,0.0013954351,0.014801916,0.042999566,0.033028327],"study_design_scores_gemma":[0.000018728402,0.00013099312,0.004769409,0.00020051993,0.000017266153,0.00034837882,0.85404944,0.00072620396,0.0007596398,0.0013173,0.13753892,0.00012315116],"about_ca_topic_score_codex":0.86538696,"about_ca_topic_score_gemma":0.92952615,"teacher_disagreement_score":0.86538696,"about_ca_system_score_codex":0.10247467,"about_ca_system_score_gemma":0.16718788,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4366384908","doi":"10.3138/cjpe.0027.003","title":"The Paris Declaration on aid Effectiveness: History and Significance","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"International Development and Aid","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Context (archaeology); Relevance (law); Harmonization; Political science; Accountability; Diversity (politics); Public administration; Law; History","score_opus":0.08823242356445216,"score_gpt":0.3453501775041823,"score_spread":0.25711775393973013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384908","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007813304,0.07099068,0.016941432,0.39118198,0.009595066,0.00024929817,0.0010658844,0.00038658298,0.50177574],"genre_scores_gemma":[0.68608534,0.05360648,0.033698756,0.086384006,0.009781689,0.0012802507,0.0014130814,0.00064156245,0.12710889],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8677985,0.07648567,0.005925958,0.004826924,0.038930163,0.006032743],"domain_scores_gemma":[0.87717116,0.07928059,0.0074161617,0.005620462,0.027051095,0.003460512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.086213045,0.0013277207,0.0009063226,0.0057139695,0.008103444,0.03128666,0.0033616743,0.0087759765,0.009649047],"category_scores_gemma":[0.105270326,0.00065423973,0.0007294238,0.0052255187,0.034244403,0.010017305,0.014178717,0.012606512,0.001808579],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041531977,0.000028086615,0.0006396766,0.0003792243,0.000018749517,0.00009216645,0.0033528898,0.0007756624,0.00005117551,0.84802043,0.088300034,0.05830025],"study_design_scores_gemma":[0.000019646284,0.000056025638,0.0015143616,0.0024363692,0.000019280831,0.00010387989,0.0034030806,0.00030771317,0.00059566315,0.06117608,0.9302664,0.000101530044],"about_ca_topic_score_codex":0.039620556,"about_ca_topic_score_gemma":0.018293217,"teacher_disagreement_score":0.086213045,"about_ca_system_score_codex":0.03792822,"about_ca_system_score_gemma":0.054195553,"threshold_uncertainty_score":0.45594358},"labels":[],"label_agreement":null},{"id":"W4366385078","doi":"10.3138/cjpe.0025.008","title":"La figure de l’évaluateur, mi-ingénieur mi-bricoleur","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Context (archaeology); Process (computing); Field (mathematics); Focus (optics); Health promotion; Quality (philosophy); Sociology; Computer science; Knowledge management; Public relations; Political science; Public health; Epistemology; Medicine; Nursing; Geography; Politics","score_opus":0.46755217661853343,"score_gpt":0.4971907212220889,"score_spread":0.029638544603555472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366385078","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09921674,0.018564485,0.05577563,0.31720763,0.013045333,0.0006971362,0.0005944732,0.002741954,0.49215657],"genre_scores_gemma":[0.55044466,0.005210225,0.020414764,0.023893874,0.0017533251,0.00056942063,0.00022611549,0.0017169042,0.39577076],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98378134,0.009435544,0.000403548,0.0010496988,0.0044877236,0.0008422566],"domain_scores_gemma":[0.9865085,0.0037568877,0.000571532,0.0007929282,0.006109565,0.0022605695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014173386,0.0008204678,0.00047799826,0.0016448573,0.008212451,0.009168847,0.0009418946,0.0035912793,0.027247168],"category_scores_gemma":[0.024328463,0.0005365934,0.0007135471,0.00096297055,0.0056167357,0.004703955,0.003874544,0.0062213573,0.0071318476],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005943436,0.00037511674,0.006109546,0.00070510205,0.000073160576,0.0024845873,0.13851675,0.0009254385,0.009848135,0.16965014,0.45610672,0.21461096],"study_design_scores_gemma":[0.000022777205,0.00008957902,0.0020379946,0.00022432709,0.000010090229,0.0005419403,0.011688597,0.00036615817,0.001257757,0.002097273,0.9816103,0.000053261425],"about_ca_topic_score_codex":0.07538921,"about_ca_topic_score_gemma":0.045037594,"teacher_disagreement_score":0.07538921,"about_ca_system_score_codex":0.0127348,"about_ca_system_score_gemma":0.0117366165,"threshold_uncertainty_score":0.1499008},"labels":[],"label_agreement":null},{"id":"W4366446333","doi":"10.3138/cjpe.024.003","title":"Décentralisation et renforcement des capacités de suivi-évaluation des collectivités territoriales : expériences de l’afrique de l’ouest","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Centralisation; Valuation (finance); Political science; Regional science; Developing country; Geography; Welfare economics; Economic growth; Economics; Accounting","score_opus":0.14801289380178623,"score_gpt":0.4212520019667107,"score_spread":0.27323910816492447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9286079,0.0006438989,0.003817291,0.0041575953,0.000035273548,0.00017855853,0.000058461304,0.00004672736,0.062454212],"genre_scores_gemma":[0.9951338,0.00010512059,0.0005395744,0.000065160835,0.0000075348617,0.000048231323,0.000013812787,0.000015918038,0.0040707546],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9755612,0.01765552,0.00057143474,0.00092136266,0.0027917738,0.0024985666],"domain_scores_gemma":[0.96313775,0.020872531,0.002423059,0.0026592002,0.008242958,0.0026645365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03314109,0.00031740952,0.0005787133,0.0011800886,0.0066718636,0.005546483,0.0013130778,0.001217691,0.0057583186],"category_scores_gemma":[0.03319301,0.00034332337,0.00050237624,0.0013343641,0.007821212,0.0030668264,0.0045312527,0.0020568587,0.0005234792],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009674274,0.0011969067,0.117513604,0.0006720156,0.00015129833,0.00058046944,0.5444171,0.008447529,0.0025265499,0.108288944,0.0065508783,0.20868726],"study_design_scores_gemma":[0.00031793906,0.0015947609,0.30338547,0.0007448961,0.00008613607,0.00043125573,0.5018785,0.007785241,0.0039313287,0.022456078,0.15720873,0.00017959488],"about_ca_topic_score_codex":0.125567,"about_ca_topic_score_gemma":0.13884081,"teacher_disagreement_score":0.125567,"about_ca_system_score_codex":0.015127375,"about_ca_system_score_gemma":0.014078737,"threshold_uncertainty_score":0.2496723},"labels":[],"label_agreement":null},{"id":"W4366446369","doi":"10.3138/cjpe.29.1.135","title":"Edmonds, W. A., &amp; Kennedy, T. D. (2012). <i>An Applied Reference Guide to Research Designs: Quantitative, Qualitative, and Mixed Methods.</i>","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Research Methods and Applications","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Qualitative research; Psychology; Sociology; Social science","score_opus":0.7179043795718172,"score_gpt":0.6988737180230122,"score_spread":0.01903066154880495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446369","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044554076,0.19337347,0.41763818,0.16251917,0.012150842,0.009579049,0.013952423,0.005283531,0.18104792],"genre_scores_gemma":[0.03369164,0.18172747,0.6726738,0.022908743,0.0013411954,0.01378041,0.0037320917,0.0013941851,0.06875047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9755627,0.014680251,0.0029665935,0.0005715778,0.0059606256,0.00025829292],"domain_scores_gemma":[0.84748036,0.10665996,0.005076709,0.0048126853,0.034580383,0.0013898428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053654484,0.0013817429,0.0011523552,0.009241605,0.004406022,0.0058362465,0.0033192085,0.0029812637,0.016887832],"category_scores_gemma":[0.10671568,0.0025092866,0.0014334543,0.008543725,0.0039276653,0.007002602,0.0023039442,0.0071605616,0.01251914],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007242924,0.00009579114,0.0008617989,0.004716609,0.000069317226,0.000116736184,0.0055285157,0.00018358944,0.00097057427,0.017446363,0.6536665,0.31627175],"study_design_scores_gemma":[0.000053344662,0.000116870346,0.0050366484,0.013296188,0.00012875689,0.00026559833,0.0028030272,0.00035993347,0.0019809383,0.02350127,0.95234835,0.00010896537],"about_ca_topic_score_codex":0.030912336,"about_ca_topic_score_gemma":0.06654764,"teacher_disagreement_score":0.053654484,"about_ca_system_score_codex":0.0065123755,"about_ca_system_score_gemma":0.016399948,"threshold_uncertainty_score":0.28375536},"labels":[],"label_agreement":null},{"id":"W4366446371","doi":"10.3138/cjpe.24.005","title":"Coûts de transaction et politiques agri-environnementales","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Agriculture and Rural Development Research","field":"Agricultural and Biological Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transaction cost; Information asymmetry; Database transaction; Business; Government (linguistics); Public policy; Industrial organization; Public economics; Economics; Environmental economics; Finance; Economic growth; Computer science","score_opus":0.09131189450315809,"score_gpt":0.35297510327141474,"score_spread":0.26166320876825666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20281753,0.0073879147,0.5201985,0.011717913,0.00028906018,0.00043381567,0.0010345199,0.00017736091,0.25594345],"genre_scores_gemma":[0.93594986,0.0014323404,0.050548743,0.00016946114,0.00010708501,0.0004764295,0.00017468407,0.00003705756,0.0111043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9881705,0.0068999855,0.00033379864,0.00082527724,0.003149701,0.00062071177],"domain_scores_gemma":[0.97364175,0.021294244,0.002015538,0.0010570235,0.0016647261,0.00032678148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009660252,0.0008883308,0.000760292,0.0035234722,0.0017881885,0.0087783,0.0010390071,0.0017704009,0.012132456],"category_scores_gemma":[0.024095643,0.000475767,0.0008889782,0.0050024814,0.0069554513,0.0066826167,0.0017092616,0.003044315,0.00042306204],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018902167,0.000014582328,0.001573382,0.000042990025,0.000020841975,0.00005954525,0.00052867737,0.0051844744,0.00008167936,0.98551106,0.00032458975,0.0066392757],"study_design_scores_gemma":[0.000046276567,0.000066811845,0.006059384,0.0001715233,0.000036113473,0.00032969567,0.0018204392,0.09074082,0.00060755917,0.8712779,0.028795915,0.000047609043],"about_ca_topic_score_codex":0.03004646,"about_ca_topic_score_gemma":0.0120356055,"teacher_disagreement_score":0.03004646,"about_ca_system_score_codex":0.012680873,"about_ca_system_score_gemma":0.003409994,"threshold_uncertainty_score":0.092006624},"labels":[],"label_agreement":null},{"id":"W4366446383","doi":"10.3138/cjpe.26.001","title":"In Search of a Balanced Canadian Federal Evaluation Function: Getting to Relevance","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Canadian Policy and Governance","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Relevance (law); Function (biology); Treasury; Argument (complex analysis); Criticism; Government (linguistics); Public relations; Public policy; Political science; Public administration; Management science; Computer science; Economics; Law","score_opus":0.16135091642842883,"score_gpt":0.40068610538775684,"score_spread":0.239335188959328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446383","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013355964,0.01052378,0.047297727,0.7768461,0.0044712606,0.00074479554,0.00033510255,0.0004822516,0.14594309],"genre_scores_gemma":[0.6983058,0.007481138,0.107042216,0.12220482,0.0019743745,0.000993454,0.00042087727,0.0007642427,0.060812958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8448142,0.055181984,0.006570273,0.00912605,0.06957789,0.014729533],"domain_scores_gemma":[0.72524583,0.044443384,0.0053995927,0.013122068,0.1943554,0.01743369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18302207,0.001035072,0.001751216,0.010349557,0.031289883,0.034020573,0.0047188886,0.009173315,0.0046499074],"category_scores_gemma":[0.250128,0.0011661107,0.001150916,0.008329116,0.031141821,0.013223127,0.010797858,0.016812315,0.0009620343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000646041,0.00005309761,0.003633458,0.00044629068,0.00006109779,0.00009739405,0.0070652138,0.0011691306,0.00037909913,0.73319244,0.14235833,0.11147985],"study_design_scores_gemma":[0.0001355666,0.00010591772,0.01722075,0.0036260912,0.00017648905,0.00014724403,0.0130523285,0.0049665845,0.001642445,0.2484959,0.7099963,0.00043449292],"about_ca_topic_score_codex":0.89237016,"about_ca_topic_score_gemma":0.88559276,"teacher_disagreement_score":0.7347842,"about_ca_system_score_codex":0.2652158,"about_ca_system_score_gemma":0.52529657,"threshold_uncertainty_score":0.9679248},"labels":[],"label_agreement":null},{"id":"W4366446449","doi":"10.3138/cjpe.023.002","title":"Un mot du rédacteur en chef","year":2008,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.11097335407368754,"score_gpt":0.32804052207745515,"score_spread":0.21706716800376763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446449","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07733789,0.017291535,0.067436025,0.26643068,0.037641354,0.00090431195,0.0030129259,0.0069537973,0.5229915],"genre_scores_gemma":[0.34114376,0.0071132085,0.04825791,0.02241745,0.0055249413,0.0009721954,0.0022371958,0.003425548,0.5689078],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9577808,0.019670412,0.001336627,0.0024036765,0.016597528,0.0022110092],"domain_scores_gemma":[0.9499273,0.01709154,0.0019970927,0.0031189043,0.024534376,0.003330785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02200249,0.0017517228,0.0017441316,0.00390398,0.007527651,0.01410775,0.0019079398,0.006547867,0.058400933],"category_scores_gemma":[0.06489837,0.0009025658,0.0015888497,0.0027503816,0.0043577226,0.011516658,0.0040521338,0.011929334,0.0105357105],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012221783,0.00066479674,0.0073124617,0.000929919,0.00010931516,0.0010890285,0.008277471,0.0019645405,0.005048544,0.17336302,0.321595,0.47842374],"study_design_scores_gemma":[0.0001577208,0.00022316266,0.0050857095,0.0007156777,0.0000461706,0.0008143069,0.0055096666,0.0019013977,0.005730876,0.010315321,0.96935195,0.00014799778],"about_ca_topic_score_codex":0.09438717,"about_ca_topic_score_gemma":0.06290663,"teacher_disagreement_score":0.09438717,"about_ca_system_score_codex":0.01590081,"about_ca_system_score_gemma":0.01640221,"threshold_uncertainty_score":0.19537055},"labels":[],"label_agreement":null},{"id":"W4366446502","doi":"10.3138/cjpe.023.008","title":"Reliability of the Canadian Incidence Study Data Collection Instrument","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Child Abuse and Trauma","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; University of Calgary; McGill University","funders":"","keywords":"Neglect; Reliability (semiconductor); Data collection; Test (biology); Psychology; Incidence (geometry); Child neglect; Child abuse; Scope (computer science); Poison control; Statistics; Injury prevention; Environmental health; Medicine; Computer science; Psychiatry; Mathematics","score_opus":0.2250990247771382,"score_gpt":0.40252002066499987,"score_spread":0.17742099588786167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70299894,0.0032728605,0.039227854,0.005731109,0.0015649477,0.026871195,0.09452894,0.0010997559,0.12470439],"genre_scores_gemma":[0.8785662,0.0015505305,0.053014692,0.0009063938,0.000113448164,0.018720984,0.039221603,0.00026541128,0.00764078],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.899381,0.019914513,0.0143880425,0.004708769,0.057688996,0.003918761],"domain_scores_gemma":[0.7571214,0.028398331,0.0107029965,0.009287681,0.19093934,0.0035502769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08753675,0.0007524575,0.0012466427,0.0076022814,0.0038176717,0.0031493441,0.0030126642,0.0006125006,0.003595717],"category_scores_gemma":[0.18876016,0.00084428914,0.00199751,0.010057861,0.0021221794,0.0011310084,0.003987094,0.0019597216,0.00091898785],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054141815,0.00035626537,0.8386734,0.0009950919,0.0005000392,0.0000777777,0.0072698095,0.0014539624,0.0005452141,0.0047188355,0.03218451,0.11268372],"study_design_scores_gemma":[0.0000857216,0.00016114333,0.96491796,0.0005178403,0.0001451781,0.00004505603,0.0024948148,0.001998179,0.0008482636,0.00042279589,0.028272795,0.000090214344],"about_ca_topic_score_codex":0.81026477,"about_ca_topic_score_gemma":0.79590815,"teacher_disagreement_score":0.81026477,"about_ca_system_score_codex":0.030635817,"about_ca_system_score_gemma":0.07936293,"threshold_uncertainty_score":0.46294415},"labels":[],"label_agreement":null},{"id":"W4366446537","doi":"10.3138/cjpe.24.009","title":"Michael Quinn Patton. (2008). <i>Utilization-Focused Evaluation</i> (4 <sup>e</sup> éd.). Thousand Oaks, CA: Sage. 667 Pages.","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Gerontology; Physics; Nuclear physics; Medicine","score_opus":0.20132387130639365,"score_gpt":0.45162505319901114,"score_spread":0.2503011818926175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446537","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00083173433,0.67058295,0.013470799,0.19708247,0.01085303,0.00021098582,0.002410615,0.0011873607,0.10337001],"genre_scores_gemma":[0.022817718,0.58136624,0.024612624,0.04175556,0.004635599,0.00056559336,0.001490403,0.0006841716,0.3220721],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987344,0.00027607172,0.00010075643,0.00012864449,0.0006978951,0.000062209176],"domain_scores_gemma":[0.99361426,0.0025066475,0.0004374546,0.00015540449,0.0027901991,0.00049614825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046310145,0.0010907718,0.0006107227,0.0021224187,0.0015966942,0.003006502,0.0013011018,0.0027547928,0.06369612],"category_scores_gemma":[0.013986163,0.0009049403,0.00043056384,0.0029803286,0.0011028916,0.0049561486,0.0013651003,0.003812054,0.04316023],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002352737,0.000008702536,0.00020602225,0.00032413765,0.0000041873664,0.000027059281,0.00017828344,0.000050966322,0.000065997665,0.001547089,0.83153886,0.1660252],"study_design_scores_gemma":[0.000019177161,0.000023927236,0.0023511886,0.0026436776,0.000019583878,0.00016789867,0.00042260534,0.00015144027,0.0002982802,0.0071558794,0.9867207,0.000025573489],"about_ca_topic_score_codex":0.03598174,"about_ca_topic_score_gemma":0.085955076,"teacher_disagreement_score":0.06369612,"about_ca_system_score_codex":0.0020335875,"about_ca_system_score_gemma":0.0046157986,"threshold_uncertainty_score":0.21308476},"labels":[],"label_agreement":null},{"id":"W4366446569","doi":"10.3138/cjpe.28.004","title":"Informed Consent of 16- to 18-Year-Old Participants in Evaluations","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Ethics and Legal Issues in Pediatric Healthcare","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Informed consent; Parental consent; Psychology; Social psychology; Medicine; Alternative medicine","score_opus":0.3498737870772751,"score_gpt":0.5205024888142364,"score_spread":0.17062870173696132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6549708,0.0057300692,0.058436573,0.046124257,0.003804119,0.10111857,0.003231733,0.00035357897,0.12623028],"genre_scores_gemma":[0.8438053,0.0035058504,0.043480303,0.0147768725,0.00055123214,0.06951049,0.001095233,0.00008477728,0.023190022],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93704826,0.047269996,0.0074992306,0.001516931,0.003140125,0.00352542],"domain_scores_gemma":[0.9338488,0.027338415,0.006909192,0.010678586,0.015624278,0.0056008026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09457024,0.0006278136,0.0009578395,0.0013190893,0.005008758,0.0027701093,0.0016509804,0.0035183227,0.012223962],"category_scores_gemma":[0.11459609,0.00071381335,0.0008017153,0.000768873,0.0030052771,0.0029027658,0.003387012,0.0035433925,0.0034269763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052406816,0.0027691456,0.108332604,0.0032338921,0.00015103414,0.015334344,0.29443985,0.00074807083,0.011345343,0.070391014,0.1544519,0.33356214],"study_design_scores_gemma":[0.0014232991,0.0055207936,0.115656205,0.019096801,0.00025434632,0.018016549,0.2115574,0.004511823,0.027702924,0.042340953,0.55337036,0.00054853136],"about_ca_topic_score_codex":0.0035254334,"about_ca_topic_score_gemma":0.008219223,"teacher_disagreement_score":0.09457024,"about_ca_system_score_codex":0.0019845397,"about_ca_system_score_gemma":0.024407705,"threshold_uncertainty_score":0.50014126},"labels":[],"label_agreement":null},{"id":"W4366446575","doi":"10.3138/cjpe.023.007","title":"Reconnecting Knowledge Utilization and Evaluation Utilization Domains of Inquiry","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Social Sciences and Humanities Research Council","funders":"","keywords":"Situated; Variety (cybernetics); Context (archaeology); Domain (mathematical analysis); Knowledge management; Epistemology; Cognate; Thematic analysis; Sociology; Psychology; Computer science; Qualitative research; Social science; Geography; Artificial intelligence; Philosophy; Mathematics","score_opus":0.7789619921436738,"score_gpt":0.5916862318486936,"score_spread":0.18727576029498016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446575","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02074848,0.0201788,0.072374254,0.796637,0.0067908494,0.00037417642,0.00006427853,0.0001089665,0.08272331],"genre_scores_gemma":[0.8214272,0.00975,0.035232745,0.117151946,0.007253844,0.0022482602,0.00006285919,0.00024096457,0.006632163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5929572,0.32963073,0.011332957,0.010242273,0.046205364,0.009631424],"domain_scores_gemma":[0.36318266,0.5541038,0.014142974,0.019178862,0.045708086,0.0036836783],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27318898,0.0008854066,0.0023740851,0.011253179,0.016345954,0.03151998,0.008212117,0.01705809,0.0031200396],"category_scores_gemma":[0.3093868,0.0008633984,0.0014708085,0.009000392,0.13443771,0.043746162,0.027998103,0.022412911,0.00046571222],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057915277,0.00004339342,0.0008831046,0.000702577,0.00002681204,0.00018786752,0.08562596,0.00015628566,0.00008868066,0.8740487,0.010146681,0.02803203],"study_design_scores_gemma":[0.00010418375,0.00009870394,0.0019482129,0.007984812,0.00006980399,0.0003459404,0.17144151,0.0022812176,0.0010532315,0.6346399,0.1799109,0.00012145562],"about_ca_topic_score_codex":0.021163223,"about_ca_topic_score_gemma":0.020485526,"teacher_disagreement_score":0.27318898,"about_ca_system_score_codex":0.039251845,"about_ca_system_score_gemma":0.057242207,"threshold_uncertainty_score":0.8962874},"labels":[],"label_agreement":null},{"id":"W4366446578","doi":"10.3138/cjpe.023.003","title":"Guest Editors’ Introduction","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Posthumanist Ethics and Activism","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Psychology","score_opus":0.15007568507870164,"score_gpt":0.39959566810841296,"score_spread":0.24951998302971132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446578","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001384346,0.0028271256,0.00029290654,0.05700281,0.9293654,0.00005190486,0.00015512371,0.00012665924,0.01003961],"genre_scores_gemma":[0.0040556206,0.004142685,0.00060096884,0.06112853,0.77547675,0.00017821432,0.00024007788,0.00025006253,0.15392707],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99442863,0.0007555865,0.00053976313,0.000831981,0.0027909696,0.00065303495],"domain_scores_gemma":[0.95793086,0.006694891,0.002499245,0.0020731844,0.023073353,0.007728399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008223169,0.001422403,0.0012962661,0.003221556,0.0020958937,0.0059949257,0.0024826284,0.006173665,0.08382547],"category_scores_gemma":[0.045554027,0.00062416063,0.0013016992,0.0012859562,0.0013003685,0.0027666483,0.0027882936,0.007935175,0.034922823],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017424627,0.0000061979936,0.000044876415,0.00008339219,0.0000026623193,0.000044662425,0.000015901522,0.00001274959,0.000051131647,0.00042425052,0.99039006,0.008906657],"study_design_scores_gemma":[0.000017271084,0.000017099508,0.00032644073,0.00015018471,0.0000087915605,0.000113988295,0.000049352813,0.000047093006,0.00012659564,0.0005330961,0.99860066,0.000009434901],"about_ca_topic_score_codex":0.0019233925,"about_ca_topic_score_gemma":0.0038852477,"teacher_disagreement_score":0.08382547,"about_ca_system_score_codex":0.0024488717,"about_ca_system_score_gemma":0.0043870476,"threshold_uncertainty_score":0.28042412},"labels":[],"label_agreement":null},{"id":"W4366446582","doi":"10.3138/cjpe.023.005","title":"Comparaison de trois stratégies de travail en réseau afin de favoriser l’application des connaissances issues de la recherche","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal; Université du Québec à Trois-Rivières","funders":"","keywords":"Intervention (counseling); Promotion (chess); Public relations; Nursing; Psychology; Political science; Sociology; Medicine; Politics","score_opus":0.7591416187318623,"score_gpt":0.5869267113305026,"score_spread":0.1722149074013597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8985745,0.0047067516,0.01669064,0.010436372,0.00027922055,0.0015067782,0.00017368209,0.00037298203,0.06725916],"genre_scores_gemma":[0.9838631,0.001004331,0.00828479,0.00068636413,0.00005171418,0.00058294536,0.00012144036,0.00007948334,0.0053258515],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.90849423,0.06674058,0.0050050304,0.0041615455,0.010466151,0.0051323697],"domain_scores_gemma":[0.7447491,0.18174154,0.018109372,0.012095129,0.03197431,0.011330504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.062155828,0.0007184915,0.0007285505,0.0047653792,0.004705087,0.011803389,0.0030285288,0.0036115407,0.005961128],"category_scores_gemma":[0.15260063,0.0005289362,0.0015407804,0.0032734894,0.0036347292,0.008467057,0.006474409,0.0022226865,0.0014450854],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016965496,0.0016131751,0.2084899,0.0024558685,0.00065329444,0.0008200164,0.23105894,0.0009519667,0.003858636,0.040514655,0.006724192,0.5011628],"study_design_scores_gemma":[0.0004172728,0.0036539612,0.30925116,0.0026737135,0.00076731923,0.0016837877,0.5364122,0.005442972,0.0077677555,0.01852996,0.11313924,0.00026067253],"about_ca_topic_score_codex":0.0084666805,"about_ca_topic_score_gemma":0.011368825,"teacher_disagreement_score":0.062155828,"about_ca_system_score_codex":0.0066969064,"about_ca_system_score_gemma":0.016499491,"threshold_uncertainty_score":0.32871538},"labels":[],"label_agreement":null},{"id":"W4366446708","doi":"10.3138/cjpe.026.002","title":"Obstacles à l’implantation d’un programme de boire contrôlé dans le contexte organisationnel des services en dépendance","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université de Montréal","funders":"","keywords":"Resource (disambiguation); Business; Dissemination; Welfare economics; Political science; Computer science; Economics; Law","score_opus":0.10649954579671252,"score_gpt":0.3423592517054962,"score_spread":0.2358597059087837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88149184,0.0043861223,0.012406545,0.05985379,0.00055760227,0.004980894,0.00018555057,0.00020050386,0.035937235],"genre_scores_gemma":[0.98504597,0.00077006296,0.008038859,0.0018755194,0.000060833623,0.0013556702,0.000073307325,0.000022198717,0.0027575872],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.95759547,0.029631287,0.0013242373,0.0009573469,0.00507772,0.0054140263],"domain_scores_gemma":[0.9386626,0.02608107,0.004296293,0.0020451157,0.012709092,0.016205853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059408367,0.00058184756,0.0004801663,0.0010890918,0.0054165297,0.0061369026,0.0023792812,0.0023975612,0.00482283],"category_scores_gemma":[0.048856206,0.00044748923,0.0006948363,0.0011008721,0.0035082744,0.0031712807,0.0050589037,0.0032150338,0.00027960757],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040278337,0.015891166,0.13324977,0.0058744946,0.00041721106,0.001941525,0.11613462,0.0064568804,0.0069153933,0.040259443,0.016438873,0.6523928],"study_design_scores_gemma":[0.002694375,0.02737302,0.5302293,0.014135643,0.0007222407,0.000802337,0.17980427,0.0146859465,0.010561382,0.0084125465,0.21009551,0.00048342114],"about_ca_topic_score_codex":0.22384676,"about_ca_topic_score_gemma":0.26563382,"teacher_disagreement_score":0.22384676,"about_ca_system_score_codex":0.034322407,"about_ca_system_score_gemma":0.0857666,"threshold_uncertainty_score":0.44508767},"labels":[],"label_agreement":null},{"id":"W4366446724","doi":"10.3138/cjpe.26.002","title":"A Commentary on Shepherd’s “In Search of a Balanced Canadian Federal Evaluation Function: Getting to Relevance”","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Political Systems and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Relevance (law); Function (biology); Psychology; Social psychology; Political science; Law; Biology","score_opus":0.14043348326928656,"score_gpt":0.38541693479293293,"score_spread":0.24498345152364637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446724","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009182019,0.0006464302,0.00010444467,0.9878435,0.010227528,0.000009474214,0.00003074002,0.000009714673,0.0010363994],"genre_scores_gemma":[0.001468196,0.00021813736,0.00018119007,0.99136484,0.004189404,0.00002815155,0.000008840571,0.000028677154,0.0025125924],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8790019,0.032130327,0.008912681,0.01583947,0.04464129,0.019474229],"domain_scores_gemma":[0.72867525,0.15521897,0.00812186,0.004897611,0.07678476,0.026301568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07551827,0.002227744,0.004106252,0.00428544,0.0394288,0.026288392,0.0148873925,0.17134534,0.008433544],"category_scores_gemma":[0.2614873,0.0035264834,0.004779875,0.0068303403,0.03947717,0.017693957,0.011255885,0.17767256,0.0033811198],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014792403,0.000006117179,0.00007167332,0.00006240385,0.000016252663,0.00006411418,0.0010767883,0.000028416978,0.000040450497,0.012721914,0.9846742,0.0012229197],"study_design_scores_gemma":[0.00011676533,0.000022247552,0.0012624073,0.0013518921,0.00012931784,0.00014077201,0.0041226447,0.00022728195,0.00037297473,0.019362643,0.9725687,0.0003222454],"about_ca_topic_score_codex":0.70399034,"about_ca_topic_score_gemma":0.8221315,"teacher_disagreement_score":0.91710305,"about_ca_system_score_codex":0.08289694,"about_ca_system_score_gemma":0.19477709,"threshold_uncertainty_score":0.60146224},"labels":[],"label_agreement":null},{"id":"W4366446755","doi":"10.3138/cjpe.023.012","title":"The BC Cancer Agency Primary Prevention Program: Using Negotiated Accountability to Evaluate a Community-Determined Health Initiative","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program 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":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"BC Cancer Agency","keywords":"Agency (philosophy); Accountability; Cancer prevention; Program evaluation; Public relations; Political science; Cancer; Public administration; Business; Medicine; Sociology","score_opus":0.8620351057720511,"score_gpt":0.714442030105509,"score_spread":0.14759307566654212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86758065,0.00050425756,0.012756567,0.0061055217,0.00020695833,0.019649396,0.0009914177,0.00029743166,0.09190774],"genre_scores_gemma":[0.9622209,0.00013834481,0.021679068,0.00061416527,0.00002558824,0.0119347,0.00036878267,0.000049856648,0.0029687143],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8003372,0.16870788,0.003677666,0.0034976008,0.018211203,0.0055683535],"domain_scores_gemma":[0.8359863,0.08052551,0.011547154,0.012476338,0.05034296,0.009121658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14824142,0.00072532846,0.00064150075,0.0020064206,0.00856878,0.0059007695,0.0019048542,0.0015204113,0.0034624906],"category_scores_gemma":[0.13499406,0.0005687502,0.00055793725,0.0029030996,0.00457948,0.0024752237,0.0073092347,0.0034752898,0.00032603083],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007329022,0.03750694,0.25289908,0.0025292626,0.0011860109,0.0005064585,0.08476093,0.007367186,0.0025815077,0.029433753,0.035361394,0.5385384],"study_design_scores_gemma":[0.014398653,0.052799623,0.5374693,0.004948059,0.0021674538,0.00037157242,0.15050769,0.03572607,0.02951236,0.015547933,0.15580563,0.00074569805],"about_ca_topic_score_codex":0.09943586,"about_ca_topic_score_gemma":0.11779598,"teacher_disagreement_score":0.90056413,"about_ca_system_score_codex":0.028554738,"about_ca_system_score_gemma":0.06248701,"threshold_uncertainty_score":0.7839849},"labels":[],"label_agreement":null},{"id":"W4366446952","doi":"10.3138/cjpe.28.008","title":"Barbier, J. C., &amp; Hawkins, P. (Eds.). (2012). <i>Evaluation Cultures: Sense-making in Complex Times.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sense (electronics); Psychology; Sociology; Chemistry; Physical chemistry","score_opus":0.3467359600038095,"score_gpt":0.5222283353461814,"score_spread":0.1754923753423719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446952","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009638444,0.9168148,0.007172968,0.038016967,0.00290747,0.000044489017,0.00044559655,0.00025807478,0.033375848],"genre_scores_gemma":[0.016445292,0.9594483,0.0084043415,0.0015594157,0.0010012536,0.00007190623,0.00034710273,0.00012302322,0.012599296],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99790037,0.0006923617,0.00021089193,0.00015954857,0.0008936631,0.00014314435],"domain_scores_gemma":[0.99062085,0.0056305104,0.00074665056,0.00023957285,0.0020066116,0.0007557412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052207275,0.0020535784,0.001544994,0.0069184443,0.0028189095,0.010855809,0.0025301266,0.003629873,0.015680177],"category_scores_gemma":[0.009553848,0.0014091186,0.0007996526,0.011428085,0.0038479848,0.011960128,0.002285247,0.0050205877,0.013477738],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047815975,0.00003158451,0.0010744516,0.0024548348,0.000027739527,0.000089586916,0.004776347,0.00030994133,0.0001655685,0.012592867,0.41963887,0.5587904],"study_design_scores_gemma":[0.000021082144,0.00006154831,0.008468274,0.01012415,0.00012534222,0.0008176965,0.009634145,0.0006710299,0.0007660263,0.030831585,0.93837804,0.00010104375],"about_ca_topic_score_codex":0.09269927,"about_ca_topic_score_gemma":0.16106826,"teacher_disagreement_score":0.09269927,"about_ca_system_score_codex":0.0070421724,"about_ca_system_score_gemma":0.011977875,"threshold_uncertainty_score":0.18431938},"labels":[],"label_agreement":null},{"id":"W4366447009","doi":"10.3138/cjpe.022.007","title":"Considérations théoriques et méthodologiques lors de l’évaluation de programmes d’intervention de crise","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Confusion; Valuation (finance); Psychology; Intervention (counseling); Crisis intervention; Applied psychology; Social psychology; Business; Psychoanalysis; Psychiatry; Finance","score_opus":0.4661128635653234,"score_gpt":0.5942212119329685,"score_spread":0.12810834836764512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447009","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024604704,0.011967886,0.8883484,0.036936335,0.0010176608,0.010025615,0.00026388373,0.00020329218,0.0266322],"genre_scores_gemma":[0.28934184,0.0026552638,0.68108594,0.0024587628,0.00032975356,0.02276178,0.00013803561,0.00008697549,0.001141676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.15560761,0.79644513,0.013500574,0.0044490565,0.028457252,0.0015403287],"domain_scores_gemma":[0.0967725,0.86387074,0.009154318,0.011853422,0.01759116,0.00075786404],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6036283,0.0032024316,0.004953809,0.014630278,0.0054597845,0.02739398,0.008672878,0.007792033,0.006512147],"category_scores_gemma":[0.6628566,0.0024760775,0.003939976,0.011270494,0.03735066,0.020650912,0.0073201796,0.009732491,0.00063118775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009313287,0.0006203581,0.006158619,0.009949105,0.0012309465,0.00029445195,0.03031107,0.009582896,0.0004487502,0.79303306,0.0028656155,0.14457376],"study_design_scores_gemma":[0.001771961,0.0010236251,0.00504836,0.019922096,0.00082126545,0.000484867,0.022864584,0.061558083,0.0026221361,0.85633886,0.027236933,0.00030726974],"about_ca_topic_score_codex":0.009107343,"about_ca_topic_score_gemma":0.008521074,"teacher_disagreement_score":0.6036283,"about_ca_system_score_codex":0.026795799,"about_ca_system_score_gemma":0.025064696,"threshold_uncertainty_score":0.48879695},"labels":[],"label_agreement":null},{"id":"W4366447026","doi":"10.3138/cjpe.020.007","title":"The Sustainable Economic Product: A Way to Measure and Compare National Sustainable Development","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Canadian Policy and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Treasury Board of Canada Secretariat","funders":"","keywords":"Sustainable development; Government (linguistics); Product (mathematics); Business; Public economics; Environmental resource management; Political science; Environmental economics; Economic growth; Economics","score_opus":0.0621112625519433,"score_gpt":0.3496914995645922,"score_spread":0.2875802370126489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447026","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08423102,0.007981596,0.24657416,0.010695526,0.003124769,0.0038827676,0.09785727,0.004969857,0.5406831],"genre_scores_gemma":[0.44387707,0.0048833424,0.4768883,0.001070745,0.00029788126,0.008146758,0.0360499,0.0016382594,0.027147785],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97029054,0.010179636,0.0017844847,0.00088418054,0.016375493,0.00048564048],"domain_scores_gemma":[0.9668724,0.009485995,0.002637592,0.0026357423,0.017412033,0.0009562209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019439561,0.00095711835,0.0012364526,0.024101108,0.0016906271,0.004900778,0.0011448943,0.000776522,0.015371106],"category_scores_gemma":[0.06654078,0.00035164153,0.0010751002,0.037840433,0.0030520745,0.004016814,0.0037154618,0.001755774,0.0022570116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004867411,0.00028145898,0.08068782,0.0016571315,0.0007367009,0.00011900583,0.0031863397,0.004097915,0.0008871072,0.22898634,0.24723335,0.43164003],"study_design_scores_gemma":[0.00015899808,0.00052977377,0.19666079,0.0016204491,0.00033481137,0.00021495376,0.0049631256,0.009857852,0.0026370063,0.093943745,0.68878,0.00029842975],"about_ca_topic_score_codex":0.104826644,"about_ca_topic_score_gemma":0.113605104,"teacher_disagreement_score":0.104826644,"about_ca_system_score_codex":0.010427969,"about_ca_system_score_gemma":0.013686369,"threshold_uncertainty_score":0.20843291},"labels":[],"label_agreement":null},{"id":"W4366447032","doi":"10.3138/cjpe.0022.009","title":"La comparabilité des échantillons dans les enquêtes de l’international association for the evaluation of educational achievement","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Association (psychology); Perspective (graphical); Educational research; Student achievement; Psychology; Pedagogy; Mathematics education; Sociology; Academic achievement; Political science; Mathematics","score_opus":0.4409650328077531,"score_gpt":0.5430028838125461,"score_spread":0.10203785100479301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73958564,0.017113188,0.1226222,0.015789649,0.0045497105,0.0017896006,0.008833422,0.0012950652,0.08842161],"genre_scores_gemma":[0.9594042,0.0011327587,0.02613532,0.00068842573,0.00042090483,0.0011956777,0.0038617016,0.0003603632,0.0068006925],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.70132285,0.1713891,0.03909529,0.017464438,0.063708305,0.0070199594],"domain_scores_gemma":[0.5187461,0.2622524,0.035950735,0.032611176,0.14724843,0.0031911775],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2950604,0.0010331253,0.0014209719,0.012062749,0.0025888719,0.012339656,0.0024954195,0.002085993,0.006959401],"category_scores_gemma":[0.40961647,0.0009925932,0.0030414532,0.012716475,0.0025565056,0.008409068,0.0067675845,0.0033980203,0.0020350998],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028100174,0.0004694953,0.71193594,0.0015240189,0.0020098374,0.00012662214,0.016624566,0.003299503,0.002748073,0.016899448,0.013044026,0.22850853],"study_design_scores_gemma":[0.00015298456,0.0013145884,0.8986744,0.00140985,0.000986213,0.00019720565,0.014200872,0.008776364,0.007526082,0.007393509,0.059098907,0.00026905764],"about_ca_topic_score_codex":0.03041928,"about_ca_topic_score_gemma":0.03232493,"teacher_disagreement_score":0.2950604,"about_ca_system_score_codex":0.0076490263,"about_ca_system_score_gemma":0.0065550427,"threshold_uncertainty_score":0.86931604},"labels":[],"label_agreement":null},{"id":"W4366447033","doi":"10.3138/cjpe.020.001","title":"Un état des lieux théoriques de l’évaluation: une discipline à la remorque d’une révolution scientifique qui n’en finit pas","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Schism; Epistemology; Sociology; Acknowledgement; Scientific revolution; Valuation (finance); Humanities; Philosophy; Political science; Law; Economics","score_opus":0.2405922775106585,"score_gpt":0.48362414033165124,"score_spread":0.24303186282099273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447033","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019725263,0.1077392,0.3162091,0.4749127,0.002825992,0.0002258826,0.0000872068,0.00021663221,0.07805812],"genre_scores_gemma":[0.7400798,0.04176936,0.1856506,0.021252455,0.0037581963,0.00085802743,0.00006566448,0.00022771485,0.006338153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89984393,0.07138677,0.003453863,0.005056389,0.01818264,0.002076389],"domain_scores_gemma":[0.7177234,0.23915824,0.007715237,0.015877321,0.016776815,0.0027489213],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.11424989,0.0012974994,0.0025768825,0.009465032,0.0068814214,0.021871146,0.0034488563,0.009859524,0.00273326],"category_scores_gemma":[0.11532116,0.0010331101,0.0016470607,0.0068920334,0.09614849,0.03206502,0.007037946,0.01197009,0.0007431365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022171993,0.00003593118,0.00034293445,0.00029130376,0.000014083541,0.000022235346,0.0026219327,0.00072775857,0.00006420943,0.97693187,0.0015894715,0.017336076],"study_design_scores_gemma":[0.000042346142,0.000038829152,0.0002544486,0.00084320165,0.000016243583,0.000053365187,0.0018520713,0.002839424,0.00022924793,0.9632863,0.03050791,0.00003656103],"about_ca_topic_score_codex":0.014640359,"about_ca_topic_score_gemma":0.007472212,"teacher_disagreement_score":0.9931186,"about_ca_system_score_codex":0.030877495,"about_ca_system_score_gemma":0.03263015,"threshold_uncertainty_score":0.60421836},"labels":[],"label_agreement":null},{"id":"W4366447375","doi":"10.3138/cjpe.021.008","title":"Impacts du pirs en milieu scolaire","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Reading (process); Scale (ratio); Medical education; Mathematics education; Pedagogy; Geography; Political science; Medicine; Cartography","score_opus":0.18663340726645056,"score_gpt":0.48755375552323066,"score_spread":0.3009203482567801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8173508,0.0022246868,0.0026168157,0.0037793964,0.00021800092,0.0003604192,0.0005959396,0.00039454616,0.17245941],"genre_scores_gemma":[0.9710533,0.0017726336,0.00264295,0.00029265406,0.00007071834,0.0001493266,0.0003632717,0.000044709206,0.023610324],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98809505,0.004549107,0.00025965538,0.0005558683,0.005138219,0.0014021076],"domain_scores_gemma":[0.9931409,0.0023756824,0.0008439426,0.0003155496,0.0020827272,0.0012413022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066273017,0.0010184495,0.0004888244,0.002449184,0.0043047806,0.0056741782,0.0012507943,0.000907794,0.018318353],"category_scores_gemma":[0.015272842,0.0002751167,0.00087926857,0.0016473855,0.0026414758,0.0014228229,0.004028751,0.0015772232,0.0016089911],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017123598,0.004901104,0.24728398,0.0014249309,0.0004096301,0.0042901793,0.033695877,0.0066737193,0.0049425126,0.031512678,0.016365012,0.64678794],"study_design_scores_gemma":[0.000488206,0.004110787,0.47300845,0.0020826515,0.00045814228,0.0028796531,0.09445693,0.007450567,0.016146107,0.0058380337,0.39286226,0.0002182624],"about_ca_topic_score_codex":0.34939498,"about_ca_topic_score_gemma":0.27637857,"teacher_disagreement_score":0.34939498,"about_ca_system_score_codex":0.015755711,"about_ca_system_score_gemma":0.014989381,"threshold_uncertainty_score":0.69472253},"labels":[],"label_agreement":null},{"id":"W4366447383","doi":"10.3138/cjpe.26.004","title":"In Search of a Balanced Canadian Federal Evaluation Function: Getting Back to the Future","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Canadian Policy and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Function (biology); Business; Biology","score_opus":0.11949959935858546,"score_gpt":0.3816260544440669,"score_spread":0.26212645508548144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447383","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016590299,0.0055941213,0.0030675405,0.97142315,0.0034380257,0.000052889343,0.00019994065,0.00012855045,0.0144368075],"genre_scores_gemma":[0.25852484,0.017191561,0.043504436,0.62670255,0.0063084117,0.00037084727,0.0008559658,0.00065319834,0.04588825],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9057849,0.02560314,0.003579583,0.005408814,0.040487505,0.019136027],"domain_scores_gemma":[0.71015894,0.029232781,0.0051268986,0.0073664384,0.18318659,0.06492839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.113602296,0.0014688043,0.0025804623,0.007862143,0.023967601,0.030765118,0.0071736076,0.019848062,0.015668098],"category_scores_gemma":[0.19959697,0.0010988311,0.001562557,0.008271019,0.019725723,0.018253304,0.010498157,0.027981343,0.0021976335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00014733318,0.000093105045,0.0033268842,0.0005148216,0.000122374,0.00009259474,0.0017712385,0.001131556,0.00034822448,0.33159992,0.5659832,0.09486877],"study_design_scores_gemma":[0.00024881435,0.00010277578,0.016432248,0.0031694707,0.00019402051,0.00009945975,0.0067665293,0.002879977,0.0005171572,0.18446127,0.7847038,0.00042462567],"about_ca_topic_score_codex":0.93712366,"about_ca_topic_score_gemma":0.95546323,"teacher_disagreement_score":0.8019029,"about_ca_system_score_codex":0.19809712,"about_ca_system_score_gemma":0.5879484,"threshold_uncertainty_score":0.93009365},"labels":[],"label_agreement":null},{"id":"W4366447384","doi":"10.3138/cjpe.0028.001","title":"Editor’s Remarks","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.05255447403694678,"score_gpt":0.41697149248220355,"score_spread":0.36441701844525676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447384","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015334632,0.0019681817,0.00014288258,0.4456787,0.5472297,0.000032734333,0.000113457725,0.000080378195,0.0046005934],"genre_scores_gemma":[0.0021156461,0.0013725983,0.00046638594,0.7123002,0.23852506,0.00007997995,0.000052014577,0.000080861086,0.045007344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9826063,0.001749305,0.0018849663,0.002806559,0.0087199025,0.0022330338],"domain_scores_gemma":[0.937236,0.015425971,0.004834988,0.0031669908,0.03099478,0.00834122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015075835,0.0016389467,0.0027078951,0.0024972646,0.0053404337,0.010526718,0.004979023,0.042466745,0.030279338],"category_scores_gemma":[0.12774715,0.0012052349,0.0033327737,0.001978756,0.0036974032,0.0037218092,0.0028680738,0.039072357,0.022749664],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017076905,0.0000066297544,0.00005627192,0.000038274193,0.000010326146,0.000118245705,0.000025020812,0.00001546786,0.000037292033,0.00047395565,0.99712,0.002081562],"study_design_scores_gemma":[0.000041366682,0.00001370433,0.0004710181,0.00021240315,0.000030195035,0.00018157999,0.00010959507,0.000073309275,0.00014273284,0.00091936,0.99776816,0.000036585854],"about_ca_topic_score_codex":0.014411924,"about_ca_topic_score_gemma":0.032722246,"teacher_disagreement_score":0.042466745,"about_ca_system_score_codex":0.008113672,"about_ca_system_score_gemma":0.013150616,"threshold_uncertainty_score":0.10129446},"labels":[],"label_agreement":null},{"id":"W4366447432","doi":"10.3138/cjpe.21.007","title":"Simulating or Imputing Non-participant Intervention Durations Using a Flexible Semi-Parametric Model","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program 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":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Treasury Board of Canada Secretariat; Employment and Social Development Canada","funders":"","keywords":"Propensity score matching; Matching (statistics); Outcome (game theory); Duration (music); Intervention (counseling); Parametric statistics; Participant observation; Psychology; Data collection; Nonparametric statistics; Computer science; Econometrics; Applied psychology; Statistics; Economics; Mathematics; Sociology; Microeconomics","score_opus":0.46350289171535847,"score_gpt":0.5179772456966617,"score_spread":0.054474353981303236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447432","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12369605,0.00029813472,0.87048024,0.0008036805,0.00007473276,0.0010024436,0.0006386169,0.000217791,0.0027883574],"genre_scores_gemma":[0.8535094,0.00024373695,0.1391517,0.00029926965,0.00003267855,0.0021668554,0.00066101935,0.000046636524,0.0038886648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98212194,0.014289086,0.00057928136,0.0013794542,0.0008577455,0.0007724418],"domain_scores_gemma":[0.76936555,0.21616536,0.005524601,0.005019446,0.0030316357,0.00089336676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052008055,0.0012514491,0.002605193,0.0015900029,0.0006317637,0.0019230081,0.0034116164,0.0029407805,0.004435618],"category_scores_gemma":[0.13205263,0.0013759014,0.0026417547,0.00161,0.0019116047,0.0020042926,0.002483369,0.0035187171,0.00041914236],"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":[0.00053911365,0.00015324714,0.0029154397,0.000110314,0.00016771062,0.000058189304,0.00011637577,0.96817744,0.00013156916,0.018463368,0.00029469858,0.008872551],"study_design_scores_gemma":[0.00008310858,0.00011989957,0.00052651315,0.000028963526,0.00006220201,0.000014731936,0.000027114142,0.99021417,0.00024290655,0.008318724,0.00034684266,0.00001488376],"about_ca_topic_score_codex":0.018246302,"about_ca_topic_score_gemma":0.006771829,"teacher_disagreement_score":0.052008055,"about_ca_system_score_codex":0.0037683072,"about_ca_system_score_gemma":0.004046173,"threshold_uncertainty_score":0.27504814},"labels":[],"label_agreement":null},{"id":"W4366447847","doi":"10.3138/cjpe.24.008","title":"L. Bickman &amp; D.J. Rog (Eds.). (2009). <i>The Sage Handbook of Applied Social Research Methods</i> (2nd ed.). Thousand Oaks, CA: Sage. 659 Pages.","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Diverse Educational Innovations Studies","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Sociology; Humanities; Philosophy; Physics","score_opus":0.18241188179778625,"score_gpt":0.42896152958851325,"score_spread":0.246549647790727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447847","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089054607,0.9269263,0.011894609,0.012630268,0.0033772318,0.000104089966,0.0015133003,0.0005610294,0.04210269],"genre_scores_gemma":[0.0034627381,0.94599545,0.0121862525,0.000807421,0.00061256986,0.000091541,0.00068795646,0.00017181804,0.035984278],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990503,0.00021944618,0.000091879825,0.00012969272,0.00045439485,0.00005439569],"domain_scores_gemma":[0.9974758,0.0013316796,0.00024708864,0.00008773835,0.0006046831,0.00025305626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022400836,0.002168959,0.0017049287,0.0032093055,0.00085329526,0.0037795117,0.0015447711,0.0018854252,0.03297128],"category_scores_gemma":[0.004568067,0.001522199,0.0006301014,0.0041712862,0.0011258385,0.0040364787,0.0011187722,0.0022950296,0.03351348],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027617074,0.000033366665,0.00032880425,0.0014851963,0.000013316489,0.000051701834,0.00027866854,0.00028574295,0.0001780838,0.002037761,0.36902538,0.6262543],"study_design_scores_gemma":[0.000010695084,0.0000469971,0.0022410983,0.004021081,0.00004439237,0.00044640643,0.0004819583,0.0003512776,0.00057029724,0.006361571,0.9853747,0.00004950117],"about_ca_topic_score_codex":0.018818878,"about_ca_topic_score_gemma":0.050115235,"teacher_disagreement_score":0.03297128,"about_ca_system_score_codex":0.0017748922,"about_ca_system_score_gemma":0.005907391,"threshold_uncertainty_score":0.110299945},"labels":[],"label_agreement":null},{"id":"W4366447855","doi":"10.3138/cjpe.20.009","title":"How Can Information About the Competencies Required for Evaluation Be Useful?","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Accreditation; Certification; Medical education; Psychology; Thematic analysis; Knowledge management; Engineering ethics; Computer science; Political science; Medicine; Sociology; Engineering; Qualitative research","score_opus":0.407391146677462,"score_gpt":0.4961895575741692,"score_spread":0.0887984108967072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447855","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04627936,0.01292762,0.14115614,0.54745597,0.0032274358,0.0027242827,0.0014400211,0.0010788376,0.24371031],"genre_scores_gemma":[0.6570574,0.020390086,0.27047372,0.03585735,0.0022188642,0.0029948342,0.0016552077,0.00031901174,0.009033539],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9131217,0.06349521,0.0049316697,0.0012597352,0.015068518,0.0021232562],"domain_scores_gemma":[0.6724858,0.2513666,0.010663929,0.010110733,0.048378505,0.0069944295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11048151,0.000550705,0.0010986929,0.0046926094,0.0023403761,0.011031775,0.0020190484,0.0042577717,0.011475487],"category_scores_gemma":[0.3996285,0.00048543638,0.0008285879,0.002520592,0.004421723,0.017024126,0.0037128346,0.0037233655,0.0047383495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025935288,0.0003904603,0.010202877,0.0054246844,0.00006532096,0.0006089721,0.006858673,0.0014589524,0.0007537956,0.060239073,0.0848222,0.82891566],"study_design_scores_gemma":[0.00027036018,0.0006073852,0.030167848,0.04225212,0.00022547318,0.0021445777,0.03627266,0.006858163,0.007963678,0.27853152,0.59419096,0.0005152265],"about_ca_topic_score_codex":0.005503506,"about_ca_topic_score_gemma":0.0057057883,"teacher_disagreement_score":0.11048151,"about_ca_system_score_codex":0.006639955,"about_ca_system_score_gemma":0.019726863,"threshold_uncertainty_score":0.5842891},"labels":[],"label_agreement":null},{"id":"W4366447868","doi":"10.3138/cjpe.27.008","title":"H. J. Rubin &amp; I. S. Rubin (2011). <i>Qualitative Interviewing: The Art of Hearing Data</i> (3ième éd.). Thousand Oaks, CA : Sage, 360 pages.","year":2012,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Interview; Psychology; Gerontology; Sociology; Medicine; Physics; Anthropology","score_opus":0.28259188932892504,"score_gpt":0.45164360832026634,"score_spread":0.1690517189913413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447868","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027912771,0.30794978,0.47948423,0.13073666,0.0037999854,0.0023120008,0.00978311,0.0042890827,0.058853954],"genre_scores_gemma":[0.04795403,0.4023182,0.48493886,0.0136394305,0.0019541832,0.0059048375,0.003838972,0.0030357752,0.036415704],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.970584,0.021142598,0.002468065,0.0013386593,0.004136283,0.0003303976],"domain_scores_gemma":[0.8113815,0.15283214,0.007788092,0.010078399,0.016412191,0.001507699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07010708,0.0014728493,0.0019559732,0.010442977,0.0035245086,0.004546528,0.003027521,0.0026587648,0.024621444],"category_scores_gemma":[0.14456525,0.0034102208,0.0011861478,0.014663626,0.0063455263,0.006649961,0.002485494,0.0066190353,0.012879664],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007364236,0.00008521492,0.0015953932,0.003382879,0.00013196457,0.0001747858,0.003167272,0.0007542603,0.00041089614,0.044972043,0.48292628,0.46232536],"study_design_scores_gemma":[0.00010353147,0.000113662514,0.007819081,0.011323651,0.00022784603,0.00070834503,0.0031008967,0.001996102,0.0031879556,0.11702275,0.8540742,0.0003219667],"about_ca_topic_score_codex":0.029879235,"about_ca_topic_score_gemma":0.040187865,"teacher_disagreement_score":0.07010708,"about_ca_system_score_codex":0.0036432995,"about_ca_system_score_gemma":0.011447927,"threshold_uncertainty_score":0.3707661},"labels":[],"label_agreement":null},{"id":"W4366448017","doi":"10.3138/cjpe.22.002","title":"Collaborative Evaluation in a Community Change Initiative: Dilemmas of Control Over Technical Decision Making","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Control (management); Process (computing); Dimension (graph theory); Work (physics); Meaning (existential); Process management; Knowledge management; Management science; Computer science; Sociology; Public relations; Political science; Psychology; Business; Engineering","score_opus":0.3796100750810484,"score_gpt":0.568284039236673,"score_spread":0.18867396415562465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2298,0.008110638,0.32674366,0.24692023,0.0015232262,0.0031490545,0.000051524326,0.00040966223,0.18329199],"genre_scores_gemma":[0.9484185,0.00084219873,0.041915786,0.004157866,0.00018566615,0.0008748783,0.000014187463,0.00007156511,0.0035193835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.44514537,0.48261926,0.0098932395,0.008094491,0.046110965,0.008136689],"domain_scores_gemma":[0.43897426,0.47199103,0.017655779,0.017777922,0.040841263,0.012759657],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.3555969,0.001139191,0.0014625778,0.0037265122,0.028971473,0.04102395,0.0057563265,0.010962229,0.0031650881],"category_scores_gemma":[0.3510148,0.0011300688,0.0012368184,0.0032701495,0.048129782,0.021035107,0.020856285,0.012428555,0.00042814418],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004955954,0.00077077607,0.008575915,0.0012957262,0.00025554944,0.0018488722,0.25725287,0.0052292943,0.0012282181,0.50071704,0.019279333,0.20305073],"study_design_scores_gemma":[0.0006673573,0.0010604766,0.006077688,0.0042757494,0.00021329858,0.0013980563,0.22874288,0.017494887,0.0052720336,0.5819577,0.1521536,0.00068628864],"about_ca_topic_score_codex":0.013864966,"about_ca_topic_score_gemma":0.014577748,"teacher_disagreement_score":0.9710285,"about_ca_system_score_codex":0.024539312,"about_ca_system_score_gemma":0.054551117,"threshold_uncertainty_score":0.7946638},"labels":[],"label_agreement":null},{"id":"W4366448036","doi":"10.3138/cjpe.021.001","title":"The Role of the Office of the Auditor General in Canada and the Concept of Independence","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Taxation and Legal Issues","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Independence (probability theory); Audit; Auditor independence; Accounting; Psychology; Business; Political science; Mathematics; Statistics; Internal audit; Joint audit","score_opus":0.01364898708745004,"score_gpt":0.23639063683030226,"score_spread":0.2227416497428522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448036","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11002999,0.013501914,0.0049071703,0.23288563,0.0018558025,0.00015433115,0.00034895676,0.00010609078,0.63621014],"genre_scores_gemma":[0.9081783,0.0036368482,0.0020619873,0.015655963,0.00028010324,0.00005162606,0.00008620331,0.000086965454,0.06996206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9730031,0.0033905122,0.0006393974,0.001514546,0.009820672,0.011631806],"domain_scores_gemma":[0.9560224,0.01083747,0.0018618566,0.0010079697,0.017619321,0.0126509685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014069011,0.000393236,0.0007765901,0.00417931,0.028253881,0.018156659,0.0030081188,0.006742457,0.0073272334],"category_scores_gemma":[0.040085103,0.0008789318,0.0005447561,0.004718703,0.02886504,0.005704333,0.0059766322,0.011013233,0.00037270252],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00006652357,0.00004610371,0.0062305136,0.00006521052,0.000015612895,0.0001868538,0.006173961,0.00052274496,0.00014568213,0.92041785,0.03325613,0.032872915],"study_design_scores_gemma":[0.00016179353,0.00009278677,0.0920307,0.0014203058,0.00013696816,0.00035073442,0.026833167,0.0029642624,0.0007670343,0.17238666,0.70248324,0.0003723498],"about_ca_topic_score_codex":0.99045044,"about_ca_topic_score_gemma":0.9943856,"teacher_disagreement_score":0.8336948,"about_ca_system_score_codex":0.16630521,"about_ca_system_score_gemma":0.42061722,"threshold_uncertainty_score":0.96696776},"labels":[],"label_agreement":null},{"id":"W4366448042","doi":"10.3138/cjpe.0021.009","title":"L’animation de groupe : une pratique à redécouvrir afin de développer le pouvoir d’agir des individus!","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Empowerment; Facilitation; Sociology; Humanities; Psychology; Action (physics); Political science; Art","score_opus":0.11176658902825047,"score_gpt":0.4131906731681911,"score_spread":0.3014240841399406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448042","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13665669,0.011222164,0.17498139,0.43633652,0.0063090157,0.0007967456,0.00017158761,0.0018144398,0.23171134],"genre_scores_gemma":[0.7830072,0.005813412,0.119457185,0.01620861,0.00063224195,0.0008043825,0.0000862197,0.00046901053,0.07352184],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9899961,0.008452792,0.000080325975,0.0003298882,0.00081520353,0.00032558283],"domain_scores_gemma":[0.98837924,0.007206242,0.00048847165,0.0013798194,0.0013252405,0.0012209306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015602663,0.00062361354,0.00033777358,0.00090744253,0.008807657,0.005681848,0.0018272785,0.003165252,0.011595438],"category_scores_gemma":[0.02283913,0.0003186335,0.00039074148,0.0007968153,0.015010214,0.0073817405,0.005639638,0.004337538,0.0013294537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002652371,0.00035631744,0.0060662907,0.0007480325,0.0000378819,0.00075556705,0.2676937,0.0014123514,0.0037190136,0.21172841,0.110575564,0.3966417],"study_design_scores_gemma":[0.00007442946,0.0003253628,0.004039883,0.0013757724,0.000037727,0.000626421,0.090931356,0.0029636107,0.001961695,0.045821603,0.8517397,0.00010244568],"about_ca_topic_score_codex":0.057473376,"about_ca_topic_score_gemma":0.11911846,"teacher_disagreement_score":0.057473376,"about_ca_system_score_codex":0.004845543,"about_ca_system_score_gemma":0.009010464,"threshold_uncertainty_score":0.11427766},"labels":[],"label_agreement":null},{"id":"W4366448066","doi":"10.3138/cjpe.026.007","title":"Stake, R. E. (2010). <i>Qualitative Research: Studying How Things Work.</i> New York, NY: Guilford Press. 244 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Work (physics); Media studies; Engineering; Mechanical engineering","score_opus":0.9420309666332343,"score_gpt":0.5946086491900977,"score_spread":0.34742231744313656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448066","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015992334,0.42825475,0.1302726,0.236384,0.010367001,0.0030232396,0.0055520283,0.0018890374,0.16826494],"genre_scores_gemma":[0.28291956,0.43632653,0.17356172,0.025858862,0.0020594217,0.005833111,0.0032226942,0.0014830806,0.06873498],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98999864,0.005510069,0.0010836344,0.00036207456,0.0027404858,0.00030507974],"domain_scores_gemma":[0.8707728,0.10473908,0.0039838753,0.002368253,0.015752183,0.0023838077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03660505,0.0010698675,0.0010125682,0.0060159294,0.006923459,0.007479951,0.002162678,0.0025394836,0.01726693],"category_scores_gemma":[0.090365656,0.0022599418,0.0006896513,0.005085458,0.007658895,0.0133683495,0.0046806782,0.008209786,0.006003886],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016691044,0.00009889446,0.00455375,0.007941968,0.00008431146,0.00033677564,0.047303468,0.00027957966,0.0021894074,0.04318325,0.43714288,0.4567188],"study_design_scores_gemma":[0.00012027954,0.0002540722,0.021664772,0.026900921,0.00026205933,0.0007208247,0.070537664,0.00041791526,0.0033066818,0.104521565,0.7710294,0.0002638677],"about_ca_topic_score_codex":0.01821965,"about_ca_topic_score_gemma":0.043473035,"teacher_disagreement_score":0.03660505,"about_ca_system_score_codex":0.004800465,"about_ca_system_score_gemma":0.009593559,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4366448126","doi":"10.3138/cjpe.0027.005","title":"The Paris Declaration Evaluation Process and Methods","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Process (computing); Process management; Engineering ethics; Corporate governance; Quality (philosophy); Perspective (graphical); Management science; Political science; Computer science; Business; Engineering; Epistemology; Law","score_opus":0.42934184573180173,"score_gpt":0.6085040427500894,"score_spread":0.17916219701828767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448126","genre_codex":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007626058,0.0029650624,0.3746683,0.02068361,0.004736697,0.41159067,0.0105412165,0.0015830926,0.16560523],"genre_scores_gemma":[0.038883656,0.0012961696,0.3314489,0.005533864,0.000646712,0.5891288,0.0044178674,0.0006143277,0.028029712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.58978933,0.2997561,0.040550172,0.012699575,0.04808339,0.009121463],"domain_scores_gemma":[0.6087349,0.14789909,0.016570302,0.05111136,0.16950226,0.006182175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.36948496,0.0024394256,0.0022301653,0.012859848,0.007810921,0.016743038,0.0073772417,0.0068768635,0.034801107],"category_scores_gemma":[0.3469156,0.0024790198,0.0026327292,0.008927803,0.0109352805,0.0057123955,0.009330296,0.009143851,0.010878741],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014815426,0.0005871155,0.0035137627,0.008816883,0.00021218657,0.0007732143,0.030619156,0.005068922,0.0016237629,0.4243706,0.19038934,0.3325435],"study_design_scores_gemma":[0.00051451765,0.00033630978,0.0028511866,0.009506358,0.00007563562,0.00015044992,0.004850543,0.002385832,0.0032520283,0.03375244,0.942134,0.00019066561],"about_ca_topic_score_codex":0.015672518,"about_ca_topic_score_gemma":0.012873493,"teacher_disagreement_score":0.36948496,"about_ca_system_score_codex":0.027814765,"about_ca_system_score_gemma":0.13662419,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4366448130","doi":"10.3138/cjpe.20.002","title":"A Theory-Driven Approach to Evaluating a Communication Intervention","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; Toronto Rehabilitation Institute; University of Toronto; Ministry of Health and Long Term Care","funders":"","keywords":"Generalizability theory; Intervention (counseling); Randomized controlled trial; Psychological intervention; Psychology; Applied psychology; Nursing; Management science; Psychotherapist; Medicine; Engineering; Developmental psychology","score_opus":0.5184974503264448,"score_gpt":0.5452525557772251,"score_spread":0.026755105450780303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448130","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030861752,0.0011284115,0.7933075,0.0053816,0.0010033074,0.13868628,0.0010189605,0.0003724394,0.028239662],"genre_scores_gemma":[0.15873988,0.00037963662,0.69110644,0.0017986151,0.000093356095,0.14693323,0.00016336105,0.000041857755,0.0007436051],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.61933815,0.33773568,0.011807957,0.005589336,0.024164498,0.0013642912],"domain_scores_gemma":[0.7359551,0.22365367,0.008476225,0.01092079,0.019556973,0.0014372943],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23300907,0.0028359029,0.0030447245,0.0070036068,0.0025388761,0.0058478285,0.00455575,0.0037351628,0.010480854],"category_scores_gemma":[0.24950364,0.0013370457,0.003540417,0.0031010143,0.0066700624,0.0037891136,0.00366983,0.005306131,0.0010887914],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0055135065,0.008376446,0.009400277,0.024527205,0.0046042935,0.00036989767,0.0058670267,0.039513934,0.0051680696,0.5501073,0.008590901,0.3379611],"study_design_scores_gemma":[0.031591784,0.04637793,0.012333101,0.016671386,0.0067076785,0.00067170855,0.0063005416,0.20258227,0.02938882,0.571314,0.07547641,0.0005842832],"about_ca_topic_score_codex":0.0024900793,"about_ca_topic_score_gemma":0.0024275077,"teacher_disagreement_score":0.23300907,"about_ca_system_score_codex":0.0128389755,"about_ca_system_score_gemma":0.028171167,"threshold_uncertainty_score":0.94583637},"labels":[],"label_agreement":null},{"id":"W4366448156","doi":"10.3138/cjpe.23.015","title":"Hedley Dimock. (2004). <i>Outcome-based Program Development and Evaluation (Dimock series on groups).</i> Concord, ON: Cactus Press. 77 pages.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Diverse Educational Innovations Studies","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cactus; Outcome (game theory); Series (stratigraphy); Geology; Ecology; Biology; Economics; Mathematical economics","score_opus":0.2575810803238636,"score_gpt":0.34169530440325224,"score_spread":0.08411422407938862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448156","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039500925,0.55754083,0.011795469,0.20727138,0.02769006,0.00073665107,0.006417261,0.0014216088,0.18317664],"genre_scores_gemma":[0.050767634,0.40409988,0.020184949,0.033591803,0.004870229,0.0010247205,0.0039392817,0.0007306269,0.48079085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998315,0.00040843754,0.00013558098,0.000120319986,0.0009351618,0.00008560319],"domain_scores_gemma":[0.99015754,0.0029641616,0.0007016718,0.0002958038,0.0047827307,0.0010980371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050607496,0.0009535241,0.00051115436,0.0023190891,0.0011840475,0.002091576,0.0014386949,0.0020271644,0.06657215],"category_scores_gemma":[0.01594315,0.00069606944,0.00026311813,0.0029333993,0.000765969,0.0034958338,0.0012771873,0.0025530292,0.022312306],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003866547,0.00001473928,0.00024658322,0.000224465,0.0000034573882,0.00001287772,0.00012118913,0.000033124885,0.000058833495,0.00049487554,0.82942444,0.16932668],"study_design_scores_gemma":[0.00008304127,0.00006947296,0.0068354285,0.0021577273,0.00004314674,0.00009311124,0.00062885165,0.00009228387,0.0006390165,0.0024703806,0.9868547,0.000032852116],"about_ca_topic_score_codex":0.04306457,"about_ca_topic_score_gemma":0.10037805,"teacher_disagreement_score":0.06657215,"about_ca_system_score_codex":0.0023320785,"about_ca_system_score_gemma":0.004545048,"threshold_uncertainty_score":0.22270608},"labels":[],"label_agreement":null},{"id":"W4366448430","doi":"10.3138/cjpe.23.013","title":"M.J. Bamberger, J. Rugh, and L. Mabry. (2006). <i>RealWorld Evaluation: Working Under Budget, Time, Data, and Political Constraints.</i> Thousand Oaks, CA: Sage.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Politics; Psychology; Gerontology; Political science; Medicine; Physics; Law","score_opus":0.21413066728362704,"score_gpt":0.45988540608889716,"score_spread":0.24575473880527013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448430","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006042542,0.35301042,0.10174153,0.265619,0.009806522,0.0007896755,0.006202791,0.0018819823,0.25490552],"genre_scores_gemma":[0.1314972,0.39577597,0.1928045,0.039339766,0.0032255286,0.0012147358,0.0035992153,0.0013320311,0.23121096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99715483,0.00093448046,0.00019905745,0.00015384314,0.0014549133,0.00010273566],"domain_scores_gemma":[0.97982603,0.012211774,0.0012003904,0.00048017167,0.005649583,0.00063202303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008296529,0.00085257925,0.00048778384,0.0026983428,0.0021618311,0.0043844944,0.0013108149,0.0024681543,0.03078804],"category_scores_gemma":[0.030359926,0.00083270966,0.00044617523,0.0029892258,0.0015367006,0.0063948194,0.00141708,0.0030092346,0.017157972],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066305554,0.00003454045,0.0014764755,0.00066451787,0.000016011842,0.000049015252,0.0006632703,0.00019477733,0.00023606591,0.008112027,0.70885533,0.27963164],"study_design_scores_gemma":[0.0000547092,0.00012068902,0.014816774,0.004017811,0.0001328471,0.00032613648,0.0019704734,0.0006632442,0.0022082287,0.043275636,0.93232995,0.0000835284],"about_ca_topic_score_codex":0.027974587,"about_ca_topic_score_gemma":0.103822716,"teacher_disagreement_score":0.03078804,"about_ca_system_score_codex":0.0020934916,"about_ca_system_score_gemma":0.00541152,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4366448432","doi":"10.3138/cjpe.0022.006","title":"Secondary Analysis with Minority Group Data: A Research Team’s Account of the Challenges","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Strengths and weaknesses; Scale (ratio); Population; Statistical analysis; Psychology; Data science; Management science; Computer science; Sociology; Social psychology; Statistics; Engineering; Geography; Mathematics","score_opus":0.4136951938413966,"score_gpt":0.4533811426616206,"score_spread":0.039685948820224026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102790035,0.0052864663,0.4636706,0.38757598,0.0056181294,0.007871217,0.00037336204,0.00056641665,0.026247803],"genre_scores_gemma":[0.5261109,0.0034386264,0.39746588,0.05205123,0.0021687434,0.011770242,0.0002214593,0.00088309246,0.005889819],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.4505514,0.46692654,0.02827927,0.006227554,0.04510083,0.002914351],"domain_scores_gemma":[0.2381708,0.602824,0.018665688,0.040250644,0.09499723,0.0050916336],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.542108,0.0009873201,0.0020553977,0.0043589976,0.013969037,0.014361193,0.005573235,0.005564656,0.0020761725],"category_scores_gemma":[0.6276365,0.0013176999,0.0021244113,0.005754043,0.013524405,0.011084186,0.010712798,0.010705669,0.0007306482],"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":[0.0004162862,0.00034890487,0.024708215,0.0032699634,0.00048498609,0.0034996876,0.60862315,0.0024918239,0.0038480046,0.074063115,0.059831504,0.21841429],"study_design_scores_gemma":[0.0003151912,0.0010118271,0.022299783,0.014145417,0.0006056252,0.008010535,0.3951929,0.022661954,0.010043058,0.15827926,0.36677983,0.0006545863],"about_ca_topic_score_codex":0.011004927,"about_ca_topic_score_gemma":0.011650529,"teacher_disagreement_score":0.542108,"about_ca_system_score_codex":0.008025887,"about_ca_system_score_gemma":0.031404953,"threshold_uncertainty_score":0.5646624},"labels":[],"label_agreement":null},{"id":"W4366448437","doi":"10.3138/cjpe.027.007","title":"Hesse-Biber, S. N. (2010). <i>Mixed Methods Research: Merging Theory with Practice.</i> New York, NY: Guilford. 242 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Sociology","score_opus":0.7423552584982398,"score_gpt":0.6234861653502343,"score_spread":0.11886909314800553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448437","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023752272,0.6874312,0.17441784,0.07459945,0.017649611,0.0016972425,0.005353742,0.0018292945,0.0346464],"genre_scores_gemma":[0.043647304,0.5754998,0.32876047,0.012686284,0.006595378,0.004632444,0.0040788148,0.0014060406,0.022693472],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9655444,0.022156283,0.0037405665,0.0010230797,0.007297401,0.00023826858],"domain_scores_gemma":[0.6689225,0.28717962,0.0071633337,0.007556975,0.027778478,0.0013990266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08951511,0.0021231007,0.001865355,0.009662995,0.0030759326,0.008052217,0.0033650722,0.00401185,0.022108901],"category_scores_gemma":[0.19284564,0.0032607182,0.001746037,0.01061719,0.006112538,0.010670396,0.0034353568,0.008275385,0.012407974],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020924056,0.00007092467,0.0019667218,0.0075637475,0.00029516403,0.00009559317,0.0023345356,0.00061463227,0.000631025,0.01758959,0.39787838,0.57075036],"study_design_scores_gemma":[0.00030292833,0.0003605711,0.014214536,0.03242386,0.0010416151,0.00081796,0.0033701519,0.0018842221,0.00321817,0.08742186,0.8545617,0.00038251665],"about_ca_topic_score_codex":0.013944429,"about_ca_topic_score_gemma":0.031272523,"teacher_disagreement_score":0.08951511,"about_ca_system_score_codex":0.003413454,"about_ca_system_score_gemma":0.0075284136,"threshold_uncertainty_score":0.4734068},"labels":[],"label_agreement":null},{"id":"W4366448452","doi":"10.3138/cjpe.0021.017","title":"Les dispositifs de la participation aux étapes stratégiques de l’évaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deliberation; Participatory evaluation; Valuation (finance); Citizen journalism; Relevance (law); Knowledge management; Rationality; Process management; Sociology; Management science; Psychology; Business; Computer science; Political science; Engineering; Social science; Accounting","score_opus":0.4004949898556033,"score_gpt":0.5989514537971734,"score_spread":0.19845646394157013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36438033,0.004014792,0.3194521,0.024842512,0.0006061473,0.003447558,0.00061323855,0.0012263723,0.28141692],"genre_scores_gemma":[0.89333713,0.0013228653,0.094307855,0.00050910393,0.00019809626,0.0025676237,0.00034630953,0.00015499837,0.007256091],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.63313067,0.27027604,0.014353713,0.008119024,0.06916414,0.0049563837],"domain_scores_gemma":[0.4969657,0.40824398,0.016607272,0.021940224,0.050423093,0.005819819],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19419444,0.002276762,0.0009405101,0.006513359,0.0056110793,0.025010375,0.0022586347,0.0046115923,0.009511078],"category_scores_gemma":[0.29758897,0.0013121832,0.002277181,0.0040265415,0.0074552186,0.014772208,0.0067855245,0.0059558013,0.001983823],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011622875,0.0014998534,0.07350793,0.0022091572,0.00057461846,0.0013952174,0.066677764,0.01417874,0.005193706,0.24223277,0.008304559,0.58306354],"study_design_scores_gemma":[0.0012916496,0.0029873431,0.109612934,0.009054398,0.0012031865,0.0028340353,0.082027785,0.100813426,0.03544678,0.3839637,0.2697593,0.0010054001],"about_ca_topic_score_codex":0.013209067,"about_ca_topic_score_gemma":0.0075762873,"teacher_disagreement_score":0.19419444,"about_ca_system_score_codex":0.010948181,"about_ca_system_score_gemma":0.014638343,"threshold_uncertainty_score":0.9937017},"labels":[],"label_agreement":null},{"id":"W4366448470","doi":"10.3138/cjpe.29.1.141","title":"Guest, G., MacQueen, K. M., &amp; Namey, E. E. (2012). <i>Applied Thematic Analysis.</i>","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thematic map; Thematic analysis; Chemistry; Sociology; Geography; Qualitative research","score_opus":0.11541150713220373,"score_gpt":0.3234607848665827,"score_spread":0.20804927773437898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448470","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029756801,0.064238854,0.28308347,0.34625897,0.02507301,0.01053966,0.016544022,0.0031923759,0.22131284],"genre_scores_gemma":[0.32608035,0.086221255,0.4160239,0.035923574,0.0022117142,0.016744487,0.006176314,0.0028078477,0.10781045],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912554,0.004448728,0.00088542857,0.00039736248,0.00284485,0.00016819035],"domain_scores_gemma":[0.935792,0.04198662,0.0028207807,0.0017557789,0.016428696,0.0012161427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023488002,0.0005901097,0.00079750136,0.0053402716,0.0052648564,0.0043893997,0.0020203632,0.0013139859,0.008529507],"category_scores_gemma":[0.12184997,0.0006444013,0.0005213783,0.008238654,0.0042776563,0.0053016306,0.003099174,0.0034719526,0.0027409235],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000800238,0.000039777668,0.0027294322,0.0046297135,0.00003796567,0.00018940124,0.03871691,0.00012705663,0.0021459067,0.014557343,0.6802903,0.25645626],"study_design_scores_gemma":[0.00004758645,0.00010698194,0.01831641,0.008808962,0.00011365036,0.00046131696,0.052387524,0.00062346336,0.0026207054,0.027785813,0.88864726,0.000080329366],"about_ca_topic_score_codex":0.02469495,"about_ca_topic_score_gemma":0.087156884,"teacher_disagreement_score":0.02469495,"about_ca_system_score_codex":0.0051404717,"about_ca_system_score_gemma":0.01146697,"threshold_uncertainty_score":0.12421793},"labels":[],"label_agreement":null},{"id":"W4366448482","doi":"10.3138/cjpe.020.005","title":"The Delphi Technique as a Method for Increasing Inclusion in the Evaluation Process","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Delphi method; Delphi; Compromise; Inclusion (mineral); Process (computing); Set (abstract data type); Evaluation methods; Psychology; Economic Justice; Representation (politics); Public relations; Management science; Sociology; Engineering ethics; Computer science; Social psychology; Political science; Engineering; Social science; Artificial intelligence; Law","score_opus":0.3689523270921288,"score_gpt":0.6178187315297932,"score_spread":0.2488664044376644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03981146,0.00057357945,0.86187094,0.004977835,0.0008772229,0.05976003,0.00019424058,0.00059533323,0.031339362],"genre_scores_gemma":[0.071929336,0.00036049247,0.8722822,0.000637926,0.00013714157,0.052047044,0.00005236096,0.00015835151,0.002395155],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.34212998,0.60420716,0.016451383,0.0036589494,0.031639654,0.0019128323],"domain_scores_gemma":[0.5753041,0.3326742,0.009167216,0.022452122,0.057545464,0.0028568679],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3784713,0.0022564568,0.0020650318,0.010040768,0.007172154,0.0060959673,0.0032041413,0.0023802684,0.010406978],"category_scores_gemma":[0.32956684,0.0018769492,0.0013155884,0.006516421,0.009790544,0.0065864143,0.015763018,0.0064116293,0.0022521461],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012068702,0.0008302667,0.0021693106,0.005599879,0.0002046603,0.00081762887,0.29076824,0.0029106368,0.017306715,0.07881551,0.01720865,0.5821616],"study_design_scores_gemma":[0.0023133743,0.006126159,0.01368456,0.017129606,0.00041580718,0.0024690528,0.22028083,0.034646653,0.032665394,0.27729622,0.39146784,0.0015044846],"about_ca_topic_score_codex":0.0012804382,"about_ca_topic_score_gemma":0.002470285,"teacher_disagreement_score":0.3784713,"about_ca_system_score_codex":0.004406443,"about_ca_system_score_gemma":0.013149284,"threshold_uncertainty_score":0.7664556},"labels":[],"label_agreement":null},{"id":"W4366448488","doi":"10.3138/cjpe.26.009","title":"M. Q. Patton. (2011). <i>Developmental Evaluation: Applying Complexity Concepts to Enhance Innovation and Use.</i> New York, NY: Guilford Press. 373 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognitive science; Psychology; Management; Economics","score_opus":0.692320291059202,"score_gpt":0.5156360293542,"score_spread":0.17668426170500195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448488","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038070926,0.51325005,0.0734856,0.23302624,0.0132776555,0.00044813467,0.0018701789,0.001852128,0.15898296],"genre_scores_gemma":[0.06831374,0.5444366,0.09763504,0.028947914,0.0051176473,0.0007858944,0.0013468354,0.0009920023,0.25242442],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988116,0.00028468337,0.00009388917,0.000095473,0.00067545683,0.000038856368],"domain_scores_gemma":[0.9886348,0.0061731213,0.0005093447,0.00020088175,0.003961393,0.0005204232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040431647,0.00083952234,0.0005034769,0.002449284,0.0016711402,0.0026435833,0.0010087471,0.00246554,0.049490884],"category_scores_gemma":[0.017352305,0.00071229227,0.00031738562,0.00248036,0.0011269099,0.006482321,0.0013253456,0.002579741,0.02022372],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004583425,0.000019869818,0.0005573317,0.00057546905,0.000007039348,0.00006121257,0.00057214516,0.00008012724,0.00026007913,0.0044620885,0.63922876,0.35413003],"study_design_scores_gemma":[0.00004475528,0.000093008246,0.008203352,0.0027654925,0.000049236638,0.00054861244,0.0010551204,0.0005095608,0.0016165519,0.019909116,0.96515846,0.00004664851],"about_ca_topic_score_codex":0.011525727,"about_ca_topic_score_gemma":0.03326983,"teacher_disagreement_score":0.049490884,"about_ca_system_score_codex":0.0012668569,"about_ca_system_score_gemma":0.0024912662,"threshold_uncertainty_score":0.16556352},"labels":[],"label_agreement":null},{"id":"W4366448608","doi":"10.3138/cjpe.0021.016","title":"Le magicien du temps : approche participative axée sur le développement d’un projet et l’utilisation des résultats d’une évaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Valuation (finance); Destiny (ISS module); Relevance (law); Sociology; Welfare economics; Political science; Business; Economics; Engineering","score_opus":0.23516404660556098,"score_gpt":0.4060862575426964,"score_spread":0.17092221093713542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6893459,0.0028296832,0.1704963,0.009953373,0.00045586072,0.013033374,0.0005462613,0.0004365334,0.1129028],"genre_scores_gemma":[0.8570897,0.0010390282,0.1264049,0.00049177994,0.000034813653,0.0058496837,0.0002403006,0.000092910275,0.008756728],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.77425295,0.18926658,0.005766041,0.0031420838,0.02500167,0.0025707467],"domain_scores_gemma":[0.7605242,0.16039199,0.007049002,0.010307068,0.057852726,0.0038749073],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23550233,0.0013486968,0.0009103913,0.005990969,0.006312863,0.013709445,0.0028561498,0.0025070226,0.004006524],"category_scores_gemma":[0.16537066,0.0008075155,0.00088725146,0.00466899,0.007141304,0.006073569,0.0063709314,0.0022226793,0.0006028064],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011756774,0.0021190103,0.02610626,0.004471248,0.00021170995,0.0008801161,0.37649503,0.004504907,0.005426544,0.037392754,0.006342029,0.5348746],"study_design_scores_gemma":[0.0013520488,0.0067882403,0.07223239,0.014614081,0.00081265403,0.0008686553,0.580116,0.027392564,0.030110171,0.040002085,0.22504736,0.000663813],"about_ca_topic_score_codex":0.03602805,"about_ca_topic_score_gemma":0.0512589,"teacher_disagreement_score":0.23550233,"about_ca_system_score_codex":0.020842128,"about_ca_system_score_gemma":0.03054122,"threshold_uncertainty_score":0.9427617},"labels":[],"label_agreement":null},{"id":"W4366448611","doi":"10.3138/cjpe.0028.010","title":"M&amp;E Competencies in Support of the AIDS Response: A Sector-Specific Example","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Human immunodeficiency virus (HIV); Service delivery framework; Process (computing); Business; Psychology; Service (business); Knowledge management; Nursing; Medical education; Public relations; Medicine; Political science; Marketing; Computer science; Family medicine","score_opus":0.4760414459172037,"score_gpt":0.4932620036647494,"score_spread":0.017220557747545717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7161269,0.0049200323,0.016621932,0.043653805,0.00042959047,0.0011322037,0.0004961338,0.00024167873,0.21637775],"genre_scores_gemma":[0.9729953,0.002026563,0.013257282,0.0016335,0.000056715126,0.00013141605,0.00015953611,0.000019421135,0.009720315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967996,0.002003017,0.00009252339,0.000053333762,0.00038616857,0.0006652828],"domain_scores_gemma":[0.9953661,0.0021391995,0.00019085442,0.00015157035,0.0013892486,0.000763144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004686202,0.00029411414,0.00014715466,0.0009505044,0.0023171008,0.0016398459,0.00056996656,0.001621654,0.0076949224],"category_scores_gemma":[0.0056584543,0.0001108958,0.0003377071,0.0012001283,0.00074178865,0.0011784761,0.00205887,0.0010607828,0.00113083],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090146175,0.0049036993,0.10134289,0.0030904498,0.00004283924,0.011155096,0.05680302,0.006123028,0.004717394,0.03618125,0.06572472,0.7090142],"study_design_scores_gemma":[0.00051944284,0.0030071074,0.20558895,0.0045192274,0.000121454905,0.013367357,0.16240124,0.015556379,0.014285033,0.013414326,0.5670361,0.00018339424],"about_ca_topic_score_codex":0.011094477,"about_ca_topic_score_gemma":0.0299994,"teacher_disagreement_score":0.011094477,"about_ca_system_score_codex":0.0029608689,"about_ca_system_score_gemma":0.006473118,"threshold_uncertainty_score":0.025742114},"labels":[],"label_agreement":null},{"id":"W4366448613","doi":"10.3138/cjpe.031.1.vi","title":"Un mot du rédacteur","year":2016,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.16177410226179187,"score_gpt":0.46182805204444066,"score_spread":0.30005394978264877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448613","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048899604,0.02889993,0.01174827,0.28244585,0.14684856,0.0006566673,0.0019317614,0.0019614545,0.52061754],"genre_scores_gemma":[0.0460384,0.02782712,0.016442074,0.104982235,0.032880668,0.0011575164,0.003008643,0.0026722348,0.7649911],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97999465,0.006255236,0.0012607011,0.0024037117,0.0085723335,0.0015134272],"domain_scores_gemma":[0.9528729,0.0086621605,0.002295727,0.005736682,0.023515232,0.0069173845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01359196,0.0017417406,0.001060989,0.0036068454,0.005928118,0.013906996,0.0032046076,0.006505666,0.19497646],"category_scores_gemma":[0.060165092,0.0009613384,0.001552521,0.0027471294,0.0041072527,0.014149653,0.011081442,0.011016153,0.092559695],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009521763,0.000058300757,0.0010088234,0.0007153489,0.000020379131,0.00032815075,0.0013493461,0.00008067539,0.00039607988,0.02434709,0.8108151,0.1607855],"study_design_scores_gemma":[0.000011169098,0.000026492287,0.0003998782,0.0006002416,0.000010044804,0.00034523424,0.00075787975,0.000051978666,0.00027130122,0.0029446995,0.9945621,0.000019085155],"about_ca_topic_score_codex":0.0078085484,"about_ca_topic_score_gemma":0.00899574,"teacher_disagreement_score":0.19497646,"about_ca_system_score_codex":0.007652567,"about_ca_system_score_gemma":0.019169394,"threshold_uncertainty_score":0.65226126},"labels":[],"label_agreement":null},{"id":"W4366448663","doi":"10.3138/cjpe.0021.003","title":"Guest Editor’s Introduction","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Posthumanist Ethics and Activism","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.09699812284345119,"score_gpt":0.4191019620742321,"score_spread":0.3221038392307809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448663","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010189845,0.0014300147,0.0001332659,0.07023223,0.9231484,0.000032221757,0.00008937787,0.00006436321,0.004768271],"genre_scores_gemma":[0.0028715665,0.002306338,0.00040185073,0.11451281,0.792359,0.00010616775,0.00012026,0.00011618708,0.08720577],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954259,0.0006043303,0.000472335,0.0006547886,0.0022915127,0.00055116334],"domain_scores_gemma":[0.9670534,0.006442593,0.0020228794,0.001494717,0.01825119,0.0047352477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066633364,0.0013579554,0.0014886601,0.0024753688,0.0022624978,0.0049129855,0.0024862008,0.009847396,0.05867144],"category_scores_gemma":[0.041713063,0.00064900634,0.001719987,0.0009886958,0.0011718046,0.0021402857,0.0018037114,0.010008845,0.021167556],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001752604,0.0000062131267,0.000042419593,0.000069311944,0.000004374792,0.00009057845,0.000008152729,0.000010885291,0.0000394401,0.00022370392,0.99499965,0.0044877147],"study_design_scores_gemma":[0.00003302159,0.000021670201,0.0005349052,0.0002230696,0.000022165103,0.00021836424,0.000054170825,0.00008339056,0.00015941806,0.0005071321,0.9981269,0.000015651507],"about_ca_topic_score_codex":0.0023538286,"about_ca_topic_score_gemma":0.005603127,"teacher_disagreement_score":0.05867144,"about_ca_system_score_codex":0.0022812441,"about_ca_system_score_gemma":0.0039183376,"threshold_uncertainty_score":0.19627553},"labels":[],"label_agreement":null},{"id":"W4366448925","doi":"10.3138/cjpe.20.010","title":"Le développement des capacités pour les évaluateurs de programmes: apporter une solution au mauvais problème?","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"","keywords":"Political science; Function (biology); Sociology; Business; Welfare economics; Psychology; Economics","score_opus":0.20613744319629426,"score_gpt":0.4049283132911466,"score_spread":0.19879087009485233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18053687,0.010077885,0.4238375,0.19003189,0.00043112267,0.0011602298,0.0005406827,0.0007219567,0.19266194],"genre_scores_gemma":[0.90401995,0.0018875895,0.08391953,0.001091551,0.000146684,0.0008981869,0.00010452246,0.00019885694,0.007733148],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92644495,0.054476477,0.0022864395,0.003279932,0.009713031,0.0037991388],"domain_scores_gemma":[0.7688564,0.16393776,0.008323647,0.011523819,0.03838077,0.00897766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.091232985,0.0017900068,0.0015604619,0.0056652618,0.0047486625,0.019937877,0.005201767,0.0062733316,0.010503553],"category_scores_gemma":[0.22854969,0.0012790735,0.0011147365,0.005562685,0.014795475,0.027506994,0.010970075,0.0070129307,0.0011923636],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015525107,0.00027331055,0.009405002,0.0011333021,0.000101610305,0.00013928779,0.011065574,0.01637659,0.00059967034,0.80564874,0.0073028016,0.14779885],"study_design_scores_gemma":[0.0001608347,0.00057021994,0.021284413,0.0047363373,0.0001198555,0.00052148773,0.033545997,0.10129435,0.0046393936,0.74378693,0.08906918,0.00027108408],"about_ca_topic_score_codex":0.030586816,"about_ca_topic_score_gemma":0.024250317,"teacher_disagreement_score":0.091232985,"about_ca_system_score_codex":0.025050405,"about_ca_system_score_gemma":0.041349623,"threshold_uncertainty_score":0.4824919},"labels":[],"label_agreement":null},{"id":"W4366449208","doi":"10.3138/cjpe.23.011","title":"L’examen de la qualité des évaluations fédérales: une méta-évaluation réussie?","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Credibility; Treasury; Valuation (finance); Quality (philosophy); Relevance (law); Political science; Psychology; Accounting; Business; Philosophy; Epistemology","score_opus":0.5449930809225783,"score_gpt":0.5670762013901169,"score_spread":0.022083120467538686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449208","genre_codex":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011916039,0.8736547,0.059769794,0.043280717,0.0044461405,0.0017484275,0.00086009793,0.00023035826,0.0040937546],"genre_scores_gemma":[0.5841991,0.21382408,0.16561003,0.020156162,0.0057756277,0.0076859826,0.0009853799,0.0005739366,0.0011897478],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.21929681,0.6183816,0.08684938,0.009819954,0.06416585,0.0014863564],"domain_scores_gemma":[0.073889814,0.7753016,0.048300467,0.060285132,0.041391637,0.0008314764],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6752882,0.0027791983,0.015005322,0.020827059,0.0029801612,0.021160515,0.007963373,0.005497147,0.0028056952],"category_scores_gemma":[0.8506874,0.0034660776,0.019307712,0.021724703,0.009118379,0.019103894,0.0067348224,0.0081061,0.0004035423],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033182877,0.0002566147,0.02763932,0.24230118,0.29775676,0.00026450938,0.004959663,0.0037093554,0.0012160268,0.045452368,0.014897595,0.35822836],"study_design_scores_gemma":[0.0027299041,0.0018510869,0.03490398,0.53111345,0.25862548,0.00085797906,0.0033134334,0.010121474,0.0057693417,0.07452521,0.07553737,0.00065124],"about_ca_topic_score_codex":0.014393453,"about_ca_topic_score_gemma":0.018086972,"teacher_disagreement_score":0.97746056,"about_ca_system_score_codex":0.022539437,"about_ca_system_score_gemma":0.024614146,"threshold_uncertainty_score":0.40042752},"labels":[],"label_agreement":null},{"id":"W4366449213","doi":"10.3138/cjpe.26.007","title":"J. Daniel. (2012). <i>Sampling Essentials: Practical Guidelines for Making Sampling Choices.</i> Thousand Oaks, CA: Sage. 291 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Collège de Maisonneuve","funders":"","keywords":"SAGE; Sampling (signal processing); Psychology; Library science; Sociology; Computer science; Telecommunications; Physics","score_opus":0.7643446773847061,"score_gpt":0.5796727911761839,"score_spread":0.18467188620852226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449213","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025099372,0.030544264,0.8150863,0.0701994,0.011204492,0.006462748,0.01923953,0.002838812,0.04191454],"genre_scores_gemma":[0.013498306,0.009067426,0.93570524,0.015625864,0.0012518497,0.0091011105,0.0026746676,0.0011392623,0.011936295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9197745,0.059710238,0.006588434,0.002052344,0.011248351,0.0006262158],"domain_scores_gemma":[0.5475584,0.36452672,0.010828084,0.014842693,0.059628244,0.0026159205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15610993,0.0016333184,0.00216569,0.005245232,0.0049649766,0.0051868213,0.004718385,0.004078332,0.031679064],"category_scores_gemma":[0.4470634,0.0043236595,0.001444601,0.006925751,0.0042280024,0.0046811025,0.0031913177,0.010049237,0.015855448],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015214946,0.000055716595,0.0017202313,0.0014572823,0.00007431398,0.00012227768,0.0024300006,0.0006329542,0.00032086822,0.025510877,0.73245645,0.23506695],"study_design_scores_gemma":[0.0003110095,0.00018404539,0.0060278457,0.008816315,0.00027259896,0.00076715276,0.0034256396,0.004353254,0.002245397,0.1425118,0.8307413,0.00034359685],"about_ca_topic_score_codex":0.03625887,"about_ca_topic_score_gemma":0.07636151,"teacher_disagreement_score":0.15610993,"about_ca_system_score_codex":0.005110174,"about_ca_system_score_gemma":0.014573866,"threshold_uncertainty_score":0.82559806},"labels":[],"label_agreement":null},{"id":"W4366449214","doi":"10.3138/cjpe.26.008","title":"R. K. Yin. (2012). <i>Applications of Case Study Research.</i> Thousand Oaks, CA : Sage. 231 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Psychology; Sociology; Gerontology; Medicine; Physics","score_opus":0.5104853260324024,"score_gpt":0.5639836468724017,"score_spread":0.05349832083999928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449214","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004835676,0.63491374,0.09718656,0.107383765,0.018013863,0.0019453617,0.005160859,0.0026970606,0.12786305],"genre_scores_gemma":[0.04418832,0.67205596,0.1892438,0.010304325,0.0026419216,0.00290265,0.0034160472,0.0015680117,0.07367899],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956518,0.0018198539,0.00046016555,0.0002546817,0.0017137497,0.00009976419],"domain_scores_gemma":[0.94912416,0.025456658,0.0024655233,0.0011992555,0.020468239,0.0012861299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015178724,0.0014488898,0.0009799307,0.0059100436,0.0023810056,0.002572342,0.0014428089,0.0012337492,0.02396165],"category_scores_gemma":[0.042263616,0.0012796883,0.000544692,0.0059136194,0.0025762538,0.005008055,0.0015376762,0.0036537522,0.017433807],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006822332,0.00004065333,0.0009444036,0.0041436544,0.000031395615,0.00019077984,0.0032530199,0.0001797591,0.000698974,0.0062272297,0.63015574,0.35406613],"study_design_scores_gemma":[0.000049093294,0.000100403835,0.012115907,0.016029356,0.00012448822,0.00076479244,0.005503351,0.00028723074,0.0012880175,0.017008854,0.94660693,0.00012175276],"about_ca_topic_score_codex":0.016530007,"about_ca_topic_score_gemma":0.047935955,"teacher_disagreement_score":0.02396165,"about_ca_system_score_codex":0.0021658724,"about_ca_system_score_gemma":0.00807061,"threshold_uncertainty_score":0.08027375},"labels":[],"label_agreement":null},{"id":"W4366449340","doi":"10.3138/cjpe.0022.012","title":"Achievement Assessment Programs in Reading and Writing: What Lessons Can Be Learned?","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reading (process); Mathematics education; Literacy; Accountability; Test (biology); Psychology; Academic achievement; Achievement test; Pedagogy; Standardized test; Political science","score_opus":0.3287598229889723,"score_gpt":0.4633364146822562,"score_spread":0.13457659169328395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449340","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016584704,0.1866769,0.0022006745,0.7676167,0.0050214604,0.00054024823,0.0012594764,0.00033474757,0.019765098],"genre_scores_gemma":[0.40101904,0.45417967,0.02914124,0.085926875,0.007499512,0.0023379542,0.0026008775,0.0001529243,0.017141819],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948308,0.0023562196,0.00025502735,0.00029935324,0.001447706,0.0008110485],"domain_scores_gemma":[0.9619486,0.013782705,0.0011113994,0.0007729314,0.014745142,0.0076392326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020457907,0.0011010944,0.0014651847,0.0019336472,0.002140579,0.0057646013,0.0039402833,0.0038262026,0.008829572],"category_scores_gemma":[0.04744841,0.0003639884,0.00082167046,0.0029808045,0.001859094,0.0063227112,0.0019799042,0.00513712,0.0011229797],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003142969,0.00062052405,0.009995572,0.0038859413,0.00007319475,0.00020208793,0.0021874518,0.00038715478,0.00006650832,0.0076244427,0.18284726,0.79179555],"study_design_scores_gemma":[0.0019093152,0.0017151461,0.17816874,0.14827083,0.00097591913,0.0006292447,0.052832313,0.005166735,0.0008727521,0.053748988,0.555326,0.00038401075],"about_ca_topic_score_codex":0.468984,"about_ca_topic_score_gemma":0.64193267,"teacher_disagreement_score":0.468984,"about_ca_system_score_codex":0.010246523,"about_ca_system_score_gemma":0.071642846,"threshold_uncertainty_score":0.9325084},"labels":[],"label_agreement":null},{"id":"W4366449357","doi":"10.3138/cjpe.0027.006","title":"Results of the Paris Declaration Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program 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":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Variety (cybernetics); Aid effectiveness; Relevance (law); Development aid; Political science; Developing country; Economic growth; Public administration; Public relations; Business; Computer science; Economics; Law","score_opus":0.1528120077654701,"score_gpt":0.4022964131134687,"score_spread":0.2494844053479986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449357","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18068983,0.017510448,0.020205377,0.021803703,0.0034173913,0.089535594,0.12979695,0.0014549963,0.53558576],"genre_scores_gemma":[0.678618,0.0071203476,0.040834688,0.008416005,0.0006639682,0.15335973,0.037520014,0.000961142,0.07250599],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.66210306,0.25789952,0.018142348,0.006919965,0.04897814,0.0059570293],"domain_scores_gemma":[0.64442104,0.16735636,0.014736066,0.010819747,0.15949056,0.0031762917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23292357,0.002480195,0.0027045836,0.014678523,0.0038019791,0.012989367,0.0029180632,0.0026319295,0.044180557],"category_scores_gemma":[0.33594754,0.0012015497,0.0036025005,0.012041588,0.0033969353,0.005614747,0.007075584,0.0025089704,0.0073333164],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021572614,0.0032700123,0.035341572,0.027254052,0.0042705857,0.00045249652,0.047170594,0.008743782,0.0008592622,0.03550025,0.23981829,0.5757465],"study_design_scores_gemma":[0.006336964,0.008504476,0.11101999,0.039388314,0.007344392,0.00022076874,0.086400844,0.0032837326,0.012214994,0.01230254,0.7121778,0.0008051408],"about_ca_topic_score_codex":0.020714026,"about_ca_topic_score_gemma":0.015272907,"teacher_disagreement_score":0.23292357,"about_ca_system_score_codex":0.038742997,"about_ca_system_score_gemma":0.03836858,"threshold_uncertainty_score":0.9459418},"labels":[],"label_agreement":null},{"id":"W4366449367","doi":"10.3138/cjpe.0027.002","title":"Un mot du rédacteur du numéro spécial","year":2013,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Chemistry","score_opus":0.12592431156465866,"score_gpt":0.43179234296887364,"score_spread":0.305868031404215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449367","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09670434,0.034914818,0.022125045,0.34193444,0.06735573,0.00079240085,0.009470583,0.0024780012,0.42422462],"genre_scores_gemma":[0.4966985,0.03195371,0.062244415,0.047119707,0.023801245,0.0027676085,0.006833389,0.0018409154,0.3267405],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9771189,0.0073987516,0.001501243,0.0012914874,0.010689926,0.0019996997],"domain_scores_gemma":[0.94096196,0.018975526,0.0045185746,0.0028126577,0.026666809,0.0060644816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01538614,0.0011958708,0.0015826538,0.006757598,0.0038333666,0.006187941,0.0014586409,0.0029804532,0.038932744],"category_scores_gemma":[0.08460481,0.00065743685,0.001733127,0.0043598646,0.0025006996,0.0055371523,0.0036209302,0.0068565235,0.0048751147],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080688327,0.000585752,0.04051515,0.0014810222,0.00014346094,0.0006101554,0.0035332409,0.00068517996,0.001787449,0.05725096,0.24160115,0.65099955],"study_design_scores_gemma":[0.00027023978,0.00042105434,0.06593356,0.0027121725,0.00011033786,0.0018727158,0.0038949815,0.00094477966,0.0034585476,0.007753109,0.9124383,0.0001902497],"about_ca_topic_score_codex":0.12702157,"about_ca_topic_score_gemma":0.09415028,"teacher_disagreement_score":0.12702157,"about_ca_system_score_codex":0.012092157,"about_ca_system_score_gemma":0.018447366,"threshold_uncertainty_score":0.25256443},"labels":[],"label_agreement":null},{"id":"W4366449571","doi":"10.3138/cjpe.0022.005","title":"Design and Development Issues in Provincial Large-Scale Assessments: Designing Assessments to Inform Policy and Practice","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Accountability; Scale (ratio); Quality (philosophy); Key (lock); Management science; Engineering ethics; Political science; Psychology; Public relations; Computer science; Engineering","score_opus":0.4087057107089686,"score_gpt":0.5695313585263149,"score_spread":0.16082564781734626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449571","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16553141,0.004003033,0.60150963,0.05401365,0.0010131199,0.08648338,0.0023347791,0.0014679229,0.08364294],"genre_scores_gemma":[0.4996287,0.0008193658,0.470756,0.0014549975,0.00008395852,0.025585352,0.00036374712,0.00012288748,0.0011849386],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.57652116,0.35756174,0.020782795,0.006106496,0.033830814,0.0051969183],"domain_scores_gemma":[0.28542137,0.4727946,0.037565526,0.044903636,0.15095577,0.008359139],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.41322884,0.0011258541,0.001901044,0.0048225396,0.008168668,0.014384147,0.005010139,0.0031942101,0.0025321108],"category_scores_gemma":[0.6437905,0.001927073,0.0012651936,0.0103190085,0.009698749,0.0116422735,0.009484575,0.0054618954,0.0009149549],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015558514,0.0020180177,0.123550095,0.009077248,0.0006561511,0.0004115592,0.059221346,0.051473178,0.002738642,0.1282359,0.024413284,0.59664875],"study_design_scores_gemma":[0.0033041774,0.0036922703,0.16713206,0.019424295,0.0011128249,0.00035807004,0.081485845,0.16452867,0.011434322,0.38974246,0.15689567,0.0008893116],"about_ca_topic_score_codex":0.16175327,"about_ca_topic_score_gemma":0.27602822,"teacher_disagreement_score":0.41322884,"about_ca_system_score_codex":0.049494293,"about_ca_system_score_gemma":0.17254335,"threshold_uncertainty_score":0.72359335},"labels":[],"label_agreement":null},{"id":"W4366449572","doi":"10.3138/cjpe.0021.004","title":"Will Evaluation Prosper in the Future?","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Professionalization; Accountability; Audit; Public sector; Public relations; Professional standards; Business; Political science; Accounting; Public administration; Sociology; Engineering ethics; Engineering; Law","score_opus":0.2834746849839425,"score_gpt":0.5446628427125925,"score_spread":0.26118815772864995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449572","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001355672,0.021626564,0.0031295836,0.9568571,0.006364068,0.00006212104,0.00006748772,0.00006657976,0.010470792],"genre_scores_gemma":[0.24304211,0.092157684,0.040511627,0.5660455,0.02364116,0.0009775356,0.0004629514,0.00034464872,0.032816757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90759754,0.05856508,0.004749766,0.0033712925,0.019568432,0.00614795],"domain_scores_gemma":[0.65818304,0.16992746,0.017824916,0.01881961,0.10580531,0.029439729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.25691396,0.00068974466,0.0019531138,0.0017975544,0.004332201,0.019026436,0.0026800511,0.016849661,0.014180428],"category_scores_gemma":[0.30198434,0.00043910937,0.0014598742,0.0018692743,0.014814199,0.03643085,0.0072977054,0.012774038,0.004959969],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060532737,0.00030701986,0.0035595882,0.0024662379,0.000113852344,0.00021500244,0.0014011546,0.0008314068,0.00034160278,0.42120036,0.26356572,0.30539268],"study_design_scores_gemma":[0.00030854935,0.0004588964,0.004048165,0.009277311,0.000117594085,0.0005451985,0.0048740073,0.0016152551,0.0009457137,0.36930364,0.6083395,0.00016615893],"about_ca_topic_score_codex":0.005901466,"about_ca_topic_score_gemma":0.0051082256,"teacher_disagreement_score":0.25691396,"about_ca_system_score_codex":0.011403993,"about_ca_system_score_gemma":0.060234748,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4366449591","doi":"10.3138/cjpe.023.006","title":"La méthode de cartographie conceptuelle pour identifier les priorités de recherche sur le transfert des connaissances en santé des populations : quelques enjeux méthodologiques","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"The Quebec Population Health Research Network; Université de Montréal","funders":"","keywords":"Identifier; Computer science","score_opus":0.9068279838512547,"score_gpt":0.6204096034709966,"score_spread":0.28641838038025813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449591","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009371903,0.0006125479,0.9843604,0.00078936975,0.00011931018,0.0018543357,0.00045923813,0.00030350286,0.0021293692],"genre_scores_gemma":[0.040072616,0.00026057608,0.9546357,0.00010455603,0.000024394109,0.0041965684,0.00016562465,0.00007829227,0.00046166085],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8110041,0.17030345,0.005692065,0.005744469,0.006572404,0.0006834547],"domain_scores_gemma":[0.5966243,0.3752499,0.004376133,0.014318107,0.009110492,0.00032109016],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12039581,0.0025536548,0.0030789622,0.011508746,0.0022888505,0.008066302,0.003264123,0.0020540778,0.008220129],"category_scores_gemma":[0.20893878,0.001322972,0.0047671096,0.012074506,0.005568277,0.006972688,0.0039380174,0.004353388,0.0008446171],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007345112,0.0003606174,0.015340074,0.0073168566,0.0027392406,0.0002797131,0.03574351,0.00936466,0.0042705596,0.35717562,0.005437919,0.5612368],"study_design_scores_gemma":[0.0015771452,0.0011094274,0.028187362,0.0073285503,0.0022382557,0.001754498,0.030905329,0.14716394,0.014438791,0.6452977,0.11903879,0.0009601903],"about_ca_topic_score_codex":0.009377238,"about_ca_topic_score_gemma":0.008387332,"teacher_disagreement_score":0.8796042,"about_ca_system_score_codex":0.0036919324,"about_ca_system_score_gemma":0.008989386,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4366449610","doi":"10.3138/cjpe.22.001","title":"Methodological and Conceptual Challenges in Studying Evaluation Process Use","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Process (computing); Construct (python library); Context (archaeology); Exploratory research; Process management; Quality (philosophy); Knowledge management; Management science; Computer science; Qualitative research; Conceptual model; Scale (ratio); Psychology; Sociology; Epistemology; Business; Engineering","score_opus":0.9321012710267086,"score_gpt":0.6602703593788898,"score_spread":0.2718309116478188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449610","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09611199,0.030467872,0.7693117,0.05122063,0.0016955179,0.008582356,0.00049278827,0.00030613024,0.04181104],"genre_scores_gemma":[0.6766781,0.0050513884,0.2924297,0.0043036705,0.00065958,0.019211322,0.00018674576,0.000213923,0.0012655441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3220897,0.57610995,0.038209103,0.0136496015,0.04654845,0.0033932137],"domain_scores_gemma":[0.13887297,0.7620833,0.022597432,0.030564148,0.044471204,0.0014109926],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5136543,0.0015565916,0.002606742,0.011141113,0.009070501,0.02476512,0.008456855,0.004912969,0.0032414186],"category_scores_gemma":[0.6456859,0.0016621698,0.0023951,0.014055703,0.038284402,0.025180113,0.013194387,0.007836842,0.00061631505],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024730197,0.0006942366,0.02691387,0.014672646,0.0006403093,0.00030778904,0.116285205,0.0031441771,0.001073537,0.61094874,0.003164774,0.22190735],"study_design_scores_gemma":[0.00035750197,0.0009070359,0.017552495,0.018639619,0.00058010593,0.00079060026,0.16190557,0.012699507,0.0056399666,0.71408755,0.06653776,0.00030230466],"about_ca_topic_score_codex":0.007767413,"about_ca_topic_score_gemma":0.004852144,"teacher_disagreement_score":0.4863457,"about_ca_system_score_codex":0.016143676,"about_ca_system_score_gemma":0.028117009,"threshold_uncertainty_score":0.5997509},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4366449624","doi":"10.3138/cjpe.0027.001","title":"Remarks from the Editor of the Special Issue","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Jewish Identity and Society","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.04260344883538068,"score_gpt":0.3365879868239664,"score_spread":0.2939845379885857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449624","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001146492,0.0017062858,0.00011881824,0.5416648,0.4556388,0.000016250762,0.000059688555,0.000027589616,0.0006531978],"genre_scores_gemma":[0.0012951172,0.0017399376,0.00017663947,0.52727145,0.46278334,0.000043565502,0.000029821646,0.000041351403,0.0066188085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907968,0.0013220351,0.0014700644,0.0015007153,0.003966669,0.0009437335],"domain_scores_gemma":[0.94686663,0.018962884,0.0030877304,0.0014774719,0.02211478,0.007490531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015172048,0.0019927572,0.003433196,0.002046195,0.0053532277,0.009013023,0.0041382737,0.039335027,0.0063949074],"category_scores_gemma":[0.06597449,0.0014885057,0.0029492446,0.0014445281,0.003222106,0.0052125785,0.0022000188,0.04211741,0.004993044],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028890341,0.0000142777435,0.00011577227,0.000045617595,0.000014301456,0.00012394413,0.000028529368,0.000013799862,0.00003533725,0.00020113456,0.99758947,0.0017888597],"study_design_scores_gemma":[0.00008763071,0.00004243647,0.0017036808,0.00032074348,0.000101472666,0.00034015562,0.00026433478,0.00020978715,0.00024935804,0.0010719383,0.9955331,0.000075303375],"about_ca_topic_score_codex":0.011003936,"about_ca_topic_score_gemma":0.019069185,"teacher_disagreement_score":0.039335027,"about_ca_system_score_codex":0.005507378,"about_ca_system_score_gemma":0.008742409,"threshold_uncertainty_score":0.0802384},"labels":[],"label_agreement":null},{"id":"W4366449629","doi":"10.3138/cjpe.0021.006","title":"Studies Are Not Enough: The Necessary Transformation of Evaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"GRASP; Public sector; Business; Knowledge management; Profit (economics); Public relations; Not for profit; Political science; Economics; Computer science","score_opus":0.55640313541793,"score_gpt":0.5856812041578379,"score_spread":0.029278068739907903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449629","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003914469,0.016241742,0.016657203,0.9329439,0.005094341,0.00025474938,0.0000519847,0.0001205609,0.024721038],"genre_scores_gemma":[0.60922915,0.016966628,0.056181774,0.30188364,0.0076192715,0.0017986961,0.000119834134,0.00027380357,0.0059272344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.60665894,0.3052572,0.02256578,0.006812635,0.053788543,0.0049168384],"domain_scores_gemma":[0.22918646,0.6286788,0.013875626,0.05303248,0.062949166,0.012277447],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.353658,0.000822185,0.00256768,0.0052229045,0.008942256,0.029035408,0.0043998077,0.010679073,0.003920452],"category_scores_gemma":[0.44887072,0.0011514967,0.0012603621,0.0033595997,0.077280976,0.044399943,0.01873572,0.026371043,0.0007883733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012301878,0.00028633073,0.0028904662,0.0018756471,0.000077670265,0.0002956429,0.027813917,0.0005019939,0.00033709768,0.71525854,0.08077608,0.16976362],"study_design_scores_gemma":[0.00014371176,0.00017690155,0.0017762976,0.006042819,0.000066236935,0.00034422884,0.030143417,0.0008729195,0.0005523886,0.7162625,0.24352492,0.00009366114],"about_ca_topic_score_codex":0.0070136553,"about_ca_topic_score_gemma":0.007928526,"teacher_disagreement_score":0.353658,"about_ca_system_score_codex":0.018475506,"about_ca_system_score_gemma":0.065648,"threshold_uncertainty_score":0.79705477},"labels":[],"label_agreement":null},{"id":"W4366449631","doi":"10.3138/cjpe.0023.001","title":"Editor’s Remarks","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Jewish Identity and Society","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.050022523513755836,"score_gpt":0.3831771860339665,"score_spread":0.33315466252021064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449631","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023407316,0.0013621147,0.00016700575,0.50509477,0.48881122,0.000042200867,0.000115521536,0.00007221415,0.0041008964],"genre_scores_gemma":[0.002528694,0.0008952811,0.0004786899,0.73128974,0.22219303,0.00009676,0.000045742952,0.00007982925,0.042392187],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98438096,0.0014958391,0.0018591057,0.0024697324,0.0076310607,0.0021633],"domain_scores_gemma":[0.92500585,0.019174187,0.0045297,0.0039084014,0.040090468,0.007291289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016311068,0.0017152824,0.00304382,0.0024337613,0.007061726,0.010581097,0.0059646387,0.055017438,0.022691857],"category_scores_gemma":[0.13126746,0.001498555,0.0031471057,0.0022322268,0.0035962858,0.0044911765,0.003486854,0.039996035,0.01654166],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020224554,0.000009206214,0.0000745164,0.000040550512,0.000010638114,0.00014457345,0.000035733217,0.000023499768,0.000059060658,0.0005745056,0.99682426,0.0021831596],"study_design_scores_gemma":[0.000049000275,0.00001338547,0.00075918774,0.00019640283,0.00003625929,0.00019243533,0.00015409161,0.00015383496,0.00022467652,0.0011034119,0.99706846,0.00004888811],"about_ca_topic_score_codex":0.01770656,"about_ca_topic_score_gemma":0.028910734,"teacher_disagreement_score":0.055017438,"about_ca_system_score_codex":0.008438227,"about_ca_system_score_gemma":0.012681822,"threshold_uncertainty_score":0.08626217},"labels":[],"label_agreement":null},{"id":"W4366449951","doi":"10.3138/cjpe.0023.003","title":"Perceptions of Evaluation Capacity Building in the United States: A Descriptive Study of American Evaluation Association Members","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Association (psychology); Descriptive research; Psychology; Organizational change; Descriptive statistics; Organizational learning; Capacity building; Political science; Public relations; Social psychology; Medical education; Sociology; Management; Economics; Medicine; Social science; Law; Statistics","score_opus":0.40916432990698465,"score_gpt":0.5208469713431527,"score_spread":0.11168264143616807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988526,0.00008042163,0.000051847463,0.00020116217,0.000003083829,0.0000064909996,0.000020510028,0.0000013495255,0.0007824098],"genre_scores_gemma":[0.9994167,0.00012924151,0.000079607285,0.000117456984,0.000004637139,0.000012999015,0.000032550193,0.0000015209445,0.00020522738],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99700016,0.0014894415,0.00025375612,0.00014605962,0.0007366411,0.00037394062],"domain_scores_gemma":[0.97869796,0.008170498,0.0051533654,0.0005954231,0.004698186,0.0026846514],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062625213,0.00014884486,0.00024978656,0.0015171531,0.0017578371,0.0019147925,0.00039067704,0.0005108755,0.0014993344],"category_scores_gemma":[0.013388731,0.00028325478,0.0002155526,0.0013965965,0.0013626446,0.0014152896,0.0014151057,0.0011285901,0.00016053174],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010958777,0.0005095811,0.87840205,0.000054544747,0.00003477609,0.00019782409,0.10180008,0.00008702505,0.000723458,0.00031003248,0.0009649418,0.016806094],"study_design_scores_gemma":[0.000005544783,0.0002753934,0.72388524,0.00009597367,0.000014221283,0.00027440584,0.2699771,0.00029724665,0.00033664794,0.00010185786,0.004709234,0.000027125558],"about_ca_topic_score_codex":0.020128012,"about_ca_topic_score_gemma":0.02235081,"teacher_disagreement_score":0.99373746,"about_ca_system_score_codex":0.0012750791,"about_ca_system_score_gemma":0.0015756381,"threshold_uncertainty_score":0.040021718},"labels":[],"label_agreement":null},{"id":"W4366449986","doi":"10.3138/cjpe.0021.002","title":"Evaluation Practice in Canada: Results of a National Survey","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Merck Canada Inc. (Canada); Environment and Climate Change Canada","funders":"","keywords":"Certification; Workforce; Professionalization; Public relations; Work (physics); Psychology; Accountability; Population; Medical education; Action (physics); Position (finance); Professional certification (computer technology); Political science; Business; Sociology; Medicine; Engineering; Law","score_opus":0.5394801885554342,"score_gpt":0.5848590900140788,"score_spread":0.04537890145864454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98323214,0.0013259456,0.00031489896,0.0017713043,0.000026559557,0.00031081858,0.0037457624,0.000042008833,0.009230587],"genre_scores_gemma":[0.9947267,0.0009212614,0.000458687,0.0003646868,0.000006441916,0.00011453011,0.0015059544,0.000012850289,0.001888883],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9900315,0.0019005003,0.001008623,0.00065815874,0.00498871,0.0014125452],"domain_scores_gemma":[0.948512,0.005336603,0.005197521,0.0007521881,0.03516505,0.0050366702],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0085466495,0.00018918814,0.00047642755,0.0028082016,0.00397619,0.002199906,0.00096860604,0.00041047254,0.0019851518],"category_scores_gemma":[0.022482483,0.0003299501,0.0004913379,0.005911293,0.001196126,0.00079479674,0.0021012942,0.0008134666,0.00035198467],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015258456,0.00017355499,0.9424674,0.0003142573,0.000047051937,0.00010829611,0.015140682,0.00016039432,0.00014302056,0.00021900651,0.0058356836,0.035238132],"study_design_scores_gemma":[0.0000064605892,0.000048891772,0.98368466,0.00009134769,0.000008230203,0.000022287744,0.011814306,0.0002228629,0.00007330291,0.000021978543,0.003989306,0.000016442435],"about_ca_topic_score_codex":0.976583,"about_ca_topic_score_gemma":0.9800149,"teacher_disagreement_score":0.99145335,"about_ca_system_score_codex":0.04357096,"about_ca_system_score_gemma":0.08101599,"threshold_uncertainty_score":0.31613094},"labels":[],"label_agreement":null},{"id":"W4366450235","doi":"10.3138/cjpe.0024.001","title":"Challenges and Approaches to Evaluating Comprehensive Complex Tobacco Control Strategies","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; Public Health Ontario; University of Toronto","funders":"","keywords":"Variety (cybernetics); Management science; Computer science; Control (management); Risk analysis (engineering); Ideal (ethics); Intervention (counseling); Attribution; Psychological intervention; Process management; Psychology; Epistemology; Artificial intelligence; Business; Economics; Social psychology","score_opus":0.8095393556398636,"score_gpt":0.5490757212984705,"score_spread":0.2604636343413931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450235","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091692716,0.051148295,0.7380828,0.059419133,0.0007998967,0.006331582,0.00063197786,0.00054933643,0.051344264],"genre_scores_gemma":[0.45893657,0.008586422,0.5254512,0.0017932504,0.00012522064,0.0041280612,0.0001602611,0.000052793388,0.0007661629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.69194406,0.2441415,0.020042991,0.0064628185,0.03583988,0.0015687001],"domain_scores_gemma":[0.5136204,0.40767604,0.021917215,0.0127522,0.041664254,0.0023698644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24181436,0.0019865145,0.0032837181,0.009771752,0.002981006,0.018019456,0.005269121,0.00337281,0.0034022795],"category_scores_gemma":[0.3668606,0.0010693244,0.0023563704,0.008171338,0.0107668135,0.016408712,0.008128679,0.006054844,0.0004169261],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003388526,0.00092160655,0.011350586,0.014003073,0.0016174945,0.00014244442,0.013077065,0.034381203,0.00096603343,0.29763073,0.0035104426,0.62206054],"study_design_scores_gemma":[0.0004719101,0.0027594427,0.011509126,0.023656145,0.0014374305,0.0002713619,0.025741933,0.09238636,0.006525356,0.7963075,0.038336318,0.000597083],"about_ca_topic_score_codex":0.0067185424,"about_ca_topic_score_gemma":0.010635905,"teacher_disagreement_score":0.24181436,"about_ca_system_score_codex":0.018971438,"about_ca_system_score_gemma":0.026615638,"threshold_uncertainty_score":0.9349779},"labels":[],"label_agreement":null},{"id":"W4366450241","doi":"10.3138/cjpe.024.007","title":"Richard A. Krueger and Mary Anne Casey. (2009). <i>Focus Groups: A Practical Guide for Applied Research</i> (4th ed.). Thousand Oaks, CA: Sage. 205 pages, plus preface, acknowledgements, references, and indices.","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Focus Groups and Qualitative Methods","field":"Social Sciences","cited_by":114,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Psychology; Focus (optics); Sociology; Library science; Gerontology; Computer science; Medicine","score_opus":0.19416003882541363,"score_gpt":0.4936611830970598,"score_spread":0.2995011442716462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450241","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040996824,0.40563124,0.1092291,0.33314008,0.026787335,0.0018462782,0.0029814448,0.002410341,0.11387459],"genre_scores_gemma":[0.033875205,0.51545024,0.1866544,0.0627459,0.0038957044,0.0021106245,0.0016568858,0.0015393863,0.19207166],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99652594,0.0012243171,0.0002868778,0.00024716923,0.0016085964,0.0001070524],"domain_scores_gemma":[0.97890466,0.009948602,0.00092289335,0.00051568635,0.008809623,0.00089850614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008913502,0.0008998857,0.0006525559,0.003058212,0.0029124664,0.0026505587,0.0019153084,0.002661467,0.031834584],"category_scores_gemma":[0.038477592,0.0013129677,0.0005610997,0.0024139085,0.001853803,0.006993175,0.0020362264,0.0070320666,0.024202097],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043413598,0.000039259914,0.0003938139,0.0009708312,0.0000066135767,0.0000932122,0.001712683,0.000056178586,0.00035364213,0.0036235824,0.76495993,0.22774683],"study_design_scores_gemma":[0.000039616236,0.00009415314,0.0036533452,0.004560464,0.000034399363,0.000681225,0.0037682955,0.00016687889,0.0011608375,0.014994736,0.97074205,0.00010404126],"about_ca_topic_score_codex":0.02449945,"about_ca_topic_score_gemma":0.07457152,"teacher_disagreement_score":0.031834584,"about_ca_system_score_codex":0.0014796555,"about_ca_system_score_gemma":0.0054067457,"threshold_uncertainty_score":0.10649723},"labels":[],"label_agreement":null},{"id":"W4366450272","doi":"10.3138/cjpe.022.009","title":"What an Eight-Year-Old Can Teach Us About Logic Modelling and Mainstreaming","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hindsight bias; Narrative; Process (computing); Mainstreaming; Computer science; Simplicity; Point (geometry); Management science; SWORD; Process management; Engineering ethics; Epistemology; Psychology; Engineering; Mathematics education; Cognitive psychology; Programming language; Mathematics; Special education; Philosophy","score_opus":0.13905330773756333,"score_gpt":0.36849270031541737,"score_spread":0.22943939257785403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450272","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52467585,0.008131407,0.008955798,0.19804853,0.0039500687,0.00024770576,0.0002666113,0.0003930292,0.2553311],"genre_scores_gemma":[0.8274411,0.0064610243,0.00932607,0.029036425,0.00028819556,0.00012639127,0.00012184233,0.00012303721,0.12707588],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99803704,0.00068619946,0.00006019469,0.00018635773,0.0005060528,0.00052415865],"domain_scores_gemma":[0.9975746,0.00043371192,0.00016924446,0.00013363897,0.0005144828,0.0011742965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048471503,0.000659785,0.0006423352,0.00089619146,0.008819766,0.004747272,0.0012583511,0.0045395414,0.007527384],"category_scores_gemma":[0.006798092,0.00042858886,0.0006700181,0.0004595264,0.0067856144,0.0056756344,0.0038923318,0.008308522,0.0022953083],"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":[0.00012826048,0.0028070537,0.027102778,0.0002988945,0.000024161682,0.0341921,0.58830184,0.00025483913,0.003133254,0.12118583,0.117984995,0.10458592],"study_design_scores_gemma":[0.00002423035,0.00046407746,0.006265569,0.00091718853,0.00003491557,0.024949096,0.3110836,0.00036064096,0.0024569572,0.028766759,0.6245769,0.00010010641],"about_ca_topic_score_codex":0.014599287,"about_ca_topic_score_gemma":0.033205595,"teacher_disagreement_score":0.014599287,"about_ca_system_score_codex":0.0040350044,"about_ca_system_score_gemma":0.0040154564,"threshold_uncertainty_score":0.029276192},"labels":[],"label_agreement":null},{"id":"W4366450277","doi":"10.3138/cjpe.022.008","title":"Navigating Uncharted Waters: Project Monitoring at Cida","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Monitoring and evaluation; Agency (philosophy); Citizen journalism; Interpretation (philosophy); Participatory evaluation; Set (abstract data type); Process management; Relation (database); International development; Knowledge management; Computer science; Public relations; Business; Sociology; Political science; Public administration","score_opus":0.49079338051818244,"score_gpt":0.592320400631158,"score_spread":0.10152702011297554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.868348,0.0015425954,0.016612835,0.02455105,0.0002341317,0.003534382,0.0014560706,0.0011437683,0.08257709],"genre_scores_gemma":[0.970454,0.0006118142,0.01894417,0.0007700323,0.00002448927,0.00068425376,0.00049908727,0.00005350954,0.00795854],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914192,0.0041731265,0.00026174623,0.00061088527,0.0020466524,0.001488331],"domain_scores_gemma":[0.98366714,0.0041594277,0.0015658634,0.0009927743,0.0050400165,0.0045746835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01547181,0.00036545115,0.00029927518,0.0023384308,0.010496885,0.0042190584,0.002580072,0.0013608225,0.0037187112],"category_scores_gemma":[0.024262229,0.00032213418,0.00022954412,0.0032631909,0.0022354706,0.002272363,0.00534279,0.0019371491,0.0004418321],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007496034,0.0015683781,0.16637628,0.001281516,0.00008633894,0.0021778243,0.118011154,0.0031362867,0.0045962236,0.008941418,0.0501444,0.64293057],"study_design_scores_gemma":[0.00021035329,0.0028152154,0.35431463,0.0011595904,0.00015203164,0.0008341979,0.21841694,0.007368778,0.014130632,0.007906268,0.39240867,0.00028271883],"about_ca_topic_score_codex":0.15673204,"about_ca_topic_score_gemma":0.3161669,"teacher_disagreement_score":0.15673204,"about_ca_system_score_codex":0.016437905,"about_ca_system_score_gemma":0.04910012,"threshold_uncertainty_score":0.3116395},"labels":[],"label_agreement":null},{"id":"W4366450287","doi":"10.3138/cjpe.0021.012","title":"Le développement du pouvoir d’agir <i>(empowerment)</i> appliqué à une expérience d’insertion par l’économique : suggestion d’indicateurs d’évaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Empowerment; Valuation (finance); Psychology; Inclusion (mineral); Sociology; Intervention (counseling); Welfare economics; Political science; Business; Social psychology; Economic growth; Economics; Accounting","score_opus":0.07519419775479799,"score_gpt":0.35307381656879766,"score_spread":0.2778796188139997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450287","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9130395,0.00047441135,0.021246517,0.010672507,0.00019403159,0.0041489303,0.00012947139,0.00017416979,0.049920395],"genre_scores_gemma":[0.9696137,0.00032833556,0.022409046,0.0006982052,0.000023380568,0.0015832952,0.00005306683,0.000026219404,0.0052648066],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97362083,0.021357672,0.00053464354,0.00065937266,0.0023129378,0.0015146123],"domain_scores_gemma":[0.97327167,0.015838252,0.0014992867,0.0015090858,0.005690249,0.0021915229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041710462,0.00062003813,0.00038067682,0.0009002905,0.002862228,0.0041174074,0.0017682138,0.0015326776,0.0050361394],"category_scores_gemma":[0.02968251,0.00033670236,0.00042381548,0.0007476018,0.0044122427,0.0026335898,0.0022730248,0.0013736507,0.0004265749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024758978,0.017608704,0.048285518,0.0040202085,0.00013972442,0.0012938841,0.30056068,0.0026422488,0.021786356,0.05590313,0.017019948,0.5282636],"study_design_scores_gemma":[0.0022179955,0.027525052,0.21549994,0.0036473707,0.00045479875,0.00057360565,0.37552068,0.008764432,0.06589348,0.014706959,0.28476697,0.00042878214],"about_ca_topic_score_codex":0.028671812,"about_ca_topic_score_gemma":0.039268978,"teacher_disagreement_score":0.041710462,"about_ca_system_score_codex":0.009087351,"about_ca_system_score_gemma":0.015342783,"threshold_uncertainty_score":0.22058868},"labels":[],"label_agreement":null},{"id":"W4366450544","doi":"10.3138/cjpe.021.002","title":"Audit and Evaluation in Public Management: Challenges, Reforms, and Different Roles","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Public Policy and Administration Research","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Public sector; Confusion; Business; New public management; Public relations; Public management; Face (sociological concept); Relation (database); Accounting; Political science; Sociology; Psychology; Computer science","score_opus":0.19781411456872958,"score_gpt":0.42815858640496085,"score_spread":0.23034447183623127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450544","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01244301,0.11482828,0.013849101,0.8084091,0.0027800272,0.00021939423,0.000046196896,0.00011169807,0.047313157],"genre_scores_gemma":[0.8094403,0.08564563,0.030290442,0.060061723,0.0060523753,0.00045334236,0.00006745862,0.00014563116,0.00784301],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6900478,0.236898,0.011241019,0.0044936747,0.044518683,0.012800884],"domain_scores_gemma":[0.52611876,0.327488,0.018041154,0.01559534,0.090167135,0.022589594],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22761033,0.00063366693,0.0015970081,0.008470509,0.009990237,0.031401902,0.0025990312,0.009422389,0.0033207673],"category_scores_gemma":[0.2016524,0.00080655346,0.00091475615,0.008173614,0.042488076,0.02260265,0.010954869,0.013053916,0.000589697],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020822849,0.00022691759,0.008560669,0.002062896,0.000060139217,0.00017068889,0.004621073,0.0021412545,0.00018195681,0.61617315,0.03435851,0.33123457],"study_design_scores_gemma":[0.00022483588,0.0004972552,0.022188822,0.019157061,0.00011633426,0.0007805863,0.027786167,0.005639534,0.0012793298,0.55003387,0.37177756,0.00051861355],"about_ca_topic_score_codex":0.030957548,"about_ca_topic_score_gemma":0.039391074,"teacher_disagreement_score":0.22761033,"about_ca_system_score_codex":0.044699978,"about_ca_system_score_gemma":0.072292246,"threshold_uncertainty_score":0.95249397},"labels":[],"label_agreement":null},{"id":"W4366450567","doi":"10.3138/cjpe.021.004","title":"Evaluability Assessment as a Tool for Research Network Development: Experiences of the Complementary and Alternative Medicine Education and Research Network of Alberta, Canada","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Sciences Research and Education","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Alberta Health; University of Alberta; University of Calgary; Canadian Foundation for Healthcare Improvement; Research Canada","funders":"","keywords":"Plan (archaeology); Management science; Engineering ethics; Knowledge management; Psychology; Sociology; Computer science; Engineering","score_opus":0.4261489626898609,"score_gpt":0.627842518974254,"score_spread":0.20169355628439312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7982177,0.0036146264,0.03385464,0.045805447,0.0005141522,0.012000757,0.0005027149,0.00031430754,0.105175786],"genre_scores_gemma":[0.9513957,0.0011987335,0.03317865,0.0014682022,0.000052200874,0.0019477704,0.00018347953,0.00006994575,0.01050537],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.88552296,0.08743025,0.0022582768,0.0016078256,0.016056469,0.007124142],"domain_scores_gemma":[0.82763916,0.08095674,0.004921542,0.0048173866,0.063506395,0.018158823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16179591,0.00040686465,0.00044417224,0.0020983447,0.014897075,0.0057886597,0.0032017115,0.0012367489,0.003336942],"category_scores_gemma":[0.106261574,0.00045533848,0.00034862867,0.002671955,0.004364425,0.002329269,0.0064846957,0.0019940785,0.00027128882],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001092346,0.002161746,0.07510406,0.0014066636,0.000086461136,0.0016754977,0.3818096,0.0034134674,0.002280963,0.015783712,0.037315764,0.47786972],"study_design_scores_gemma":[0.00078955054,0.0027402886,0.104318336,0.0019067532,0.00018357424,0.00056738127,0.59536606,0.010727042,0.004789161,0.006593127,0.2716764,0.00034239335],"about_ca_topic_score_codex":0.7765784,"about_ca_topic_score_gemma":0.88759357,"teacher_disagreement_score":0.7765784,"about_ca_system_score_codex":0.08575015,"about_ca_system_score_gemma":0.1946901,"threshold_uncertainty_score":0.8556688},"labels":[],"label_agreement":null},{"id":"W4366450581","doi":"10.3138/cjpe.0021.011","title":"Un outil d’évaluation de <i>l’empowerment</i> : une tentative en haïti","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Empowerment; Valuation (finance); Sociology; Psychology; Promotion (chess); Management science; Epistemology; Political science; Business; Economics; Philosophy","score_opus":0.2649696778036359,"score_gpt":0.5361563451404582,"score_spread":0.2711866673368223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450581","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.478321,0.045855,0.12434194,0.13322447,0.0052755033,0.005585002,0.0009835126,0.00035695633,0.20605654],"genre_scores_gemma":[0.93195677,0.007830192,0.048119437,0.0033910295,0.0001807698,0.0018527693,0.00021544984,0.00006899186,0.0063845697],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9267847,0.056049433,0.003134672,0.0015733939,0.010809061,0.0016487477],"domain_scores_gemma":[0.9372095,0.040402077,0.0028374915,0.003120278,0.015318202,0.0011125504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.094451755,0.0013279895,0.0012063214,0.004237724,0.0056684217,0.011763805,0.0030230542,0.0030517203,0.0029409023],"category_scores_gemma":[0.070615746,0.0007607757,0.0010938835,0.003832438,0.013687739,0.009092196,0.0074680443,0.006384741,0.00029763364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008092993,0.0012859193,0.026671695,0.0060604727,0.00022147536,0.0011186632,0.16169171,0.0027189623,0.003008894,0.2876316,0.014542063,0.49423924],"study_design_scores_gemma":[0.0004987316,0.0016489417,0.049939692,0.03480801,0.00050152466,0.0015577475,0.38132435,0.0147839375,0.022659943,0.061688535,0.43005192,0.00053673005],"about_ca_topic_score_codex":0.100996174,"about_ca_topic_score_gemma":0.092731394,"teacher_disagreement_score":0.100996174,"about_ca_system_score_codex":0.024538912,"about_ca_system_score_gemma":0.030818647,"threshold_uncertainty_score":0.49951458},"labels":[],"label_agreement":null},{"id":"W4366451079","doi":"10.3138/cjpe.23.010","title":"A Journey Through Five Evaluation Projects with the Same Analysis Framework","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Strengths and weaknesses; Accountability; Process (computing); Interpretation (philosophy); Process management; Principal (computer security); Context (archaeology); Field (mathematics); Management science; Computer science; Knowledge management; Business; Political science; Psychology; Engineering; Social psychology; Computer security; Law","score_opus":0.46380024285771465,"score_gpt":0.5339974314860121,"score_spread":0.07019718862829744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48051417,0.006482151,0.24928185,0.06888618,0.0013468185,0.011729275,0.00073447026,0.00071557786,0.1803095],"genre_scores_gemma":[0.6252468,0.001564365,0.34622204,0.0022752522,0.000082804,0.005133758,0.0006301268,0.00025330123,0.018591646],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8269049,0.15225029,0.0033148646,0.0024103555,0.008842278,0.0062773116],"domain_scores_gemma":[0.8904195,0.050786827,0.0035398563,0.0064023947,0.04026256,0.008588855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14451192,0.0010529261,0.001259972,0.0055504222,0.022567198,0.022714434,0.0040632198,0.004727135,0.005133824],"category_scores_gemma":[0.07802901,0.00095843605,0.0012093126,0.0072649545,0.011306615,0.012148498,0.014462769,0.0075284205,0.0010300276],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005693142,0.0029644445,0.008455049,0.0012873324,0.00008079622,0.0016235601,0.35272563,0.0042799343,0.001892406,0.3408367,0.024551772,0.260733],"study_design_scores_gemma":[0.00025651985,0.001841733,0.009454016,0.0048299213,0.00015394132,0.00080434687,0.5114921,0.015366748,0.004549241,0.07664236,0.37427402,0.00033502677],"about_ca_topic_score_codex":0.04071216,"about_ca_topic_score_gemma":0.05466838,"teacher_disagreement_score":0.14451192,"about_ca_system_score_codex":0.040951565,"about_ca_system_score_gemma":0.052520633,"threshold_uncertainty_score":0.76426125},"labels":[],"label_agreement":null},{"id":"W4366451084","doi":"10.3138/cjpe.0022.010","title":"International Association for the Evaluation of Educational Achievement (2006). <i>PIRLS 2006 Assessment Framework and Specifications</i> (2nd ed.). Chestnut Hill, MA: Author. 107 pages.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education Systems and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Association (psychology); Psychology; Mathematics education","score_opus":0.23734936610274737,"score_gpt":0.46370527691699165,"score_spread":0.22635591081424428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451084","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006509435,0.43949673,0.06251122,0.04669006,0.034212634,0.009504046,0.10472232,0.0058323154,0.29052126],"genre_scores_gemma":[0.08006733,0.4028807,0.17139934,0.010380556,0.005221331,0.05817837,0.1269236,0.0038205076,0.14112821],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9421628,0.019887306,0.015712561,0.0017386513,0.018776039,0.0017225161],"domain_scores_gemma":[0.82046443,0.028706115,0.01598878,0.008861728,0.12165532,0.004323588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06651934,0.0033288212,0.00499069,0.0112851905,0.0016764395,0.0053059477,0.0036703602,0.0041790935,0.019741505],"category_scores_gemma":[0.09890654,0.0023469534,0.0037417645,0.01869945,0.0020608352,0.004946073,0.005293103,0.010531441,0.021483954],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006374676,0.00031355795,0.013675204,0.004288703,0.0003954101,0.00007767722,0.0005597157,0.00047300276,0.0003512486,0.0071517457,0.55138755,0.42068878],"study_design_scores_gemma":[0.0003327,0.00029896392,0.07693864,0.015198671,0.0006745987,0.00034624836,0.00071770366,0.0004642397,0.0013349724,0.007892346,0.89562947,0.00017136842],"about_ca_topic_score_codex":0.036753222,"about_ca_topic_score_gemma":0.026979024,"teacher_disagreement_score":0.06651934,"about_ca_system_score_codex":0.008128806,"about_ca_system_score_gemma":0.02519864,"threshold_uncertainty_score":0.3517921},"labels":[],"label_agreement":null},{"id":"W4366451089","doi":"10.3138/cjpe.022.006","title":"Youth Voices: Evaluation of Participatory Action Research","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Participatory Visual Research Methods","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Participatory action research; Participatory evaluation; Citizen journalism; Reflexivity; Psychosocial; Action research; Psychology; Sociology; Action (physics); Process (computing); Applied psychology; Community-based participatory research; Public relations; Medical education; Pedagogy; Political science; Social science; Computer science; Medicine; Psychotherapist","score_opus":0.9730869743906994,"score_gpt":0.7857522584583132,"score_spread":0.18733471593238615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59986866,0.0042146053,0.160503,0.009534791,0.0012076233,0.060676925,0.0011820338,0.00075486896,0.16205758],"genre_scores_gemma":[0.8506115,0.0011461732,0.11803461,0.00069014804,0.00008001948,0.025425788,0.00027645833,0.00012394156,0.0036113888],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.54823416,0.41145602,0.010276868,0.004120916,0.022494467,0.0034175767],"domain_scores_gemma":[0.7037481,0.22981803,0.011947661,0.014851174,0.034890372,0.004744631],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2672002,0.001035076,0.0010862884,0.0026913008,0.0048025525,0.0067762053,0.0025702824,0.0020764067,0.0063575343],"category_scores_gemma":[0.25328255,0.00059616315,0.0012319038,0.0027098916,0.005189474,0.0039040537,0.009032641,0.0016768066,0.0005506985],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038718246,0.0033419738,0.013053331,0.011456881,0.0003854455,0.00075930473,0.26221853,0.0032982603,0.00321074,0.048455015,0.008784953,0.6411638],"study_design_scores_gemma":[0.006761469,0.025596261,0.0327822,0.02807043,0.001574958,0.0014372056,0.393413,0.014385857,0.03970745,0.068269715,0.38735047,0.0006509658],"about_ca_topic_score_codex":0.0045379037,"about_ca_topic_score_gemma":0.005711209,"teacher_disagreement_score":0.2672002,"about_ca_system_score_codex":0.009852321,"about_ca_system_score_gemma":0.018921629,"threshold_uncertainty_score":0.90367264},"labels":[],"label_agreement":null},{"id":"W4366451121","doi":"10.3138/cjpe.0022.001","title":"Un mot de la rédactrice invitée","year":2008,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.44765903617640895,"score_gpt":0.5226109746291024,"score_spread":0.07495193845269349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451121","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022306347,0.02164911,0.04969943,0.43138078,0.11803665,0.0019056114,0.0042000627,0.007795891,0.34302607],"genre_scores_gemma":[0.12803484,0.010185593,0.046356644,0.07334708,0.035886597,0.0037660953,0.0036474497,0.00394325,0.6948324],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93730074,0.026681839,0.0027122286,0.0038016522,0.026311023,0.0031925163],"domain_scores_gemma":[0.92504084,0.025438549,0.0034360697,0.0053039524,0.034376677,0.0064038984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0305018,0.002485371,0.0021683625,0.00391681,0.006539033,0.016236989,0.0026786854,0.010071053,0.070385955],"category_scores_gemma":[0.098147765,0.001247388,0.0029948854,0.0024895605,0.00350633,0.008203701,0.0056341216,0.017555404,0.020850467],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010617261,0.00062911765,0.0030222551,0.0012615225,0.00013818766,0.0011542516,0.0029291848,0.0011456208,0.0042442484,0.08176287,0.6278225,0.2748285],"study_design_scores_gemma":[0.00020195285,0.00017433564,0.0025565866,0.00045102683,0.000025918167,0.00085531507,0.0007136608,0.0007097789,0.0015405776,0.0031825942,0.9895018,0.000086532666],"about_ca_topic_score_codex":0.048053443,"about_ca_topic_score_gemma":0.03530494,"teacher_disagreement_score":0.070385955,"about_ca_system_score_codex":0.01301491,"about_ca_system_score_gemma":0.016398208,"threshold_uncertainty_score":0.23546451},"labels":[],"label_agreement":null},{"id":"W4366451125","doi":"10.3138/cjpe.21.005","title":"Comment favoriser la réussite d’une démarche d’implantation d’un programme au sein d’un milieu d’intervention : leçons tirées d’une étude de cas","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Context (archaeology); Process (computing); Process management; Identification (biology); Psychology; Intervention (counseling); Knowledge management; Sociology; Business; Computer science; Geography","score_opus":0.39765218906630984,"score_gpt":0.5755501354226789,"score_spread":0.17789794635636902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8863694,0.0030219324,0.017572293,0.05719566,0.0008979074,0.000854235,0.00022004356,0.00031438636,0.033554092],"genre_scores_gemma":[0.9660193,0.00169228,0.008148035,0.004049608,0.00020849721,0.0006811419,0.00014395276,0.00008190995,0.018975232],"study_design_codex":"design_other","study_design_gemma":"case_report","domain_scores_codex":[0.9847766,0.009326816,0.00053518265,0.00080816564,0.0026441908,0.0019089361],"domain_scores_gemma":[0.9843662,0.0066721784,0.001688706,0.0014219014,0.004223873,0.0016271969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01744407,0.0006861479,0.00037347004,0.00091597764,0.0058739586,0.004115738,0.0025866493,0.004385923,0.006255192],"category_scores_gemma":[0.03661134,0.000451571,0.0008521342,0.0015779359,0.0050093285,0.0032439614,0.0017542378,0.0028736386,0.0009688575],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017042116,0.0034876328,0.15795864,0.003956761,0.00030996656,0.018743357,0.27134922,0.006284787,0.012600005,0.047497645,0.03089876,0.44520897],"study_design_scores_gemma":[0.0005257443,0.0032104729,0.19328403,0.0039199768,0.00043940943,0.00894369,0.23569077,0.004995244,0.017010609,0.004546331,0.52706695,0.0003667503],"about_ca_topic_score_codex":0.37673295,"about_ca_topic_score_gemma":0.40824544,"teacher_disagreement_score":0.37673295,"about_ca_system_score_codex":0.013594863,"about_ca_system_score_gemma":0.024055837,"threshold_uncertainty_score":0.74908024},"labels":[],"label_agreement":null},{"id":"W4366451139","doi":"10.3138/cjpe.0024.008","title":"Advocacy Evaluation Theory as a Tool for Strategic Conversation: A 25-Year Review of Tobacco Control Advocacy at the Canadian Cancer Society","year":2010,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Circumstantial evidence; Conversation; Tobacco control; Control (management); Key (lock); Public relations; Political science; Policy advocacy; Sociology; Medicine; Management; Nursing; Law; Public health; Computer science; Economics","score_opus":0.3649842729698006,"score_gpt":0.551830417055927,"score_spread":0.18684614408612632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451139","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020112855,0.9941255,0.00049036526,0.0028344798,0.00019488917,0.00006762453,0.00001495441,0.000006125203,0.0020648113],"genre_scores_gemma":[0.0076949396,0.9884411,0.002478233,0.00073260936,0.00008490045,0.00013158232,0.000021775086,0.000007543914,0.00040729603],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96831405,0.0153196,0.0024686127,0.00095020456,0.012277433,0.0006701026],"domain_scores_gemma":[0.89883405,0.06674171,0.003976667,0.0011554608,0.02792174,0.0013704109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06013727,0.0015615893,0.0031539116,0.021262405,0.0032274534,0.006891155,0.0035231388,0.0025096447,0.0026225497],"category_scores_gemma":[0.07079015,0.001025526,0.0012960562,0.026376298,0.007856394,0.004752601,0.0028663012,0.003474963,0.0005336913],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057282756,0.000078847064,0.0008121797,0.05368756,0.00020536763,0.00007693146,0.0023381095,0.0005358941,0.00013037215,0.021202205,0.020348944,0.90052634],"study_design_scores_gemma":[0.00006166431,0.00015453414,0.008799219,0.23242533,0.0007096594,0.0003949812,0.0062525566,0.000887238,0.00055313995,0.012208679,0.7373717,0.0001812776],"about_ca_topic_score_codex":0.25270903,"about_ca_topic_score_gemma":0.43892172,"teacher_disagreement_score":0.25270903,"about_ca_system_score_codex":0.051245,"about_ca_system_score_gemma":0.095736384,"threshold_uncertainty_score":0.5024762},"labels":[],"label_agreement":null},{"id":"W4366451145","doi":"10.3138/cjpe.031.1.v","title":"Editor’s Remarks","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.2352312171100758,"score_gpt":0.5173110315008186,"score_spread":0.2820798143907428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451145","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014665557,0.001990157,0.00042133828,0.25656658,0.724978,0.00006143684,0.0003364325,0.0003570393,0.01514232],"genre_scores_gemma":[0.003463786,0.0030197606,0.0018021199,0.4816312,0.33446896,0.00023032313,0.00038783666,0.0004753755,0.17452064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9889233,0.001102022,0.0010371859,0.001971014,0.005709233,0.0012572447],"domain_scores_gemma":[0.96216714,0.006404685,0.0018428734,0.0024234038,0.022057986,0.0051039425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009194723,0.0016013896,0.00159921,0.0022440187,0.0042250385,0.009611264,0.0050435783,0.017848488,0.11464453],"category_scores_gemma":[0.07745363,0.00079023297,0.002661982,0.0015876996,0.002700217,0.0057691834,0.0039465106,0.018355258,0.07994871],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010772106,0.0000065671206,0.00003478084,0.00004774045,0.000002818972,0.00007470737,0.000022670756,0.000014135758,0.000036278932,0.0008944688,0.99381316,0.005041834],"study_design_scores_gemma":[0.0000078224175,0.0000068974164,0.000105552914,0.00012384632,0.0000030529668,0.00009469465,0.000048568396,0.00003066479,0.00008601014,0.00073652784,0.9987453,0.000010953676],"about_ca_topic_score_codex":0.0034606878,"about_ca_topic_score_gemma":0.0060274256,"teacher_disagreement_score":0.11464453,"about_ca_system_score_codex":0.004112032,"about_ca_system_score_gemma":0.009466333,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4366451349","doi":"10.3138/cjpe.0022.003","title":"Teachers’ and Researchers’ Uses of Assessment and Evaluation Can Bring Reading and Writing Together","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Viewpoints; Reading (process); Value (mathematics); Writing assessment; Psychology; Mathematics education; Scale (ratio); Pedagogy; Computer science; Linguistics","score_opus":0.3373658739577437,"score_gpt":0.5040456137303412,"score_spread":0.16667973977259748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451349","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33127496,0.0095318165,0.15245257,0.08934485,0.001459023,0.0015232489,0.0001697849,0.0010327938,0.41321096],"genre_scores_gemma":[0.9771022,0.00069847616,0.01627065,0.0013039202,0.0000703228,0.0005508757,0.000019060753,0.000085988664,0.0038984169],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5192054,0.38558865,0.017938303,0.008649268,0.06389242,0.004726007],"domain_scores_gemma":[0.577205,0.29135117,0.02216805,0.025844954,0.07558904,0.007841782],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20561418,0.00072669354,0.0009998108,0.0056558414,0.005565307,0.019690156,0.0019326985,0.0031314446,0.003162813],"category_scores_gemma":[0.3280233,0.0007003386,0.0006376144,0.0034859611,0.017644273,0.012849163,0.014992184,0.0052693733,0.00073698105],"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":[0.00025235818,0.00046803692,0.030509178,0.000997372,0.0001847156,0.00034142841,0.48885408,0.0007501765,0.002502023,0.12695208,0.0098946765,0.33829385],"study_design_scores_gemma":[0.00035022185,0.001150986,0.05689279,0.0049594827,0.00034127056,0.0014527289,0.54339814,0.0041411673,0.014631886,0.15039434,0.2215867,0.00070020295],"about_ca_topic_score_codex":0.007410772,"about_ca_topic_score_gemma":0.011185053,"teacher_disagreement_score":0.20561418,"about_ca_system_score_codex":0.010191127,"about_ca_system_score_gemma":0.016420744,"threshold_uncertainty_score":0.97961915},"labels":[],"label_agreement":null},{"id":"W4366451365","doi":"10.3138/cjpe.021.006","title":"Pragmatism or Transformation? Participatory Evaluation of a Humanitarian Education Project in Sierra Leone","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sierra leone; Transformative learning; Citizen journalism; Participatory evaluation; Stakeholder; Humanitarian aid; Sociology; Context (archaeology); Humanitarian intervention; Political science; Public relations; Pedagogy; Public administration; Socioeconomics; Law","score_opus":0.4904049515913237,"score_gpt":0.5642115556092092,"score_spread":0.07380660401788552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9250827,0.0010316189,0.012443949,0.006203986,0.00013153993,0.012713761,0.00010777985,0.00006218728,0.04222238],"genre_scores_gemma":[0.983968,0.0003419893,0.009348609,0.00030116248,0.000011948763,0.0042914487,0.000026682394,0.000007248971,0.0017027605],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.84584314,0.14035666,0.0023110106,0.0014641809,0.0064898506,0.0035351277],"domain_scores_gemma":[0.90233976,0.076349646,0.004298133,0.0034820985,0.01133177,0.0021985022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.120977364,0.00073760987,0.0006350194,0.0011841829,0.004331765,0.0046714884,0.0013732564,0.0016997318,0.002786132],"category_scores_gemma":[0.11298126,0.00034410722,0.0004769269,0.0010762679,0.0055607515,0.002805627,0.0057704253,0.00186215,0.00020409201],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005573667,0.010484647,0.020936057,0.0067364303,0.00043443235,0.0019976723,0.30779433,0.014220627,0.006321367,0.04644775,0.0067427102,0.5723103],"study_design_scores_gemma":[0.0077229883,0.042531025,0.059026875,0.010935584,0.0008357771,0.00071148714,0.60803074,0.015351334,0.04026481,0.05534844,0.15881014,0.0004308251],"about_ca_topic_score_codex":0.0062581394,"about_ca_topic_score_gemma":0.011955762,"teacher_disagreement_score":0.120977364,"about_ca_system_score_codex":0.008267351,"about_ca_system_score_gemma":0.016040245,"threshold_uncertainty_score":0.6397971},"labels":[],"label_agreement":null},{"id":"W4366451376","doi":"10.3138/cjpe.020.003","title":"Exploration of the Validity and Usefulness of an Integrated Performance Indicator for Postgraduate Scholarship Programs","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Scholarship; Value (mathematics); Psychology; Public relations; Medical education; Sociology; Marketing; Business; Computer science; Political science; Medicine","score_opus":0.4762830993263373,"score_gpt":0.46879250713405074,"score_spread":0.007490592192286538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451376","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99068743,0.00015436354,0.0024406328,0.00024382446,0.000025630769,0.00026045134,0.0002288833,0.00003294098,0.005925912],"genre_scores_gemma":[0.9955031,0.00008609019,0.003865731,0.000017012719,0.000009698466,0.00013467099,0.0001652584,0.00000402925,0.00021435728],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98297954,0.0041670715,0.0013696088,0.00064205035,0.010046034,0.00079570437],"domain_scores_gemma":[0.92230767,0.02864118,0.011346843,0.002778115,0.030662814,0.004263338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020000502,0.00041542487,0.0006527456,0.0050127786,0.001267123,0.0030039146,0.0013887892,0.0004838583,0.001417821],"category_scores_gemma":[0.07864253,0.00016258255,0.00062119507,0.005593024,0.001526672,0.0017376371,0.003500976,0.001039464,0.0001758599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036789937,0.00064861664,0.8517495,0.00034464052,0.00017581461,0.00005488744,0.005570412,0.0009761708,0.00086110266,0.0014699018,0.00064040005,0.13714068],"study_design_scores_gemma":[0.00004175186,0.001242414,0.9783384,0.00033125427,0.00016622519,0.000053851647,0.0074758697,0.009081783,0.0012732932,0.00049548404,0.0014591531,0.000040496787],"about_ca_topic_score_codex":0.06822833,"about_ca_topic_score_gemma":0.07169118,"teacher_disagreement_score":0.06822833,"about_ca_system_score_codex":0.006559599,"about_ca_system_score_gemma":0.0135322325,"threshold_uncertainty_score":0.13566238},"labels":[],"label_agreement":null},{"id":"W4366451556","doi":"10.3138/cjpe.020.004","title":"The Changing Role of the Evaluator in the Process of Organizational Learning","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Facilitator; Organizational learning; Knowledge management; Process (computing); Context (archaeology); Organization development; Participatory evaluation; Psychology; Computer science; Process management; Social psychology; Business; Sociology","score_opus":0.12489349374341881,"score_gpt":0.4789306428987973,"score_spread":0.3540371491553785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451556","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3470622,0.0071193883,0.2766681,0.1361324,0.0022507585,0.0006625323,0.000056306402,0.0006610015,0.22938722],"genre_scores_gemma":[0.9578455,0.0009139758,0.027850948,0.0035618728,0.0003130036,0.00016542697,0.000015581883,0.00014781339,0.009185871],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8811838,0.09828088,0.0026452392,0.0042009605,0.010109996,0.0035791488],"domain_scores_gemma":[0.89713013,0.064392574,0.007101493,0.006331218,0.018532798,0.0065118694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07541827,0.00048286904,0.0005533395,0.002142358,0.008917939,0.019565254,0.001711762,0.0047347937,0.004592645],"category_scores_gemma":[0.07684847,0.00057550817,0.0004848091,0.0012551675,0.023365667,0.01357185,0.010187322,0.006333481,0.0011181996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039091057,0.00056638283,0.026698219,0.0007326401,0.00007254583,0.0020285444,0.29119337,0.0019771021,0.0069315177,0.48691785,0.010236285,0.17225467],"study_design_scores_gemma":[0.00017494043,0.0009895551,0.020057451,0.0030464723,0.00013392237,0.0019346254,0.22436291,0.012267506,0.013096499,0.31799272,0.40550414,0.00043928626],"about_ca_topic_score_codex":0.0018456515,"about_ca_topic_score_gemma":0.0017579978,"teacher_disagreement_score":0.07541827,"about_ca_system_score_codex":0.0062346905,"about_ca_system_score_gemma":0.011263603,"threshold_uncertainty_score":0.39885473},"labels":[],"label_agreement":null},{"id":"W4366451565","doi":"10.3138/cjpe.023.011","title":"Evaluating Inter-, Multi-, and Transdisciplinary Research in the European Research Area","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Innovation Policy and R&D","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Knowledge production; European Research Area; Production (economics); Transdisciplinarity; Political science; Knowledge management; Engineering ethics; Sociology; Computer science; Social science; Engineering","score_opus":0.8465502461807435,"score_gpt":0.5431084941054731,"score_spread":0.30344175207527035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5749149,0.05264218,0.11926978,0.026985819,0.001137869,0.0025803589,0.0005850079,0.00021019301,0.22167397],"genre_scores_gemma":[0.9598786,0.003486262,0.033284184,0.0010402775,0.0001394302,0.0007937954,0.00016262237,0.00004446175,0.0011702906],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.39187038,0.54524326,0.018830903,0.005968746,0.03445997,0.003626717],"domain_scores_gemma":[0.47423396,0.3255711,0.040139172,0.022932922,0.12627111,0.010851648],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4095018,0.0008635412,0.0021694677,0.009699651,0.0035226636,0.021357497,0.0018955276,0.0031890948,0.0026670953],"category_scores_gemma":[0.2755892,0.0003663541,0.0010273937,0.013394444,0.007832609,0.009829846,0.0145514,0.0019357079,0.0003770129],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025443204,0.0014925448,0.09035297,0.004466433,0.0023771706,0.00038585707,0.012620263,0.027200004,0.0013108616,0.3268332,0.0064436067,0.5239728],"study_design_scores_gemma":[0.0015057472,0.007929857,0.18884827,0.02737993,0.0040917927,0.00095280807,0.06704139,0.06648409,0.017274015,0.4258498,0.19192526,0.0007170568],"about_ca_topic_score_codex":0.0045869434,"about_ca_topic_score_gemma":0.004851315,"teacher_disagreement_score":0.5904982,"about_ca_system_score_codex":0.018237937,"about_ca_system_score_gemma":0.02314832,"threshold_uncertainty_score":0.72818947},"labels":[],"label_agreement":null},{"id":"W4366451792","doi":"10.3138/cjpe.23.002","title":"Introduction de la Rédactrice Invitée","year":2008,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Healthcare Systems and Practices","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Political science","score_opus":0.3018887392819874,"score_gpt":0.5387609142151596,"score_spread":0.2368721749331722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451792","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01395764,0.025637483,0.10010316,0.46461535,0.13761902,0.0016220548,0.0037273902,0.008431028,0.24428676],"genre_scores_gemma":[0.07649723,0.009279981,0.08725112,0.10713769,0.04196966,0.0033058305,0.003701643,0.003463924,0.6673929],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.974969,0.010231817,0.0015636917,0.002311026,0.009406062,0.001518306],"domain_scores_gemma":[0.9617505,0.013614723,0.0013487505,0.0029461277,0.017262189,0.0030777215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028181547,0.0012060525,0.0011034412,0.0022375432,0.0022542996,0.009465492,0.0020274858,0.006471364,0.037956],"category_scores_gemma":[0.044723265,0.00080094754,0.0019539255,0.0010258914,0.0027884594,0.00362768,0.0040504425,0.0108036455,0.015822966],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037366792,0.0002985244,0.0014782243,0.0009763425,0.000058671034,0.0005450209,0.0015008695,0.0009860493,0.003192838,0.07226377,0.6552623,0.2630638],"study_design_scores_gemma":[0.000040017803,0.000050551214,0.0009251378,0.00027510745,0.000007056586,0.00024372542,0.000095479656,0.0002704595,0.00046519513,0.001640104,0.9959649,0.00002223803],"about_ca_topic_score_codex":0.015548945,"about_ca_topic_score_gemma":0.012554239,"teacher_disagreement_score":0.037956,"about_ca_system_score_codex":0.0056194765,"about_ca_system_score_gemma":0.009716838,"threshold_uncertainty_score":0.1490401},"labels":[],"label_agreement":null},{"id":"W4366451836","doi":"10.3138/cjpe.0021.010","title":"Former des intervenants pour intervenir en faveur du renforcement du pouvoir d’agir","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"HIV/AIDS Impact and Responses","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Coaching; Empowerment; Sociology; Perspective (graphical); Humanities; Political science; Management; Philosophy","score_opus":0.10545773680875346,"score_gpt":0.3357885445792216,"score_spread":0.2303308077704681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57893723,0.014643081,0.034331612,0.20778696,0.005155483,0.0021790054,0.0002323768,0.00038111556,0.15635304],"genre_scores_gemma":[0.94288474,0.003684692,0.011225354,0.0074691204,0.00037192059,0.0008650394,0.000082978826,0.000050967406,0.03336527],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98521715,0.00946009,0.00042673567,0.000942809,0.0015242082,0.0024289626],"domain_scores_gemma":[0.97757554,0.007925803,0.0018076429,0.00071227737,0.00363447,0.008344204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01898157,0.00055024645,0.0004609454,0.0010273893,0.008148406,0.004868995,0.0015203789,0.0039657117,0.022746645],"category_scores_gemma":[0.03313165,0.00047427817,0.0005290809,0.00050994114,0.0030406164,0.0031351917,0.004747862,0.00611725,0.0021629455],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010735034,0.0035690642,0.04966047,0.001629959,0.000114327086,0.0047097076,0.2235929,0.001153946,0.004827938,0.06512065,0.050321076,0.5942264],"study_design_scores_gemma":[0.0004162624,0.0025656903,0.049546108,0.005430636,0.00020303385,0.003198307,0.27799854,0.0025945588,0.006078603,0.017600557,0.6341645,0.00020327252],"about_ca_topic_score_codex":0.008717349,"about_ca_topic_score_gemma":0.019956123,"teacher_disagreement_score":0.022746645,"about_ca_system_score_codex":0.0041667605,"about_ca_system_score_gemma":0.017260492,"threshold_uncertainty_score":0.10038537},"labels":[],"label_agreement":null},{"id":"W4366452033","doi":"10.3138/cjpe.0027.009","title":"Lessons Learned and the Contributions of the Paris Declaration Evaluation to Evaluation Theory and Practice","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; General partnership; Stakeholder; Declaration of independence; Political science; Management; Public relations; Engineering ethics; Sociology; Law; Engineering; Economics","score_opus":0.4365949081454484,"score_gpt":0.5688416158670923,"score_spread":0.13224670772164387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452033","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011788729,0.020346973,0.062393542,0.8289315,0.004634685,0.00042201098,0.00005795704,0.00029210275,0.0711324],"genre_scores_gemma":[0.8231661,0.015000363,0.08143722,0.06560046,0.002043735,0.0017617283,0.00011062381,0.00038856713,0.010491167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.43095413,0.5047524,0.011640584,0.007303404,0.036511783,0.008837685],"domain_scores_gemma":[0.44913292,0.4361589,0.009103415,0.022158526,0.07054829,0.012897945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4280559,0.0012813788,0.0013164174,0.006330268,0.0125543745,0.034654535,0.0076265237,0.009635604,0.0036356726],"category_scores_gemma":[0.41988832,0.0015696865,0.0015297141,0.0048792087,0.05936373,0.025450679,0.018163892,0.02571559,0.00080618163],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014979587,0.00020226947,0.0031520536,0.0015438936,0.00010713568,0.0004665994,0.06347961,0.003993361,0.0001206817,0.63715065,0.07454047,0.21509351],"study_design_scores_gemma":[0.00016270937,0.00031410885,0.0037894365,0.016252078,0.000075091,0.00044725585,0.09623911,0.0053036716,0.001141124,0.4200722,0.45574507,0.00045810788],"about_ca_topic_score_codex":0.032056455,"about_ca_topic_score_gemma":0.030336373,"teacher_disagreement_score":0.4280559,"about_ca_system_score_codex":0.07631671,"about_ca_system_score_gemma":0.095456794,"threshold_uncertainty_score":0.7053089},"labels":[],"label_agreement":null},{"id":"W4366452150","doi":"10.3138/cjpe.0021.001","title":"Special Edition / Edition Speciale Crossing Borders / Crossing Boundaries Editors’ Remarks","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.1617430004729702,"score_gpt":0.49414516120917895,"score_spread":0.33240216073620876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452150","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007217729,0.0033544519,0.00019518317,0.10078361,0.87620443,0.000039872786,0.000109457025,0.00014772324,0.019093052],"genre_scores_gemma":[0.0014184486,0.005978342,0.0006350871,0.1247442,0.73935133,0.00015721255,0.00025578417,0.00021432144,0.12724525],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99311125,0.0007503144,0.0009524151,0.0009651618,0.0033981032,0.0008228106],"domain_scores_gemma":[0.9730988,0.0052637206,0.001172164,0.0015324175,0.016414825,0.0025180068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009173739,0.0021018593,0.0019566612,0.0027724325,0.0032937198,0.011748099,0.003831797,0.015502076,0.056372453],"category_scores_gemma":[0.032176144,0.0010556133,0.001984656,0.002183694,0.00274901,0.009026061,0.0029325904,0.013834499,0.05805431],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000832822,0.000006858275,0.000021421985,0.000045320987,9.852835e-7,0.000030375435,0.000008891906,0.0000081854305,0.000027968435,0.00051102485,0.9957008,0.0036299278],"study_design_scores_gemma":[0.000010561478,0.000011048781,0.00021567235,0.00013772945,0.000003396839,0.000075494856,0.000040622923,0.000033592132,0.000045891233,0.0008783628,0.99853766,0.000009922556],"about_ca_topic_score_codex":0.0033512693,"about_ca_topic_score_gemma":0.005384062,"teacher_disagreement_score":0.056372453,"about_ca_system_score_codex":0.0030551055,"about_ca_system_score_gemma":0.0043888055,"threshold_uncertainty_score":0.18858463},"labels":[],"label_agreement":null},{"id":"W4366452167","doi":"10.3138/cjpe.23.014","title":"Carl F. Brun. (2005). <i>A Practical Guide to Social Service Evaluation.</i> Chicago: Lyceum Books. 204 pages, plus preface, appendices, glossary, references, and index.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Glossary; Index (typography); Library science; Gerontology; Medicine; Computer science; Philosophy; World Wide Web; Linguistics","score_opus":0.36228510341394915,"score_gpt":0.5103163508900976,"score_spread":0.1480312474761485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452167","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010254399,0.5285437,0.023137059,0.12048449,0.0119215995,0.0006021757,0.00631579,0.0012613006,0.3067084],"genre_scores_gemma":[0.017154677,0.47879374,0.052334886,0.018491067,0.0012720673,0.0012339498,0.0024452407,0.00061107817,0.42766333],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986426,0.0003303738,0.000116644616,0.00011432274,0.0006792475,0.00011671327],"domain_scores_gemma":[0.9953679,0.0022373348,0.0002528015,0.000115796145,0.0017145426,0.00031160304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005721432,0.0010899081,0.0008281151,0.0037133307,0.0024979596,0.0030873884,0.0012088461,0.0034022601,0.0786862],"category_scores_gemma":[0.01073735,0.0010462616,0.00037526968,0.00489553,0.0013976276,0.0056828563,0.001394393,0.003999034,0.043913774],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014967955,0.000008332716,0.00025031096,0.0003395578,0.0000019402057,0.00003229054,0.00032930818,0.000053717038,0.00006204536,0.004128353,0.77387375,0.22090541],"study_design_scores_gemma":[0.000008272156,0.000010770995,0.0010568602,0.0018016362,0.000004206835,0.00010616024,0.00055691233,0.000056603993,0.00014934101,0.00640154,0.9898225,0.000025234222],"about_ca_topic_score_codex":0.10215637,"about_ca_topic_score_gemma":0.2315739,"teacher_disagreement_score":0.10215637,"about_ca_system_score_codex":0.0064814095,"about_ca_system_score_gemma":0.013315704,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4366452169","doi":"10.3138/cjpe.20.007","title":"Preparing School Evaluators: Hiroshima Pilot Test of the Japan Evaluation Society’s Accreditation Project","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Accreditation; Certification; Certification and Accreditation; Test (biology); Context (archaeology); Medical education; Sustainability; Program evaluation; Government (linguistics); Political science; Quality (philosophy); Public relations; Psychology; Medicine; Public administration","score_opus":0.3502415788863397,"score_gpt":0.5226132347110275,"score_spread":0.17237165582468778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452169","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932225,0.000024558947,0.001230655,0.00029756725,0.00004883734,0.0024483579,0.00004708346,0.000046556717,0.0026339968],"genre_scores_gemma":[0.98420584,0.000056211775,0.0074227755,0.0003011936,0.000042300537,0.0041687964,0.00026981425,0.0000357357,0.0034973044],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97800887,0.015695248,0.0011153541,0.0010461592,0.0025099395,0.0016244573],"domain_scores_gemma":[0.931825,0.029559469,0.002648722,0.0059415502,0.024214363,0.0058109066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.056190718,0.0005695109,0.000722226,0.0010844134,0.0048046154,0.0015576791,0.0014491018,0.0013059189,0.0036145637],"category_scores_gemma":[0.050290763,0.0009786045,0.0007388417,0.0007338455,0.0016668576,0.0017425996,0.0030487406,0.002576447,0.0008968445],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012188407,0.15099198,0.28277797,0.00094425795,0.0003109568,0.0018927631,0.21605058,0.004155488,0.014389489,0.0032927305,0.017348794,0.2956566],"study_design_scores_gemma":[0.007025252,0.139349,0.6205212,0.0003457063,0.00037698637,0.00045099264,0.12399674,0.009868419,0.030326117,0.0013662939,0.065913215,0.0004601176],"about_ca_topic_score_codex":0.010424268,"about_ca_topic_score_gemma":0.023972923,"teacher_disagreement_score":0.056190718,"about_ca_system_score_codex":0.0038079731,"about_ca_system_score_gemma":0.008589119,"threshold_uncertainty_score":0.29716843},"labels":[],"label_agreement":null},{"id":"W4366452184","doi":"10.3138/cjpe.0022.002","title":"Guest Editor’s Remarks","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Jewish Identity and Society","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.0833357882124698,"score_gpt":0.3760709743046956,"score_spread":0.2927351860922258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452184","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025179354,0.001156138,0.00014512653,0.41573805,0.5789767,0.000032340475,0.000087181405,0.00009443555,0.0035182626],"genre_scores_gemma":[0.0038934024,0.0009603424,0.00042793335,0.6146893,0.33987868,0.00009502713,0.00004317082,0.000103217884,0.039908893],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98924214,0.0010727664,0.0011970735,0.002114188,0.004668461,0.001705363],"domain_scores_gemma":[0.9543203,0.011069252,0.0037691959,0.002523712,0.021927321,0.006390261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012677776,0.001515194,0.0025098515,0.0016334048,0.005159256,0.009943726,0.004556676,0.038635347,0.021253403],"category_scores_gemma":[0.096695885,0.0011780508,0.0028541037,0.0013839133,0.0028220748,0.003489549,0.003151833,0.038351208,0.013548766],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027777745,0.000006675922,0.00008576833,0.00003439898,0.000009614675,0.00020656621,0.00003997269,0.000018710627,0.000059246755,0.00047266568,0.9973623,0.0016762824],"study_design_scores_gemma":[0.00006422668,0.00002477522,0.0009278782,0.00019256369,0.000048563812,0.00028668027,0.00026451386,0.00017656604,0.00030474435,0.0010505166,0.99660563,0.00005349407],"about_ca_topic_score_codex":0.010327148,"about_ca_topic_score_gemma":0.019009218,"teacher_disagreement_score":0.038635347,"about_ca_system_score_codex":0.005969051,"about_ca_system_score_gemma":0.007668966,"threshold_uncertainty_score":0.07109976},"labels":[],"label_agreement":null},{"id":"W4366452402","doi":"10.3138/cjpe.22.005","title":"Thickening the Plot: Combining Objectives- and Methods-Oriented Approaches in the Evaluation of a Provincial Superintendents’ Qualification Program","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Commensurability (mathematics); Legislature; Evaluation methods; Program evaluation; Plot (graphics); Computer science; Management science; Political science; Public administration; Mathematics; Engineering; Statistics","score_opus":0.5865720125219641,"score_gpt":0.5866314486560237,"score_spread":0.00005943613405956505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452402","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2711659,0.0019386996,0.6333087,0.009423501,0.0003754436,0.0040093036,0.00034514305,0.0011610652,0.07827227],"genre_scores_gemma":[0.6739617,0.00036389258,0.32122567,0.00036416267,0.000024392582,0.0015893674,0.00009363671,0.00014109963,0.002235985],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.85292476,0.13052794,0.0023061107,0.0016605407,0.011487135,0.0010935222],"domain_scores_gemma":[0.86078906,0.1091401,0.0076119113,0.0065170247,0.014662663,0.0012793229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10416995,0.00086238794,0.00072557974,0.006451403,0.0025604642,0.00764063,0.001806398,0.0012714464,0.0033573348],"category_scores_gemma":[0.1423541,0.00051316275,0.00078998646,0.0048234896,0.0051116752,0.005528688,0.0064409245,0.0018820507,0.00031066322],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009953418,0.00090766087,0.02865857,0.0020121422,0.00022870694,0.0002397898,0.037821505,0.0109853735,0.0024863468,0.08241904,0.0070609706,0.8261846],"study_design_scores_gemma":[0.0025370424,0.008399565,0.12306282,0.010919689,0.0011292069,0.00064821145,0.15367143,0.17557572,0.030752225,0.33184364,0.16089544,0.00056500494],"about_ca_topic_score_codex":0.0076117604,"about_ca_topic_score_gemma":0.015882174,"teacher_disagreement_score":0.10416995,"about_ca_system_score_codex":0.009318927,"about_ca_system_score_gemma":0.011046857,"threshold_uncertainty_score":0.55090994},"labels":[],"label_agreement":null},{"id":"W4366452409","doi":"10.3138/cjpe.022.001","title":"Value-for-Money Analysis of Active Labour Market Programs","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec; Employment and Social Development Canada; University of Manitoba","funders":"","keywords":"Value for money; Value (mathematics); Time value of money; Context (archaeology); Accountability; Disadvantaged; Relevance (law); Economics; Government (linguistics); Money measurement concept; Business; Microeconomics; Actuarial science; Public economics; Endogenous money; Finance; Computer science; Monetary policy; Macroeconomics; Economic growth; Velocity of money; Political science","score_opus":0.29403001195915573,"score_gpt":0.5330757016348798,"score_spread":0.2390456896757241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84038097,0.0035797153,0.08122147,0.0022510292,0.00018934842,0.005383189,0.004523396,0.0002307408,0.062240057],"genre_scores_gemma":[0.97955143,0.00034237595,0.01587673,0.00008038825,0.00005111436,0.0013297856,0.00076247484,0.000020530983,0.0019851488],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9594744,0.028672317,0.0013123002,0.000764744,0.0083004935,0.001475762],"domain_scores_gemma":[0.8215002,0.13911209,0.01408961,0.0029077318,0.020502867,0.0018874393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031585045,0.0007343674,0.0010531227,0.0084098475,0.000717791,0.0023752055,0.0020256718,0.0007781131,0.006573684],"category_scores_gemma":[0.12238358,0.00022545482,0.0013276985,0.0075276224,0.0011384316,0.0024230625,0.0018693525,0.0013412553,0.00032283514],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005126314,0.003584716,0.13229737,0.0052235015,0.0017383425,0.00017450585,0.003968918,0.11432875,0.00087373174,0.11824745,0.008724183,0.6057121],"study_design_scores_gemma":[0.0009837023,0.0130161885,0.39229655,0.0043686093,0.0028806312,0.00019675537,0.007902815,0.42376316,0.011740456,0.10386189,0.038613148,0.0003760663],"about_ca_topic_score_codex":0.012744252,"about_ca_topic_score_gemma":0.009224384,"teacher_disagreement_score":0.031585045,"about_ca_system_score_codex":0.010153629,"about_ca_system_score_gemma":0.005722164,"threshold_uncertainty_score":0.16703969},"labels":[],"label_agreement":null},{"id":"W4366452411","doi":"10.3138/cjpe.0022.004","title":"Walking in Their Shoes: Students’ Perceptions of Large-Scale High-Stakes Testing","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education Systems and Policy","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Graduation (instrument); Test (biology); Literacy; Psychology; Perception; Scale (ratio); Mathematics education; Focus group; Medical education; Standardized test; Pedagogy; Sociology; Medicine; Engineering","score_opus":0.18729520662270566,"score_gpt":0.4436968600455949,"score_spread":0.25640165342288923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452411","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99827325,0.00003625024,0.000059011232,0.00031603055,0.000007019272,0.000018873125,0.000011651826,0.000003629893,0.0012742896],"genre_scores_gemma":[0.9994362,0.000044610413,0.000061786996,0.00009829836,0.0000028810791,0.000011705531,0.000010973114,0.0000023146035,0.00033126472],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99463683,0.0021207433,0.0003438597,0.00023155478,0.0015019575,0.0011650353],"domain_scores_gemma":[0.98130184,0.0060507837,0.0035413112,0.00044430426,0.0025159863,0.0061456976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00457848,0.00028231816,0.00038967462,0.00087160524,0.0030458318,0.0034559513,0.0009090517,0.0013513152,0.0047736363],"category_scores_gemma":[0.01782357,0.00037364953,0.00053512905,0.0006948652,0.0027493525,0.0012128726,0.0019456872,0.0016595356,0.00039256722],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032971727,0.0023418914,0.60454917,0.00022372787,0.00006478558,0.0016204228,0.35370785,0.00021071556,0.002665988,0.00054639665,0.0023393456,0.031400047],"study_design_scores_gemma":[0.00002692754,0.0009979063,0.38347808,0.00012780412,0.000034470784,0.00034307252,0.6084767,0.00048223988,0.00065423007,0.00020107924,0.005111802,0.00006569294],"about_ca_topic_score_codex":0.067835175,"about_ca_topic_score_gemma":0.09718947,"teacher_disagreement_score":0.067835175,"about_ca_system_score_codex":0.0027419783,"about_ca_system_score_gemma":0.004012646,"threshold_uncertainty_score":0.13488066},"labels":[],"label_agreement":null},{"id":"W4366452413","doi":"10.3138/cjpe.0026.003","title":"Évaluer une intervention complexe : enjeux conceptuels, méthodologiques, et opérationnels","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Healthcare Systems and Practices","field":"Health Professions","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Intervention (counseling); Psychology; Health care; Applied psychology; Sociology; Management science; Epistemology; Political science; Engineering; Philosophy; Psychiatry","score_opus":0.6950709422006884,"score_gpt":0.6322101438240929,"score_spread":0.06286079837659553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052679114,0.016049001,0.856135,0.029394906,0.0010809324,0.016467098,0.00045598662,0.0004055111,0.027332379],"genre_scores_gemma":[0.27105105,0.0035060348,0.70353377,0.0018620802,0.00024170088,0.018301785,0.00012833512,0.000116009454,0.0012592894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.54538655,0.40461946,0.014619635,0.007570454,0.026251376,0.0015525187],"domain_scores_gemma":[0.4220528,0.53310597,0.010905338,0.014355081,0.01812811,0.0014527151],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3362937,0.0024265088,0.0030344822,0.0075352457,0.0041661947,0.019288724,0.0038283933,0.0047470103,0.006716045],"category_scores_gemma":[0.33226043,0.0014694856,0.0028593375,0.00605588,0.024697172,0.01806408,0.0062302044,0.0067284177,0.0004465156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010368231,0.0010874729,0.0072902646,0.018073436,0.00096033054,0.00020556379,0.029110203,0.008547309,0.001445294,0.6946198,0.004040217,0.23358321],"study_design_scores_gemma":[0.002283092,0.0025730447,0.0076497886,0.052160975,0.0016801471,0.0007229276,0.03178177,0.06112585,0.008978453,0.73746014,0.09310203,0.0004818736],"about_ca_topic_score_codex":0.004708855,"about_ca_topic_score_gemma":0.0049398555,"teacher_disagreement_score":0.3362937,"about_ca_system_score_codex":0.018214097,"about_ca_system_score_gemma":0.02888837,"threshold_uncertainty_score":0.81846803},"labels":[],"label_agreement":null},{"id":"W4366452424","doi":"10.3138/cjpe.28.010","title":"King, J. A., &amp; Stevahn, L. (2013). <i>Interactive Evaluation Practice: Mastering the Interpersonal Dynamics of Program Evaluation.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpersonal communication; Dynamics (music); Psychology; Interpersonal relationship; Sociology; Applied psychology; Social psychology; Pedagogy","score_opus":0.3003669884072015,"score_gpt":0.5346756791914403,"score_spread":0.23430869078423883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452424","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026889527,0.52610254,0.013161722,0.27449474,0.024367863,0.000473443,0.0010286239,0.00058737467,0.15709484],"genre_scores_gemma":[0.096184626,0.7045427,0.03012639,0.037758186,0.0081788255,0.0007506378,0.0011426752,0.0007217591,0.12059419],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937443,0.0025896234,0.0006442674,0.00022467315,0.002627516,0.00016951053],"domain_scores_gemma":[0.9288735,0.031017017,0.003544238,0.0015303415,0.032568995,0.0024659473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018662946,0.0004753878,0.0004731953,0.0041131293,0.0019411601,0.0046272334,0.001738108,0.001859186,0.016132742],"category_scores_gemma":[0.07393756,0.00037250787,0.00037832724,0.0038941493,0.0032966656,0.0029897715,0.0019223884,0.003323115,0.009165023],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004184248,0.00001691426,0.00096698524,0.0017985186,0.000018334988,0.00006387102,0.0017915812,0.00008036702,0.00023465158,0.002692835,0.70600146,0.28629264],"study_design_scores_gemma":[0.000013415685,0.000030346902,0.005739252,0.0065439693,0.0000447178,0.00023287657,0.0016913292,0.000094690615,0.0004413649,0.002828064,0.9823101,0.000029947676],"about_ca_topic_score_codex":0.03597296,"about_ca_topic_score_gemma":0.10424514,"teacher_disagreement_score":0.03597296,"about_ca_system_score_codex":0.0036324125,"about_ca_system_score_gemma":0.011156584,"threshold_uncertainty_score":0.098700285},"labels":[],"label_agreement":null},{"id":"W4366452428","doi":"10.3138/cjpe.22.003","title":"Increasing Research Skills in Rural Health Boards: An Evaluation of a Training Program from Western Newfoundland","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Sciences Research and Education","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Medical education; Training (meteorology); Terminology; Psychology; Program evaluation; Continuing education; Rural area; Rural health; Medicine; Political science; Geography","score_opus":0.5943953754627833,"score_gpt":0.6497873529761754,"score_spread":0.05539197751339209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919993,0.00032348,0.00046814702,0.0009088432,0.000063986,0.0033758283,0.00009867323,0.00007569436,0.0026860167],"genre_scores_gemma":[0.977404,0.0010430036,0.009049431,0.0014448971,0.000107967346,0.0057639973,0.00041281266,0.000026167547,0.0047477055],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959455,0.002175827,0.00017289916,0.00031865845,0.00039647735,0.0009907346],"domain_scores_gemma":[0.98239535,0.0041712075,0.0012120524,0.0007252946,0.002585829,0.008910217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012442843,0.0004039788,0.00033685548,0.00065597444,0.0026284994,0.0008938378,0.0013349367,0.0008261616,0.0033275224],"category_scores_gemma":[0.0081716925,0.0004677316,0.0003327232,0.0005051452,0.000831007,0.0005554331,0.0022569087,0.001083288,0.00048358622],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01384642,0.19812204,0.09249522,0.003916465,0.00030736803,0.0021484664,0.04079197,0.0024683997,0.024443343,0.00034902777,0.012535552,0.60857576],"study_design_scores_gemma":[0.012925325,0.17334253,0.7233275,0.0015287873,0.0004368942,0.00050867134,0.029751988,0.0018249579,0.008137321,0.000208314,0.047868457,0.00013927935],"about_ca_topic_score_codex":0.053690262,"about_ca_topic_score_gemma":0.19362235,"teacher_disagreement_score":0.053690262,"about_ca_system_score_codex":0.0053298743,"about_ca_system_score_gemma":0.018553205,"threshold_uncertainty_score":0.106755495},"labels":[],"label_agreement":null},{"id":"W4366452616","doi":"10.3138/cjpe.0028.002","title":"Un mot du rédacteur","year":2014,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.13848030031327,"score_gpt":0.4555496659907949,"score_spread":0.31706936567752486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452616","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003125359,0.012918843,0.0030628904,0.6161959,0.23409311,0.00021566488,0.0017451639,0.00070411945,0.12793885],"genre_scores_gemma":[0.050665643,0.014964425,0.0114254765,0.22433342,0.07099107,0.0005770454,0.0026050075,0.0011271611,0.62331074],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96510625,0.00946017,0.0027835043,0.0025149754,0.017151576,0.002983527],"domain_scores_gemma":[0.8310352,0.029786602,0.0060246442,0.009972007,0.10707033,0.016111145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026046833,0.0011406428,0.0012421352,0.0033308342,0.0057148333,0.010459813,0.0029551086,0.0076513356,0.099781446],"category_scores_gemma":[0.13550444,0.0007054328,0.0014153733,0.0028686845,0.0032982046,0.008183566,0.004689083,0.010541105,0.027586231],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011198353,0.000050258255,0.0015363378,0.00044378272,0.0000216256,0.0002898027,0.0005338631,0.0000865538,0.00029683168,0.016402764,0.87448996,0.105736256],"study_design_scores_gemma":[0.00003220053,0.000033719007,0.0015419234,0.0005377955,0.000017067925,0.00048401917,0.00056309986,0.00010104223,0.00031539839,0.002455085,0.99389064,0.000027919827],"about_ca_topic_score_codex":0.07042767,"about_ca_topic_score_gemma":0.07911267,"teacher_disagreement_score":0.099781446,"about_ca_system_score_codex":0.012715403,"about_ca_system_score_gemma":0.042309787,"threshold_uncertainty_score":0.33380222},"labels":[],"label_agreement":null},{"id":"W4366452622","doi":"10.3138/cjpe.0026.005","title":"L’approche <i>Realist</i> à l’épreuve du réel de l’évaluation des programmes","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"","keywords":"Epistemology; Context (archaeology); Valuation (finance); Psychological intervention; Outcome (game theory); Sociology; Psychology; GRASP; Mechanism (biology); Philosophy; Computer science; Economics; History","score_opus":0.4946108818232891,"score_gpt":0.5147343735641988,"score_spread":0.020123491740909716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452622","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017000688,0.018396404,0.5717394,0.29496694,0.0033444266,0.00201972,0.00033406125,0.0007630296,0.09143543],"genre_scores_gemma":[0.4868591,0.0053361175,0.4684272,0.02566255,0.0018357728,0.0039970893,0.0001925537,0.00029088362,0.0073986757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4982219,0.4232413,0.012989632,0.00967039,0.05312068,0.0027561353],"domain_scores_gemma":[0.5944596,0.30889222,0.0146278525,0.036824286,0.042908233,0.002287871],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3288297,0.001969506,0.0029623231,0.0068509667,0.004127048,0.027467743,0.009255858,0.011912221,0.009080827],"category_scores_gemma":[0.24822062,0.0012981923,0.0038032744,0.003934316,0.03007935,0.019661814,0.010867684,0.016007239,0.0018753598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028867702,0.0003729081,0.001355286,0.0046321037,0.00045141077,0.00016604163,0.008559674,0.006529707,0.0006950184,0.87583965,0.01015514,0.0909544],"study_design_scores_gemma":[0.00068141724,0.00078755146,0.0023442793,0.01162401,0.000343409,0.00048616165,0.0063116755,0.019293174,0.0037495948,0.7206769,0.23343806,0.00026377983],"about_ca_topic_score_codex":0.006955909,"about_ca_topic_score_gemma":0.008750296,"teacher_disagreement_score":0.3288297,"about_ca_system_score_codex":0.02224774,"about_ca_system_score_gemma":0.02126961,"threshold_uncertainty_score":0.8276725},"labels":[],"label_agreement":null},{"id":"W4366452662","doi":"10.3138/cjpe.22.006","title":"Developing a Special Education Accountability Framework Using Program Evaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Bureaucracy; Context (archaeology); Citizen journalism; Public administration; Public relations; Political science; Business; Politics; Geography","score_opus":0.5571351357964983,"score_gpt":0.6246417530511743,"score_spread":0.067506617254676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011693836,0.0013491136,0.9252312,0.011684489,0.0002262129,0.0029672023,0.0003115727,0.0005278,0.0460085],"genre_scores_gemma":[0.33505094,0.0005438331,0.6583263,0.00066348666,0.00007971766,0.0032373047,0.00030715042,0.000045859102,0.0017454351],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80779636,0.1622148,0.00736896,0.0037614084,0.015212749,0.003645776],"domain_scores_gemma":[0.81172043,0.11650855,0.011371481,0.0065432987,0.049444005,0.0044122557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1646614,0.0015739055,0.0018723363,0.012821154,0.0043899,0.010492878,0.003945225,0.0033733535,0.0038466384],"category_scores_gemma":[0.09562767,0.00082688575,0.0018278656,0.007141176,0.011188741,0.009076683,0.007671768,0.0042404495,0.00040455954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066753324,0.00042193165,0.0061324043,0.0010934096,0.00015485617,0.0001916052,0.0022968417,0.042487588,0.00029903415,0.860638,0.005694437,0.08052304],"study_design_scores_gemma":[0.00023745121,0.0006209163,0.0039681327,0.004533578,0.00029798737,0.000247379,0.005928094,0.17799343,0.0029449959,0.7261481,0.07689296,0.0001868353],"about_ca_topic_score_codex":0.02023976,"about_ca_topic_score_gemma":0.01823334,"teacher_disagreement_score":0.1646614,"about_ca_system_score_codex":0.022707554,"about_ca_system_score_gemma":0.04416173,"threshold_uncertainty_score":0.8708231},"labels":[],"label_agreement":null},{"id":"W4366452874","doi":"10.3138/cjpe.0021.013","title":"Porter et gérer une action transformatrice : quelques outils de discernement pour quand on est dans ça avec d’autres","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Discernment; Transformative learning; Theme (computing); Action (physics); Set (abstract data type); Function (biology); Psychology; Sociology; Humanities; Social psychology; Epistemology; Philosophy; Computer science; Pedagogy","score_opus":0.13216074010859913,"score_gpt":0.4386739707949799,"score_spread":0.30651323068638076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452874","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31699738,0.0051469067,0.124087125,0.22226934,0.0017753686,0.0010000635,0.00021316647,0.00041939397,0.32809123],"genre_scores_gemma":[0.9469975,0.0009428696,0.024014387,0.003821238,0.00007707673,0.0004181613,0.000045090623,0.00010443251,0.023579318],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9313739,0.057636082,0.0007960196,0.0017087231,0.006196694,0.0022885292],"domain_scores_gemma":[0.9701928,0.01698488,0.0019175321,0.0026490146,0.005697491,0.0025582802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04227072,0.00081760355,0.0005134686,0.0013509844,0.012714541,0.014155707,0.0017862202,0.003493614,0.005634541],"category_scores_gemma":[0.046452604,0.00042274702,0.0005850086,0.0014840771,0.031029591,0.012613303,0.0055849683,0.0069233836,0.00071358046],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012445284,0.00025967901,0.0033991716,0.00027251316,0.000024571978,0.00045265915,0.60518456,0.0004326706,0.001209131,0.28214446,0.016032627,0.09046353],"study_design_scores_gemma":[0.000067959925,0.00020871664,0.0048720986,0.001172996,0.00003466981,0.00031536818,0.61686563,0.001787756,0.0030388026,0.053116135,0.31841207,0.000107816304],"about_ca_topic_score_codex":0.09692457,"about_ca_topic_score_gemma":0.15457436,"teacher_disagreement_score":0.09692457,"about_ca_system_score_codex":0.019587493,"about_ca_system_score_gemma":0.040387258,"threshold_uncertainty_score":0.22355163},"labels":[],"label_agreement":null},{"id":"W4366452898","doi":"10.3138/cjpe.0021.008","title":"Introduction du Rédacteur Invité","year":2007,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science","score_opus":0.08504421294021272,"score_gpt":0.34078710051007,"score_spread":0.2557428875698573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452898","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011769273,0.011649042,0.041870557,0.23824254,0.120477505,0.0010987162,0.0041500386,0.007066138,0.5636761],"genre_scores_gemma":[0.04089716,0.002943001,0.016053643,0.027158214,0.011496646,0.0006914671,0.0022355288,0.0021508276,0.89637357],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9881754,0.003139263,0.000583642,0.0015354096,0.005513173,0.001053103],"domain_scores_gemma":[0.9730891,0.005632658,0.000679624,0.0018114527,0.016264647,0.0025224509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014432821,0.0008464468,0.0007628469,0.0020990307,0.003017506,0.008868642,0.0021623394,0.0045181513,0.089090854],"category_scores_gemma":[0.02669642,0.0006055823,0.0010554016,0.0010232364,0.0017101112,0.00410557,0.0038197103,0.006304911,0.025188902],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002453527,0.00012912962,0.00095465354,0.00042704906,0.000015039998,0.0002685451,0.0010077882,0.0003316227,0.001828875,0.05060274,0.7972369,0.14695239],"study_design_scores_gemma":[0.000016195978,0.000028262131,0.00062115176,0.00014189053,0.0000040698924,0.000074835116,0.00015022201,0.0001442739,0.00047285706,0.0015521059,0.9967817,0.000012535266],"about_ca_topic_score_codex":0.025491463,"about_ca_topic_score_gemma":0.028661555,"teacher_disagreement_score":0.089090854,"about_ca_system_score_codex":0.0065067876,"about_ca_system_score_gemma":0.010699883,"threshold_uncertainty_score":0.2980386},"labels":[],"label_agreement":null},{"id":"W4366453107","doi":"10.3138/cjpe.023.004","title":"L’utilisation de l’évaluation fondée sur la théorie du programme comme stratégie d’application des connaissances issues de la recherche","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Centre intégré universitaire de santé et de services sociaux de la Mauricie-et-du-Centre-du-Québec; Université du Québec à Trois-Rivières; Université du Québec à Montréal","funders":"","keywords":"Knowledge management; Tacit knowledge; Valuation (finance); Sociology; Psychology; Business; Computer science","score_opus":0.8056653558025793,"score_gpt":0.5756305185019046,"score_spread":0.23003483730067464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03583585,0.009016717,0.6721793,0.04696322,0.0011138306,0.00088649034,0.00018957071,0.00040172366,0.23341334],"genre_scores_gemma":[0.7357295,0.005341709,0.24178416,0.0018597931,0.00033860691,0.0016378047,0.00012552843,0.00018148727,0.013001352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85362154,0.11062159,0.0046250774,0.0045945235,0.024367874,0.0021693786],"domain_scores_gemma":[0.7772335,0.17878322,0.006564211,0.013041899,0.022769567,0.0016076284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.092643395,0.002047318,0.0015129651,0.008133075,0.0034067368,0.023152187,0.002875239,0.004855869,0.009172873],"category_scores_gemma":[0.12805757,0.0010638924,0.002397269,0.006043198,0.025553873,0.018493952,0.0054532457,0.004645412,0.0016976447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007047567,0.00011194594,0.0020432456,0.0008685955,0.00007526863,0.00012033182,0.0046229893,0.00638863,0.00043397132,0.92337763,0.0019178807,0.059968993],"study_design_scores_gemma":[0.00015374151,0.000488724,0.004060528,0.0031553968,0.0002177909,0.00059713,0.0081065325,0.05884143,0.00589173,0.7828751,0.13542515,0.0001867906],"about_ca_topic_score_codex":0.017772697,"about_ca_topic_score_gemma":0.010550375,"teacher_disagreement_score":0.092643395,"about_ca_system_score_codex":0.020701848,"about_ca_system_score_gemma":0.0211975,"threshold_uncertainty_score":0.48995095},"labels":[],"label_agreement":null},{"id":"W4366453124","doi":"10.3138/cjpe.020.006","title":"Participatory Evaluation in the Context of CBPD: Theory and Practice in International Development","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Citizen journalism; Context (archaeology); International development; Political science; Democracy; Participatory development; Participatory evaluation; Sociology; International community; Engineering ethics; Public administration; Politics; Engineering; Law; Geography","score_opus":0.4738059708487722,"score_gpt":0.5804406649322703,"score_spread":0.10663469408349813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050726395,0.045094904,0.47321656,0.08819317,0.0017760178,0.005913796,0.000104235434,0.00032617358,0.33464873],"genre_scores_gemma":[0.84812254,0.012399233,0.12672842,0.0027702479,0.000261002,0.0046778754,0.000041795578,0.00009054661,0.0049082115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6934641,0.27975798,0.0043153367,0.0041404497,0.015377793,0.0029443745],"domain_scores_gemma":[0.73566157,0.23040223,0.0055596502,0.0098323785,0.014830669,0.00371357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1842238,0.0010992488,0.0020001887,0.0074119153,0.011766759,0.018235307,0.0035786154,0.0049903253,0.0046031093],"category_scores_gemma":[0.13445424,0.00072581315,0.00078691426,0.009274482,0.05269681,0.012091371,0.017273065,0.0056035337,0.00043335135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012118088,0.00051445054,0.0034574084,0.0042389138,0.00008485945,0.0004860458,0.090504795,0.0043852516,0.0003190163,0.6117073,0.005393375,0.27878743],"study_design_scores_gemma":[0.00019408442,0.00046693828,0.0028513372,0.015173351,0.00007616817,0.0005050507,0.11700287,0.0067704595,0.0012690768,0.6927023,0.16286007,0.00012832858],"about_ca_topic_score_codex":0.0110686375,"about_ca_topic_score_gemma":0.010381096,"teacher_disagreement_score":0.1842238,"about_ca_system_score_codex":0.024115924,"about_ca_system_score_gemma":0.049104907,"threshold_uncertainty_score":0.97428024},"labels":[],"label_agreement":null},{"id":"W4366453126","doi":"10.3138/cjpe.23.016","title":"Donna M. Mertens. (2009). <i>Transformative Research and Evaluation.</i> New York: Guilford Press. 402 pages.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transformative learning; Psychology; Pedagogy","score_opus":0.7747036186145636,"score_gpt":0.5580962906247038,"score_spread":0.21660732798985982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453126","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056648266,0.7196775,0.014689191,0.1325517,0.011223479,0.00014795832,0.0031062118,0.0013925941,0.11664488],"genre_scores_gemma":[0.01999297,0.7228971,0.029957525,0.018311262,0.0038336865,0.00059906923,0.0020650795,0.0013069522,0.20103627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972277,0.0007399407,0.00035503384,0.00021794894,0.0013535578,0.00010577142],"domain_scores_gemma":[0.97927195,0.010468837,0.0011166444,0.00074186723,0.00745853,0.0009422429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007688899,0.0017185705,0.0010246212,0.0047493814,0.0029489442,0.004490746,0.0021912165,0.0050714645,0.07290011],"category_scores_gemma":[0.026444947,0.0017291445,0.00064090156,0.0047429143,0.0023380516,0.009390293,0.0020140978,0.0053066146,0.04277909],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028560617,0.00001322701,0.00021255368,0.0007501645,0.000008816745,0.000043997334,0.0005277631,0.00008181243,0.00012162311,0.0048347847,0.83975244,0.15362439],"study_design_scores_gemma":[0.000023693785,0.000018375258,0.0026411766,0.0044889636,0.000040007468,0.00020327856,0.0007248255,0.00013252159,0.00044696423,0.012609954,0.97862476,0.000045513912],"about_ca_topic_score_codex":0.064036146,"about_ca_topic_score_gemma":0.16368827,"teacher_disagreement_score":0.07290011,"about_ca_system_score_codex":0.0045015435,"about_ca_system_score_gemma":0.008925153,"threshold_uncertainty_score":0.2438752},"labels":[],"label_agreement":null},{"id":"W4366453138","doi":"10.3138/cjpe.28.007","title":"The Five Cs for Innovating in Evaluation Capacity Building: Lessons from the Field","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Excellence; Coaching; Curiosity; Capacity building; Courage; Key (lock); Field (mathematics); Public relations; Business; Psychology; Knowledge management; Political science; Economic growth; Management; Economics; Computer science; Social psychology","score_opus":0.5626414314017943,"score_gpt":0.558423062289945,"score_spread":0.004218369111849363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453138","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052314546,0.022607671,0.14163987,0.6089982,0.0015305895,0.0014011873,0.00010878515,0.0004306323,0.17096852],"genre_scores_gemma":[0.8113225,0.011205622,0.15883754,0.012823965,0.00041796188,0.0011776083,0.000060427228,0.00012327025,0.004031157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.95056665,0.037324384,0.0016869798,0.0015197826,0.005090894,0.0038113692],"domain_scores_gemma":[0.8370237,0.113426134,0.004137492,0.0070327595,0.015889606,0.022490257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08879726,0.0010436017,0.001010843,0.0045539844,0.009648121,0.0193727,0.003705436,0.006203955,0.006872322],"category_scores_gemma":[0.07113439,0.00080930575,0.00135096,0.003039375,0.038599744,0.01331576,0.014751612,0.010787121,0.0007809529],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015204068,0.000665737,0.0062577883,0.0015573851,0.00007611114,0.0002970359,0.0141477315,0.0034014555,0.00029753364,0.7102151,0.018145218,0.24478693],"study_design_scores_gemma":[0.00021529694,0.0003007617,0.008085953,0.0053686006,0.00007235869,0.00027037814,0.029840104,0.009585979,0.0012502027,0.82658786,0.11821719,0.00020531772],"about_ca_topic_score_codex":0.02356003,"about_ca_topic_score_gemma":0.038032047,"teacher_disagreement_score":0.08879726,"about_ca_system_score_codex":0.029231288,"about_ca_system_score_gemma":0.10883571,"threshold_uncertainty_score":0.4696104},"labels":[],"label_agreement":null},{"id":"W4366453259","doi":"10.3138/cjpe.24.003","title":"La fidélité de l’implantation d’un programme d’intervention pour des adolescentes agressées sexuellement : une mesure par observation systématique","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Fidelity; Intervention (counseling); Psychology; Sexual behavior; Protocol (science); Adaptation (eye); Clinical psychology; Developmental psychology; Medicine; Psychiatry; Computer science","score_opus":0.48845899051625297,"score_gpt":0.6024196195698711,"score_spread":0.11396062905361815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9379755,0.00088038656,0.049590018,0.0008137579,0.00008078453,0.0041936417,0.00037792296,0.00021999129,0.0058679897],"genre_scores_gemma":[0.9208374,0.001264893,0.070117004,0.00012682528,0.00008401791,0.003870185,0.00026936576,0.000039655133,0.003390664],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98608774,0.0104842475,0.00053643156,0.00050537515,0.0018952437,0.00049094175],"domain_scores_gemma":[0.98246425,0.010998108,0.0020502338,0.0014107878,0.0023789671,0.000697697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01402121,0.00065653084,0.00039522484,0.00096252246,0.0010119944,0.0008785692,0.0007138729,0.00081262016,0.0024441853],"category_scores_gemma":[0.03601665,0.0004570209,0.0006286959,0.0007528874,0.0012162124,0.00084581424,0.0007461793,0.001088987,0.00042440937],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004877515,0.00670457,0.20130154,0.0023518796,0.00022172996,0.0006232793,0.03441984,0.003516756,0.031031571,0.002097299,0.0016179181,0.7112361],"study_design_scores_gemma":[0.0025044451,0.03213653,0.8179294,0.0018278755,0.00063023285,0.00091564644,0.016449552,0.009307671,0.059832823,0.0010161413,0.057192065,0.00025762297],"about_ca_topic_score_codex":0.021714125,"about_ca_topic_score_gemma":0.014993578,"teacher_disagreement_score":0.021714125,"about_ca_system_score_codex":0.0019341396,"about_ca_system_score_gemma":0.0050770855,"threshold_uncertainty_score":0.07415211},"labels":[],"label_agreement":null},{"id":"W4366453266","doi":"10.3138/cjpe.0027.004","title":"Preparing, Governing, and Managing the Paris Declaration Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credibility; Declaration; Stakeholder; Process management; Corporate governance; Joint (building); Stakeholder engagement; Business; Quality (philosophy); Public relations; Environmental resource management; Political science; Economics; Engineering","score_opus":0.30437993122529117,"score_gpt":0.5013173760618445,"score_spread":0.1969374448365533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453266","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11287017,0.00405388,0.21355736,0.08930738,0.0045153275,0.04831483,0.0018589039,0.0034930469,0.52202916],"genre_scores_gemma":[0.5933992,0.001958079,0.29347065,0.006888285,0.0008708077,0.021048132,0.0017767069,0.001065237,0.0795229],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.77747875,0.1450579,0.013495904,0.006990395,0.04056575,0.01641133],"domain_scores_gemma":[0.7021986,0.09660797,0.016231988,0.01718799,0.15115954,0.01661385],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28409865,0.0009949271,0.0008101962,0.008862161,0.012928941,0.027195988,0.00411694,0.003292438,0.010058027],"category_scores_gemma":[0.22070137,0.0011724958,0.00080949394,0.005161041,0.009835794,0.008343898,0.010636606,0.0067801634,0.003117088],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003518341,0.0004229235,0.013802777,0.0014083796,0.00014049768,0.0011124181,0.06816839,0.01523529,0.0025702382,0.22048336,0.211353,0.46495092],"study_design_scores_gemma":[0.00021699262,0.00046069088,0.017649967,0.0034516002,0.000104700266,0.00017114104,0.055262376,0.0062799556,0.0061841654,0.03916227,0.87047696,0.0005791355],"about_ca_topic_score_codex":0.08084298,"about_ca_topic_score_gemma":0.1143203,"teacher_disagreement_score":0.28409865,"about_ca_system_score_codex":0.07973497,"about_ca_system_score_gemma":0.19916448,"threshold_uncertainty_score":0.88283384},"labels":[],"label_agreement":null},{"id":"W4366453272","doi":"10.3138/cjpe.0024.003","title":"Common Measures to Advance the Science and Practice of Population Intervention for Chronic Disease Prevention: The Promise and Two Early Experiences in Tobacco Control","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Impact; Canadian Cancer Society; University of Waterloo","funders":"","keywords":"Intervention (counseling); Psychological intervention; Tobacco control; Disease; Control (management); Population; Disease prevention; Disease control; Chronic disease; Psychology; Medicine; Environmental health; Family medicine; Public health; Nursing; Pathology; Computer science","score_opus":0.4597532768262813,"score_gpt":0.669289201925334,"score_spread":0.20953592509905272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453272","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10852733,0.04456386,0.18756631,0.55035645,0.004572828,0.00560704,0.00065887783,0.0005978595,0.09754941],"genre_scores_gemma":[0.56291294,0.011494795,0.3903802,0.026715916,0.00070124713,0.0041104853,0.00020029637,0.00016196241,0.0033221585],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.74447465,0.22507831,0.0068950513,0.0028233875,0.018178115,0.0025504432],"domain_scores_gemma":[0.69958645,0.22660719,0.01113192,0.02939703,0.025703415,0.0075739543],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2039173,0.00107137,0.001193717,0.003922298,0.004754577,0.0062209065,0.0034203448,0.0038642576,0.005597033],"category_scores_gemma":[0.19938223,0.00051113416,0.0014294398,0.003195902,0.019316286,0.010788414,0.015558035,0.007182823,0.0003991745],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054057164,0.0017558355,0.01263435,0.004131011,0.00026510085,0.00022659346,0.025179502,0.0012563261,0.0008161088,0.31584907,0.021726182,0.61561936],"study_design_scores_gemma":[0.0009643526,0.0058711697,0.05453153,0.025143722,0.0005595698,0.00068275473,0.041814983,0.0044248253,0.007709033,0.5313965,0.32644188,0.00045965725],"about_ca_topic_score_codex":0.013122994,"about_ca_topic_score_gemma":0.02262252,"teacher_disagreement_score":0.2039173,"about_ca_system_score_codex":0.012063863,"about_ca_system_score_gemma":0.03804554,"threshold_uncertainty_score":0.9817117},"labels":[],"label_agreement":null},{"id":"W4366453408","doi":"10.3138/cjpe.020.002","title":"Ensuring Quality for Evaluation: Lessons from Auditors","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Documentation; Quality assurance; Quality (philosophy); Variety (cybernetics); Quality audit; Business; Point (geometry); Accounting; Process management; Computer science; Marketing","score_opus":0.6231916254204312,"score_gpt":0.6243646498296325,"score_spread":0.0011730244092013065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453408","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015295975,0.027519178,0.1809328,0.7331759,0.005275179,0.001670858,0.00009237571,0.00088183576,0.035156008],"genre_scores_gemma":[0.60958177,0.018356407,0.29711056,0.06079642,0.0031501867,0.0028281969,0.0001368059,0.000720174,0.0073194425],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.40113857,0.48983103,0.028452964,0.0073620467,0.06455124,0.008664235],"domain_scores_gemma":[0.17887315,0.55838627,0.02383618,0.055552486,0.16616221,0.017189741],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.55871564,0.0017279875,0.0024319873,0.0061111245,0.013817173,0.031631663,0.0066264826,0.009906914,0.002858269],"category_scores_gemma":[0.6229061,0.0017858571,0.0016375717,0.0066641383,0.034144673,0.026519222,0.015685815,0.021028148,0.00078803493],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003405541,0.0005000432,0.012805076,0.0038124288,0.00029794633,0.00058066106,0.04720318,0.005294644,0.0005607492,0.1711644,0.10041312,0.65702724],"study_design_scores_gemma":[0.00065267604,0.00072310306,0.008861854,0.018315999,0.00021400196,0.00078222284,0.029611403,0.007378082,0.00271685,0.6089078,0.3212598,0.00057617936],"about_ca_topic_score_codex":0.027980564,"about_ca_topic_score_gemma":0.028283065,"teacher_disagreement_score":0.55871564,"about_ca_system_score_codex":0.03536398,"about_ca_system_score_gemma":0.14628084,"threshold_uncertainty_score":0.5441822},"labels":[],"label_agreement":null},{"id":"W4366505031","doi":"10.3138/cjpe.33.3.435","title":"Peer Reviewers for Volume 33 and Manuscripts Submitted in 2018 / Examinateurs des manuscrits du volume 33 et des manuscrits soumis en 2018","year":2019,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Medical Research and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Art; Volume (thermodynamics); Physics","score_opus":0.15162953531294576,"score_gpt":0.39551143279990714,"score_spread":0.24388189748696137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366505031","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01757792,0.024298958,0.012720935,0.13705745,0.6924356,0.0099761365,0.011217883,0.0042788386,0.090436324],"genre_scores_gemma":[0.05409667,0.021706207,0.03007541,0.018182658,0.18977273,0.00682333,0.009608916,0.0046913307,0.6650427],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9638187,0.005696821,0.005791032,0.0022459442,0.020613864,0.0018336264],"domain_scores_gemma":[0.5605767,0.020363754,0.013385452,0.008147098,0.377349,0.020178063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028508276,0.0017692661,0.0028523253,0.012888646,0.0057347068,0.01103755,0.0024059378,0.004118862,0.13879529],"category_scores_gemma":[0.1524182,0.0010082091,0.0020881342,0.005956547,0.0016051839,0.0038758256,0.00331312,0.003336853,0.08109669],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004448419,0.00008687013,0.0022540223,0.001182397,0.00006605291,0.00030213076,0.00027662775,0.000056100467,0.0008988667,0.00074057246,0.9233365,0.070355035],"study_design_scores_gemma":[0.00016526478,0.00014245356,0.006780891,0.0008263326,0.00007447668,0.0003522409,0.0005795724,0.00027461603,0.0010572922,0.0012224914,0.988468,0.000056280816],"about_ca_topic_score_codex":0.0033406485,"about_ca_topic_score_gemma":0.010350807,"teacher_disagreement_score":0.9970345,"about_ca_system_score_codex":0.0029655346,"about_ca_system_score_gemma":0.021707108,"threshold_uncertainty_score":0.4643165},"labels":[],"label_agreement":null},{"id":"W4366523527","doi":"10.3138/cjpe.33.3.vi","title":"Un mot de la rédactrice","year":2019,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.06508585322297354,"score_gpt":0.353867338390934,"score_spread":0.28878148516796043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366523527","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016189527,0.014512769,0.078742415,0.18695438,0.060059447,0.0009083907,0.0067107035,0.010993169,0.62492925],"genre_scores_gemma":[0.09926661,0.008776628,0.055671897,0.024232125,0.015897356,0.0012249358,0.005807366,0.0060215076,0.78310156],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97003114,0.0117748445,0.0012650588,0.0024756545,0.013181938,0.0012714103],"domain_scores_gemma":[0.95919967,0.01080448,0.0016036207,0.0039050002,0.02280991,0.0016773874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015568388,0.0020982209,0.0015869696,0.003732059,0.006460701,0.016527472,0.0020277356,0.0050211567,0.09383516],"category_scores_gemma":[0.050004885,0.0010522612,0.0019417679,0.0030762162,0.003765618,0.009375949,0.004575543,0.0119261425,0.03554974],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005362339,0.00020538288,0.0017169369,0.00087620167,0.00006671231,0.0006280699,0.0029670554,0.00095906685,0.0037818842,0.13849735,0.53486085,0.31490433],"study_design_scores_gemma":[0.000056793808,0.000040857725,0.0010672702,0.00023937416,0.00001471494,0.0003733002,0.00067655847,0.0005211286,0.0013626569,0.0045457776,0.99105173,0.000049716],"about_ca_topic_score_codex":0.089553714,"about_ca_topic_score_gemma":0.05501051,"teacher_disagreement_score":0.09383516,"about_ca_system_score_codex":0.011406273,"about_ca_system_score_gemma":0.012104205,"threshold_uncertainty_score":0.3139099},"labels":[],"label_agreement":null},{"id":"W4366523617","doi":"10.3138/cjpe.028.008","title":"Bold, C. (2012). <i>Using Narrative in Research.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Digital Storytelling and Education","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Narrative; Psychology; Philosophy; Linguistics","score_opus":0.5934300910390827,"score_gpt":0.5879990778213935,"score_spread":0.00543101321768924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366523617","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067357775,0.10580308,0.037618358,0.572536,0.012556939,0.0008916863,0.0024790582,0.0006487295,0.2607305],"genre_scores_gemma":[0.29167986,0.20178227,0.12607582,0.15938355,0.0031295076,0.004298193,0.0026921155,0.0012749172,0.20968378],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99227774,0.0038010417,0.00054896716,0.0002728143,0.0029003965,0.00019891109],"domain_scores_gemma":[0.9196029,0.04891575,0.002659666,0.0020928443,0.022782862,0.003946039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021026801,0.00043845625,0.00025387426,0.0028184433,0.005562242,0.0065438296,0.0014559182,0.0027521912,0.013721126],"category_scores_gemma":[0.08908677,0.00058591255,0.0002549364,0.0025270297,0.0043367594,0.009997955,0.004053079,0.0061675394,0.004660462],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094840194,0.000029527251,0.0019760297,0.0012467894,0.000015568792,0.000095672396,0.013433548,0.000062355226,0.00057544804,0.020398602,0.75181925,0.21025242],"study_design_scores_gemma":[0.00003134682,0.000050502145,0.004551494,0.0047798064,0.000038574755,0.00025611566,0.015089916,0.00011167821,0.0009199699,0.01994385,0.9541884,0.000038347524],"about_ca_topic_score_codex":0.03745092,"about_ca_topic_score_gemma":0.10720363,"teacher_disagreement_score":0.03745092,"about_ca_system_score_codex":0.0042222044,"about_ca_system_score_gemma":0.012608946,"threshold_uncertainty_score":0.1112017},"labels":[],"label_agreement":null},{"id":"W4366523626","doi":"10.3138/cjpe.028.006","title":"Fetterman, D. M. (2013). <i>Empowerment Evaluation in the Digital Villages: Hewlett Packard’s $15 Million Race Towards Social Justice.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Innovative Approaches in Technology and Social Development","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Race (biology); Empowerment; Social justice; Sociology; Economic Justice; Gender studies; Political science; Criminology; Law","score_opus":0.06148526210021266,"score_gpt":0.30671355397918326,"score_spread":0.2452282918789706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366523626","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049087056,0.054705787,0.015824385,0.70670444,0.007782541,0.0005861993,0.0011694934,0.0005808774,0.2077376],"genre_scores_gemma":[0.3060467,0.1177375,0.05678261,0.20567788,0.0028020614,0.0029628454,0.0014160073,0.0011178579,0.3054565],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958656,0.0018944552,0.00019947618,0.00015527518,0.0016489589,0.00023627825],"domain_scores_gemma":[0.9682639,0.016445912,0.0010780578,0.0005572951,0.010981654,0.0026731521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015665935,0.000481308,0.00031247785,0.0020924718,0.0066206,0.005231506,0.0015224678,0.0033424178,0.033149306],"category_scores_gemma":[0.043310832,0.0005631332,0.00028406992,0.0018063792,0.0037141896,0.008969054,0.003020345,0.007088121,0.0067558633],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006120879,0.000033733206,0.00083733216,0.00024366024,0.0000063601165,0.000035052908,0.0016956712,0.000056148314,0.0001406206,0.011114509,0.81273675,0.1730389],"study_design_scores_gemma":[0.00008588866,0.0001492102,0.01160962,0.0031502633,0.00004717,0.000104465165,0.008470753,0.00021987203,0.0010220855,0.028697224,0.9463798,0.00006375373],"about_ca_topic_score_codex":0.057284947,"about_ca_topic_score_gemma":0.2070019,"teacher_disagreement_score":0.057284947,"about_ca_system_score_codex":0.0046857544,"about_ca_system_score_gemma":0.012367547,"threshold_uncertainty_score":0.113903046},"labels":[],"label_agreement":null},{"id":"W4366545244","doi":"10.3138/cjpe.028.007","title":"Hurteau, M., Houle, S., &amp; Guillemette, F. (Éds.). (2012). <i>L’évaluation de programme axée sur le jugement crédible.</i>","year":2013,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Healthcare Systems and Practices","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Economics; Humanities; Philosophy; Finance","score_opus":0.3728807464212603,"score_gpt":0.4781061994206049,"score_spread":0.1052254529993446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366545244","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011834747,0.87156224,0.0047003394,0.058057502,0.0029348813,0.000117003314,0.0008798466,0.0002224489,0.060342193],"genre_scores_gemma":[0.020158064,0.94100565,0.00850968,0.003088478,0.0015747992,0.00015971482,0.0006131397,0.00010586327,0.024784604],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99651116,0.0012799818,0.00026676664,0.0001430988,0.001638157,0.00016082634],"domain_scores_gemma":[0.98537755,0.010553591,0.0008391122,0.00023978867,0.0023498721,0.0006401174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006709721,0.0010740913,0.0009212238,0.007024849,0.0015143999,0.00462513,0.0018351586,0.002602195,0.027187588],"category_scores_gemma":[0.016308298,0.0008241683,0.00088625954,0.0064800335,0.0018036566,0.005591099,0.0017462706,0.003759798,0.009872562],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058608675,0.000040036466,0.0012457569,0.0027113806,0.000039356826,0.00006055065,0.0014613048,0.00022966377,0.00010460569,0.0051030917,0.49421167,0.49473396],"study_design_scores_gemma":[0.00004549497,0.000097666234,0.011221736,0.01636573,0.00014146425,0.0005290675,0.0032545868,0.0004455968,0.00069666276,0.009853613,0.95728093,0.00006731933],"about_ca_topic_score_codex":0.09784486,"about_ca_topic_score_gemma":0.18670261,"teacher_disagreement_score":0.09784486,"about_ca_system_score_codex":0.00634021,"about_ca_system_score_gemma":0.011604322,"threshold_uncertainty_score":0.1945507},"labels":[],"label_agreement":null},{"id":"W4366675048","doi":"10.3138/cjpe.0020.005","title":"Patient Satisfaction with Health Care: Recent Theoretical Developments and Implications for Evaluation Practice","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Patient satisfaction; Quality (philosophy); Health care; Psychology; Consumer satisfaction; Service quality; Customer satisfaction; Service (business); Management science; Simple (philosophy); Applied psychology; Knowledge management; Computer science; Nursing; Marketing; Medicine; Business; Epistemology; Political science; Engineering","score_opus":0.12322856287840847,"score_gpt":0.49547218012484967,"score_spread":0.37224361724644117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675048","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04543693,0.5787006,0.0841966,0.21794751,0.0014734643,0.0005178059,0.00017306636,0.00016128499,0.0713928],"genre_scores_gemma":[0.7430336,0.19848067,0.04248771,0.011090399,0.0018392543,0.0012779107,0.0001175825,0.00007338076,0.0015994675],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9634084,0.02815309,0.002063135,0.0010275502,0.0048884843,0.00045931357],"domain_scores_gemma":[0.74295026,0.23373376,0.00446025,0.0025053355,0.014761518,0.0015889511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09617216,0.00058156485,0.001234023,0.005437351,0.0013632404,0.007874803,0.0019327822,0.003054391,0.003915307],"category_scores_gemma":[0.12482444,0.0004003101,0.0008193034,0.006526799,0.013254217,0.006912108,0.0031701517,0.0037686655,0.00030299535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002173982,0.00026377448,0.014386694,0.0045114686,0.00009168441,0.00007567351,0.004266155,0.0021450154,0.00012517559,0.21448795,0.0046361727,0.75479287],"study_design_scores_gemma":[0.00024509337,0.0016167689,0.063333645,0.039727043,0.0003855224,0.0010206606,0.026790723,0.031840585,0.0015453277,0.6549586,0.17823346,0.00030263435],"about_ca_topic_score_codex":0.0054211863,"about_ca_topic_score_gemma":0.005544785,"teacher_disagreement_score":0.09617216,"about_ca_system_score_codex":0.012719774,"about_ca_system_score_gemma":0.00772632,"threshold_uncertainty_score":0.5086131},"labels":[],"label_agreement":null},{"id":"W4366675051","doi":"10.3138/cjpe.019.003","title":"Unnatural Selection: An Examination of the Fraser Institute’s Performance Index for the Donner Canadian Foundation Awards for Excellence in the Delivery of Social Services","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Nonprofit Sector and Volunteering","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Excellence; Profit (economics); Index (typography); Context (archaeology); For profit; Management; Operational excellence; Sociology; Marketing; Economics; Public relations; Business; Political science; Law; Computer science; Finance","score_opus":0.07314999274241017,"score_gpt":0.3592812778528839,"score_spread":0.2861312851104737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83646977,0.0005230007,0.0022797345,0.0031026923,0.000091717644,0.00013093454,0.0006564307,0.00006316491,0.15668248],"genre_scores_gemma":[0.9969137,0.00010934531,0.0007918433,0.00007543463,0.000016843529,0.000027807808,0.0002105675,0.000015912268,0.0018384346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9841644,0.0026132925,0.0004895669,0.00043715007,0.011292697,0.0010028742],"domain_scores_gemma":[0.9639435,0.010499035,0.005399101,0.0012138684,0.01645075,0.0024937503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013922435,0.00021312152,0.0003475061,0.010770546,0.0034525588,0.0035264164,0.0009856072,0.00026987717,0.0026399272],"category_scores_gemma":[0.048842292,0.00008603272,0.00032258226,0.013602378,0.0033888828,0.0015503982,0.0022425363,0.0006743952,0.00023259477],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027502133,0.00012606833,0.7027302,0.0001335348,0.000084587926,0.0002527143,0.03519981,0.0009135017,0.00053464656,0.069582045,0.018591797,0.17157619],"study_design_scores_gemma":[0.000006747794,0.00007949802,0.95220673,0.000056873923,0.000017987271,0.00007082923,0.019859027,0.0017715356,0.00026353396,0.004301719,0.021316448,0.000049089726],"about_ca_topic_score_codex":0.4568436,"about_ca_topic_score_gemma":0.5939789,"teacher_disagreement_score":0.98114645,"about_ca_system_score_codex":0.01885356,"about_ca_system_score_gemma":0.015425495,"threshold_uncertainty_score":0.90836895},"labels":[],"label_agreement":null},{"id":"W4366675053","doi":"10.3138/cjpe.0017.005","title":"Evaluation Capacity Building in the Voluntary/Nonprofit Sector","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Ontario","funders":"","keywords":"Nonprofit sector; Work (physics); Capacity building; Business; Process (computing); Resource (disambiguation); Public relations; Knowledge management; Political science; Economic growth; Economics; Computer science","score_opus":0.582860873132594,"score_gpt":0.5211126018594392,"score_spread":0.06174827127315485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675053","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13414061,0.018659996,0.1891179,0.3178084,0.002659491,0.010525707,0.0004013235,0.001456701,0.3252299],"genre_scores_gemma":[0.93383926,0.002808004,0.0413161,0.0072830184,0.00048536487,0.0026251168,0.00029211945,0.00017231153,0.011178744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.67729443,0.26490942,0.009830038,0.0048437403,0.026509736,0.016612578],"domain_scores_gemma":[0.4765844,0.29013535,0.018997058,0.02353546,0.1398759,0.05087184],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3211932,0.0007156821,0.0010829386,0.007004542,0.011325782,0.02377819,0.005880182,0.0044297297,0.011676106],"category_scores_gemma":[0.2585513,0.0009144655,0.00081395934,0.0035883118,0.011974551,0.0133665195,0.027980436,0.005864471,0.0014712036],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038194243,0.0017754477,0.017292032,0.004222904,0.00023726474,0.0005452415,0.017380944,0.010636721,0.00092830113,0.42180824,0.07991373,0.4448772],"study_design_scores_gemma":[0.00049836695,0.0007991048,0.018369067,0.012853254,0.00008654835,0.00053519453,0.06476327,0.018860165,0.004390621,0.41565478,0.46281275,0.00037688948],"about_ca_topic_score_codex":0.013603959,"about_ca_topic_score_gemma":0.01311068,"teacher_disagreement_score":0.986396,"about_ca_system_score_codex":0.029099034,"about_ca_system_score_gemma":0.17360468,"threshold_uncertainty_score":0.83708966},"labels":[],"label_agreement":null},{"id":"W4366675057","doi":"10.3138/cjpe.0016.001","title":"Introduction","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Psychology; Business","score_opus":0.15089910334963733,"score_gpt":0.3536273452464801,"score_spread":0.20272824189684277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675057","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015080305,0.0015714164,0.0052604824,0.019633844,0.006503586,0.00039884244,0.004118702,0.0008435921,0.96016145],"genre_scores_gemma":[0.010844047,0.0017825667,0.0043519177,0.008639405,0.0012465339,0.00035986642,0.0032696757,0.0003091318,0.96919674],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975592,0.0003359715,0.00007461261,0.00039724135,0.0012759242,0.00035719736],"domain_scores_gemma":[0.9949301,0.0005232458,0.00015802159,0.0004619515,0.002863718,0.0010629722],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0028234813,0.00058324425,0.00037329973,0.0016905803,0.002268713,0.004989165,0.0017556922,0.0017554191,0.42602122],"category_scores_gemma":[0.00842308,0.00025236304,0.0005568187,0.0015403712,0.000834502,0.0022401155,0.002609764,0.0017871336,0.18518364],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039040464,0.00005740246,0.00069208344,0.00015967665,0.0000025236666,0.00005255323,0.00032457782,0.00007461645,0.00019728382,0.044123054,0.78048676,0.17379038],"study_design_scores_gemma":[0.000003698659,0.00000985663,0.0006143562,0.000114292096,0.0000015562337,0.000039596955,0.0001737769,0.0000223282,0.000085746986,0.0027425524,0.99618834,0.0000039810675],"about_ca_topic_score_codex":0.020294946,"about_ca_topic_score_gemma":0.03256583,"teacher_disagreement_score":0.5739788,"about_ca_system_score_codex":0.0040662447,"about_ca_system_score_gemma":0.010090315,"threshold_uncertainty_score":0.81871104},"labels":[],"label_agreement":null},{"id":"W4366675147","doi":"10.3138/cjpe.0016.009","title":"Program Evaluation in the Government of the Northwest Territories, 1967–2000","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Northwest Territories","funders":"","keywords":"Cabinet (room); Documentation; Government (linguistics); Business; Public administration; Political science; Public relations; Geography; Archaeology; Computer science","score_opus":0.29140734594736467,"score_gpt":0.46572274541019243,"score_spread":0.17431539946282776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82351047,0.008506458,0.0017988371,0.011456039,0.00022342525,0.0013224487,0.006128909,0.00022498034,0.14682841],"genre_scores_gemma":[0.90216565,0.0034230228,0.0036853182,0.0009979255,0.00003772233,0.0005180271,0.0033410494,0.000065678454,0.08576557],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99379,0.001677789,0.00031309912,0.0002467223,0.002726167,0.0012461368],"domain_scores_gemma":[0.96708226,0.003883409,0.0020107073,0.0009831798,0.020945268,0.0050951974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007817531,0.00016287022,0.00024030101,0.0016045658,0.004659677,0.0025867256,0.00089009706,0.00048916537,0.0036997243],"category_scores_gemma":[0.020710869,0.00037611692,0.0001480567,0.0039653163,0.0012494362,0.00073545193,0.0018894712,0.001004803,0.0005718817],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014544145,0.00078080356,0.4005199,0.0011168986,0.00017008839,0.00095708214,0.026857594,0.0030175552,0.002050449,0.009916772,0.09483707,0.45832145],"study_design_scores_gemma":[0.000049727878,0.0002046813,0.8249551,0.00041200023,0.000045152574,0.00012209613,0.015370355,0.00073689065,0.001764671,0.000334275,0.15596098,0.000044062763],"about_ca_topic_score_codex":0.9499614,"about_ca_topic_score_gemma":0.9790822,"teacher_disagreement_score":0.9290291,"about_ca_system_score_codex":0.070970915,"about_ca_system_score_gemma":0.14101477,"threshold_uncertainty_score":0.51493245},"labels":[],"label_agreement":null},{"id":"W4366675148","doi":"10.3138/cjpe.0016.005","title":"Evaluation Policy and Practice in Ontario","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Optimism; Government (linguistics); Public service; Public policy; Public administration; Service (business); Political science; Business; Public relations; Program evaluation; Psychology; Marketing; Social psychology","score_opus":0.5598804861443701,"score_gpt":0.5713121749383623,"score_spread":0.011431688793992145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675148","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08383043,0.040008105,0.0053360276,0.58107436,0.0015779481,0.0016900019,0.0010656147,0.00026808938,0.2851494],"genre_scores_gemma":[0.86364126,0.019175204,0.010526115,0.037643008,0.0006190796,0.00097021204,0.000532434,0.0001595332,0.0667332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9305533,0.027247876,0.004966387,0.0029702014,0.022033982,0.012228158],"domain_scores_gemma":[0.7844888,0.053548332,0.011634219,0.004553046,0.103387535,0.04238797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.065396,0.0004043001,0.00070478563,0.0039352146,0.018212158,0.014508276,0.0036386256,0.0061850157,0.011465932],"category_scores_gemma":[0.11066097,0.00095684984,0.0006699542,0.006398629,0.013435913,0.0046404097,0.008437608,0.0033148746,0.0006305468],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00067077694,0.00040940903,0.062184263,0.0046061147,0.00017727545,0.0015103704,0.044680886,0.0057119224,0.0011499363,0.40587625,0.23742768,0.23559508],"study_design_scores_gemma":[0.00025567322,0.00020552661,0.09092442,0.0048745256,0.00008441836,0.00030875154,0.021262482,0.0028067399,0.0007910827,0.029106315,0.8492006,0.0001795535],"about_ca_topic_score_codex":0.96499455,"about_ca_topic_score_gemma":0.9723541,"teacher_disagreement_score":0.65528166,"about_ca_system_score_codex":0.3447183,"about_ca_system_score_gemma":0.6178708,"threshold_uncertainty_score":0.7600339},"labels":[],"label_agreement":null},{"id":"W4366675150","doi":"10.3138/cjpe.15.005","title":"Support to Business in Underdeveloped Regions Makes Economic Sense: A Reply","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Regional Development and Policy","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Atlantic Canada Opportunities Agency","funders":"","keywords":"Sense (electronics); Business; Engineering","score_opus":0.137452283526265,"score_gpt":0.41010760991580825,"score_spread":0.27265532638954326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675150","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002881289,0.0003879103,0.000026960895,0.9973894,0.001455676,0.0000015472089,0.000018201174,0.0000018624976,0.0004302841],"genre_scores_gemma":[0.009150595,0.0008478261,0.0001000213,0.98358005,0.0050363108,0.000014165664,0.000018051722,0.000013444295,0.0012394493],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99175006,0.0026208353,0.0007588988,0.0015087598,0.0017623383,0.0015990668],"domain_scores_gemma":[0.9002318,0.07324807,0.00320372,0.0024393348,0.013288191,0.007588949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014187904,0.0007921551,0.0016274599,0.0011737032,0.0076027783,0.008562216,0.0035331743,0.06748033,0.009701886],"category_scores_gemma":[0.079130806,0.0008441922,0.0010641468,0.0027066926,0.015797345,0.012659745,0.0076252,0.057370964,0.0025040954],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008313943,0.00003593476,0.0022047716,0.00013187923,0.000046715686,0.00031810228,0.0021778874,0.000082409315,0.0001515255,0.030524606,0.95561767,0.00862534],"study_design_scores_gemma":[0.0003766894,0.000057427074,0.0077510513,0.0010844336,0.00017905931,0.00059500994,0.019574601,0.0002991698,0.0008282264,0.08197619,0.8870457,0.000232514],"about_ca_topic_score_codex":0.046209656,"about_ca_topic_score_gemma":0.051930636,"teacher_disagreement_score":0.95379037,"about_ca_system_score_codex":0.007829345,"about_ca_system_score_gemma":0.021776823,"threshold_uncertainty_score":0.091881394},"labels":[],"label_agreement":null},{"id":"W4366675152","doi":"10.3138/cjpe.0017.002","title":"Comprehensive Costing of Support Services for Vulnerable Populations: A Case Study","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Royal Ottawa Mental Health Centre; University of Ottawa","funders":"","keywords":"Activity-based costing; Context (archaeology); Business; Social Welfare; Health care; Mental health; Christian ministry; Program evaluation; Nursing; Medicine; Marketing; Economic growth; Psychiatry; Political science; Economics; Geography; Public administration","score_opus":0.40875027956240995,"score_gpt":0.5598748487268099,"score_spread":0.15112456916439998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869991,0.00059359625,0.0006345866,0.0026093586,0.000029536892,0.0005882636,0.00011310366,0.000009944331,0.0084225265],"genre_scores_gemma":[0.9943409,0.0013083925,0.0021536173,0.00039020315,0.00003241862,0.00042156613,0.00005052383,0.0000088899815,0.001293547],"study_design_codex":"qualitative","study_design_gemma":"case_report","domain_scores_codex":[0.9947594,0.0027331407,0.00020052075,0.0001477817,0.00078841974,0.0013706399],"domain_scores_gemma":[0.9946074,0.0024447415,0.0006035443,0.0002962831,0.00077160634,0.0012764757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044707456,0.00079046906,0.0005485305,0.003012759,0.01583341,0.0021548849,0.0020347966,0.0034155727,0.0029208031],"category_scores_gemma":[0.010030878,0.0005391342,0.0007764761,0.0038575013,0.0027156582,0.0014361584,0.0029522565,0.0030093733,0.00020093824],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010456603,0.014473061,0.20633379,0.0015853607,0.00019426255,0.22632638,0.34003633,0.0036609431,0.0017866063,0.035263285,0.017665455,0.15162893],"study_design_scores_gemma":[0.0004400163,0.0044121305,0.11766478,0.001426364,0.00028777643,0.10605713,0.70594835,0.0056590666,0.0027802407,0.0050343126,0.05006583,0.00022401549],"about_ca_topic_score_codex":0.15571384,"about_ca_topic_score_gemma":0.31293094,"teacher_disagreement_score":0.15571384,"about_ca_system_score_codex":0.018961,"about_ca_system_score_gemma":0.01201744,"threshold_uncertainty_score":0.30961502},"labels":[],"label_agreement":null},{"id":"W4366675191","doi":"10.3138/cjpe.0017.009","title":"Epilogue: Comments on the Special Issue","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Critical Realism in Sociology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"","keywords":"Psychology; Epistemology; Philosophy","score_opus":0.201124026542461,"score_gpt":0.46531612636534697,"score_spread":0.26419209982288594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675191","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002469572,0.0012845781,0.0002603404,0.35680175,0.63462377,0.0002854004,0.0010193223,0.00023269333,0.005245186],"genre_scores_gemma":[0.0022507596,0.0013510328,0.00035649785,0.6265039,0.30668256,0.00053995487,0.0005283437,0.00018600296,0.06160107],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99315864,0.0013333829,0.0009583763,0.0005923801,0.0030309677,0.0009261842],"domain_scores_gemma":[0.93403286,0.03300386,0.003855059,0.0022529378,0.022205837,0.0046493732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010816718,0.0021746506,0.002689919,0.003760591,0.004336891,0.0054117823,0.0037212665,0.04280469,0.056852978],"category_scores_gemma":[0.07812115,0.0012876887,0.0034026967,0.0025060996,0.0022978866,0.00369773,0.0025892167,0.024337983,0.02757989],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067206405,0.000013505101,0.00007524887,0.00009982954,0.000006900113,0.00009070032,0.000020346599,0.000014614534,0.000047648933,0.00018456232,0.9979207,0.0014588056],"study_design_scores_gemma":[0.00012450773,0.00008586549,0.0021481712,0.00043061748,0.000057006622,0.0001317895,0.00018294419,0.00016346328,0.00022786824,0.0010555836,0.99533564,0.000056532255],"about_ca_topic_score_codex":0.012721336,"about_ca_topic_score_gemma":0.01503337,"teacher_disagreement_score":0.056852978,"about_ca_system_score_codex":0.0049837474,"about_ca_system_score_gemma":0.006421059,"threshold_uncertainty_score":0.19019216},"labels":[],"label_agreement":null},{"id":"W4366675196","doi":"10.3138/cjpe.0016.008","title":"Evaluation in Newfoundland: Then Was Then and Now Is Now","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Accountability; Plan (archaeology); Audit; Business; Program evaluation; Strategic planning; Public administration; Political science; Public relations; Accounting; Process management; Environmental resource management; Geography; Marketing; Economics; Archaeology","score_opus":0.39082580630976066,"score_gpt":0.49751921985585973,"score_spread":0.10669341354609907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5245639,0.033008337,0.0022756835,0.19570239,0.0012153948,0.0011062023,0.0024454626,0.00037801312,0.23930457],"genre_scores_gemma":[0.87743455,0.0068566008,0.0032672214,0.017259194,0.0001137253,0.00046105732,0.0011880969,0.00006936413,0.09335016],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.989565,0.003739759,0.00045442538,0.00058778666,0.001777826,0.0038751748],"domain_scores_gemma":[0.9645447,0.0065119304,0.0020313717,0.0012748007,0.016366916,0.009270213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013021618,0.00023524144,0.00038156315,0.0010129123,0.0086648045,0.005546615,0.0012367324,0.0012607973,0.008604782],"category_scores_gemma":[0.014921832,0.00039152656,0.00033065263,0.0014805694,0.0033604058,0.0022166257,0.003832083,0.002495557,0.00064009184],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024842694,0.0012011584,0.20919351,0.0023346955,0.0002491039,0.003099523,0.039711814,0.0023729852,0.0031554874,0.023390235,0.33342463,0.37938255],"study_design_scores_gemma":[0.00014230303,0.00035386108,0.60252154,0.002310918,0.00012892928,0.00045924247,0.05099547,0.00061317265,0.002356398,0.0014151039,0.338579,0.00012405844],"about_ca_topic_score_codex":0.9358274,"about_ca_topic_score_gemma":0.97813934,"teacher_disagreement_score":0.8780897,"about_ca_system_score_codex":0.121910274,"about_ca_system_score_gemma":0.15151578,"threshold_uncertainty_score":0.88452506},"labels":[],"label_agreement":null},{"id":"W4366675198","doi":"10.3138/cjpe.0020.010","title":"Program Evaluation in the Government of Canada: Plus ça change …","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Treasury; Government (linguistics); Public administration; State (computer science); Function (biology); State government; Political science; Business; Accounting; Local government; Computer science; Law","score_opus":0.4207187134281067,"score_gpt":0.5004735994535432,"score_spread":0.07975488602543651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675198","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09433067,0.018665107,0.01201209,0.60223305,0.0029374196,0.0008518718,0.0007484678,0.000723466,0.26749787],"genre_scores_gemma":[0.8686604,0.0062092603,0.020178758,0.048773963,0.0005661076,0.0001889625,0.0004831326,0.000100163794,0.05483928],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9723389,0.0074936147,0.0008497603,0.0011203601,0.01280335,0.005393962],"domain_scores_gemma":[0.94923866,0.005065725,0.0017516448,0.0012932001,0.033062704,0.009587943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02070764,0.00032439164,0.00033721986,0.0021140913,0.008317769,0.0094914725,0.0022625322,0.0025154206,0.0044912146],"category_scores_gemma":[0.037554998,0.0003043387,0.00050779217,0.0026451917,0.003988736,0.0020928413,0.0031479555,0.0033626647,0.00038091734],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00032657827,0.00045815465,0.04048671,0.0013068327,0.00014924917,0.00044895604,0.0054373783,0.004651286,0.0012885655,0.1934554,0.25090984,0.5010811],"study_design_scores_gemma":[0.00016087915,0.00026857297,0.10365492,0.0019493009,0.00015423128,0.00023084045,0.008463077,0.005244394,0.0019717275,0.019583702,0.8581417,0.00017661705],"about_ca_topic_score_codex":0.97153676,"about_ca_topic_score_gemma":0.98449755,"teacher_disagreement_score":0.83641416,"about_ca_system_score_codex":0.16358584,"about_ca_system_score_gemma":0.42860642,"threshold_uncertainty_score":0.97012186},"labels":[],"label_agreement":null},{"id":"W4366675228","doi":"10.3138/cjpe.0020.001","title":"Guest Editor’s Remarks","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Jewish Identity and Society","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Philosophy; Psychology","score_opus":0.041757670729325756,"score_gpt":0.36123874962874647,"score_spread":0.31948107889942073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675228","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002855904,0.0011604845,0.0001561159,0.41194266,0.5825287,0.000035106972,0.00009630027,0.0001052804,0.0036897187],"genre_scores_gemma":[0.0041751843,0.00094948476,0.0004673559,0.6156645,0.33623156,0.000100453035,0.000048041547,0.00011022932,0.042253245],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98967814,0.0010150988,0.0011862738,0.002039933,0.0044275406,0.0016530206],"domain_scores_gemma":[0.955405,0.010823373,0.0037444425,0.0025190702,0.021470722,0.0060373796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012452115,0.0015320772,0.0025243293,0.0016803786,0.005109326,0.009562275,0.004587614,0.03834136,0.02121213],"category_scores_gemma":[0.09241351,0.0011883066,0.0029221063,0.0014289144,0.0026911881,0.0034019093,0.0030724604,0.036816917,0.013444455],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032133936,0.0000073432693,0.000097187796,0.000037407182,0.0000107445485,0.0002328521,0.00004221571,0.000021058622,0.0000689283,0.00048395866,0.9971921,0.0017739948],"study_design_scores_gemma":[0.00006995639,0.000027179873,0.0010648334,0.00019024029,0.000054758068,0.0002995584,0.00026817128,0.00019741282,0.00034560685,0.0010453421,0.99638075,0.000056143286],"about_ca_topic_score_codex":0.010402412,"about_ca_topic_score_gemma":0.019113453,"teacher_disagreement_score":0.03834136,"about_ca_system_score_codex":0.005808755,"about_ca_system_score_gemma":0.0070093693,"threshold_uncertainty_score":0.070961654},"labels":[],"label_agreement":null},{"id":"W4366675233","doi":"10.3138/cjpe.0016.006","title":"The Long March from Evaluation to Accreditation: Quebec’s New “Government Management Framework”","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Accreditation; Accountability; Government (linguistics); Certification and Accreditation; Higher education; Political science; Commission; Business; Public administration; Public relations; Accounting; Medical education; Medicine; Law","score_opus":0.14831448627035254,"score_gpt":0.4072966376101577,"score_spread":0.2589821513398052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675233","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01126858,0.008935694,0.016533336,0.7916964,0.0034630648,0.00028920075,0.00043135314,0.0002663587,0.1671159],"genre_scores_gemma":[0.57448953,0.005589866,0.041206025,0.23782705,0.0020322162,0.0005652105,0.0005021351,0.0003435057,0.13744456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.943218,0.020112252,0.0021453232,0.005231316,0.02164058,0.0076524653],"domain_scores_gemma":[0.92452407,0.019574635,0.0027278464,0.0046990463,0.036704894,0.0117696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04975487,0.0009335543,0.0009133709,0.0045746155,0.01787005,0.030043598,0.006140396,0.016704358,0.0073194928],"category_scores_gemma":[0.038115956,0.001227294,0.001200476,0.0044621374,0.029036906,0.008468478,0.007787073,0.015061873,0.00072830956],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000045920002,0.00010743213,0.0050478205,0.00020632862,0.000040207407,0.00023533059,0.0035283873,0.0018876444,0.00043918274,0.725814,0.20254397,0.060103808],"study_design_scores_gemma":[0.000075886535,0.00010753699,0.016480148,0.0014652385,0.000052999374,0.00013596192,0.0038183993,0.005751607,0.00042223523,0.06873276,0.90263385,0.00032333896],"about_ca_topic_score_codex":0.97273153,"about_ca_topic_score_gemma":0.9794295,"teacher_disagreement_score":0.7741844,"about_ca_system_score_codex":0.22581558,"about_ca_system_score_gemma":0.32869476,"threshold_uncertainty_score":0.8979442},"labels":[],"label_agreement":null},{"id":"W4366675237","doi":"10.3138/cjpe.15.001","title":"Monitoring Health Technology Assessment Agencies","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Negotiation; CONTEST; Health technology; Corporate governance; Technology assessment; Business; Component (thermodynamics); Health care; Public relations; Knowledge management; Political science; Computer science; Law","score_opus":0.5870732618191481,"score_gpt":0.533859559650962,"score_spread":0.053213702168186106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675237","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19999686,0.005404049,0.16039765,0.050235715,0.0014310286,0.013990653,0.0289193,0.0064794333,0.5331454],"genre_scores_gemma":[0.8272263,0.002597242,0.09874535,0.0031760694,0.0015505514,0.0061303833,0.012127416,0.00029747354,0.04814925],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.90957934,0.04211315,0.008963036,0.0074053775,0.029154219,0.002784941],"domain_scores_gemma":[0.7060117,0.086938486,0.053735007,0.026966989,0.11933096,0.007016834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05934696,0.00082468404,0.000476971,0.0087840725,0.0024305615,0.0063091666,0.0027217022,0.0024127718,0.013711141],"category_scores_gemma":[0.09888199,0.0005263752,0.00057457335,0.007518188,0.0013034963,0.0046287975,0.003999389,0.0026390862,0.0056279427],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066785986,0.0010191676,0.22748105,0.0014892177,0.00023118364,0.00016409127,0.005220716,0.0053758495,0.003803364,0.052641187,0.16485564,0.5370506],"study_design_scores_gemma":[0.00050637574,0.0014264343,0.1324898,0.0016947889,0.0004539946,0.00047080772,0.0049178996,0.028585013,0.025273673,0.024852227,0.77905977,0.00026914105],"about_ca_topic_score_codex":0.013394759,"about_ca_topic_score_gemma":0.00809468,"teacher_disagreement_score":0.05934696,"about_ca_system_score_codex":0.007731926,"about_ca_system_score_gemma":0.025308106,"threshold_uncertainty_score":0.31386048},"labels":[],"label_agreement":null},{"id":"W4366675251","doi":"10.3138/cjpe.019.005","title":"An Empirical Study of Building the Evaluation Capacity of K–12 Site-Managed Project Personnel","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Argument (complex analysis); Psychology; Medical education; Program evaluation; Professional development; Evaluation methods; Capacity building; Applied psychology; Pedagogy; Political science; Engineering; Medicine","score_opus":0.5928942452671162,"score_gpt":0.566262734771,"score_spread":0.02663151049611623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988193,0.000022160499,0.00016831837,0.00005753705,0.0000018795618,0.000058728576,0.0000060671605,0.0000040306377,0.00086192274],"genre_scores_gemma":[0.9991536,0.000026626702,0.0004816443,0.000030110721,0.00000280405,0.00007144114,0.00001138729,0.0000018027192,0.00022057763],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9761721,0.017937828,0.00075502566,0.00090766966,0.0017284192,0.0024990297],"domain_scores_gemma":[0.87796223,0.07186505,0.014158406,0.0064716344,0.019654142,0.009888516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025815103,0.00033756965,0.00027237163,0.001041308,0.003744675,0.0021287773,0.0014668412,0.0007234177,0.0029005047],"category_scores_gemma":[0.0632002,0.00057680055,0.0002895893,0.00065358565,0.0024022448,0.0014387517,0.0023968755,0.0016354807,0.00038550163],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013999403,0.01691382,0.56937367,0.0007544888,0.00018796128,0.0008119243,0.23538657,0.0015600034,0.0068398756,0.0014267637,0.0020783911,0.16326655],"study_design_scores_gemma":[0.00031490804,0.010524827,0.68309563,0.00042003242,0.0001026438,0.00037281113,0.28563353,0.0027330688,0.006841015,0.0005505122,0.009281681,0.00012928774],"about_ca_topic_score_codex":0.009282048,"about_ca_topic_score_gemma":0.014984841,"teacher_disagreement_score":0.025815103,"about_ca_system_score_codex":0.0034995603,"about_ca_system_score_gemma":0.00862353,"threshold_uncertainty_score":0.13652492},"labels":[],"label_agreement":null},{"id":"W4366675256","doi":"10.3138/cjpe.0020.002","title":"Un mot du rédacteur invité","year":2006,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Psychology","score_opus":0.12277611778150786,"score_gpt":0.4372547176960584,"score_spread":0.3144785999145505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675256","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004741171,0.043510605,0.004491103,0.34639093,0.24203828,0.00019105761,0.0005794104,0.00068597094,0.3573715],"genre_scores_gemma":[0.04034769,0.028113963,0.0051262183,0.11878708,0.0667096,0.00036679898,0.00081383815,0.0011804636,0.7385544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97663206,0.005541165,0.0013834833,0.0025202697,0.012176064,0.0017470414],"domain_scores_gemma":[0.94247985,0.013078036,0.002956926,0.0047101453,0.031935256,0.004839776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013358416,0.0011960663,0.0010113958,0.004192685,0.0075395047,0.019532165,0.0025688452,0.0073349653,0.058635816],"category_scores_gemma":[0.053218294,0.0006076901,0.0014912246,0.0035857332,0.0058132284,0.01244112,0.0087513225,0.009336345,0.036791697],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008241989,0.000054456374,0.00091986544,0.0008588558,0.00002438219,0.00028576466,0.0068800356,0.00006244829,0.00080041675,0.09816744,0.8013629,0.09050098],"study_design_scores_gemma":[0.0000043092264,0.000013936419,0.00028275317,0.00039029913,0.000005857536,0.00012106906,0.0011799952,0.000017600121,0.00018569207,0.0021449293,0.9956422,0.000011462244],"about_ca_topic_score_codex":0.010455333,"about_ca_topic_score_gemma":0.015368624,"teacher_disagreement_score":0.058635816,"about_ca_system_score_codex":0.009055807,"about_ca_system_score_gemma":0.021511588,"threshold_uncertainty_score":0.19615632},"labels":[],"label_agreement":null},{"id":"W4366675259","doi":"10.3138/cjpe.0016.010","title":"Epilogue","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Psychology","score_opus":0.28020403887745027,"score_gpt":0.380605414758771,"score_spread":0.10040137588132075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675259","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011198058,0.006874712,0.0016241095,0.10405125,0.48430622,0.003960903,0.029967846,0.0027176908,0.36537746],"genre_scores_gemma":[0.0035212522,0.0033524071,0.0015347017,0.07650539,0.04746651,0.0022238905,0.010144897,0.00050849735,0.8547424],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810034,0.00048281476,0.00019743678,0.00015493474,0.00079407106,0.00027048346],"domain_scores_gemma":[0.98533154,0.003119893,0.0007230768,0.00084495975,0.0075248745,0.0024557007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031540783,0.0011923499,0.0014241231,0.003857613,0.0012672619,0.0033756196,0.0019010793,0.005096577,0.6212545],"category_scores_gemma":[0.02437282,0.00052858796,0.0014794996,0.0016613345,0.00045466423,0.0015754115,0.0015311496,0.0027478915,0.31680256],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007606943,0.000021465454,0.00009054444,0.00029781106,0.0000035764601,0.00005325747,0.0000048662723,0.000017597707,0.000033508917,0.00022383392,0.98050743,0.0186699],"study_design_scores_gemma":[0.00011647596,0.00005362375,0.000923495,0.00048656436,0.00001262162,0.00010867383,0.000038317903,0.000055304692,0.00009728044,0.00071219314,0.9973814,0.00001409618],"about_ca_topic_score_codex":0.0037693349,"about_ca_topic_score_gemma":0.007675192,"teacher_disagreement_score":0.6212545,"about_ca_system_score_codex":0.0014430425,"about_ca_system_score_gemma":0.0033177398,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4366675260","doi":"10.3138/cjpe.016.005","title":"The Politics and Practice of Empowerment Evaluation and Social Interventions: Lessons from the Atlantic Community Action Program for Children Regional Evaluation","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nova Scotia Health Authority; Health Canada; Saint Mary's University","funders":"Health Canada","keywords":"Empowerment; Popularity; Politics; Context (archaeology); Sociology; Participatory action research; Action (physics); Citizen journalism; Psychological intervention; Public relations; Political science; Psychology; Social psychology; Law","score_opus":0.596221525877389,"score_gpt":0.6159796392535666,"score_spread":0.01975811337617761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675260","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14791556,0.023464592,0.031163575,0.4406171,0.0007179286,0.0015993774,0.000079547855,0.00016524534,0.35427713],"genre_scores_gemma":[0.96145916,0.0059106466,0.014508014,0.008178806,0.00019618907,0.0013169628,0.000025276615,0.0000888155,0.008316094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.86281,0.120226786,0.0014825509,0.0018336353,0.008305597,0.0053414577],"domain_scores_gemma":[0.86168414,0.12326635,0.0020751855,0.0025453386,0.006244695,0.004184265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11440589,0.0004376088,0.00073312555,0.0018750795,0.01657893,0.012275865,0.0028502145,0.0036573033,0.002881603],"category_scores_gemma":[0.06990275,0.00052317197,0.0005812797,0.0017718357,0.040139567,0.0065839184,0.012417509,0.007959238,0.0001779829],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002194756,0.0007138069,0.0052757245,0.0011056021,0.000054019165,0.0006879563,0.18760332,0.0025155444,0.00024095211,0.53758925,0.024748554,0.23924586],"study_design_scores_gemma":[0.0005697805,0.0006428216,0.027810274,0.006620818,0.00013506925,0.00048230262,0.2817785,0.004818689,0.0016737647,0.2132202,0.46196815,0.00027968484],"about_ca_topic_score_codex":0.2194252,"about_ca_topic_score_gemma":0.41494521,"teacher_disagreement_score":0.7805748,"about_ca_system_score_codex":0.060684178,"about_ca_system_score_gemma":0.08575929,"threshold_uncertainty_score":0.6050434},"labels":[],"label_agreement":null},{"id":"W4366675279","doi":"10.3138/cjpe.15.008","title":"Proposition d'un modèle d'évaluation de la mise en oeuvre et des effets de la planification des programmes régionaux d'organisation des services de santé mentale au Québec","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Douglas College","funders":"","keywords":"Valuation (finance); Welfare economics; Mental health; Context (archaeology); Government (linguistics); Health services; Political science; Business; Sociology; Geography; Psychology; Economics; Finance","score_opus":0.045182805581353694,"score_gpt":0.3653610053270226,"score_spread":0.3201781997456689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13260609,0.0026597322,0.67223793,0.03552566,0.00032400084,0.0075846477,0.0024896343,0.0007244783,0.14584781],"genre_scores_gemma":[0.80980206,0.0007539838,0.17968473,0.0006970394,0.000047271693,0.004731276,0.00038769198,0.00003611387,0.0038598299],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9576651,0.033783145,0.0011330678,0.0020442316,0.0041220444,0.0012523677],"domain_scores_gemma":[0.9306692,0.05362333,0.0029369504,0.001470827,0.01000791,0.0012917616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045949046,0.0020355154,0.0016774334,0.0041773953,0.0018696665,0.009470918,0.0028176191,0.0037901627,0.0072362777],"category_scores_gemma":[0.07386454,0.00070692017,0.002339932,0.0029401234,0.0043096635,0.007104278,0.0027422144,0.0022092327,0.0004291913],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010239965,0.0008884385,0.016577631,0.0015020286,0.0009868183,0.00025390097,0.0035620772,0.42539167,0.00059592637,0.4575465,0.0041130097,0.087558016],"study_design_scores_gemma":[0.00081507594,0.0011454112,0.0068080355,0.0018384801,0.0011253455,0.00010414401,0.0029686764,0.81594676,0.0013704398,0.15281571,0.01493912,0.00012284676],"about_ca_topic_score_codex":0.0936698,"about_ca_topic_score_gemma":0.048043244,"teacher_disagreement_score":0.9063302,"about_ca_system_score_codex":0.026977435,"about_ca_system_score_gemma":0.0340876,"threshold_uncertainty_score":0.24300468},"labels":[],"label_agreement":null},{"id":"W4366675286","doi":"10.3138/cjpe.0020.003","title":"Program Evaluation in Canada Seen through the Articles Published in CJPE","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"St. Lawrence College; Université Laval","funders":"","keywords":"Honour; Audit; Political science; Library science; Sociology; Public administration; Law; Management; Computer science; Economics","score_opus":0.3053697535010307,"score_gpt":0.4944470437878705,"score_spread":0.18907729028683984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675286","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13328937,0.47091603,0.0026245464,0.10227308,0.017134896,0.000980063,0.035424933,0.0008510211,0.23650604],"genre_scores_gemma":[0.5032083,0.37632537,0.0072561554,0.008393533,0.0036894828,0.0004023476,0.009028038,0.00041602386,0.09128072],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9792164,0.002271401,0.0016344601,0.0007108988,0.014132466,0.0020343142],"domain_scores_gemma":[0.7932322,0.025953218,0.0121346675,0.0023714588,0.1572644,0.009044044],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.013752905,0.0008279095,0.0010796998,0.039771855,0.0061093,0.012317696,0.0012469711,0.0009547576,0.011966374],"category_scores_gemma":[0.07836136,0.0005103849,0.00072266976,0.07263093,0.0021566758,0.00243422,0.002263975,0.0014073477,0.0013363633],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061304204,0.00016582526,0.043134872,0.012267698,0.00028990605,0.0013548128,0.014404199,0.0006324756,0.002264576,0.009488835,0.35572687,0.5596569],"study_design_scores_gemma":[0.000026797681,0.000098466415,0.13021034,0.006586279,0.0002106519,0.000452544,0.010634871,0.0002148435,0.0020324502,0.00075285335,0.8486638,0.000116099276],"about_ca_topic_score_codex":0.81893736,"about_ca_topic_score_gemma":0.9176964,"teacher_disagreement_score":0.9862471,"about_ca_system_score_codex":0.048256643,"about_ca_system_score_gemma":0.20109467,"threshold_uncertainty_score":0.36425787},"labels":[],"label_agreement":null},{"id":"W4366675287","doi":"10.3138/cjpe.17.004","title":"L’innovation sociale, une condition pour accroître la qualité de l’action en partenariat dans le champ de la santé publique","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Technocracy; General partnership; Citizen journalism; Sociology; Quality (philosophy); Participatory action research; Political science; Welfare economics; Epistemology; Politics; Economics","score_opus":0.1111347151731183,"score_gpt":0.4342279922298852,"score_spread":0.3230932770567669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675287","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60536593,0.004080752,0.037260775,0.040513504,0.00037669193,0.0009609089,0.00042581517,0.0003427311,0.3106729],"genre_scores_gemma":[0.9918229,0.00029931462,0.0036784043,0.00023667057,0.000054847613,0.00024141467,0.000040014143,0.000015141017,0.0036112329],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9594184,0.020953909,0.001179141,0.00199162,0.013353292,0.0031034693],"domain_scores_gemma":[0.910587,0.04534701,0.0138687,0.005801748,0.018629665,0.005765851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036967147,0.0005121361,0.0006607459,0.0024892571,0.006776632,0.0122179175,0.0014155263,0.002899924,0.013410641],"category_scores_gemma":[0.054213863,0.00044062748,0.0009234123,0.0022969358,0.012950957,0.005674617,0.0062378678,0.002162393,0.0009912584],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007111129,0.0010068376,0.16289192,0.003404246,0.00063339475,0.0016269343,0.08692082,0.0046840026,0.021635951,0.4112164,0.0097385645,0.29552984],"study_design_scores_gemma":[0.00056244584,0.0027849076,0.3365233,0.0027915756,0.0005963638,0.0014389642,0.08706751,0.0071752737,0.026374184,0.18770884,0.3465443,0.00043236229],"about_ca_topic_score_codex":0.022480445,"about_ca_topic_score_gemma":0.03342396,"teacher_disagreement_score":0.036967147,"about_ca_system_score_codex":0.015394051,"about_ca_system_score_gemma":0.04524861,"threshold_uncertainty_score":0.1955033},"labels":[],"label_agreement":null},{"id":"W4366675294","doi":"10.3138/cjpe.0020.007","title":"Evaluation in Canada’s Social Services: Progress, Rifts, and Challenges","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conceptualization; Empowerment; Business; Investment (military); Service (business); Public relations; Knowledge management; Tertiary sector of the economy; Marketing; Economic growth; Economics; Political science; Computer science","score_opus":0.3307560674375689,"score_gpt":0.4735947203942487,"score_spread":0.1428386529566798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675294","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08735348,0.18977617,0.0066053844,0.5984897,0.003163983,0.00091428723,0.0007425468,0.00039692086,0.112557516],"genre_scores_gemma":[0.8323859,0.093599394,0.01863761,0.029886292,0.00097564555,0.00042900274,0.0006024138,0.00019866388,0.023285093],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9406428,0.021041576,0.003103721,0.0017636233,0.024421886,0.009026441],"domain_scores_gemma":[0.82354265,0.045295157,0.0057719643,0.0024671499,0.09553846,0.027384594],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07108818,0.00070178905,0.0012252172,0.0059498562,0.013692581,0.017395679,0.0039831325,0.0029928687,0.004789586],"category_scores_gemma":[0.070773035,0.0005737079,0.0009409909,0.008214218,0.0110410545,0.0045762463,0.008374476,0.0041241054,0.00032352345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0003956318,0.00047253328,0.026651202,0.0046257223,0.00020058069,0.0005357727,0.01378448,0.0018775787,0.00042815713,0.100749895,0.09942221,0.75085616],"study_design_scores_gemma":[0.00024557073,0.0008328798,0.15633567,0.01838,0.00025277297,0.00060728233,0.07270643,0.0052850717,0.002624099,0.03715588,0.70502955,0.0005447658],"about_ca_topic_score_codex":0.96633786,"about_ca_topic_score_gemma":0.9721376,"teacher_disagreement_score":0.9289118,"about_ca_system_score_codex":0.22502282,"about_ca_system_score_gemma":0.4947649,"threshold_uncertainty_score":0.8988637},"labels":[],"label_agreement":null},{"id":"W4366675384","doi":"10.3138/cjpe.0020.011","title":"Interview with Joe Hudson, Founding Editor of CJPE","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Canadian Identity and History","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Art","score_opus":0.07020049809053805,"score_gpt":0.3404342375389162,"score_spread":0.27023373944837814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675384","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093549374,0.009022221,0.00019464202,0.8966228,0.08827784,0.00007535465,0.00017595445,0.000059284048,0.00463645],"genre_scores_gemma":[0.011978393,0.009216893,0.0005078721,0.855934,0.053538654,0.0002554172,0.00013692453,0.00016858862,0.068263195],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967434,0.0011237105,0.00028692945,0.000395344,0.0010264545,0.00042409],"domain_scores_gemma":[0.9550422,0.012857441,0.0018933876,0.0005829031,0.018246055,0.011377995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01022837,0.0007290064,0.0012707623,0.0023671226,0.011163052,0.007089736,0.0020066537,0.009482793,0.022261674],"category_scores_gemma":[0.06884394,0.00070875627,0.0006047964,0.0026277907,0.0024344155,0.0048525813,0.0025169728,0.0180893,0.0059520146],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007566378,0.000006138798,0.00015144913,0.000040944276,0.0000015289409,0.0002034551,0.000457337,0.000008510646,0.000022084305,0.000118408985,0.9966085,0.0023741282],"study_design_scores_gemma":[0.000009888092,0.000010447283,0.00087028695,0.00019946655,0.0000050254175,0.00038007027,0.003627344,0.00003886159,0.000046634617,0.00018716734,0.9945998,0.00002492356],"about_ca_topic_score_codex":0.072658375,"about_ca_topic_score_gemma":0.15599652,"teacher_disagreement_score":0.072658375,"about_ca_system_score_codex":0.008369081,"about_ca_system_score_gemma":0.019397495,"threshold_uncertainty_score":0.14447087},"labels":[],"label_agreement":null},{"id":"W4366675407","doi":"10.3138/cjpe.016.003","title":"La participation des femmes de milieux économiquement faibles aux services prénatals: essai de modélisation","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Global Maternal and Child Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Disadvantaged; Psychosocial; Pregnancy; Prenatal care; Medicine; Psychology; Obstetrics; Environmental health; Psychiatry; Population; Economic growth; Economics","score_opus":0.1672319749606928,"score_gpt":0.42530876862190015,"score_spread":0.25807679366120734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81399363,0.001157594,0.15236022,0.003150662,0.00009128648,0.00039007128,0.00064238353,0.00016178933,0.028052336],"genre_scores_gemma":[0.964311,0.0004737604,0.031584293,0.000071366994,0.000021963378,0.0004142743,0.00023757192,0.000019395613,0.0028662535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710435,0.0021629964,0.00006494917,0.00027436335,0.00018196451,0.00021143751],"domain_scores_gemma":[0.98764616,0.010965716,0.00033971886,0.00019297376,0.00057816296,0.00027735482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060649365,0.000807771,0.0007133299,0.0011896152,0.0010243923,0.0043475307,0.0015964571,0.0015806004,0.006922689],"category_scores_gemma":[0.010173782,0.00036410414,0.0018184988,0.0010733384,0.00188246,0.0022763233,0.0019373816,0.0012928741,0.00037322234],"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":[0.0012444464,0.0013492933,0.13364609,0.0005133205,0.00072239037,0.0004366071,0.013143148,0.5874755,0.00098193,0.19059014,0.0017473638,0.068149745],"study_design_scores_gemma":[0.000119496384,0.00033907636,0.010070089,0.00018243001,0.00018748251,0.00008374179,0.0037785799,0.94961345,0.00020686741,0.03210164,0.0032713623,0.000045828336],"about_ca_topic_score_codex":0.070109755,"about_ca_topic_score_gemma":0.028928718,"teacher_disagreement_score":0.070109755,"about_ca_system_score_codex":0.004064575,"about_ca_system_score_gemma":0.0040613776,"threshold_uncertainty_score":0.13940334},"labels":[],"label_agreement":null},{"id":"W4366678314","doi":"10.3138/cjpe.017.001","title":"Les coûts de la non-évaluation des politiques de l’éducation au Québec","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université TÉLUQ; Université Laval","funders":"","keywords":"Ideology; Sociology; Interpretation (philosophy); Valuation (finance); Positive economics; Welfare economics; Relevance (law); Epistemology; Political science; Economics; Philosophy; Law","score_opus":0.6347540541420319,"score_gpt":0.5938711188532354,"score_spread":0.040882935288796496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366678314","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105188094,0.07331518,0.05484761,0.46495983,0.0023314697,0.0013922777,0.0017443782,0.0003646486,0.29585657],"genre_scores_gemma":[0.93367463,0.008676417,0.023775414,0.009663273,0.000377461,0.0010060223,0.0003004164,0.00007822493,0.022448111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8555624,0.10354166,0.003928179,0.0027467757,0.029702738,0.004518235],"domain_scores_gemma":[0.8203124,0.1286358,0.0044456027,0.0050325897,0.038599554,0.002974193],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10296227,0.00077922683,0.001190008,0.0033467046,0.0051556183,0.014325748,0.002310881,0.0034811308,0.0055618673],"category_scores_gemma":[0.14516272,0.0005127239,0.00083447853,0.0038111743,0.008744864,0.004943644,0.002870491,0.0045867697,0.000299939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00048633124,0.00023880498,0.0123858815,0.0035004965,0.00048548,0.0002805737,0.004881867,0.019522727,0.00080506806,0.6726613,0.047333956,0.23741753],"study_design_scores_gemma":[0.00086084974,0.0009129391,0.09100897,0.017537942,0.0005890562,0.00024146432,0.01044513,0.04379198,0.0052245134,0.25063702,0.5782811,0.00046905645],"about_ca_topic_score_codex":0.90076786,"about_ca_topic_score_gemma":0.8946522,"teacher_disagreement_score":0.89703774,"about_ca_system_score_codex":0.13913907,"about_ca_system_score_gemma":0.17542313,"threshold_uncertainty_score":0.9984767},"labels":[],"label_agreement":null},{"id":"W4366678674","doi":"10.3138/cjpe.0017.004","title":"Validation d’une version française du Outcome Questionnaire et évaluation d’un service de counselling en milieu clinique","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Counseling Practices and Supervision","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Cégep de l'Outaouais; University of Ottawa","funders":"","keywords":"Internal consistency; Psychology; Clinical psychology; Psychometrics; Medicine; Family medicine","score_opus":0.10181234397933883,"score_gpt":0.4034309544081539,"score_spread":0.3016186104288151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366678674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96002716,0.002070701,0.011123511,0.0023918555,0.00046992832,0.0057719927,0.0032669816,0.00021061028,0.014667242],"genre_scores_gemma":[0.9686376,0.00087638927,0.015907515,0.00050147565,0.00013851478,0.008514691,0.0021554618,0.00006313861,0.003205191],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97362095,0.013503349,0.0026813438,0.00072847045,0.008049338,0.0014166248],"domain_scores_gemma":[0.9523752,0.019363856,0.0067321365,0.0013823904,0.018104436,0.0020419487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03956454,0.0006396122,0.000772076,0.0030729778,0.0010731841,0.0016786141,0.00085724046,0.0008059964,0.002745864],"category_scores_gemma":[0.049502432,0.0002876439,0.0010446332,0.00216596,0.0010455527,0.0013021954,0.001316127,0.0011460787,0.0005481372],"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":[0.0013127604,0.0016697772,0.6280199,0.0008115256,0.000489998,0.00019990983,0.008774443,0.0012868367,0.0015161325,0.0012864714,0.008509816,0.34612244],"study_design_scores_gemma":[0.00038583344,0.0021691194,0.970392,0.00050199986,0.0001248951,0.00027686314,0.0022302766,0.0019180704,0.0009500703,0.00031148456,0.020653483,0.00008589418],"about_ca_topic_score_codex":0.027655944,"about_ca_topic_score_gemma":0.027182136,"teacher_disagreement_score":0.03956454,"about_ca_system_score_codex":0.004923557,"about_ca_system_score_gemma":0.0077384305,"threshold_uncertainty_score":0.20923978},"labels":[],"label_agreement":null},{"id":"W4366678681","doi":"10.3138/cjpe.0017.003","title":"The Pitfalls and the Potential of Early Evaluation Efforts: Lessons Learned from the Health Services Sector","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Accountability; Protocol (science); Program evaluation; Outcome (game theory); Service delivery framework; Service (business); Psychology; Public relations; Process management; Computer science; Business; Medical education; Medicine; Political science; Marketing; Alternative medicine; Public administration","score_opus":0.2971180000051674,"score_gpt":0.5015325592971431,"score_spread":0.20441455929197572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366678681","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06804227,0.08868457,0.07445431,0.7318006,0.0032443053,0.0019204833,0.000113319365,0.00066993263,0.031070186],"genre_scores_gemma":[0.77778584,0.03579507,0.13603397,0.040928554,0.0015345458,0.002648434,0.000079075544,0.00026939437,0.0049251486],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.68224657,0.27599293,0.009094464,0.0035494603,0.023488652,0.005627943],"domain_scores_gemma":[0.33863306,0.53411674,0.012267459,0.01688073,0.08451486,0.013587149],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35738865,0.0012623841,0.0017246463,0.003855799,0.00911328,0.015086489,0.0057115965,0.0066329297,0.0026527317],"category_scores_gemma":[0.35783193,0.0012814763,0.0014623062,0.0026381337,0.015794624,0.017175285,0.013350142,0.01327816,0.0005925368],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076283293,0.001113998,0.016407607,0.005866358,0.00020349302,0.0012780043,0.053452328,0.0029726296,0.00035115235,0.059389688,0.04203808,0.81616384],"study_design_scores_gemma":[0.0017041964,0.0030686134,0.047766387,0.05533019,0.000513076,0.004105741,0.15373553,0.015038676,0.0056892703,0.2980651,0.41384646,0.0011367033],"about_ca_topic_score_codex":0.032482494,"about_ca_topic_score_gemma":0.055835545,"teacher_disagreement_score":0.6426114,"about_ca_system_score_codex":0.019611448,"about_ca_system_score_gemma":0.06721988,"threshold_uncertainty_score":0.79245424},"labels":[],"label_agreement":null},{"id":"W4366678805","doi":"10.3138/cjpe.19.004","title":"Le benchmarking et l’amélioration continue","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Benchmarking; Identification (biology); Process (computing); Context (archaeology); Quality (philosophy); Process management; Business; Best practice; Computer science; Knowledge management; Marketing; Management; Economics; Geography","score_opus":0.11124375098056793,"score_gpt":0.4150975325821589,"score_spread":0.303853781601591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366678805","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045801464,0.081059225,0.076118596,0.45499322,0.006584301,0.00014283042,0.00029004857,0.0009162518,0.33409417],"genre_scores_gemma":[0.8488923,0.0276537,0.042679075,0.016968625,0.0046799425,0.0004507342,0.0003377476,0.00047153232,0.057866372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9442274,0.036271136,0.0014256706,0.0022381232,0.013767247,0.0020703443],"domain_scores_gemma":[0.97167116,0.015773568,0.0019624315,0.0032575254,0.006110837,0.0012245394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03687699,0.0013309745,0.001142252,0.0028854324,0.004675383,0.017030168,0.0019690196,0.0066647916,0.00865805],"category_scores_gemma":[0.04105089,0.00048250007,0.0010114517,0.0045836247,0.011980256,0.015234952,0.005802994,0.009964849,0.0016255234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010813065,0.00018098668,0.002298198,0.00029401507,0.00005953527,0.00023670847,0.0050846594,0.0029840071,0.00048272643,0.79434407,0.028760293,0.16516669],"study_design_scores_gemma":[0.0000694618,0.00020412316,0.004257241,0.0011694547,0.000023707498,0.00039259807,0.0047949697,0.0043452936,0.0016667834,0.19114289,0.79185325,0.000080265556],"about_ca_topic_score_codex":0.022603335,"about_ca_topic_score_gemma":0.010747501,"teacher_disagreement_score":0.03687699,"about_ca_system_score_codex":0.0138400365,"about_ca_system_score_gemma":0.010858953,"threshold_uncertainty_score":0.19502652},"labels":[],"label_agreement":null},{"id":"W4366679225","doi":"10.3138/cjpe.37.1.ed-fr","title":"Un mot de la rédactrice","year":2022,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.08457766494705582,"score_gpt":0.359384023416896,"score_spread":0.2748063584698402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366679225","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01572303,0.014425294,0.07829699,0.17486605,0.059272423,0.0008889057,0.007032306,0.011240392,0.6382547],"genre_scores_gemma":[0.09444796,0.008677844,0.054015342,0.022460349,0.015227746,0.0011963792,0.0060087116,0.0061318,0.7918339],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9718542,0.010995632,0.001174813,0.0023703952,0.012399336,0.0012058064],"domain_scores_gemma":[0.962356,0.009986596,0.0014656838,0.0035657359,0.021049181,0.0015768333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014639347,0.0021040286,0.0015811003,0.0036596064,0.0063308743,0.016321644,0.0019906445,0.0049672555,0.098644264],"category_scores_gemma":[0.0472334,0.0010531297,0.0019160614,0.0030516288,0.0035959168,0.009150139,0.004409274,0.011684465,0.03779169],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052231055,0.00019854179,0.0016096018,0.00083992997,0.00006315551,0.0006214371,0.0028239856,0.0009577069,0.0036467102,0.13573726,0.5450736,0.30790564],"study_design_scores_gemma":[0.0000554657,0.000038732458,0.0010146607,0.0002274929,0.000013983355,0.00036079096,0.0006344972,0.0005101035,0.0013116518,0.0043627373,0.9914215,0.00004825686],"about_ca_topic_score_codex":0.0916602,"about_ca_topic_score_gemma":0.055833988,"teacher_disagreement_score":0.098644264,"about_ca_system_score_codex":0.0111740995,"about_ca_system_score_gemma":0.011727081,"threshold_uncertainty_score":0.3299979},"labels":[],"label_agreement":null},{"id":"W4366679230","doi":"10.3138/cjpe.37.2.ed-en","title":"Editor’s Remarks","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.06340639280039151,"score_gpt":0.42163111870667735,"score_spread":0.35822472590628585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366679230","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001207673,0.0018905989,0.00012246269,0.40983072,0.5831584,0.000032129745,0.000109376175,0.0000716415,0.0046640052],"genre_scores_gemma":[0.001759855,0.0013905657,0.00042921727,0.6987512,0.251117,0.00008550344,0.00005211619,0.00007317682,0.046341494],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9813312,0.0018659359,0.0019526012,0.0027795814,0.009747804,0.0023228682],"domain_scores_gemma":[0.93390507,0.015711034,0.004726832,0.0031729154,0.03299663,0.009487502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016279133,0.0017288843,0.0027796202,0.0026917013,0.005521475,0.010954662,0.0051872074,0.041952375,0.03212528],"category_scores_gemma":[0.12950285,0.0012600272,0.0035075562,0.0021167598,0.0037971223,0.0037427738,0.002905414,0.03917884,0.02425196],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014862877,0.0000062718104,0.000048036964,0.000033521745,0.000008704981,0.00009070115,0.00001982888,0.000012923267,0.00002543084,0.00043670472,0.9974598,0.0018431777],"study_design_scores_gemma":[0.000044998877,0.000013533166,0.00042774118,0.00020934436,0.000027151453,0.00015480194,0.00010240931,0.00006612281,0.00010955996,0.0008590309,0.9979518,0.000033488133],"about_ca_topic_score_codex":0.016080853,"about_ca_topic_score_gemma":0.037133094,"teacher_disagreement_score":0.041952375,"about_ca_system_score_codex":0.008307493,"about_ca_system_score_gemma":0.01534411,"threshold_uncertainty_score":0.10746974},"labels":[],"label_agreement":null},{"id":"W4366679319","doi":"10.3138/cjpe.35.2.v","title":"Editor’s Remarks","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology; Business","score_opus":0.3130698758640696,"score_gpt":0.5203254987844013,"score_spread":0.20725562292033167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366679319","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015150067,0.0028178198,0.0006331058,0.17370543,0.799202,0.000062160994,0.0003851914,0.00029359653,0.02274924],"genre_scores_gemma":[0.0037147817,0.005350847,0.0022436685,0.28294617,0.43091407,0.00024771102,0.0006327707,0.0007628571,0.27318704],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98686975,0.0012863125,0.0012986967,0.0023791802,0.00684538,0.0013206964],"domain_scores_gemma":[0.9485488,0.007732955,0.0025348614,0.003701853,0.032353837,0.0051277736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009801211,0.0017397278,0.0014697389,0.0034399556,0.0043442217,0.012406035,0.004849035,0.011649046,0.14512321],"category_scores_gemma":[0.07096635,0.0007382456,0.0023669829,0.0027235784,0.0025404696,0.008683663,0.0045414036,0.013323945,0.103916034],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010106271,0.000007463611,0.000038941507,0.00007396696,0.000003514489,0.00006263626,0.000038014623,0.000016317425,0.000054880362,0.0013480292,0.99087733,0.007468728],"study_design_scores_gemma":[0.0000050316903,0.0000050314075,0.00007331655,0.00012503185,0.0000028838765,0.00007061248,0.000069919915,0.00002346124,0.000083152096,0.0006709051,0.9988631,0.0000074848085],"about_ca_topic_score_codex":0.0022986159,"about_ca_topic_score_gemma":0.0043702987,"teacher_disagreement_score":0.14512321,"about_ca_system_score_codex":0.004571151,"about_ca_system_score_gemma":0.008785435,"threshold_uncertainty_score":0.4854855},"labels":[],"label_agreement":null},{"id":"W4366679323","doi":"10.3138/cjpe.36.1.intro-fr","title":"Un mot de la rédactrice","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Political science","score_opus":0.08961796751011986,"score_gpt":0.36937774345787855,"score_spread":0.2797597759477587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366679323","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021863708,0.033441473,0.07252277,0.24147849,0.024940697,0.0020734055,0.0015349546,0.0012125648,0.60093194],"genre_scores_gemma":[0.30780846,0.031542424,0.13759235,0.07733462,0.006255006,0.0043827705,0.0017089638,0.0020819113,0.43129346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9383944,0.03579036,0.0027620108,0.0037331053,0.017477034,0.0018430605],"domain_scores_gemma":[0.9186272,0.037566546,0.0042680847,0.008517028,0.026918577,0.004102542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037756156,0.0012807992,0.001229602,0.0033644997,0.006359414,0.014052002,0.0022385952,0.004765676,0.041783836],"category_scores_gemma":[0.09312139,0.0007953675,0.001465299,0.0035299808,0.0086599775,0.014029467,0.009666852,0.008937157,0.010990586],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035268665,0.00022286536,0.0039371727,0.004662838,0.00010610327,0.0003705152,0.040024843,0.00044871264,0.002940767,0.28073746,0.18948558,0.47671044],"study_design_scores_gemma":[0.00003593082,0.0002000747,0.0025820872,0.002930476,0.000055151042,0.00032924168,0.009330155,0.00027569107,0.0018278371,0.027543629,0.95481324,0.00007649198],"about_ca_topic_score_codex":0.008259867,"about_ca_topic_score_gemma":0.0109518785,"teacher_disagreement_score":0.041783836,"about_ca_system_score_codex":0.008857036,"about_ca_system_score_gemma":0.018437369,"threshold_uncertainty_score":0.19967604},"labels":[],"label_agreement":null},{"id":"W4366706367","doi":"10.3138/cjpe.68217","title":"Sheila B. Robinson and Kimberly Firth Leonard. (2019). <i>Designing Quality Survey Questions</i> .","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Firth; Quality (philosophy); Sociology; Philosophy; Epistemology; Oceanography; Geology","score_opus":0.4963673742273779,"score_gpt":0.5108915850017431,"score_spread":0.01452421077436522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366706367","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029010656,0.08495538,0.04076052,0.7974224,0.023008894,0.0013711887,0.0047759633,0.0009527876,0.043851726],"genre_scores_gemma":[0.07595223,0.22403485,0.15193105,0.30970475,0.00866213,0.009791792,0.006455299,0.0016889343,0.21177906],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9837663,0.008706472,0.0011088023,0.0005578083,0.0055655614,0.00029496368],"domain_scores_gemma":[0.8756978,0.06493307,0.0055014812,0.0025009154,0.045350403,0.0060162293],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04918604,0.00086312124,0.00070211757,0.004007521,0.0024022623,0.0035455162,0.0019255669,0.00271335,0.030767115],"category_scores_gemma":[0.17864342,0.0011779565,0.0006050766,0.0040997774,0.0016180797,0.004262003,0.002306761,0.0059623797,0.023734277],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046597725,0.000025677668,0.0028085534,0.000647697,0.000012601432,0.000025404666,0.0007838558,0.00003857543,0.00011451256,0.0022132685,0.81814027,0.17514299],"study_design_scores_gemma":[0.00008963011,0.00010980779,0.012649875,0.0075404183,0.00008401401,0.00010221409,0.002910619,0.00029483577,0.0006144504,0.008522465,0.9669891,0.00009257234],"about_ca_topic_score_codex":0.05784771,"about_ca_topic_score_gemma":0.13199171,"teacher_disagreement_score":0.95081395,"about_ca_system_score_codex":0.002455525,"about_ca_system_score_gemma":0.01666426,"threshold_uncertainty_score":0.26012373},"labels":[],"label_agreement":null},{"id":"W4366706691","doi":"10.3138/cjpe.34.3.521","title":"Peer Reviewers for Volume 34 / Examinateurs des manuscrits du volume 34","year":2020,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Psychology; Art; Thermodynamics; Physics","score_opus":0.44556158096013765,"score_gpt":0.4911233468799333,"score_spread":0.04556176591979566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366706691","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01426341,0.030530225,0.023984585,0.18618177,0.5184828,0.007788865,0.0071812915,0.007648211,0.20393886],"genre_scores_gemma":[0.06067723,0.023228126,0.0378653,0.023918798,0.14462148,0.0040375446,0.0078041838,0.004696654,0.6931508],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9711604,0.007982126,0.0022346198,0.0013595475,0.016024506,0.0012388257],"domain_scores_gemma":[0.68648857,0.015823957,0.008565571,0.006435243,0.26817083,0.014515893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020319872,0.0013828981,0.0022305239,0.008370513,0.0036517975,0.007231802,0.0022984662,0.0029141728,0.1357425],"category_scores_gemma":[0.1169099,0.00074437185,0.0012393686,0.004777718,0.001236823,0.0029049541,0.0025661439,0.0024230718,0.085240826],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047723115,0.00001927863,0.00041060822,0.00028092175,0.000010213231,0.00005871858,0.00006799687,0.000020738431,0.00033614767,0.00023140323,0.9582965,0.040219814],"study_design_scores_gemma":[0.0000437286,0.00008272306,0.0036396915,0.00053818605,0.000024209736,0.00031233174,0.00026789366,0.00032632504,0.00062224985,0.00067193975,0.9934355,0.000035183526],"about_ca_topic_score_codex":0.0032193412,"about_ca_topic_score_gemma":0.011592816,"teacher_disagreement_score":0.1357425,"about_ca_system_score_codex":0.0022107773,"about_ca_system_score_gemma":0.011944901,"threshold_uncertainty_score":0.4541039},"labels":[],"label_agreement":null},{"id":"W4366707345","doi":"10.3138/cjpe.34.1.vii","title":"Un mot de la rédactrice","year":2019,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.06508585322297354,"score_gpt":0.353867338390934,"score_spread":0.28878148516796043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366707345","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016189527,0.014512769,0.078742415,0.18695438,0.060059447,0.0009083907,0.0067107035,0.010993169,0.62492925],"genre_scores_gemma":[0.09926661,0.008776628,0.055671897,0.024232125,0.015897356,0.0012249358,0.005807366,0.0060215076,0.78310156],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97003114,0.0117748445,0.0012650588,0.0024756545,0.013181938,0.0012714103],"domain_scores_gemma":[0.95919967,0.01080448,0.0016036207,0.0039050002,0.02280991,0.0016773874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015568388,0.0020982209,0.0015869696,0.003732059,0.006460701,0.016527472,0.0020277356,0.0050211567,0.09383516],"category_scores_gemma":[0.050004885,0.0010522612,0.0019417679,0.0030762162,0.003765618,0.009375949,0.004575543,0.0119261425,0.03554974],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005362339,0.00020538288,0.0017169369,0.00087620167,0.00006671231,0.0006280699,0.0029670554,0.00095906685,0.0037818842,0.13849735,0.53486085,0.31490433],"study_design_scores_gemma":[0.000056793808,0.000040857725,0.0010672702,0.00023937416,0.00001471494,0.0003733002,0.00067655847,0.0005211286,0.0013626569,0.0045457776,0.99105173,0.000049716],"about_ca_topic_score_codex":0.089553714,"about_ca_topic_score_gemma":0.05501051,"teacher_disagreement_score":0.09383516,"about_ca_system_score_codex":0.011406273,"about_ca_system_score_gemma":0.012104205,"threshold_uncertainty_score":0.3139099},"labels":[],"label_agreement":null},{"id":"W4366721346","doi":"10.3138/cjpe.017.004","title":"Paying Doctors: Impact of a Change in Remuneration Method at a Canadian Academic Health Centre","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Remuneration; Subsidy; Service (business); Payment; Accountability; Work (physics); Earnings; Business; Public relations; Political science; Medical education; Accounting; Finance; Medicine; Marketing; Law","score_opus":0.5138186901732057,"score_gpt":0.5921630760505969,"score_spread":0.07834438587739123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8387849,0.0023272806,0.001904794,0.068929374,0.0016324802,0.0019767173,0.00075343397,0.000247675,0.083443366],"genre_scores_gemma":[0.9763772,0.0005447248,0.0032292057,0.0069169533,0.00024847183,0.0002420235,0.0002125509,0.00004622003,0.012182636],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9612849,0.008172903,0.0011486433,0.002137787,0.017241364,0.010014381],"domain_scores_gemma":[0.9416748,0.010497624,0.0036645883,0.0023132632,0.017709333,0.02414032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019915879,0.0006678772,0.0004827959,0.0032704338,0.015600064,0.008247604,0.006248598,0.004558649,0.007928806],"category_scores_gemma":[0.059143566,0.0006831992,0.0008468356,0.0033303797,0.004682869,0.0014313427,0.00530141,0.0037608694,0.00071704097],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047581852,0.0059928084,0.22115159,0.0011916127,0.0004398695,0.0023587858,0.03138761,0.0077988883,0.005189715,0.05562287,0.11014076,0.55396736],"study_design_scores_gemma":[0.0026070212,0.003670033,0.7639723,0.0011248479,0.0005276488,0.0011285222,0.027383454,0.009139662,0.0033091682,0.0037063155,0.18266204,0.0007690973],"about_ca_topic_score_codex":0.95406306,"about_ca_topic_score_gemma":0.97032654,"teacher_disagreement_score":0.95406306,"about_ca_system_score_codex":0.18554302,"about_ca_system_score_gemma":0.27936086,"threshold_uncertainty_score":0.94465464},"labels":[],"label_agreement":null},{"id":"W4366721381","doi":"10.3138/cjpe.15.006","title":"Logic Models in Primary Care Reform: Navigating the Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Primary care; Logic model; Nova scotia; Strengths and weaknesses; Quality (philosophy); Political science; Public administration; Process management; Business; Economic growth; Medicine; Psychology; Sociology; Economics; Family medicine","score_opus":0.4326891670577493,"score_gpt":0.5423916433560159,"score_spread":0.10970247629826657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035915997,0.008623664,0.7875485,0.09559957,0.00033039,0.0010638521,0.0003231409,0.0005332466,0.070061654],"genre_scores_gemma":[0.5495127,0.0036930093,0.43884346,0.0036921815,0.00026208803,0.0018106318,0.00023283999,0.00012312648,0.0018299634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.83762866,0.14902061,0.0025070903,0.001702791,0.0076830997,0.0014577139],"domain_scores_gemma":[0.56654334,0.40036082,0.007638621,0.005654497,0.017163852,0.0026387998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11063437,0.0014708632,0.0023309195,0.006006106,0.0039119683,0.017431365,0.0035935545,0.003900321,0.0049617956],"category_scores_gemma":[0.2325443,0.0012367954,0.0015528181,0.005197979,0.020192502,0.023511413,0.007228509,0.007977723,0.00046793048],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011605528,0.00012445833,0.0015196075,0.0005606399,0.00007074548,0.00009797405,0.0015416179,0.032582894,0.00007774511,0.9154327,0.0030325167,0.044843078],"study_design_scores_gemma":[0.00008100703,0.000057257384,0.0001711922,0.00057872274,0.00003127528,0.00002304015,0.0010992627,0.058199972,0.00016134494,0.9340514,0.0055110184,0.000034528304],"about_ca_topic_score_codex":0.0313589,"about_ca_topic_score_gemma":0.029856874,"teacher_disagreement_score":0.11063437,"about_ca_system_score_codex":0.028512713,"about_ca_system_score_gemma":0.031260237,"threshold_uncertainty_score":0.58509743},"labels":[],"label_agreement":null},{"id":"W4366721395","doi":"10.3138/cjpe.0017.007","title":"Introducing Program Teams to Logic Models: Facilitating the Learning Process","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"University of Ottawa","keywords":"Logic model; Process (computing); Key (lock); Computer science; Articulation (sociology); Point (geometry); Facilitation; Knowledge management; Process management; Management science; Psychology; Business; Engineering; Sociology; Political science; Mathematics","score_opus":0.367515472877912,"score_gpt":0.5381391714975737,"score_spread":0.17062369861966176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15633462,0.00025828995,0.7568213,0.014749601,0.00037888144,0.002181063,0.00012994684,0.0028304516,0.06631594],"genre_scores_gemma":[0.34985834,0.0005125292,0.6360174,0.0015548735,0.00013955099,0.0020667096,0.00025326334,0.00032741812,0.009269984],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9811933,0.015402426,0.0003172448,0.000801176,0.0015980073,0.0006878796],"domain_scores_gemma":[0.941784,0.047085077,0.00166306,0.0032040507,0.0032356554,0.003028233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021292537,0.0013368891,0.0005395665,0.0015445931,0.0023585428,0.0066589066,0.0030332764,0.002313236,0.012139504],"category_scores_gemma":[0.04848566,0.00073759054,0.0009366276,0.0009986645,0.002606616,0.008690548,0.00987584,0.0045305924,0.0028232208],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007590596,0.009188925,0.007040577,0.0015972327,0.00006533417,0.0014339549,0.12599272,0.01463026,0.012210256,0.085520476,0.0603227,0.6812385],"study_design_scores_gemma":[0.0013263951,0.004943251,0.006399428,0.004282466,0.00018560071,0.0023787306,0.09157533,0.14208965,0.030556928,0.28948864,0.42624712,0.0005264465],"about_ca_topic_score_codex":0.00095911336,"about_ca_topic_score_gemma":0.0016276583,"teacher_disagreement_score":0.021292537,"about_ca_system_score_codex":0.0022853937,"about_ca_system_score_gemma":0.0051067546,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4366721445","doi":"10.3138/cjpe.0017.001","title":"Understanding Economic Evaluations: A Guide for Health and Human Services","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Economic evaluation; Dissemination; Perspective (graphical); Psychological intervention; Field (mathematics); Cost–benefit analysis; Management science; Public economics; Risk analysis (engineering); Computer science; Economics; Business; Political science; Psychology; Microeconomics","score_opus":0.4122690020583899,"score_gpt":0.44270027999454403,"score_spread":0.030431277936154133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000794167,0.037248805,0.7715187,0.073309295,0.0038467643,0.01318623,0.0088887075,0.005505944,0.085701294],"genre_scores_gemma":[0.0076136217,0.03489128,0.90706795,0.006954289,0.0016669049,0.024659023,0.003126304,0.001206137,0.0128144715],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.91965485,0.06124089,0.009357492,0.0008905357,0.00802424,0.0008319401],"domain_scores_gemma":[0.71923196,0.23906548,0.0062854714,0.007555578,0.02505416,0.0028073208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.118413,0.0056761294,0.006175924,0.012741408,0.0017692577,0.0132076815,0.0077814157,0.01000832,0.047789637],"category_scores_gemma":[0.21383084,0.0039258692,0.0036671234,0.014064281,0.005563078,0.008854575,0.004537581,0.015195341,0.020202937],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001963242,0.00031091884,0.0004844505,0.0062606367,0.00036936716,0.00036809559,0.0013433956,0.010145148,0.00033685815,0.24392429,0.50153977,0.23472066],"study_design_scores_gemma":[0.00027522285,0.00016257844,0.00052938145,0.009910971,0.00011743098,0.00026505333,0.0010071286,0.011494758,0.00031868127,0.26535007,0.7104485,0.000120103134],"about_ca_topic_score_codex":0.009104232,"about_ca_topic_score_gemma":0.0075280997,"teacher_disagreement_score":0.118413,"about_ca_system_score_codex":0.00786305,"about_ca_system_score_gemma":0.025343852,"threshold_uncertainty_score":0.62623525},"labels":[],"label_agreement":null},{"id":"W4366721600","doi":"10.3138/cjpe.15.004","title":"Is the Bottom Line “Impact” or Profits? A Rejoinder","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Regional Economics and Spatial Analysis","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Line (geometry); Economics; Mathematics; Geometry","score_opus":0.16445815606875808,"score_gpt":0.3337133497594052,"score_spread":0.16925519369064712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721600","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005367821,0.0028505628,0.00092705176,0.98003685,0.0074955,0.0000056036242,0.000028861728,0.000027159305,0.008091685],"genre_scores_gemma":[0.05941066,0.005648437,0.0030305367,0.8718242,0.02996371,0.00007476439,0.000051614566,0.00016693962,0.02982915],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906234,0.002876895,0.00057253503,0.002053687,0.0033441524,0.00052939967],"domain_scores_gemma":[0.9677536,0.019045822,0.00068847626,0.0022099186,0.008861747,0.0014404178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014117489,0.000757189,0.0014910224,0.0010394605,0.0043758834,0.011233348,0.0038976208,0.023340192,0.005587646],"category_scores_gemma":[0.047254145,0.0005419736,0.00094664085,0.0010110601,0.030356396,0.018309109,0.005444935,0.05504109,0.003341795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047847738,0.000023920162,0.00044372492,0.000055377244,0.000025390085,0.00009355954,0.0012961132,0.00011078528,0.00010989915,0.45169547,0.5269581,0.019139834],"study_design_scores_gemma":[0.000031047213,0.0000319273,0.00060141244,0.0002538832,0.000018952556,0.00012573595,0.0021006337,0.00025657253,0.00017361708,0.35630438,0.6400486,0.00005322213],"about_ca_topic_score_codex":0.012068086,"about_ca_topic_score_gemma":0.013610525,"teacher_disagreement_score":0.023340192,"about_ca_system_score_codex":0.00420643,"about_ca_system_score_gemma":0.0056186486,"threshold_uncertainty_score":0.074661314},"labels":[],"label_agreement":null},{"id":"W4366722842","doi":"10.3138/cjpe.0017.006","title":"Preparing Nonprofits for New Accountability Demands","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Accountability; Transparency (behavior); Mandate; Government (linguistics); Public relations; Business; Corporate governance; Context (archaeology); Public administration; Political science; Finance","score_opus":0.4401471567317869,"score_gpt":0.558760116059299,"score_spread":0.11861295932751209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366722842","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041917935,0.0014833929,0.013133563,0.8178988,0.0047844136,0.0006423848,0.00008948836,0.00043927575,0.11961077],"genre_scores_gemma":[0.8212199,0.0030474574,0.020340625,0.06973874,0.004606206,0.0008470131,0.00025081798,0.00022080845,0.07972834],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95735526,0.018577978,0.0011198375,0.0013866669,0.011016915,0.010543383],"domain_scores_gemma":[0.7867095,0.061912365,0.013017939,0.010017891,0.057788555,0.07055376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.065220594,0.00040540544,0.00044004296,0.002030729,0.014902681,0.021382933,0.0027849306,0.007434697,0.014253767],"category_scores_gemma":[0.09983563,0.00047117705,0.0005277512,0.0015524529,0.008816408,0.008949721,0.013332291,0.00906067,0.001862876],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008821533,0.00047453187,0.012171293,0.0004130187,0.000032632423,0.0009452122,0.016220164,0.0019090826,0.0011918795,0.34244785,0.44256896,0.18153709],"study_design_scores_gemma":[0.00009616759,0.00015692125,0.009390992,0.00083327934,0.000014862099,0.00032747394,0.03525698,0.002070157,0.0012320509,0.12157651,0.82892734,0.00011724089],"about_ca_topic_score_codex":0.032846626,"about_ca_topic_score_gemma":0.067346625,"teacher_disagreement_score":0.065220594,"about_ca_system_score_codex":0.023446733,"about_ca_system_score_gemma":0.15239277,"threshold_uncertainty_score":0.34492362},"labels":[],"label_agreement":null},{"id":"W4366722964","doi":"10.3138/cjpe.016.006","title":"An Evaluation Framework for the Maison Decision House Substance Abuse Treatment Program","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Substance abuse; Presentation (obstetrics); Abstinence; Intervention (counseling); Program evaluation; Psychology; Substance abuse treatment; Computer science; Applied psychology; Medicine; Psychiatry; Political science","score_opus":0.4319493016960513,"score_gpt":0.5692073647062006,"score_spread":0.1372580630101493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366722964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021833573,0.0058138324,0.79757,0.031560045,0.0005402861,0.037085224,0.0016940965,0.0007677663,0.10313519],"genre_scores_gemma":[0.12365363,0.0008923991,0.850735,0.0011976673,0.00008218567,0.01896292,0.0004475704,0.000041434112,0.0039872397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.83340037,0.13191012,0.009484444,0.0028598672,0.019293081,0.003052137],"domain_scores_gemma":[0.92365825,0.04128277,0.0038161462,0.0014750249,0.027463969,0.0023038443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1529129,0.0018440877,0.0018634514,0.0122339325,0.0052117235,0.012157021,0.0034228375,0.0038055768,0.0062782713],"category_scores_gemma":[0.08315117,0.00084674725,0.002178412,0.005489175,0.0046111955,0.0065620854,0.004634038,0.0034798607,0.0008784659],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044519224,0.00090157625,0.0032252127,0.0020518801,0.00014715435,0.00031749438,0.0031513902,0.03903068,0.00057234406,0.7757938,0.02132255,0.15304069],"study_design_scores_gemma":[0.0018061362,0.004490494,0.0075035812,0.015441978,0.00059724035,0.00045694024,0.013263072,0.2931352,0.0039710207,0.45502675,0.20375411,0.0005535219],"about_ca_topic_score_codex":0.036297362,"about_ca_topic_score_gemma":0.040797107,"teacher_disagreement_score":0.1529129,"about_ca_system_score_codex":0.0394933,"about_ca_system_score_gemma":0.052401006,"threshold_uncertainty_score":0.80869037},"labels":[],"label_agreement":null},{"id":"W4366723444","doi":"10.3138/cjpe.019.006","title":"The Lay of the Land: Evaluation Practice in Canada Today","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health Canada; University of Waterloo; Treasury Board of Canada Secretariat; Government of Canada; Ministry of Education, Recreation and Sports; Ministry of Children, Community and Social Services","funders":"","keywords":"Blueprint; Public relations; Rigour; General partnership; Variety (cybernetics); Psychology; Program evaluation; Competence (human resources); Political science; Medical education; Sociology; Computer science; Social psychology; Medicine; Public administration; Engineering","score_opus":0.22766863648326166,"score_gpt":0.5077868401683105,"score_spread":0.2801182036850489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723444","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26779166,0.06977011,0.011424125,0.5181228,0.0021481416,0.0005577259,0.00046300446,0.0005046148,0.12921777],"genre_scores_gemma":[0.95619905,0.011206483,0.007118754,0.012720135,0.0001361078,0.00010627629,0.0001112509,0.00014002994,0.012261916],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95343316,0.018737558,0.0023407356,0.002720642,0.015122498,0.0076453686],"domain_scores_gemma":[0.8678962,0.029023584,0.005405185,0.0029405002,0.072322644,0.022411903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0414603,0.00036979123,0.0008504559,0.003753958,0.028604334,0.015683386,0.0038173923,0.0028535775,0.0036611718],"category_scores_gemma":[0.081521794,0.00065036793,0.0004701882,0.007945572,0.014670587,0.0036056838,0.0074982573,0.00419044,0.00027350645],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00048268784,0.00031890365,0.08389584,0.0022693449,0.00017354108,0.0019540507,0.13380314,0.0023721268,0.0017829849,0.0701118,0.15566854,0.54716706],"study_design_scores_gemma":[0.00007907645,0.00020220494,0.16957715,0.004248861,0.000120051576,0.0005325184,0.23327696,0.003307701,0.0017085663,0.016572993,0.56996477,0.00040914086],"about_ca_topic_score_codex":0.97932005,"about_ca_topic_score_gemma":0.9874286,"teacher_disagreement_score":0.7795285,"about_ca_system_score_codex":0.22047152,"about_ca_system_score_gemma":0.4262967,"threshold_uncertainty_score":0.90414256},"labels":[],"label_agreement":null},{"id":"W4366723551","doi":"10.3138/cjpe.0020.009","title":"Evaluating School Improvement in Canada: A Case Example","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Shared Health","funders":"","keywords":"Work (physics); Action (physics); Management science; Psychology; Engineering ethics; Process management; Political science; Business; Engineering","score_opus":0.4300939707557752,"score_gpt":0.5277537046643593,"score_spread":0.09765973390858412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67776185,0.008318827,0.016902953,0.051694866,0.0004592322,0.0027140903,0.0010495677,0.00033395234,0.24076472],"genre_scores_gemma":[0.96231836,0.003921584,0.01868228,0.001823765,0.0000406154,0.00035752376,0.00017239491,0.000041512594,0.012642011],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98600996,0.0057435143,0.0004466476,0.0003524893,0.0040389886,0.0034083712],"domain_scores_gemma":[0.98718923,0.0033984066,0.00045852744,0.0003161512,0.006464973,0.0021727711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006715495,0.0006960014,0.00063426327,0.002252575,0.01949128,0.0050747255,0.0022971272,0.0038214254,0.0024509367],"category_scores_gemma":[0.013642706,0.00035820933,0.00076933036,0.007479338,0.003519831,0.0011627022,0.0032985243,0.0028068612,0.0002585755],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008732962,0.0037259602,0.12005438,0.0028521798,0.00025904118,0.095538735,0.123581946,0.041955676,0.0028969531,0.19970731,0.08569396,0.3228606],"study_design_scores_gemma":[0.00060064666,0.0015367853,0.12054501,0.0034505676,0.0004834734,0.01751044,0.28396267,0.04466803,0.006929276,0.021449301,0.49837056,0.0004932442],"about_ca_topic_score_codex":0.9652263,"about_ca_topic_score_gemma":0.9825832,"teacher_disagreement_score":0.9080779,"about_ca_system_score_codex":0.091922104,"about_ca_system_score_gemma":0.11910085,"threshold_uncertainty_score":0.6669447},"labels":[],"label_agreement":null},{"id":"W4366723919","doi":"10.3138/cjpe.016.004","title":"Participant Commitment to the Principles Taught in a Workplace Leadership Seminar in Relation to Personality Type","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Personality; Introspection; Personality type; Inclusion (mineral); Relation (database); Applied psychology; Social psychology; Corporation; Computer science","score_opus":0.49404771594473235,"score_gpt":0.4416524933340543,"score_spread":0.05239522261067803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99939334,0.000015240952,0.00009276618,0.0000344837,0.0000058984583,0.000018618659,0.000019615492,0.0000020422158,0.0004179055],"genre_scores_gemma":[0.9990658,0.000023179125,0.00025078832,0.00002625204,0.0000046492846,0.00006302464,0.000034352186,0.0000020266832,0.000529933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99760854,0.001270474,0.00019057246,0.00016957335,0.00048293642,0.00027798585],"domain_scores_gemma":[0.9773144,0.011023627,0.004855598,0.0007371715,0.0031137886,0.0029554004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047525535,0.00015826408,0.00019938569,0.0004889064,0.0007376721,0.0008654089,0.00028990672,0.00036285515,0.0027757303],"category_scores_gemma":[0.023135161,0.00019358014,0.00020979607,0.00023584512,0.0003232811,0.00029216256,0.00094159716,0.00086068944,0.00035529496],"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":[0.0011929709,0.0014547997,0.9518695,0.00009303195,0.00006089628,0.00018608705,0.014762819,0.00017539342,0.0048381514,0.000084940504,0.00031045984,0.024970926],"study_design_scores_gemma":[0.000029718849,0.0012893783,0.98741406,0.000027454136,0.000020703952,0.00017355074,0.008650865,0.00038841635,0.0012392749,0.00009953063,0.00064948347,0.000017398066],"about_ca_topic_score_codex":0.0006876211,"about_ca_topic_score_gemma":0.0015840634,"teacher_disagreement_score":0.0047525535,"about_ca_system_score_codex":0.00029792465,"about_ca_system_score_gemma":0.00058668375,"threshold_uncertainty_score":0.025134146},"labels":[],"label_agreement":null},{"id":"W4366723971","doi":"10.3138/cjpe.69574","title":"Strategies for Mentoring and Advising Evaluation Graduate Students of Colour","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ethnic group; Graduate students; Competence (human resources); Psychology; Salient; Cultural competence; Pedagogy; Medical education; Facilitation; Identity (music); Sociology; Social psychology; Medicine; Political science","score_opus":0.6206350525934264,"score_gpt":0.6121351996873615,"score_spread":0.00849985290606492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723971","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3166333,0.004351654,0.18927376,0.32980728,0.0036093753,0.011039301,0.00014368644,0.004115926,0.14102572],"genre_scores_gemma":[0.6604341,0.002683945,0.28882614,0.014030714,0.000885881,0.0050797765,0.000100301506,0.00024378973,0.027715286],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94006246,0.04655019,0.0023993521,0.0015034069,0.005568607,0.0039159274],"domain_scores_gemma":[0.88055193,0.043475352,0.009642871,0.008723272,0.023276461,0.03433007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08626521,0.0011521045,0.00053267187,0.002653029,0.009596082,0.00998917,0.0044807186,0.0045630196,0.0104048615],"category_scores_gemma":[0.11938839,0.00069875125,0.00084564945,0.001234063,0.0039913966,0.0057616397,0.020099597,0.0061281836,0.003127837],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001880758,0.002514324,0.013042257,0.00064757233,0.000050731604,0.0017336993,0.13214183,0.0006556004,0.0022434858,0.009140532,0.072595626,0.76504624],"study_design_scores_gemma":[0.00040938228,0.0031987021,0.021285484,0.0044045206,0.00013213365,0.0038372823,0.5211771,0.004577505,0.007896773,0.03661672,0.39598906,0.00047533924],"about_ca_topic_score_codex":0.001645405,"about_ca_topic_score_gemma":0.006382902,"teacher_disagreement_score":0.08626521,"about_ca_system_score_codex":0.0047087725,"about_ca_system_score_gemma":0.022203691,"threshold_uncertainty_score":0.4562195},"labels":[],"label_agreement":null},{"id":"W4366724034","doi":"10.3138/cjpe.019.001","title":"Toward a Best Practice for Evaluating the Impact of Government Programs on Job Creation","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Industry Canada","keywords":"Government (linguistics); Interpretation (philosophy); Strengths and weaknesses; Computer science; Management science; Engineering; Psychology","score_opus":0.5293612574148838,"score_gpt":0.6057482510986992,"score_spread":0.07638699368381541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366724034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09028004,0.08551733,0.67350215,0.046877366,0.0018110862,0.01163848,0.0027475301,0.0036299308,0.08399603],"genre_scores_gemma":[0.13810858,0.011644207,0.84396154,0.0012007155,0.0001063167,0.0031884322,0.00044599109,0.00011897088,0.0012252146],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8711482,0.07261737,0.01265225,0.0027661698,0.039837502,0.0009784382],"domain_scores_gemma":[0.75559145,0.14452621,0.014639815,0.011657592,0.07156159,0.002023294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1680062,0.0028255763,0.004129073,0.031794105,0.0027373936,0.013272027,0.0059489817,0.003953441,0.00423664],"category_scores_gemma":[0.22856022,0.0012083787,0.0030907951,0.014078718,0.0034968508,0.007193866,0.0042781984,0.0036179759,0.0019958292],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050580094,0.0014064412,0.029953917,0.023084758,0.0017144355,0.00040922276,0.0043193162,0.00884143,0.002016489,0.030396199,0.012250124,0.8851019],"study_design_scores_gemma":[0.0023794195,0.0067279567,0.10427959,0.18783867,0.008337312,0.0032450173,0.051651806,0.07186404,0.029532813,0.29463288,0.23828864,0.0012218674],"about_ca_topic_score_codex":0.008672764,"about_ca_topic_score_gemma":0.012845691,"teacher_disagreement_score":0.1680062,"about_ca_system_score_codex":0.008723243,"about_ca_system_score_gemma":0.018504601,"threshold_uncertainty_score":0.8885123},"labels":[],"label_agreement":null},{"id":"W4366724104","doi":"10.3138/cjpe.019.004","title":"Analyser le degré d’intégration de l’approche écologique dans les programmes de promotion de la santé: le cas des programmations de réduction de tabagisme de deux directions de la santé publique québécoises","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Environmental and Social Impact Assessments","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Santé Montérégie; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; Université de Montréal","funders":"","keywords":"Public health; Promotion (chess); Health promotion; Political science; Humanities; Sociology; Nursing; Medicine; Philosophy","score_opus":0.03607927942929266,"score_gpt":0.3672976578804679,"score_spread":0.33121837845117524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366724104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733925,0.00058011245,0.005762249,0.003065361,0.000020376518,0.0008220211,0.0006749643,0.000040571143,0.015641788],"genre_scores_gemma":[0.9896646,0.00025982712,0.007187966,0.00016969659,0.000013443047,0.0004657451,0.0003123288,0.000009974678,0.0019164237],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98056054,0.012772891,0.00039195525,0.0005658989,0.0038617607,0.001846966],"domain_scores_gemma":[0.9764559,0.01092357,0.0026759915,0.0008195404,0.0076574027,0.0014675339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020035,0.00059290713,0.00044377908,0.0027300462,0.0011799391,0.0025957958,0.0008986738,0.0008558285,0.0033419477],"category_scores_gemma":[0.032799464,0.00028868846,0.00081861,0.003860016,0.0011270022,0.00091264985,0.0017836179,0.0007849453,0.00020921057],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010210708,0.0014396198,0.7791027,0.0008613428,0.0007505146,0.00024633348,0.0055769333,0.03214953,0.001921779,0.0081302,0.0018876485,0.16691238],"study_design_scores_gemma":[0.000091936585,0.0008239744,0.967991,0.000271451,0.00022823829,0.00003577214,0.0031422076,0.018355517,0.0008531868,0.000769289,0.0074134357,0.000024081368],"about_ca_topic_score_codex":0.5192096,"about_ca_topic_score_gemma":0.6099876,"teacher_disagreement_score":0.48079038,"about_ca_system_score_codex":0.023873512,"about_ca_system_score_gemma":0.030091666,"threshold_uncertainty_score":0.9672437},"labels":[],"label_agreement":null},{"id":"W4366724861","doi":"10.3138/cjpe.15.002","title":"Caught in the Web: Piloting a Methodology to Assess Community Capacity in a Rural Heart Health Project","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Community Health and Development","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Fraser Health","funders":"","keywords":"Capacity building; Agency (philosophy); Rural community; Ranking (information retrieval); Focus group; Promotion (chess); Process (computing); Community health; Community building; Health promotion; Public relations; Medical education; Business; Process management; Knowledge management; Sociology; Nursing; Computer science; Medicine; Political science; Public health; Marketing; Socioeconomics; Social science","score_opus":0.7855824480088707,"score_gpt":0.6049181511903479,"score_spread":0.1806642968185228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366724861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87744856,0.0000658408,0.07613205,0.0008816739,0.00007086229,0.033455223,0.00053381704,0.0005239471,0.010888088],"genre_scores_gemma":[0.6966793,0.00010576921,0.25921333,0.00035436847,0.000026552072,0.039967958,0.0004520687,0.00015641429,0.0030441943],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.95231795,0.03985253,0.0018990946,0.0013305987,0.0029951097,0.0016046894],"domain_scores_gemma":[0.9136706,0.053954802,0.0033486828,0.0074465433,0.017276058,0.0043033836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.060964804,0.00081598706,0.0005183408,0.0037871734,0.0040788217,0.002845743,0.0020579326,0.0012095592,0.0035348837],"category_scores_gemma":[0.069208734,0.0010595472,0.000527955,0.0021675918,0.0026184132,0.0031232801,0.0054493756,0.0015399291,0.00075728644],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009280599,0.0147813875,0.112297855,0.0016447736,0.00011915644,0.0016612837,0.29179576,0.0037490267,0.017000744,0.004137436,0.010066131,0.5418184],"study_design_scores_gemma":[0.0021445518,0.027578644,0.20984305,0.0020695117,0.0003657922,0.0011663763,0.562157,0.028754858,0.051353093,0.012338342,0.101462685,0.00076608936],"about_ca_topic_score_codex":0.007598696,"about_ca_topic_score_gemma":0.018347837,"teacher_disagreement_score":0.060964804,"about_ca_system_score_codex":0.0030603134,"about_ca_system_score_gemma":0.009433637,"threshold_uncertainty_score":0.3224166},"labels":[],"label_agreement":null},{"id":"W4366725026","doi":"10.3138/cjpe.70376","title":"Helping Students Reflect on Their Interpersonal Skills: The Team Performance Scale (TPS)","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Innovations in Medical Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Teamwork; Interpersonal communication; Psychology; Social skills; Scale (ratio); Service (business); Service-learning; Medical education; Interpersonal relationship; Pedagogy; Social psychology; Management; Medicine; Psychotherapist; Business","score_opus":0.06579928805233264,"score_gpt":0.42500836734359604,"score_spread":0.3592090792912634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97058284,0.00024076807,0.006305053,0.0015480645,0.00026131212,0.0017620756,0.0007690058,0.00041492307,0.018115958],"genre_scores_gemma":[0.98166347,0.00028784393,0.011831452,0.00018025702,0.000046862086,0.0017564252,0.0005408618,0.000066081346,0.0036268411],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99260074,0.0028763253,0.0010412483,0.00027912343,0.0027103808,0.00049209484],"domain_scores_gemma":[0.98396605,0.0031692397,0.0030270542,0.0005306549,0.0059410217,0.0033659302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007205741,0.00043243298,0.0005738203,0.0012561537,0.00076440966,0.001138591,0.00062281167,0.0003746415,0.0050158757],"category_scores_gemma":[0.020131756,0.00021379092,0.0007220402,0.00069755764,0.00053225947,0.0008564102,0.0022847056,0.0015469275,0.0010228675],"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":[0.00076089846,0.0050875857,0.47231865,0.0008580365,0.00029792922,0.00025035714,0.009204967,0.00085281295,0.0049338792,0.00054368016,0.03496101,0.46993017],"study_design_scores_gemma":[0.00020405912,0.0044241077,0.9617549,0.0003870115,0.00012960624,0.00029210307,0.0050121383,0.0021916223,0.006434492,0.00057386764,0.018485151,0.00011094417],"about_ca_topic_score_codex":0.00111058,"about_ca_topic_score_gemma":0.0022654082,"teacher_disagreement_score":0.007205741,"about_ca_system_score_codex":0.00094669184,"about_ca_system_score_gemma":0.0019544435,"threshold_uncertainty_score":0.03810805},"labels":[],"label_agreement":null},{"id":"W4366725031","doi":"10.3138/cjpe.37.2.ed-fr","title":"Un mot de la rédactrice","year":2022,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.08457766494705582,"score_gpt":0.359384023416896,"score_spread":0.2748063584698402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725031","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01572303,0.014425294,0.07829699,0.17486605,0.059272423,0.0008889057,0.007032306,0.011240392,0.6382547],"genre_scores_gemma":[0.09444796,0.008677844,0.054015342,0.022460349,0.015227746,0.0011963792,0.0060087116,0.0061318,0.7918339],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9718542,0.010995632,0.001174813,0.0023703952,0.012399336,0.0012058064],"domain_scores_gemma":[0.962356,0.009986596,0.0014656838,0.0035657359,0.021049181,0.0015768333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014639347,0.0021040286,0.0015811003,0.0036596064,0.0063308743,0.016321644,0.0019906445,0.0049672555,0.098644264],"category_scores_gemma":[0.0472334,0.0010531297,0.0019160614,0.0030516288,0.0035959168,0.009150139,0.004409274,0.011684465,0.03779169],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052231055,0.00019854179,0.0016096018,0.00083992997,0.00006315551,0.0006214371,0.0028239856,0.0009577069,0.0036467102,0.13573726,0.5450736,0.30790564],"study_design_scores_gemma":[0.0000554657,0.000038732458,0.0010146607,0.0002274929,0.000013983355,0.00036079096,0.0006344972,0.0005101035,0.0013116518,0.0043627373,0.9914215,0.00004825686],"about_ca_topic_score_codex":0.0916602,"about_ca_topic_score_gemma":0.055833988,"teacher_disagreement_score":0.098644264,"about_ca_system_score_codex":0.0111740995,"about_ca_system_score_gemma":0.011727081,"threshold_uncertainty_score":0.3299979},"labels":[],"label_agreement":null},{"id":"W4366725054","doi":"10.3138/cjpe.36.1.intro-eng","title":"Editor’s Remarks","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Philosophy; Psychology","score_opus":0.24907328656822922,"score_gpt":0.5260421824238015,"score_spread":0.2769688958555723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725054","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009184559,0.0022009404,0.0003145359,0.3047094,0.68706834,0.00005000053,0.00019157332,0.00019112203,0.0051821745],"genre_scores_gemma":[0.0022009127,0.0040362803,0.0012687101,0.5438503,0.38466963,0.00018896985,0.00023494677,0.000336529,0.06321369],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98639804,0.0014326479,0.0012075789,0.0020340849,0.0075227884,0.0014048201],"domain_scores_gemma":[0.9367948,0.0109830005,0.0028004327,0.0027258536,0.03869456,0.008001283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013626744,0.001771624,0.0018864486,0.0023863271,0.0045066834,0.009936625,0.006091698,0.018247591,0.06098552],"category_scores_gemma":[0.104374304,0.0007442502,0.0029013776,0.0020579454,0.0036832935,0.0073754336,0.0038442547,0.021706004,0.03935422],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009232716,0.000006918033,0.000042991785,0.000052641994,0.0000031756722,0.000048678783,0.000028928025,0.000015282556,0.000023386023,0.0005196376,0.9949157,0.0043333815],"study_design_scores_gemma":[0.000007943433,0.0000078859775,0.0001331231,0.00014834636,0.000004244756,0.00007999877,0.0000815392,0.000033167533,0.000055191755,0.0005412541,0.99889356,0.0000137609995],"about_ca_topic_score_codex":0.007841386,"about_ca_topic_score_gemma":0.015200086,"teacher_disagreement_score":0.06098552,"about_ca_system_score_codex":0.006231911,"about_ca_system_score_gemma":0.014106497,"threshold_uncertainty_score":0.20401686},"labels":[],"label_agreement":null},{"id":"W4366725055","doi":"10.3138/cjpe.37.1.ed-en","title":"Editor’s Remarks","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.06340639280039151,"score_gpt":0.42163111870667735,"score_spread":0.35822472590628585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725055","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001207673,0.0018905989,0.00012246269,0.40983072,0.5831584,0.000032129745,0.000109376175,0.0000716415,0.0046640052],"genre_scores_gemma":[0.001759855,0.0013905657,0.00042921727,0.6987512,0.251117,0.00008550344,0.00005211619,0.00007317682,0.046341494],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9813312,0.0018659359,0.0019526012,0.0027795814,0.009747804,0.0023228682],"domain_scores_gemma":[0.93390507,0.015711034,0.004726832,0.0031729154,0.03299663,0.009487502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016279133,0.0017288843,0.0027796202,0.0026917013,0.005521475,0.010954662,0.0051872074,0.041952375,0.03212528],"category_scores_gemma":[0.12950285,0.0012600272,0.0035075562,0.0021167598,0.0037971223,0.0037427738,0.002905414,0.03917884,0.02425196],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014862877,0.0000062718104,0.000048036964,0.000033521745,0.000008704981,0.00009070115,0.00001982888,0.000012923267,0.00002543084,0.00043670472,0.9974598,0.0018431777],"study_design_scores_gemma":[0.000044998877,0.000013533166,0.00042774118,0.00020934436,0.000027151453,0.00015480194,0.00010240931,0.00006612281,0.00010955996,0.0008590309,0.9979518,0.000033488133],"about_ca_topic_score_codex":0.016080853,"about_ca_topic_score_gemma":0.037133094,"teacher_disagreement_score":0.041952375,"about_ca_system_score_codex":0.008307493,"about_ca_system_score_gemma":0.01534411,"threshold_uncertainty_score":0.10746974},"labels":[],"label_agreement":null},{"id":"W4366725272","doi":"10.3138/cjpe.19.006","title":"Integrating Evaluative Inquiry into the Organizational Culture: A Review and Synthesis of the Knowledge Base","year":2004,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Knowledge management; Organizational culture; Organizational learning; Knowledge base; Conceptual framework; Empirical research; Sociology; Work (physics); Management science; Epistemology; Political science; Computer science; Public relations; Social science; Engineering","score_opus":0.3839810064574307,"score_gpt":0.5592321866859272,"score_spread":0.1752511802284965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725272","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005974466,0.9958228,0.0010258957,0.0012555921,0.0001141284,0.000018816045,0.00001585614,0.000005158822,0.0011442992],"genre_scores_gemma":[0.0117623955,0.9857348,0.0017614608,0.00040694143,0.00013089433,0.000065454136,0.000022324295,0.0000049872747,0.0001106727],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98690027,0.0066268495,0.002037454,0.00092519727,0.0032055848,0.0003047224],"domain_scores_gemma":[0.8633461,0.11880514,0.0048172106,0.0015913601,0.010817832,0.0006223974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028768942,0.0010653457,0.0033491992,0.022223797,0.0016553702,0.007738108,0.0022188872,0.002386074,0.0022885099],"category_scores_gemma":[0.05061668,0.00093030406,0.0009372753,0.032476448,0.0049433256,0.006564529,0.0024334048,0.0021805926,0.0004883645],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000498778,0.00010127401,0.0017395593,0.09200201,0.00032674073,0.00022796934,0.005080316,0.0005637713,0.0003943204,0.010035025,0.0048125624,0.88466656],"study_design_scores_gemma":[0.00004231523,0.00024148727,0.015189089,0.4662342,0.0015343052,0.001426686,0.021760132,0.0009242818,0.0014688915,0.024093226,0.4669188,0.00016662231],"about_ca_topic_score_codex":0.014517844,"about_ca_topic_score_gemma":0.03136452,"teacher_disagreement_score":0.028768942,"about_ca_system_score_codex":0.0070049725,"about_ca_system_score_gemma":0.022718808,"threshold_uncertainty_score":0.15214652},"labels":[],"label_agreement":null},{"id":"W4366725921","doi":"10.3138/cjpe.35.2.vi","title":"Un mot de la rédactrice","year":2020,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.12225635952327514,"score_gpt":0.36373054832102936,"score_spread":0.24147418879775423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725921","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015188869,0.0149419885,0.07405989,0.18890865,0.061281946,0.00086029543,0.0066743856,0.010363022,0.62772095],"genre_scores_gemma":[0.095563136,0.008993058,0.05243319,0.024393378,0.01621781,0.0011911514,0.005766303,0.0059246086,0.78951746],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9705631,0.011574441,0.0012307004,0.0024523977,0.012924208,0.0012552337],"domain_scores_gemma":[0.9602754,0.010601266,0.001541567,0.003749836,0.022180753,0.001651073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0153217055,0.0020887095,0.0015852654,0.00370128,0.0064796717,0.016570045,0.0020287065,0.0050833905,0.096288994],"category_scores_gemma":[0.04945642,0.0010513654,0.0019186228,0.0030981852,0.0037427687,0.009397951,0.004520322,0.011935305,0.03665668],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050515006,0.00019365358,0.0016141009,0.00083202013,0.00006305055,0.0006102269,0.0028444054,0.00092095614,0.0034810458,0.13948105,0.55003643,0.29941788],"study_design_scores_gemma":[0.00005361663,0.000037739268,0.0010089305,0.00023073018,0.00001390022,0.0003609384,0.0006441787,0.00048760732,0.0012495897,0.004523731,0.99134153,0.000047550653],"about_ca_topic_score_codex":0.09233086,"about_ca_topic_score_gemma":0.056521468,"teacher_disagreement_score":0.096288994,"about_ca_system_score_codex":0.011584262,"about_ca_system_score_gemma":0.01218094,"threshold_uncertainty_score":0.32211876},"labels":[],"label_agreement":null},{"id":"W4366725925","doi":"10.3138/cjpe.68844","title":"Reconciliation and Energy Democracy","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Mining and Resource Management","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Democracy; Equity (law); Energy security; Nationalism; Political science; Sustainable development; Energy (signal processing); Inclusion (mineral); Political economy; Economic growth; Renewable energy; Sociology; Economics; Politics; Law; Social science; Engineering","score_opus":0.062099975306836606,"score_gpt":0.26526597087920484,"score_spread":0.20316599557236822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725925","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24208309,0.0022292845,0.01261817,0.05378333,0.0003904951,0.0010187182,0.00049478956,0.0002154985,0.68716663],"genre_scores_gemma":[0.9849622,0.00045620408,0.0031475213,0.0023077663,0.000025328844,0.00019692432,0.00009812773,0.000025549736,0.008780282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.94475394,0.032973416,0.00092892646,0.001352558,0.012385149,0.0076059885],"domain_scores_gemma":[0.9719858,0.008791494,0.0026346503,0.0033859452,0.010503379,0.002698704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035297424,0.0003897822,0.0004529126,0.001959175,0.006823661,0.0072565884,0.0013378641,0.0015862717,0.010722418],"category_scores_gemma":[0.04711254,0.00013630693,0.0004988558,0.0030676648,0.009705832,0.003797766,0.011903902,0.002777464,0.0005329946],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026657694,0.00043545675,0.01723399,0.0006302727,0.000108651926,0.00010596531,0.017959729,0.0031737913,0.00050078076,0.69735944,0.026897244,0.2353281],"study_design_scores_gemma":[0.0003987486,0.0011406044,0.07063467,0.0032350163,0.00038264645,0.0002455881,0.078786574,0.0055009127,0.009605507,0.3125293,0.51741344,0.00012701296],"about_ca_topic_score_codex":0.13423398,"about_ca_topic_score_gemma":0.20952758,"teacher_disagreement_score":0.86576605,"about_ca_system_score_codex":0.028615478,"about_ca_system_score_gemma":0.08078844,"threshold_uncertainty_score":0.2669053},"labels":[],"label_agreement":null},{"id":"W4366726152","doi":"10.3138/cjpe.34.3.vi","title":"Un mot de la rédactrice","year":2020,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.12225635952327514,"score_gpt":0.36373054832102936,"score_spread":0.24147418879775423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726152","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013806072,0.0049816314,0.020243036,0.24020599,0.018394373,0.00027542358,0.00057122554,0.00055291475,0.70096946],"genre_scores_gemma":[0.20680259,0.004732619,0.026400227,0.044880047,0.005005712,0.00053811056,0.000591988,0.000993881,0.7100548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98495793,0.0070332843,0.0004674544,0.0013179331,0.005201832,0.0010215621],"domain_scores_gemma":[0.97194237,0.0071326247,0.0015351647,0.0034476223,0.012529643,0.0034125475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011177546,0.00077383313,0.00050508906,0.0017918131,0.0077796234,0.010538683,0.0013482145,0.0034953593,0.04635227],"category_scores_gemma":[0.04201056,0.0005782449,0.0006603461,0.0017481502,0.0072657214,0.012758526,0.007850896,0.008526091,0.014621269],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013152751,0.000081254315,0.0024999059,0.00046305635,0.000020077856,0.0003322121,0.029447637,0.00014200278,0.0018945773,0.44215062,0.34315583,0.17968132],"study_design_scores_gemma":[0.000011045439,0.000038628812,0.0013776135,0.00029484427,0.000007798915,0.00027696998,0.006055269,0.00012726733,0.00070532906,0.019996453,0.97107756,0.00003122805],"about_ca_topic_score_codex":0.009240514,"about_ca_topic_score_gemma":0.015358524,"teacher_disagreement_score":0.04635227,"about_ca_system_score_codex":0.005842292,"about_ca_system_score_gemma":0.010665147,"threshold_uncertainty_score":0.15506381},"labels":[],"label_agreement":null},{"id":"W4366726230","doi":"10.3138/cjpe.35.3.473","title":"Peer Reviewers for Volume 35 and Manuscripts Submitted in 2020 / Examinateurs et examinatrices des manuscrits du volume 35 et des manuscrits soumis en 2020","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Art; Humanities; Psychology; Physics","score_opus":0.2671932895686844,"score_gpt":0.46999302576202445,"score_spread":0.20279973619334007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726230","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021988653,0.023541307,0.020794347,0.25866792,0.46503258,0.010751965,0.008872881,0.0074734567,0.18287696],"genre_scores_gemma":[0.07399514,0.024224728,0.054838832,0.05025235,0.10016009,0.00578446,0.010561267,0.0037676864,0.67641544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96738875,0.006770847,0.003421316,0.001885488,0.01910372,0.0014297826],"domain_scores_gemma":[0.67592156,0.015821204,0.010316445,0.006025712,0.27340665,0.018508323],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028351687,0.0011839635,0.0019217499,0.006455371,0.0040864414,0.009072614,0.0021384412,0.003711586,0.11312512],"category_scores_gemma":[0.11600365,0.00076797017,0.0015751242,0.003781685,0.0017357277,0.0035915955,0.003126972,0.0036442655,0.07036998],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015380983,0.000038666698,0.0009352689,0.00039812608,0.00002369125,0.00009147202,0.00017186797,0.00003626713,0.00058053894,0.0003676054,0.95620644,0.04099619],"study_design_scores_gemma":[0.00011577779,0.00018258159,0.005698478,0.00062306947,0.00005287899,0.00025511868,0.00060724345,0.00034070938,0.00097098964,0.0008419214,0.9902519,0.000059396545],"about_ca_topic_score_codex":0.005143807,"about_ca_topic_score_gemma":0.020050243,"teacher_disagreement_score":0.99724364,"about_ca_system_score_codex":0.002756339,"about_ca_system_score_gemma":0.02591227,"threshold_uncertainty_score":0.3784412},"labels":[],"label_agreement":null},{"id":"W4366726246","doi":"10.3138/cjpe.72865.fr","title":"Nos racines et nos liens: Célébrons l’évaluation autochtone","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Agriculture and Rural Development Research","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Mathematics; Economics; Accounting","score_opus":0.13394762055728568,"score_gpt":0.3654606151308302,"score_spread":0.23151299457354454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726246","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031679913,0.049087435,0.024257168,0.6338026,0.030113757,0.0006663587,0.000457774,0.00084715785,0.22908784],"genre_scores_gemma":[0.59324396,0.015878001,0.03428693,0.080193646,0.009779338,0.0017826465,0.00049517344,0.0011205337,0.26321974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.85637414,0.08120489,0.0038817986,0.0048665665,0.047600772,0.006071799],"domain_scores_gemma":[0.88160145,0.06787089,0.0041011367,0.008793253,0.028213635,0.009419701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0974931,0.0010532923,0.0011846347,0.0037124997,0.0065436093,0.02165617,0.0023124558,0.009195284,0.013003894],"category_scores_gemma":[0.14766903,0.00079129514,0.0013664406,0.0022642014,0.013896393,0.009054443,0.0074428646,0.01230253,0.00147067],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060709513,0.0005023086,0.0033339006,0.0006728376,0.00014109373,0.000312333,0.0072183493,0.0017741732,0.0010422475,0.51933426,0.24596846,0.21909283],"study_design_scores_gemma":[0.00018082958,0.00020318368,0.0036699171,0.0011184586,0.000049239286,0.00022211048,0.002241286,0.0013613763,0.0010691726,0.030278392,0.95950645,0.000099477766],"about_ca_topic_score_codex":0.117078595,"about_ca_topic_score_gemma":0.16047634,"teacher_disagreement_score":0.9651615,"about_ca_system_score_codex":0.034838475,"about_ca_system_score_gemma":0.054987125,"threshold_uncertainty_score":0.51559895},"labels":[],"label_agreement":null},{"id":"W4366726379","doi":"10.3138/cjpe.19.005","title":"L’évaluation des technologies de la santé: comment l’introduire dans les hôpitaux universitaires du Québec?","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Jewish General Hospital","funders":"","keywords":"Health technology; Context (archaeology); Library science; Political science; Sociology; Business; Psychology; Public relations; Health care; Geography","score_opus":0.24746273976255734,"score_gpt":0.41530696944900225,"score_spread":0.1678442296864449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726379","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1405383,0.046355035,0.0038979051,0.76100194,0.002302586,0.000220453,0.0005111154,0.00009273185,0.045079958],"genre_scores_gemma":[0.8838688,0.02103748,0.0070382655,0.05214004,0.001226785,0.00025683767,0.00031211614,0.00007435109,0.03404531],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96980435,0.017058773,0.0014300541,0.0010864104,0.008019467,0.0026008224],"domain_scores_gemma":[0.9109164,0.036500435,0.004822689,0.0021839754,0.039282504,0.0062939445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03671475,0.00040025546,0.0005081771,0.0012554228,0.00477882,0.009418461,0.0019443312,0.0052561704,0.00673273],"category_scores_gemma":[0.06383727,0.00031890185,0.00073996244,0.0036360922,0.0051431744,0.003999064,0.0023619775,0.0049857316,0.00057176757],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009621814,0.00070237543,0.12642613,0.006365826,0.00031107737,0.0020466596,0.04264666,0.0064016143,0.003381571,0.09400741,0.17555344,0.54119515],"study_design_scores_gemma":[0.00018839959,0.00075928145,0.2342383,0.0067923088,0.0002368423,0.0006911959,0.024824958,0.0039454224,0.00343572,0.005504357,0.71914804,0.0002351781],"about_ca_topic_score_codex":0.8767105,"about_ca_topic_score_gemma":0.8835207,"teacher_disagreement_score":0.9219746,"about_ca_system_score_codex":0.07802539,"about_ca_system_score_gemma":0.091386415,"threshold_uncertainty_score":0.5661165},"labels":[],"label_agreement":null},{"id":"W4366726740","doi":"10.3138/cjpe.19.003","title":"Stakeholder Involvement in a Government-Funded Outcome Evaluation: Lessons from the Front Line","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"","keywords":"Workload; Stakeholder; Government (linguistics); Strengths and weaknesses; Front line; Process (computing); Outcome (game theory); Data collection; Process management; Public relations; Program evaluation; Psychology; Business; Medical education; Knowledge management; Political science; Medicine; Computer science; Sociology; Public administration; Social psychology","score_opus":0.6625327886142328,"score_gpt":0.5396214187531866,"score_spread":0.12291136986104623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726740","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23034425,0.009731822,0.2395965,0.346315,0.0035310616,0.01765434,0.0003257014,0.001137399,0.15136403],"genre_scores_gemma":[0.8073453,0.001862777,0.15296632,0.018269299,0.000500769,0.01118786,0.00018034304,0.00034048245,0.007346862],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.35301426,0.60245615,0.0074095097,0.0038636196,0.02308621,0.010170262],"domain_scores_gemma":[0.5126684,0.38036805,0.012647475,0.020591417,0.057790395,0.015934326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.43329552,0.0016615277,0.0019597355,0.0030051286,0.015905883,0.020456092,0.0063143163,0.010579509,0.0051660696],"category_scores_gemma":[0.29199874,0.0014920223,0.0021587363,0.0029863764,0.012288,0.013322654,0.023163995,0.012208789,0.0012582114],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021190685,0.007102436,0.0139512,0.0054339743,0.00040503303,0.0022786707,0.10357945,0.0065709497,0.001562412,0.102302656,0.041640818,0.7130534],"study_design_scores_gemma":[0.004610161,0.010818732,0.027699567,0.027272236,0.0006476526,0.002117084,0.22377582,0.025267404,0.0109389145,0.3690916,0.296854,0.00090695167],"about_ca_topic_score_codex":0.010449612,"about_ca_topic_score_gemma":0.014304628,"teacher_disagreement_score":0.9755508,"about_ca_system_score_codex":0.024449257,"about_ca_system_score_gemma":0.09463937,"threshold_uncertainty_score":0.69884753},"labels":[],"label_agreement":null},{"id":"W4366728118","doi":"10.3138/cjpe.0016.003","title":"Evaluation in the Government of Alberta: Adapting to the “New Way”","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Government of Alberta","keywords":"Scrutiny; Government (linguistics); Meaning (existential); Emphasis (telecommunications); Focus (optics); Empowerment; Process management; Public relations; Management science; Political science; Sociology; Business; Computer science; Epistemology; Economics; Law","score_opus":0.4323374369274828,"score_gpt":0.49519588504531975,"score_spread":0.06285844811783697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728118","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27684182,0.04169432,0.036317296,0.36998945,0.0032188783,0.001269047,0.00021275465,0.0007069956,0.26974937],"genre_scores_gemma":[0.9246249,0.010419329,0.031663697,0.016299123,0.0004741495,0.00017596953,0.00014123942,0.00007248221,0.016129002],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94227874,0.03276136,0.0015791329,0.0015116467,0.01704665,0.004822525],"domain_scores_gemma":[0.953581,0.014939484,0.0018040119,0.002454865,0.021848582,0.0053720116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040680934,0.0003621779,0.00041444768,0.0029236653,0.0075915256,0.013824953,0.0026215194,0.0029505992,0.0013977428],"category_scores_gemma":[0.029932601,0.00028655858,0.00036057184,0.004320791,0.0152125675,0.00324851,0.006078764,0.0031242187,0.00013540828],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031730896,0.00033726537,0.027417604,0.0017446711,0.00009251794,0.0010714612,0.033101562,0.008560936,0.0026964794,0.19693677,0.04834745,0.67937607],"study_design_scores_gemma":[0.00018133523,0.00047206134,0.13182235,0.0040547005,0.00017778586,0.00076294586,0.09494033,0.008895115,0.00435484,0.0709081,0.68297356,0.0004568303],"about_ca_topic_score_codex":0.8401447,"about_ca_topic_score_gemma":0.9171151,"teacher_disagreement_score":0.8733185,"about_ca_system_score_codex":0.12668149,"about_ca_system_score_gemma":0.18053994,"threshold_uncertainty_score":0.91914284},"labels":[],"label_agreement":null},{"id":"W4366728120","doi":"10.3138/cjpe.0016.002","title":"Program Evaluation in British Columbia in a Time of Transition: 1995-2000","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Accountability; Transparency (behavior); Scarcity; Public administration; Government (linguistics); Politics; Performance measurement; Business; Performance management; Strategic planning; Public sector; Accounting; Political science; Public relations; Economics; Marketing; Law","score_opus":0.24730137240434352,"score_gpt":0.4603232882871255,"score_spread":0.21302191588278196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9379852,0.002551616,0.0006768134,0.017845988,0.00017080519,0.0016344379,0.0031098446,0.00024667758,0.035778508],"genre_scores_gemma":[0.9544093,0.001041397,0.0016391968,0.0042103217,0.000030604053,0.00058822124,0.0015791304,0.00004903473,0.03645274],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937849,0.0014380717,0.00027540445,0.00032043896,0.0020865477,0.00209458],"domain_scores_gemma":[0.9645117,0.004108152,0.0018799468,0.00063768594,0.019340048,0.009522616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052549616,0.00031992138,0.0003860231,0.002250819,0.0062878584,0.0031355005,0.0022208337,0.0010685332,0.004812965],"category_scores_gemma":[0.01630205,0.00045459726,0.00018443902,0.003389194,0.0017918907,0.0008311768,0.0037084275,0.0023388248,0.0006533677],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002907067,0.0031059633,0.43777475,0.0012442605,0.00021213529,0.0018947484,0.016257595,0.00289797,0.0026850281,0.0052663656,0.15261187,0.37314224],"study_design_scores_gemma":[0.00022957324,0.0006397496,0.89529586,0.0004732633,0.00009234256,0.0001664244,0.025312146,0.0016444818,0.0017415872,0.00047438935,0.07383695,0.00009329378],"about_ca_topic_score_codex":0.9638356,"about_ca_topic_score_gemma":0.98586214,"teacher_disagreement_score":0.9638356,"about_ca_system_score_codex":0.10591988,"about_ca_system_score_gemma":0.16727692,"threshold_uncertainty_score":0.76850617},"labels":[],"label_agreement":null},{"id":"W4366728330","doi":"10.3138/cjpe.0016.007","title":"Evaluation Policy and Practice in the Provincial Government of Prince Edward Island","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health PEI","funders":"","keywords":"Accountability; Theme (computing); Government (linguistics); Public administration; Public policy; Public sector; Political science; History; Law; Philosophy; Computer science","score_opus":0.2650363576252401,"score_gpt":0.5108291781477593,"score_spread":0.24579282052251922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57235616,0.015518112,0.002462591,0.27216455,0.00050652743,0.001168809,0.00060949154,0.00026757136,0.13494611],"genre_scores_gemma":[0.92586255,0.0050422177,0.0055314936,0.008582468,0.000079222365,0.00038378782,0.0002466667,0.00004521856,0.054226313],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9883909,0.0037286538,0.0008138903,0.00051969546,0.0034105578,0.0031362218],"domain_scores_gemma":[0.93125635,0.021597631,0.0024664612,0.0016419443,0.029742064,0.013295602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01656867,0.00013975064,0.00026518808,0.0015250578,0.013878559,0.007527095,0.0024020907,0.0026601686,0.00516854],"category_scores_gemma":[0.032722253,0.0005105131,0.00021037876,0.00252634,0.0062192767,0.0014227051,0.0041555376,0.0027839574,0.00036665003],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008067348,0.00074990594,0.18525527,0.0033620365,0.00017658694,0.004364153,0.12461865,0.0075083277,0.0041139806,0.16168754,0.17505418,0.33230266],"study_design_scores_gemma":[0.00014506587,0.0003303021,0.3184354,0.0027666225,0.00006705012,0.000550318,0.1819204,0.003741195,0.0027159275,0.009607398,0.47953406,0.00018637383],"about_ca_topic_score_codex":0.94429755,"about_ca_topic_score_gemma":0.9564343,"teacher_disagreement_score":0.8784646,"about_ca_system_score_codex":0.12153545,"about_ca_system_score_gemma":0.3734533,"threshold_uncertainty_score":0.88180554},"labels":[],"label_agreement":null},{"id":"W4366728344","doi":"10.3138/cjpe.0016.004","title":"Program Evaluation in the Manitoba Government: Past, Present, and Future","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Program evaluation; Civil service; State (computer science); Service (business); State government; Political science; Psychology; Public administration; Business; Local government; Public service; Computer science; Marketing","score_opus":0.31480988225866346,"score_gpt":0.47898588581411383,"score_spread":0.16417600355545037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70744306,0.12580849,0.0012209333,0.12465866,0.00037676765,0.00016931229,0.00032928705,0.00011187678,0.03988151],"genre_scores_gemma":[0.94178724,0.047176376,0.0018665291,0.0038993184,0.00012472869,0.000059258913,0.00016996634,0.000016764203,0.0048998534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9916761,0.003821917,0.0003786893,0.00030570684,0.0021943133,0.0016232972],"domain_scores_gemma":[0.9582844,0.010259605,0.0052760723,0.0006413208,0.01914123,0.0063973283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012054745,0.00018580772,0.00026700457,0.0032170513,0.0048197233,0.0059867566,0.0012978838,0.0008896035,0.0021216634],"category_scores_gemma":[0.018593144,0.00031498013,0.00024350086,0.006469295,0.0029122338,0.0014630342,0.0020393382,0.00153056,0.00019421834],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003008432,0.00059780304,0.51356715,0.003022643,0.00018133954,0.00091996574,0.027087452,0.001345597,0.0017370917,0.010184938,0.0133025935,0.42775247],"study_design_scores_gemma":[0.000033809156,0.00048178114,0.7987017,0.0039736466,0.000103242026,0.00066911784,0.06488622,0.00089754886,0.001275142,0.0011879742,0.12769476,0.00009513261],"about_ca_topic_score_codex":0.6264371,"about_ca_topic_score_gemma":0.80511636,"teacher_disagreement_score":0.9517466,"about_ca_system_score_codex":0.048253443,"about_ca_system_score_gemma":0.12224995,"threshold_uncertainty_score":0.7515257},"labels":[],"label_agreement":null},{"id":"W4366728389","doi":"10.3138/cjpe.017.005","title":"Evaluation of Client Satisfaction in a Community Health Centre: Selection of a Tool","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Health Canada","keywords":"Patient satisfaction; Customer satisfaction; Scale (ratio); Focus group; Psychology; Service (business); Health care; Knowledge management; Nursing; Applied psychology; Computer science; Medicine; Business; Marketing","score_opus":0.34787908851390137,"score_gpt":0.5072499046981792,"score_spread":0.15937081618427784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9735011,0.0003372477,0.009042624,0.00066612544,0.00004394378,0.009742998,0.00050807407,0.00012537152,0.006032566],"genre_scores_gemma":[0.9526451,0.0002428978,0.03710531,0.0001504383,0.0000144834885,0.0088282935,0.00044628582,0.000019081412,0.00054808357],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9705293,0.017772863,0.0044657732,0.0003958154,0.0057895025,0.001046753],"domain_scores_gemma":[0.95660925,0.017945753,0.004040823,0.00087226473,0.01823628,0.0022956624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032866888,0.00051381567,0.00092866394,0.0041187783,0.0014677647,0.0019623346,0.000927575,0.0008296513,0.0018394548],"category_scores_gemma":[0.045499057,0.00033361476,0.0011518032,0.0036171612,0.00093643396,0.0012845155,0.0023948355,0.0009003059,0.0003545009],"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":[0.0028396212,0.004240146,0.6014002,0.0017730673,0.00017391569,0.00052763225,0.011692746,0.0011308851,0.0031732873,0.000853149,0.003545683,0.36864966],"study_design_scores_gemma":[0.0014291613,0.015623737,0.9086457,0.0018560044,0.0004171928,0.0010410566,0.029162584,0.018728195,0.013970398,0.0010263808,0.007837804,0.00026166582],"about_ca_topic_score_codex":0.0025366552,"about_ca_topic_score_gemma":0.004975419,"teacher_disagreement_score":0.032866888,"about_ca_system_score_codex":0.0035218,"about_ca_system_score_gemma":0.006185009,"threshold_uncertainty_score":0.17381877},"labels":[],"label_agreement":null},{"id":"W4366728431","doi":"10.3138/cjpe.19.008","title":"Pre- and Post-Scenarios: Assessing Learning and Behaviour Outcomes in Training Settings","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Situational ethics; Training (meteorology); Psychology; Applied psychology; Process management; Computer science; Knowledge management; Medical education; Engineering; Social psychology; Medicine","score_opus":0.11823665859259931,"score_gpt":0.4674454530905961,"score_spread":0.3492087944979968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866077,0.00009113409,0.0051497123,0.00025990498,0.000053114767,0.0018966174,0.00027511583,0.00012319112,0.005543589],"genre_scores_gemma":[0.98632413,0.000113776645,0.009265029,0.00006524695,0.0000140514885,0.0028113688,0.00039274097,0.000010343996,0.0010031619],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9837303,0.01125314,0.0014184674,0.0004996604,0.0022551557,0.0008432754],"domain_scores_gemma":[0.95670813,0.023087697,0.0052208635,0.0021974903,0.008061542,0.004724335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017495733,0.00078294915,0.00041967593,0.0023112637,0.001755714,0.0015558382,0.0013740982,0.0014618628,0.004443323],"category_scores_gemma":[0.05592846,0.00046338385,0.000852079,0.0009555917,0.0012156322,0.0025259724,0.002843529,0.001574089,0.0009143475],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004232097,0.038640905,0.27390715,0.0016276983,0.00022042896,0.00075458415,0.067689985,0.006040494,0.009830887,0.0025464715,0.0057421643,0.58876723],"study_design_scores_gemma":[0.0004849341,0.0450019,0.8205052,0.0010427454,0.00017765502,0.0011525112,0.067567356,0.009195884,0.037149098,0.0048329444,0.012322568,0.00056725694],"about_ca_topic_score_codex":0.0007935555,"about_ca_topic_score_gemma":0.0015923823,"teacher_disagreement_score":0.017495733,"about_ca_system_score_codex":0.0018297005,"about_ca_system_score_gemma":0.0018789682,"threshold_uncertainty_score":0.09252739},"labels":[],"label_agreement":null},{"id":"W4367029949","doi":"10.3138/cjpe.25.002","title":"Contribution Analysis Applied: Reflections on Scope and Methodology","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Perspective (graphical); Relation (database); Elaboration; Management science; Epistemology; Computer science; Engineering ethics; Sociology; Engineering; Data mining; Philosophy","score_opus":0.6370922382666173,"score_gpt":0.6304102886950795,"score_spread":0.006681949571537782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367029949","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010050366,0.010893583,0.76241046,0.091033325,0.0019116626,0.00072605774,0.000072748866,0.00027053413,0.12263132],"genre_scores_gemma":[0.56788665,0.008063321,0.39300996,0.0109943785,0.0021122284,0.0034604205,0.00009370441,0.00080090377,0.0135784885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7174971,0.24792866,0.0055784266,0.00574485,0.019836552,0.0034143613],"domain_scores_gemma":[0.56375355,0.39148563,0.0035934946,0.016247476,0.022956451,0.001963435],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23964888,0.0014250734,0.0020564417,0.008922871,0.008250631,0.022929596,0.0063835797,0.0072371033,0.00697528],"category_scores_gemma":[0.21049608,0.0013800918,0.0023172298,0.0068000495,0.074351944,0.029936627,0.016556732,0.014674041,0.0013994856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001885318,0.000024415982,0.00039162143,0.00029306544,0.000020653391,0.000049897553,0.011956578,0.0003478204,0.00007822732,0.9544989,0.0020178573,0.030301953],"study_design_scores_gemma":[0.000023956994,0.000028939072,0.00037312388,0.0013796292,0.000013493569,0.00012163639,0.006638133,0.0021272902,0.00042357788,0.92773,0.06110235,0.00003779114],"about_ca_topic_score_codex":0.004086325,"about_ca_topic_score_gemma":0.0022017413,"teacher_disagreement_score":0.7603511,"about_ca_system_score_codex":0.0137039395,"about_ca_system_score_gemma":0.016292213,"threshold_uncertainty_score":0.9376483},"labels":[],"label_agreement":null},{"id":"W4367029978","doi":"10.3138/cjpe.0014.006","title":"Communities Evaluating Community-Level Interventions: The Development of Community-Based Indicators in the Colorado Healthy Communities Initiative","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Environmental resource management; Process (computing); Community development; Component (thermodynamics); Environmental planning; Geography; Political science; Psychology; Computer science; Environmental science","score_opus":0.6376807682358708,"score_gpt":0.562037461900088,"score_spread":0.07564330633578287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367029978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8040605,0.0030103866,0.05133565,0.02112527,0.000460907,0.044378422,0.0015518509,0.0006140122,0.073462985],"genre_scores_gemma":[0.76870346,0.0013181707,0.20306286,0.0010310317,0.00007500367,0.02285884,0.0012477079,0.000079251025,0.001623729],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9168526,0.066363424,0.0026534977,0.0017734156,0.010234034,0.0021229498],"domain_scores_gemma":[0.9137568,0.037195336,0.0072180536,0.003355671,0.030351495,0.008122723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09055682,0.00065655337,0.0006077211,0.0026690264,0.00542337,0.0048164744,0.0020708484,0.0009414447,0.0010619628],"category_scores_gemma":[0.096189804,0.00045078504,0.00041688277,0.0030969693,0.0027685422,0.002224627,0.007996444,0.0025488094,0.00012412058],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079856365,0.007839639,0.22235732,0.0033203592,0.00047714254,0.00022273252,0.07173548,0.004575635,0.0015324022,0.021999003,0.03215416,0.6329875],"study_design_scores_gemma":[0.0018918064,0.012445917,0.60866016,0.012067519,0.0010886007,0.000236222,0.15044391,0.01694137,0.012755058,0.017526776,0.16528217,0.00066044315],"about_ca_topic_score_codex":0.07828241,"about_ca_topic_score_gemma":0.17136325,"teacher_disagreement_score":0.09055682,"about_ca_system_score_codex":0.017755682,"about_ca_system_score_gemma":0.06854573,"threshold_uncertainty_score":0.478916},"labels":[],"label_agreement":null},{"id":"W4367029998","doi":"10.3138/cjpe.0015.007","title":"Critical Perspectives on Educational Evaluation","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Lifeworld; Mainstream; Rationality; Epistemology; Sociology; Critical theory; Critical thinking; Citizen journalism; Postmodernism; Formal education; Engineering ethics; Pedagogy; Social science; Political science; Law; Philosophy","score_opus":0.46646186255614186,"score_gpt":0.6165222477440031,"score_spread":0.15006038518786124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367029998","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006181868,0.085918196,0.071784884,0.5264191,0.007543043,0.00040922614,0.00011481447,0.0001147478,0.3015141],"genre_scores_gemma":[0.81011033,0.04170438,0.04718464,0.065992996,0.010391277,0.0015539808,0.0000949084,0.00025018438,0.022717286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86022747,0.11782805,0.0032631278,0.0032281482,0.012325102,0.0031280888],"domain_scores_gemma":[0.7419045,0.2286951,0.0039896183,0.004076466,0.018774264,0.0025600863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10371626,0.0018851327,0.0013411005,0.008379459,0.012941957,0.026379084,0.0035432575,0.011677738,0.006269097],"category_scores_gemma":[0.10662824,0.00060685317,0.0011511786,0.004406982,0.09889882,0.021267075,0.009505519,0.015948253,0.000661045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013000045,0.000014262609,0.000057338217,0.00023497212,0.000006074618,0.000048940718,0.0076808725,0.00016936404,0.000021745394,0.9794668,0.006253975,0.00603276],"study_design_scores_gemma":[0.000029651776,0.000027537175,0.00009844961,0.0019312075,0.000011011872,0.00009597991,0.009669893,0.0004098247,0.00021672541,0.8360851,0.15140381,0.000020846977],"about_ca_topic_score_codex":0.0068737348,"about_ca_topic_score_gemma":0.005398698,"teacher_disagreement_score":0.10371626,"about_ca_system_score_codex":0.03419914,"about_ca_system_score_gemma":0.016906913,"threshold_uncertainty_score":0.54851055},"labels":[],"label_agreement":null},{"id":"W4367030000","doi":"10.3138/cjpe.0015.004","title":"Evaluability Assessment of Staff Training in Special Care Units for Persons with Dementia: Strategic Issues","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dementia; Curriculum; Psychology; Training (meteorology); Work (physics); Medical education; Professional development; Nursing; Pedagogy; Disease; Medicine","score_opus":0.526951152664895,"score_gpt":0.5564320320386825,"score_spread":0.029480879373787516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.982337,0.000795675,0.007869649,0.0012245857,0.000054973716,0.001299936,0.0001956735,0.000038405375,0.0061840955],"genre_scores_gemma":[0.9925638,0.00015604662,0.006207662,0.000058121543,0.000012509751,0.00038938693,0.00016622282,0.000004047518,0.00044217973],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93422437,0.043310393,0.0053526377,0.00081102544,0.014950161,0.0013512985],"domain_scores_gemma":[0.7898999,0.118546546,0.021837132,0.0046450472,0.061148755,0.0039225942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.100732446,0.0003833985,0.0005449968,0.002180603,0.0012972325,0.0014649057,0.0008085785,0.00042330692,0.0011487375],"category_scores_gemma":[0.18477301,0.00017256464,0.0012200146,0.0019334946,0.0010502823,0.0015611002,0.0014443836,0.0007399614,0.00012087788],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038492656,0.0019317917,0.54011065,0.0020128635,0.00052100205,0.00008280664,0.022281043,0.004590618,0.0018165138,0.0020220468,0.0036193556,0.417162],"study_design_scores_gemma":[0.00026869238,0.009009643,0.9486605,0.00089350843,0.00038286872,0.000082267434,0.018506812,0.008301161,0.006714799,0.0020725972,0.0049880287,0.00011915196],"about_ca_topic_score_codex":0.017878562,"about_ca_topic_score_gemma":0.027905922,"teacher_disagreement_score":0.100732446,"about_ca_system_score_codex":0.007149948,"about_ca_system_score_gemma":0.0079898685,"threshold_uncertainty_score":0.53273046},"labels":[],"label_agreement":null},{"id":"W4367030010","doi":"10.3138/cjpe.0019.011","title":"Planning for Multi-Site Ethics Review","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Timeline; Ethics committee; Engineering ethics; Institutional review board; Political science; Psychology; Sociology; Management science; Public administration; Engineering; History; Archaeology","score_opus":0.9187820484258153,"score_gpt":0.7280834737579588,"score_spread":0.19069857466785656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030010","genre_codex":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023459721,0.005169386,0.26833084,0.25339586,0.012508414,0.37293828,0.00079629564,0.0015806453,0.061820548],"genre_scores_gemma":[0.1073797,0.0030314617,0.51200265,0.036883876,0.0034606035,0.29864472,0.00075332675,0.00055800675,0.03728572],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.611685,0.32373637,0.024277898,0.005297871,0.02192553,0.013077408],"domain_scores_gemma":[0.36759505,0.30374512,0.035042323,0.04605181,0.18118407,0.06638163],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.40294665,0.0014390581,0.0018715924,0.0074480413,0.012200975,0.010191401,0.0075939614,0.011439377,0.031571753],"category_scores_gemma":[0.39021975,0.0025486604,0.00285202,0.0034140411,0.004178881,0.01331561,0.018349022,0.019497883,0.012876457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011362911,0.0019763375,0.0070754713,0.0114813,0.00029930176,0.0120566515,0.06858438,0.0038699387,0.0068949484,0.07661355,0.39899805,0.4110138],"study_design_scores_gemma":[0.0012442195,0.0012719657,0.0078093545,0.0077853133,0.00011711283,0.002564314,0.07796979,0.004419917,0.004052699,0.07615741,0.8162193,0.00038862432],"about_ca_topic_score_codex":0.003815652,"about_ca_topic_score_gemma":0.010373035,"teacher_disagreement_score":0.59705335,"about_ca_system_score_codex":0.010160777,"about_ca_system_score_gemma":0.13188675,"threshold_uncertainty_score":0.73627305},"labels":[{"model":"gemma","categories":["research_integrity"],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":true,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4367030021","doi":"10.3138/cjpe.018.014","title":"Marisol Estrella (Ed.). (2000). Learning from Change: Issues and Experiences in Participatory Monitoring and Evaluation.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Psychology; Computer science; World Wide Web","score_opus":0.5219994103232556,"score_gpt":0.5476537462520411,"score_spread":0.02565433592878552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030021","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021008071,0.8585406,0.009107484,0.04509138,0.0051280856,0.000052321906,0.0011575328,0.0005791438,0.07824275],"genre_scores_gemma":[0.020872854,0.8485375,0.017068416,0.005509592,0.0014372405,0.00010192367,0.00073736615,0.00024518892,0.10548985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925953,0.00021258251,0.00005989278,0.00008708117,0.00032856822,0.00005232657],"domain_scores_gemma":[0.99740785,0.0011479702,0.00026273757,0.00012234486,0.0007927838,0.00026619155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028170485,0.0011953311,0.00062554755,0.0020921007,0.0008989859,0.0030751198,0.0011081558,0.0026714874,0.021030733],"category_scores_gemma":[0.003912539,0.00075449515,0.00031996498,0.003359523,0.0007772294,0.0036364896,0.0011979064,0.0022923716,0.01824982],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007751564,0.000032655676,0.0005654173,0.00076016603,0.000010466227,0.00013519147,0.0010410879,0.0003502661,0.00026584588,0.0033662478,0.40562707,0.58776814],"study_design_scores_gemma":[0.000010015387,0.000034374727,0.0013879106,0.001328637,0.000021349148,0.00034308343,0.0007324343,0.0001369848,0.0005589406,0.003108722,0.99232095,0.000016519762],"about_ca_topic_score_codex":0.025317019,"about_ca_topic_score_gemma":0.070059694,"teacher_disagreement_score":0.025317019,"about_ca_system_score_codex":0.0012420577,"about_ca_system_score_gemma":0.0033362412,"threshold_uncertainty_score":0.07035476},"labels":[],"label_agreement":null},{"id":"W4367030027","doi":"10.3138/cjpe.018.005","title":"Impacts of the Canadian Evaluation Society’s Evaluation Competitions for Students","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health Canada; Canadian Institutes of Health Research","funders":"","keywords":"Political science; Psychology; Business; Sociology","score_opus":0.4394839068331859,"score_gpt":0.5880745552752973,"score_spread":0.1485906484421114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030027","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32063138,0.0027858466,0.0010725666,0.47489113,0.009984124,0.00075287087,0.0037273525,0.0004214962,0.18573329],"genre_scores_gemma":[0.84975106,0.0009390724,0.0014944994,0.042305823,0.0016284523,0.0003106147,0.0021554374,0.00020774185,0.101207286],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.93230146,0.009597945,0.0014809328,0.002502065,0.034822367,0.019295178],"domain_scores_gemma":[0.80530864,0.019020513,0.0039876197,0.0020789194,0.06012927,0.10947499],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.054954425,0.0016561593,0.0015389111,0.005522936,0.030236697,0.019662557,0.007208249,0.017714,0.019805662],"category_scores_gemma":[0.0772465,0.0014313421,0.0029283564,0.004243368,0.0076163355,0.0036425688,0.010102588,0.01357185,0.0018187205],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027573656,0.004949879,0.040007297,0.0002594492,0.00023944174,0.00074378296,0.004043961,0.005143281,0.0011321041,0.04462577,0.832504,0.06359376],"study_design_scores_gemma":[0.0014236683,0.0016075338,0.4465851,0.0005307807,0.00023003273,0.00023073601,0.025662202,0.009281665,0.0017897754,0.008581955,0.5031083,0.0009682468],"about_ca_topic_score_codex":0.92792046,"about_ca_topic_score_gemma":0.98084325,"teacher_disagreement_score":0.9450456,"about_ca_system_score_codex":0.13145523,"about_ca_system_score_gemma":0.28379616,"threshold_uncertainty_score":0.9537789},"labels":[],"label_agreement":null},{"id":"W4367030031","doi":"10.3138/cjpe.0019.005","title":"A Benefit for Everyone: Family-Researcher Collaboration in the Mental Health Field","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Family and Disability Support Research","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Empowerment; Remuneration; Mental health; Reciprocal; Psychology; Public relations; Quality (philosophy); Research program; Field (mathematics); Applied psychology; Medical education; Knowledge management; Business; Medicine; Political science; Computer science; Psychotherapist; Finance","score_opus":0.20366357576897096,"score_gpt":0.5168142095416728,"score_spread":0.3131506337727018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030031","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18044862,0.016754018,0.08808794,0.61555195,0.010360217,0.0035565526,0.00018878595,0.0014181082,0.08363382],"genre_scores_gemma":[0.8706373,0.0040342174,0.07893513,0.034460593,0.0014848992,0.0024302984,0.00006472945,0.0001961764,0.0077566677],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7199502,0.26534814,0.002378422,0.0023809886,0.0047725593,0.0051696915],"domain_scores_gemma":[0.69283247,0.18506745,0.008940694,0.020447506,0.024353081,0.06835875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16985086,0.0007517145,0.0009633165,0.0023355247,0.022648953,0.013440193,0.002584486,0.0066489815,0.010665152],"category_scores_gemma":[0.1768282,0.00093306263,0.0012632621,0.0010786821,0.00945798,0.016802866,0.032250732,0.007094124,0.0022530463],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007182821,0.0013929071,0.016026393,0.001613617,0.0002826453,0.006237679,0.3266234,0.00040188094,0.0013184063,0.02674798,0.10203259,0.51660424],"study_design_scores_gemma":[0.0007342757,0.0020269554,0.010709912,0.0062427092,0.0002757908,0.0110222455,0.4822086,0.0011402017,0.001797565,0.07480574,0.40862045,0.00041556527],"about_ca_topic_score_codex":0.0022237487,"about_ca_topic_score_gemma":0.0066468185,"teacher_disagreement_score":0.16985086,"about_ca_system_score_codex":0.0048704534,"about_ca_system_score_gemma":0.037893903,"threshold_uncertainty_score":0.8982679},"labels":[],"label_agreement":null},{"id":"W4367030032","doi":"10.3138/cjpe.0019.001","title":"Guest Editors’ Remarks","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Contemporary Sociological Theory and Practice","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Community Based Research; University of Ottawa","funders":"","keywords":"Psychology; Business","score_opus":0.1550631717989852,"score_gpt":0.4372494549462033,"score_spread":0.2821862831472181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030032","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041048118,0.0015139157,0.00031866657,0.4089899,0.5809231,0.000035797882,0.00014791696,0.00017983792,0.007480403],"genre_scores_gemma":[0.010971739,0.0014355474,0.0009375718,0.5328315,0.37187356,0.00015521212,0.00010229977,0.00025514708,0.08143746],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9860714,0.0014436424,0.0013345163,0.002935229,0.006286666,0.0019285956],"domain_scores_gemma":[0.93711853,0.014856838,0.0051415097,0.0042594564,0.031488568,0.00713508],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013712495,0.0012571202,0.0019254485,0.0016937082,0.004296988,0.010390447,0.0044320603,0.020202726,0.025151638],"category_scores_gemma":[0.12592854,0.0008013601,0.0021418578,0.001460354,0.0030842698,0.0041553797,0.0042272517,0.02899046,0.016699089],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003695428,0.0000074547143,0.00011974489,0.000044524728,0.000010609208,0.0001375175,0.000082631654,0.000030835316,0.000079487836,0.0016486308,0.99521893,0.0025827542],"study_design_scores_gemma":[0.000046779463,0.000019808824,0.00092630455,0.00015340326,0.0000405172,0.00014229598,0.0002930925,0.00020148487,0.0003994961,0.002152859,0.99557894,0.000044841607],"about_ca_topic_score_codex":0.009016333,"about_ca_topic_score_gemma":0.0136267245,"teacher_disagreement_score":0.9748484,"about_ca_system_score_codex":0.0054381816,"about_ca_system_score_gemma":0.005600312,"threshold_uncertainty_score":0.0841406},"labels":[],"label_agreement":null},{"id":"W4367030034","doi":"10.3138/cjpe.018.011","title":"Le concours de simulation: le point de vue d’un juge","year":2003,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Art","score_opus":0.29226300231606334,"score_gpt":0.496086777021772,"score_spread":0.20382377470570867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030034","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2740852,0.0259307,0.2210481,0.21407336,0.0068034655,0.0017270474,0.0005159784,0.0017039381,0.25411215],"genre_scores_gemma":[0.9297748,0.0040131845,0.04537639,0.0037721489,0.0003392348,0.000721365,0.00017151806,0.00031850327,0.015512716],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9075006,0.074248254,0.001744253,0.0013007126,0.0131037235,0.002102452],"domain_scores_gemma":[0.8652674,0.090245545,0.004107102,0.007409667,0.024664255,0.008306086],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.052066673,0.0010746036,0.0010422515,0.0021226187,0.004051222,0.01363116,0.0029248942,0.005389882,0.009327194],"category_scores_gemma":[0.15495588,0.000706784,0.00092377805,0.0012697291,0.007400937,0.010113971,0.007075608,0.0056459545,0.0012921083],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032731427,0.002414172,0.0147297885,0.0018447776,0.00033129667,0.0006427255,0.039541874,0.01951552,0.002538935,0.33966875,0.043570388,0.5319287],"study_design_scores_gemma":[0.0013358075,0.005199622,0.012228971,0.010212996,0.00040277452,0.0015031127,0.043208264,0.048050866,0.01435641,0.21953617,0.6434794,0.00048556319],"about_ca_topic_score_codex":0.018086264,"about_ca_topic_score_gemma":0.02257969,"teacher_disagreement_score":0.9479333,"about_ca_system_score_codex":0.009372704,"about_ca_system_score_gemma":0.033092856,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4367030051","doi":"10.3138/cjpe.0014.010","title":"Epilogue — Comments on the Special Issue","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Youth Education and Societal Dynamics","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.13624206431209165,"score_gpt":0.417052594194031,"score_spread":0.28081052988193933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030051","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020866652,0.0014466132,0.00020071797,0.232707,0.7579987,0.0003024611,0.00094969245,0.00019646046,0.005989716],"genre_scores_gemma":[0.0020807828,0.0018507784,0.00035876906,0.5020415,0.42689377,0.00065607845,0.0007124075,0.00015385148,0.06525205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951894,0.001089946,0.0006997629,0.00038371058,0.0019781804,0.0006590989],"domain_scores_gemma":[0.9598532,0.017619018,0.0026407377,0.0013977304,0.014249204,0.004240114],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008365223,0.0019787345,0.0026196213,0.0031684572,0.0033867077,0.005001826,0.0028882914,0.03169065,0.054326553],"category_scores_gemma":[0.052522384,0.0011328171,0.003192659,0.0019878699,0.0018792463,0.0032050584,0.002034975,0.018151458,0.02595591],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010379911,0.000018475193,0.00010499962,0.00012679028,0.000008154712,0.00009571208,0.000012225817,0.000014966891,0.000046744804,0.00015359119,0.99709237,0.0022221734],"study_design_scores_gemma":[0.00017279563,0.00010576462,0.002723174,0.00044592613,0.0000610636,0.00014625142,0.000116683324,0.00015730444,0.00019469127,0.0008327268,0.99498737,0.000056176366],"about_ca_topic_score_codex":0.011159221,"about_ca_topic_score_gemma":0.01498287,"teacher_disagreement_score":0.94567347,"about_ca_system_score_codex":0.004062645,"about_ca_system_score_gemma":0.0047079166,"threshold_uncertainty_score":0.1817404},"labels":[],"label_agreement":null},{"id":"W4367030054","doi":"10.3138/cjpe.0019.012","title":"Évaluation des coûts des services de soutien en santé mentale communautaire","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Activity-based costing; Valuation (finance); Business; Mental health; Agency (philosophy); Contingent valuation; Health services; Environmental health; Psychology; Medicine; Marketing; Sociology; Willingness to pay; Economics; Finance; Psychiatry; Population","score_opus":0.2645309011810223,"score_gpt":0.509113088193697,"score_spread":0.24458218701267476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.945421,0.003825994,0.007003064,0.0031850508,0.00012123478,0.004366324,0.0036562143,0.00019122993,0.03222975],"genre_scores_gemma":[0.98500353,0.0008082085,0.009963767,0.00010493299,0.000025367955,0.00095167774,0.0008347661,0.000013206488,0.0022945376],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.93991375,0.040427685,0.0018137043,0.0012203722,0.014258911,0.0023655454],"domain_scores_gemma":[0.94679236,0.026595272,0.006497441,0.0012373119,0.01535715,0.0035203188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03922086,0.00069669925,0.000725004,0.002915143,0.0015761077,0.0039063445,0.0013284087,0.0006907425,0.0065138685],"category_scores_gemma":[0.09358173,0.00028749256,0.0010983339,0.0034943477,0.0013855234,0.001386821,0.0025511102,0.00109976,0.0004507659],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00858295,0.0028709567,0.31947038,0.0051569375,0.0018040029,0.0002762618,0.004216133,0.03552092,0.0011985472,0.014127969,0.009893058,0.59688187],"study_design_scores_gemma":[0.0027489846,0.013621668,0.83211666,0.0049751983,0.0026819916,0.00036542138,0.0075268075,0.081253015,0.0101278275,0.0056268233,0.038782913,0.00017276107],"about_ca_topic_score_codex":0.30404377,"about_ca_topic_score_gemma":0.2976422,"teacher_disagreement_score":0.30404377,"about_ca_system_score_codex":0.03527757,"about_ca_system_score_gemma":0.03599968,"threshold_uncertainty_score":0.6045481},"labels":[],"label_agreement":null},{"id":"W4367030058","doi":"10.3138/cjpe.018.015","title":"Irving Rootman, Michael Goodstadt, Brian Hyndman, David V. McQueen, Louise Potvin, Jane Springett, &amp; Erio Ziglio (Éds.) (2001). Evaluation in Health Promotion: Principles and Perspectives.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Sociology; Theology; Political science; Philosophy; Law; Politics","score_opus":0.42290356227939263,"score_gpt":0.49069272073410203,"score_spread":0.0677891584547094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030058","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007749876,0.8479762,0.014591724,0.07511101,0.004110946,0.0001548161,0.00040128906,0.0004023095,0.056476638],"genre_scores_gemma":[0.006969497,0.9143191,0.018533764,0.0058201957,0.0015897136,0.000116678595,0.00022942654,0.00016216715,0.052259512],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960372,0.0008976661,0.00022582339,0.00038006637,0.0023620508,0.00009720234],"domain_scores_gemma":[0.98818713,0.0069010193,0.0010401488,0.00037917384,0.002531058,0.0009614016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0092328815,0.0018489468,0.001999047,0.004878072,0.0016119159,0.0056832707,0.0022609206,0.0041491683,0.025686039],"category_scores_gemma":[0.013212194,0.0017429398,0.0007135525,0.0059668156,0.0026535704,0.009293907,0.0016618669,0.005180477,0.021587227],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078840625,0.000073334086,0.0006226234,0.001600649,0.000038980877,0.00007904141,0.0008304537,0.00038004515,0.00018711518,0.009583455,0.62927896,0.3572466],"study_design_scores_gemma":[0.0000649992,0.00008879526,0.0027223187,0.0049416446,0.0001190394,0.0007408612,0.0011676509,0.00043305763,0.0006153376,0.028527716,0.9604924,0.000086207074],"about_ca_topic_score_codex":0.012883853,"about_ca_topic_score_gemma":0.043486074,"teacher_disagreement_score":0.025686039,"about_ca_system_score_codex":0.0022151656,"about_ca_system_score_gemma":0.007007182,"threshold_uncertainty_score":0.08592832},"labels":[],"label_agreement":null},{"id":"W4367030059","doi":"10.3138/cjpe.25.007","title":"S. Donaldson, C.A. Christie, and M.M. Mark. (2009) <i>What Counts as Credible Evidence in Applied Research and Evaluation Practice?</i> Thousand Oaks, CA: Sage. 265 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Psychology; Physics","score_opus":0.3534349116066584,"score_gpt":0.5479246449963839,"score_spread":0.19448973338972553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030059","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008294657,0.57253504,0.037039813,0.3366677,0.017086674,0.000496166,0.0024804918,0.00031315576,0.032551423],"genre_scores_gemma":[0.049335677,0.71082044,0.106617235,0.09061256,0.011554891,0.001670294,0.0015705856,0.00058025174,0.027238026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97685015,0.01193452,0.0026306661,0.00082508073,0.00749645,0.0002630346],"domain_scores_gemma":[0.65383595,0.28735512,0.009339053,0.0042128065,0.042260673,0.002996329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04698713,0.0015281577,0.0023811494,0.01011974,0.0024408682,0.007954481,0.0037360038,0.007100559,0.019121408],"category_scores_gemma":[0.24190752,0.0017585192,0.0012178834,0.008067072,0.005135763,0.011787504,0.0028608607,0.009514848,0.0097385645],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015546325,0.000038360402,0.001327041,0.0057710153,0.00019641321,0.00012429933,0.0010410363,0.0002421894,0.00014466797,0.024658032,0.7177722,0.24852929],"study_design_scores_gemma":[0.00026185406,0.00011074367,0.005599207,0.029486647,0.0008760626,0.000599908,0.0020540247,0.0007180349,0.00130217,0.17134456,0.7873992,0.00024749653],"about_ca_topic_score_codex":0.013380487,"about_ca_topic_score_gemma":0.040783882,"teacher_disagreement_score":0.04698713,"about_ca_system_score_codex":0.0032197821,"about_ca_system_score_gemma":0.008947772,"threshold_uncertainty_score":0.24849468},"labels":[],"label_agreement":null},{"id":"W4367030095","doi":"10.3138/cjpe.0015.002","title":"System-Wide Program Assessment with Performance Indicators: Alberta’s Performance Funding Mechanism","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Mechanism (biology); Performance indicator; Business; Performance measurement; Organizational performance; Process management; Political science; Accounting; Marketing","score_opus":0.20148791032238003,"score_gpt":0.46823971684013654,"score_spread":0.26675180651775654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030095","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38712975,0.0019580238,0.13380979,0.040329672,0.00049347867,0.013615393,0.0062345117,0.0049802945,0.41144902],"genre_scores_gemma":[0.8588647,0.0005873714,0.10564185,0.0014542852,0.000112653186,0.0028473223,0.0021567661,0.00013449046,0.028200563],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9437034,0.021007095,0.0024571249,0.0017408942,0.02641697,0.0046745534],"domain_scores_gemma":[0.9125701,0.030037751,0.005383,0.0051709386,0.03958656,0.007251636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.064672075,0.00053770235,0.00042849572,0.0064780293,0.0041513285,0.008071882,0.0035523067,0.0013285916,0.0051626493],"category_scores_gemma":[0.06505205,0.0005915835,0.00037182597,0.008516576,0.0035005447,0.002528202,0.005557868,0.0015620072,0.00058706966],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007474561,0.0010081226,0.19492735,0.0008478131,0.0001530611,0.0002679518,0.0052046757,0.016809087,0.0025263936,0.14794262,0.061435763,0.5681298],"study_design_scores_gemma":[0.0014117949,0.0027001065,0.5437616,0.0014231033,0.00046826314,0.0003166228,0.007594119,0.050995905,0.012650483,0.03527405,0.34277967,0.00062429335],"about_ca_topic_score_codex":0.6778377,"about_ca_topic_score_gemma":0.7182222,"teacher_disagreement_score":0.95056605,"about_ca_system_score_codex":0.04943396,"about_ca_system_score_gemma":0.1757294,"threshold_uncertainty_score":0.6481191},"labels":[],"label_agreement":null},{"id":"W4367030101","doi":"10.3138/cjpe.25.008","title":"D. Russ-Eft &amp; H. Preskill. (2009). <i>Evaluation in Organizations: A Systematic Approach to Enhancing Learning, Performance and Change (2nd ed.)</i> . New York, NY: Basic Books. 552 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Computer science","score_opus":0.22454373486820348,"score_gpt":0.418268263955533,"score_spread":0.19372452908732954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030101","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014408121,0.48882264,0.035497822,0.14902498,0.018707871,0.0003180773,0.005041899,0.0014179618,0.29972795],"genre_scores_gemma":[0.020291425,0.5251048,0.03674367,0.024379162,0.0030145803,0.0003810792,0.0017269066,0.0006919369,0.38766637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918073,0.00012245905,0.00008420814,0.00013847186,0.0004235399,0.0000505805],"domain_scores_gemma":[0.9963247,0.0010938525,0.00022734868,0.00011796967,0.0018915096,0.00034453886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023361302,0.0012489222,0.00065192743,0.0032544814,0.0017434086,0.0029723337,0.0010779815,0.0028030868,0.06389378],"category_scores_gemma":[0.006695775,0.00081808947,0.0005703081,0.0039325263,0.001112954,0.0036208802,0.0012757491,0.0029681046,0.039638348],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016135644,0.0000257305,0.0003324334,0.000453328,0.0000062623094,0.000049768067,0.00025935037,0.00011114234,0.00012479776,0.0049801804,0.75512,0.2385209],"study_design_scores_gemma":[0.000012323333,0.0000200822,0.0017041105,0.0010917983,0.000018045572,0.00022328457,0.00022525202,0.0001401971,0.00048792493,0.006500707,0.98955697,0.000019349827],"about_ca_topic_score_codex":0.026629342,"about_ca_topic_score_gemma":0.06920133,"teacher_disagreement_score":0.06389378,"about_ca_system_score_codex":0.002245799,"about_ca_system_score_gemma":0.005425623,"threshold_uncertainty_score":0.21374601},"labels":[],"label_agreement":null},{"id":"W4367030111","doi":"10.3138/cjpe.018.006","title":"Le prix étudiant de la SCÉ … un tremplin vers le monde de l’évaluation!","year":2003,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Political science; Art","score_opus":0.3284735611709467,"score_gpt":0.49774538826996795,"score_spread":0.16927182709902122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030111","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015357604,0.032429066,0.003257999,0.93626535,0.017670138,0.00009699105,0.000047224694,0.000053411633,0.008643968],"genre_scores_gemma":[0.20334956,0.073713124,0.042974748,0.5335467,0.044792634,0.0019604708,0.00038693874,0.00060995173,0.098665826],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.8108031,0.1217881,0.011859636,0.004573138,0.04509419,0.0058818366],"domain_scores_gemma":[0.56244683,0.19818696,0.0150648095,0.017275695,0.17790039,0.029125294],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2614942,0.0009838814,0.0021784666,0.0036390128,0.008114056,0.028774602,0.0027289805,0.016890531,0.009373788],"category_scores_gemma":[0.3932287,0.00087603385,0.0015368413,0.003150518,0.022624709,0.018866403,0.007182426,0.021763735,0.0020158323],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005628127,0.00026188127,0.0033107833,0.0024221896,0.00016753306,0.00025916522,0.008439306,0.00034987455,0.0007488938,0.2809362,0.4840263,0.21851495],"study_design_scores_gemma":[0.00025407155,0.0002593212,0.0031761418,0.008227826,0.00010671457,0.0004536254,0.007821848,0.00077992596,0.00062583876,0.058891784,0.91925496,0.00014787843],"about_ca_topic_score_codex":0.06715802,"about_ca_topic_score_gemma":0.091461636,"teacher_disagreement_score":0.9758744,"about_ca_system_score_codex":0.024125598,"about_ca_system_score_gemma":0.09195972,"threshold_uncertainty_score":0.91070914},"labels":[],"label_agreement":null},{"id":"W4367030127","doi":"10.3138/cjpe.018.013","title":"Préparer la relève dans le monde de l’évaluation: le Concours de simulation du point de vue des commanditaires","year":2003,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Art; Political science","score_opus":0.08991496948856038,"score_gpt":0.38416130325775766,"score_spread":0.2942463337691973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58463866,0.00073913694,0.31638932,0.016899278,0.00045801626,0.00079099217,0.00036285736,0.0009748344,0.07874687],"genre_scores_gemma":[0.9251964,0.00021588524,0.06693789,0.00027263787,0.000019832736,0.00039561436,0.00011273019,0.00011102651,0.0067379815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9892518,0.00875236,0.00021291229,0.00033969726,0.00092716876,0.00051610277],"domain_scores_gemma":[0.96269983,0.03021789,0.00086773996,0.0017826947,0.003046786,0.0013850454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014202231,0.0008520855,0.0008312917,0.00066499214,0.0025791533,0.006527096,0.0018585322,0.0044832295,0.008012176],"category_scores_gemma":[0.058668073,0.00077120576,0.0008871234,0.0008054874,0.0032098852,0.006260462,0.0031593058,0.0039278613,0.00071476266],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009682362,0.00083676225,0.007001149,0.00029336443,0.00010040625,0.00040649725,0.008712214,0.7847761,0.0016420583,0.14609505,0.005427753,0.04374043],"study_design_scores_gemma":[0.00050237874,0.0007799062,0.0020639861,0.0002569678,0.000059945964,0.00007569848,0.0049614385,0.9008471,0.002965286,0.06749831,0.019848414,0.00014046152],"about_ca_topic_score_codex":0.055507388,"about_ca_topic_score_gemma":0.04911701,"teacher_disagreement_score":0.055507388,"about_ca_system_score_codex":0.0055713933,"about_ca_system_score_gemma":0.01283123,"threshold_uncertainty_score":0.11036861},"labels":[],"label_agreement":null},{"id":"W4367030138","doi":"10.3138/cjpe.0015.008","title":"Stakeholder Involvement in Educational Evaluation: Québec’s Commission d’évaluation de l’enseignement collégial","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Stakeholder; Commission; Valuation (finance); Program evaluation; Evaluation methods; Theory of change; Medical education; Psychology; Political science; Pedagogy; Public relations; Management; Business; Medicine; Public administration; Accounting; Engineering; Economics","score_opus":0.47640868414258253,"score_gpt":0.50445403529336,"score_spread":0.028045351150777442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030138","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022101285,0.022266325,0.023005066,0.71946156,0.0061440314,0.0046288036,0.0006652668,0.00040657597,0.20132118],"genre_scores_gemma":[0.7147912,0.007948408,0.05494276,0.1348868,0.0013801742,0.0037538316,0.0010534163,0.0004290927,0.080814414],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.67918277,0.14838426,0.019956356,0.009922837,0.11987326,0.022680482],"domain_scores_gemma":[0.39711723,0.1484782,0.014264778,0.016333831,0.37103266,0.052773345],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27957958,0.0012308382,0.0013648538,0.0065284753,0.02093001,0.0228874,0.0070412895,0.014894953,0.005023719],"category_scores_gemma":[0.27342546,0.0013123051,0.001728198,0.005965526,0.014526149,0.0052516223,0.009455769,0.013437387,0.0006761537],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029569023,0.00039625427,0.021381522,0.0027476621,0.00023943877,0.0008303541,0.02113313,0.0034611244,0.0018176427,0.24670514,0.5049697,0.19602238],"study_design_scores_gemma":[0.0001393938,0.00018759596,0.046532124,0.005898186,0.00010707219,0.00022840542,0.008153873,0.0037533399,0.0015095416,0.0149825085,0.9180688,0.00043910794],"about_ca_topic_score_codex":0.921229,"about_ca_topic_score_gemma":0.9309818,"teacher_disagreement_score":0.921229,"about_ca_system_score_codex":0.19131435,"about_ca_system_score_gemma":0.56986356,"threshold_uncertainty_score":0.93796074},"labels":[],"label_agreement":null},{"id":"W4367030139","doi":"10.3138/cjpe.0019.003","title":"No Matter How You Land: Challenges of a Longitudinal Multi-Site Evaluation","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Mindset; Variety (cybernetics); Perspective (graphical); Process (computing); Data collection; Knowledge management; Process management; Environmental resource management; Business; Sociology; Computer science; Social science; Environmental science","score_opus":0.7473077079517001,"score_gpt":0.6622929878815657,"score_spread":0.08501472007013444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4857397,0.006263979,0.1468629,0.29997885,0.0033182472,0.026277507,0.0013513765,0.0010485714,0.029158933],"genre_scores_gemma":[0.821948,0.0010662008,0.12732248,0.017376065,0.0004391226,0.029013488,0.00039761304,0.00023372614,0.002203223],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.4077937,0.53275675,0.016441578,0.0065311515,0.027933255,0.008543569],"domain_scores_gemma":[0.3279735,0.36985028,0.033092257,0.06694425,0.15640886,0.04573077],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.56078994,0.0008129385,0.0020586387,0.0031891237,0.022530923,0.01733797,0.008087864,0.005326076,0.004243132],"category_scores_gemma":[0.46666405,0.0021196927,0.0013589504,0.0045133326,0.009242413,0.01825345,0.01849738,0.011530726,0.0012127507],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016166146,0.011947604,0.19788024,0.0028016982,0.0006574905,0.0017836195,0.15594147,0.0051200045,0.0017597374,0.038907483,0.053003572,0.5285805],"study_design_scores_gemma":[0.0018577803,0.013494376,0.14392506,0.013258206,0.00046504498,0.0017993976,0.5656166,0.024737844,0.0038971566,0.09153953,0.13847141,0.0009376516],"about_ca_topic_score_codex":0.039622314,"about_ca_topic_score_gemma":0.08077371,"teacher_disagreement_score":0.56078994,"about_ca_system_score_codex":0.0224324,"about_ca_system_score_gemma":0.1158909,"threshold_uncertainty_score":0.54162425},"labels":[],"label_agreement":null},{"id":"W4367030161","doi":"10.3138/cjpe.0019.002","title":"Un mot des rédacteurs invités","year":2005,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health, Medicine and Society","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Community Based Research; University of Ottawa","funders":"","keywords":"Psychology","score_opus":0.25354885729547844,"score_gpt":0.4967290098736824,"score_spread":0.24318015257820397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030161","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044103717,0.008691762,0.0034291744,0.67699075,0.24056682,0.0002555321,0.0011686059,0.0011303031,0.06335669],"genre_scores_gemma":[0.037421577,0.007102335,0.010505925,0.21316846,0.10946643,0.00062927074,0.0018468522,0.000996493,0.6188627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9620868,0.009716156,0.002468669,0.0025601836,0.019503541,0.0036645597],"domain_scores_gemma":[0.84308785,0.032195915,0.0053610723,0.0069168005,0.09145864,0.02097965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021268833,0.0017503708,0.0013249636,0.0027633498,0.005399479,0.008864255,0.0031436742,0.010396685,0.083957255],"category_scores_gemma":[0.12375636,0.00080228917,0.0020340492,0.0021626882,0.0021993385,0.0075090528,0.0044746757,0.011375439,0.022316514],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024905667,0.00014083825,0.0015304339,0.0003834563,0.00002840208,0.00047511066,0.00066292693,0.0001709578,0.0009562435,0.008569566,0.8968932,0.08993978],"study_design_scores_gemma":[0.000066300316,0.000092290335,0.002220173,0.0002710273,0.000018744717,0.00056260196,0.0007192067,0.00023044404,0.00056793744,0.001693482,0.9935201,0.000037777216],"about_ca_topic_score_codex":0.034404654,"about_ca_topic_score_gemma":0.05092167,"teacher_disagreement_score":0.083957255,"about_ca_system_score_codex":0.008267003,"about_ca_system_score_gemma":0.025106108,"threshold_uncertainty_score":0.280865},"labels":[],"label_agreement":null},{"id":"W4367030171","doi":"10.3138/cjpe.018.002","title":"L’expérience d’une démarche pluraliste dans un pays en guerre: L’Afghanistan","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Global Maternal and Child Health","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Appropriation; Citizen journalism; Context (archaeology); Political science; Process (computing); Sociology; Public administration; Geography; Epistemology; Computer science; Law; Philosophy","score_opus":0.05294287191299554,"score_gpt":0.3484288483507825,"score_spread":0.29548597643778696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.939833,0.0014703955,0.004144418,0.028836297,0.00028144947,0.00037589134,0.00003777712,0.000035925073,0.024984835],"genre_scores_gemma":[0.98939705,0.0004387101,0.0012889709,0.0019905563,0.00005569196,0.00014228222,0.000014297805,0.000027971035,0.0066444254],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.94395787,0.045088924,0.0006846009,0.0013155168,0.002743738,0.006209251],"domain_scores_gemma":[0.96974975,0.020781863,0.0013474282,0.00090934226,0.0029611536,0.00425033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047078688,0.0009530776,0.000839928,0.0017241201,0.058185413,0.010626285,0.002542517,0.0075514456,0.005879279],"category_scores_gemma":[0.025377873,0.00095789833,0.0008189853,0.0019364284,0.022822162,0.0054942933,0.014808209,0.009606212,0.00046073805],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114124356,0.00033834315,0.0030399747,0.0001223023,0.0000122631245,0.0043060635,0.9616526,0.0003736345,0.00082419114,0.012669442,0.001781813,0.014765262],"study_design_scores_gemma":[0.00003105327,0.00026717145,0.0029841934,0.00018589686,0.0000103667135,0.001038508,0.9259893,0.00036976422,0.00087688275,0.0024174477,0.06578468,0.000044785847],"about_ca_topic_score_codex":0.10539875,"about_ca_topic_score_gemma":0.14415516,"teacher_disagreement_score":0.10539875,"about_ca_system_score_codex":0.027109424,"about_ca_system_score_gemma":0.02368007,"threshold_uncertainty_score":0.24897885},"labels":[],"label_agreement":null},{"id":"W4367030203","doi":"10.3138/cjpe.0015.001","title":"Editor’s Introduction: Educational Evaluation at the Turn of the Millennium","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Turn (biochemistry); Chemistry","score_opus":0.22207381985994942,"score_gpt":0.5014377426141619,"score_spread":0.2793639227542124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030203","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004678083,0.004918967,0.0003040882,0.06448668,0.9292025,0.000044325938,0.00013428195,0.00008454233,0.00077790546],"genre_scores_gemma":[0.0011205893,0.01068705,0.0010091467,0.17699465,0.7987597,0.00016412835,0.00019990683,0.000110167966,0.010954612],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9875373,0.0032870772,0.0022025078,0.0011649504,0.0051058475,0.000702408],"domain_scores_gemma":[0.9145736,0.029365908,0.0062994566,0.0016662825,0.040880226,0.0072144843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0162313,0.004713819,0.0049742884,0.0058321645,0.0030334452,0.0073891687,0.00687186,0.017914282,0.015043999],"category_scores_gemma":[0.06840839,0.0015137668,0.0043876264,0.0037594745,0.0030337148,0.005549359,0.002569372,0.019626664,0.009831002],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003098585,0.000010426292,0.0000381772,0.00021449143,0.000013983677,0.00003360648,0.000007197466,0.000027996773,0.000019509143,0.0001230948,0.99559057,0.0038899523],"study_design_scores_gemma":[0.00009963145,0.000059996728,0.00075772125,0.0015627121,0.00010052661,0.00022145032,0.00007758721,0.0004207259,0.00017050712,0.0013848396,0.99509454,0.000049743783],"about_ca_topic_score_codex":0.0032430072,"about_ca_topic_score_gemma":0.008424613,"teacher_disagreement_score":0.017914282,"about_ca_system_score_codex":0.004350182,"about_ca_system_score_gemma":0.0057598697,"threshold_uncertainty_score":0.085840344},"labels":[],"label_agreement":null},{"id":"W4367030204","doi":"10.3138/cjpe.0015.011","title":"Prenatal Education Class Attendance with Additional Insights Provided by a Geographic Information System","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Attendance; Population; Class (philosophy); Demography; Set (abstract data type); Geography; Medicine; Family medicine; Psychology; Environmental health; Computer science; Economic growth; Sociology","score_opus":0.07632850352996391,"score_gpt":0.3459717468238533,"score_spread":0.2696432432938894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030204","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7881573,0.00050545414,0.012836585,0.0031643522,0.00018778889,0.0024735036,0.1349372,0.0020746845,0.055663127],"genre_scores_gemma":[0.9300799,0.0004344535,0.038477615,0.00018313578,0.000092751274,0.0013294062,0.021236569,0.00008222897,0.008083998],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990527,0.0004243619,0.0001394291,0.00007411396,0.00023550358,0.00007386375],"domain_scores_gemma":[0.9957392,0.0019246502,0.00074234785,0.0004689691,0.0009054141,0.00021939847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001395602,0.00026618663,0.00023091037,0.0026763857,0.00031352378,0.00063183485,0.00047482847,0.00023860496,0.016920099],"category_scores_gemma":[0.008546662,0.00016851451,0.00023209234,0.0036007739,0.000106447034,0.0006339423,0.0008385274,0.00034175886,0.0017939712],"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":[0.0004241591,0.00057839276,0.5685366,0.001050582,0.00007029633,0.00027280668,0.0037489054,0.0022570393,0.0023488079,0.0006788854,0.040109266,0.37992427],"study_design_scores_gemma":[0.00008097438,0.00043572852,0.92279553,0.00023917464,0.00011277648,0.00022204369,0.0029448415,0.0069478517,0.00279477,0.00036124728,0.06300645,0.000058619695],"about_ca_topic_score_codex":0.036800273,"about_ca_topic_score_gemma":0.06827225,"teacher_disagreement_score":0.036800273,"about_ca_system_score_codex":0.0008218321,"about_ca_system_score_gemma":0.0013908889,"threshold_uncertainty_score":0.07317215},"labels":[],"label_agreement":null},{"id":"W4367030207","doi":"10.3138/cjpe.018.004","title":"Contribution de la cartographie de concepts à la modélisation des interventions en situation de crise en protection de la jeunesse","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Brainstorming; Context (archaeology); Elaboration; Structuring; Psychology; Agency (philosophy); Humanities; Sociology; Political science; Computer science; Geography; Philosophy; Social science","score_opus":0.1982564198429033,"score_gpt":0.5171773982803248,"score_spread":0.3189209784374215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030207","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06679287,0.0014055918,0.9027958,0.0038214815,0.00010930038,0.0008491392,0.0007640158,0.0007057384,0.022756072],"genre_scores_gemma":[0.36320087,0.0011691587,0.6317355,0.00017445716,0.000028653925,0.000985129,0.0006639312,0.00012367859,0.0019186354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940606,0.004459422,0.00025991173,0.0004229229,0.0006691807,0.00012805712],"domain_scores_gemma":[0.9854548,0.011855148,0.00059199496,0.0010362079,0.000917121,0.00014474709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072352462,0.0011903187,0.00055123726,0.0055402145,0.0014296282,0.007023858,0.0011196529,0.0014953214,0.0065508885],"category_scores_gemma":[0.018284574,0.00067665486,0.0019291101,0.004109223,0.0047995746,0.007999421,0.0018256978,0.002090579,0.00058247737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003683898,0.00020270882,0.013588616,0.0024691997,0.000321893,0.0008515762,0.08238324,0.117399566,0.0052009467,0.53491616,0.004532718,0.23776504],"study_design_scores_gemma":[0.00018766076,0.00028170223,0.008576965,0.0031612446,0.00032308284,0.0010386988,0.041919515,0.39507076,0.0041380725,0.3981968,0.14690033,0.00020524944],"about_ca_topic_score_codex":0.020962948,"about_ca_topic_score_gemma":0.010746953,"teacher_disagreement_score":0.020962948,"about_ca_system_score_codex":0.004005354,"about_ca_system_score_gemma":0.0056895018,"threshold_uncertainty_score":0.041681886},"labels":[],"label_agreement":null},{"id":"W4367030214","doi":"10.3138/cjpe.025.004","title":"De l’usage des indicateurs qualitatifs en évaluation et en suivi de gestion dans l’administration publique","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Social Sciences and Governance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval; Centre de Santé et de Services Sociaux de la Vieille-Capitale","funders":"","keywords":"Confusion; Political science; Welfare economics; Business; Psychology; Economics","score_opus":0.12468302370850737,"score_gpt":0.4411637742089216,"score_spread":0.31648075050041424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66477925,0.015530223,0.1844703,0.017857516,0.001461251,0.0006500974,0.002251699,0.00072246994,0.11227717],"genre_scores_gemma":[0.96014905,0.002048723,0.032720864,0.0003687671,0.00015585245,0.00054411904,0.0002998373,0.00009756672,0.00361524],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7735456,0.1689688,0.012736688,0.003675897,0.039455805,0.0016172212],"domain_scores_gemma":[0.60926056,0.28001335,0.030179946,0.009041261,0.06968728,0.001817486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14533432,0.0010606984,0.00090449455,0.009556298,0.0017746185,0.009325278,0.0011357664,0.0023934473,0.0030050657],"category_scores_gemma":[0.2701515,0.0005518905,0.0017790638,0.009717517,0.0049548484,0.0076345545,0.0025171596,0.003155032,0.00071194815],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017188148,0.0006868924,0.2718486,0.0037834542,0.0011639614,0.00023999905,0.06439989,0.009661936,0.0053968513,0.076477125,0.008276411,0.5563461],"study_design_scores_gemma":[0.00028892935,0.0032965268,0.66815984,0.008060048,0.001090616,0.001315374,0.05329845,0.05198469,0.028994275,0.038600463,0.1439688,0.0009420024],"about_ca_topic_score_codex":0.028706186,"about_ca_topic_score_gemma":0.017700464,"teacher_disagreement_score":0.14533432,"about_ca_system_score_codex":0.01057416,"about_ca_system_score_gemma":0.006190701,"threshold_uncertainty_score":0.76861054},"labels":[],"label_agreement":null},{"id":"W4367030218","doi":"10.3138/cjpe.0014.009","title":"Empowerment Goes Large Scale: The Canada Prenatal Nutrition Experience","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Empowerment; Referral; Scale (ratio); Psychology; Program evaluation; Nursing; Stakeholder; Medical education; Public relations; Medicine; Political science; Economic growth; Economics","score_opus":0.15092984205043414,"score_gpt":0.4754820314681291,"score_spread":0.324552189417695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85568625,0.0020771055,0.0009716725,0.062219962,0.00039361333,0.00044617144,0.0002896524,0.00007054352,0.07784502],"genre_scores_gemma":[0.9784741,0.0016575108,0.0009233147,0.0039689313,0.000035791956,0.000093925155,0.00011246602,0.00003722527,0.01469667],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9882194,0.0036173335,0.00017244795,0.0006211641,0.0033249108,0.004044763],"domain_scores_gemma":[0.9859365,0.0032817286,0.00044145994,0.0003324059,0.0028069655,0.0072009857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007503856,0.00032371873,0.00040236823,0.00087272463,0.0267524,0.003631781,0.0013509408,0.0014497014,0.005197804],"category_scores_gemma":[0.013512806,0.0004195845,0.00035263808,0.0017271849,0.009996157,0.0013542152,0.008051882,0.0046949997,0.00022359237],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003202492,0.000868096,0.05628619,0.0002498218,0.000036795234,0.0050573507,0.69140995,0.00048033465,0.0013423765,0.02807218,0.056609873,0.15926684],"study_design_scores_gemma":[0.00012977407,0.00036352262,0.07650081,0.00042837192,0.000032038308,0.0013005612,0.519062,0.0006606707,0.0009863285,0.0023118365,0.39808744,0.00013664144],"about_ca_topic_score_codex":0.9637845,"about_ca_topic_score_gemma":0.98606956,"teacher_disagreement_score":0.9637845,"about_ca_system_score_codex":0.08252995,"about_ca_system_score_gemma":0.14928102,"threshold_uncertainty_score":0.59879947},"labels":[],"label_agreement":null},{"id":"W4367030226","doi":"10.3138/cjpe.25.003","title":"Pre-Measurement Triangulation: Considerations for Program Evaluation in Human Service Enterprises","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Triangulation; Service (business); Interpretation (philosophy); Computer science; Foundation (evidence); Order (exchange); Management science; Simple (philosophy); Process management; Business; Engineering; Epistemology; Mathematics; Marketing; Political science","score_opus":0.5377527213062439,"score_gpt":0.5605725975894016,"score_spread":0.022819876283157736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030226","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017303592,0.0112981135,0.76803297,0.147382,0.0026648855,0.009330576,0.0001664442,0.00021502493,0.043606363],"genre_scores_gemma":[0.29484832,0.0037610596,0.67599374,0.0069189607,0.000841902,0.015204085,0.0001074108,0.00011670657,0.0022077425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.21798395,0.7306292,0.017219389,0.0043586437,0.027757838,0.0020509434],"domain_scores_gemma":[0.16617191,0.7284421,0.018690955,0.02658963,0.05677134,0.0033340822],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.5944983,0.0014925253,0.003301887,0.008468526,0.012294056,0.015236131,0.0069562583,0.008028075,0.0057100374],"category_scores_gemma":[0.7190122,0.0015624475,0.0025045457,0.01050906,0.03510976,0.023992805,0.012470048,0.0087279035,0.000903721],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003376079,0.00020437856,0.006514747,0.0050955475,0.00022312625,0.00043812458,0.06469868,0.0036046864,0.00054447853,0.6120976,0.013563723,0.29267734],"study_design_scores_gemma":[0.00029068286,0.0010817145,0.007074947,0.018005993,0.00025623626,0.00079094124,0.070333056,0.012712651,0.0018153609,0.8053412,0.08193454,0.0003627349],"about_ca_topic_score_codex":0.010933362,"about_ca_topic_score_gemma":0.016703317,"teacher_disagreement_score":0.5944983,"about_ca_system_score_codex":0.017546114,"about_ca_system_score_gemma":0.04780449,"threshold_uncertainty_score":0.50005585},"labels":[],"label_agreement":null},{"id":"W4367030229","doi":"10.3138/cjpe.0019.010","title":"The Experience of Developing a Package of Instruments to Measure the Critical Characteristics of Community Support Programs for People with a Severe Mental Illness","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Mental Health Association; University of Alberta; University of Toronto; Western University; Centre for Addiction and Mental Health","funders":"","keywords":"Mental illness; Measure (data warehouse); Process (computing); Process management; Program evaluation; Psychology; Computer science; Management science; Mental health; Business; Psychotherapist; Political science; Engineering","score_opus":0.26904403914193825,"score_gpt":0.48578448857306383,"score_spread":0.21674044943112558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83441895,0.0015253233,0.12548165,0.011356339,0.00018464413,0.0126934685,0.0012290612,0.0009058355,0.01220486],"genre_scores_gemma":[0.6228972,0.0009586852,0.36571696,0.0010968297,0.000065043714,0.006167505,0.0010841726,0.00018110102,0.001832441],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9424902,0.04144612,0.004173732,0.0010611824,0.00895957,0.0018691994],"domain_scores_gemma":[0.85784274,0.072158135,0.00982279,0.011415093,0.040287934,0.008473343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.094937794,0.0007102171,0.00051260885,0.0018076417,0.0023190007,0.0026108106,0.0014877114,0.0009498807,0.0014220218],"category_scores_gemma":[0.11643113,0.00049635215,0.00062971446,0.0018401659,0.0022998706,0.0023208184,0.0048144567,0.0031985054,0.00036400263],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007177227,0.0041223387,0.12734856,0.0018269649,0.00017640191,0.0002868209,0.031827394,0.0051832106,0.0075406306,0.004964369,0.0086957915,0.8073097],"study_design_scores_gemma":[0.0012662441,0.033534568,0.6295746,0.0052655363,0.0009087924,0.00237665,0.0572362,0.032300062,0.05039872,0.01272507,0.17363346,0.0007801491],"about_ca_topic_score_codex":0.020223964,"about_ca_topic_score_gemma":0.024587817,"teacher_disagreement_score":0.094937794,"about_ca_system_score_codex":0.0065407306,"about_ca_system_score_gemma":0.026578534,"threshold_uncertainty_score":0.50208503},"labels":[],"label_agreement":null},{"id":"W4367030230","doi":"10.3138/cjpe.25.006","title":"J. A. Morell. (2010). <i>Evaluation in the Face of Uncertainty: Anticipating Surprise and Responding to the Inevitable</i> . New York, NY: Guilford. 303 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Surprise; Face (sociological concept); Psychology; Social psychology; Philosophy; Linguistics","score_opus":0.38195705889810144,"score_gpt":0.489306172726481,"score_spread":0.10734911382837958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030230","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018379341,0.5298956,0.01801625,0.28630042,0.012554213,0.00020258299,0.0014281842,0.0010534386,0.14871134],"genre_scores_gemma":[0.069362946,0.5595507,0.03587208,0.07786647,0.007084167,0.00041127758,0.0010336017,0.0009106514,0.24790807],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998722,0.0003484542,0.00009070219,0.00009176996,0.00068195787,0.00006501794],"domain_scores_gemma":[0.98661333,0.008299298,0.0007776368,0.00021112317,0.0033227566,0.0007758219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006130833,0.0009720257,0.0004910158,0.002123061,0.0020297735,0.0042089797,0.0014167448,0.004348635,0.053719502],"category_scores_gemma":[0.017566742,0.00075822155,0.00037555242,0.0018608901,0.0014608456,0.0073013334,0.0012435184,0.0037520719,0.020197418],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009347051,0.0000216628,0.0006652893,0.00061417813,0.00000975384,0.00006944006,0.000618559,0.000104837665,0.00017969226,0.0038109648,0.74606395,0.24774818],"study_design_scores_gemma":[0.00007812306,0.00008892314,0.009005989,0.004605006,0.00007346188,0.00043535416,0.0022436823,0.0005598989,0.00085415354,0.027944842,0.9540235,0.00008718583],"about_ca_topic_score_codex":0.035065394,"about_ca_topic_score_gemma":0.13252147,"teacher_disagreement_score":0.053719502,"about_ca_system_score_codex":0.002225421,"about_ca_system_score_gemma":0.004350632,"threshold_uncertainty_score":0.17970967},"labels":[],"label_agreement":null},{"id":"W4367030235","doi":"10.3138/cjpe.0014.004","title":"Facilitating Development of Organizational Productive Capacity: A Role for Empowerment Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empowerment; Organization development; Group cohesiveness; Organizational effectiveness; Organizational learning; Knowledge management; Organizational commitment; Psychology; Business; Public relations; Process management; Social psychology; Political science; Economics; Economic growth; Computer science","score_opus":0.3047962368639325,"score_gpt":0.4947043086901009,"score_spread":0.18990807182616842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030235","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14160661,0.007974494,0.34731856,0.08584093,0.0007184728,0.00504701,0.00013024344,0.0009771077,0.41038656],"genre_scores_gemma":[0.8737463,0.0012272511,0.11907706,0.0013704064,0.00007176377,0.0013928397,0.00003179515,0.00006025609,0.0030223343],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.89440954,0.09307454,0.0019312896,0.0012396654,0.0073729237,0.0019720853],"domain_scores_gemma":[0.8250256,0.13868837,0.006986865,0.005026484,0.017104514,0.00716826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09324118,0.000664796,0.00064494356,0.0036164634,0.003636735,0.007818966,0.0014163575,0.0013271385,0.0050835568],"category_scores_gemma":[0.09997675,0.00034521223,0.0005574145,0.0016092316,0.00935917,0.008180084,0.007812447,0.0024767711,0.0003149318],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002797074,0.0013281262,0.017325912,0.0015922656,0.000098961056,0.00026954178,0.016442226,0.002565686,0.0010402197,0.2995805,0.013325687,0.64615124],"study_design_scores_gemma":[0.0010025954,0.0027811825,0.05940411,0.014938952,0.0005499644,0.0011038136,0.0627189,0.03283847,0.019445498,0.5599658,0.24476662,0.00048409257],"about_ca_topic_score_codex":0.0028379867,"about_ca_topic_score_gemma":0.0045686504,"teacher_disagreement_score":0.09324118,"about_ca_system_score_codex":0.008623999,"about_ca_system_score_gemma":0.025181795,"threshold_uncertainty_score":0.4931124},"labels":[],"label_agreement":null},{"id":"W4367030240","doi":"10.3138/cjpe.0019.007","title":"Conducting Evaluation Research with Hard-to-Follow Populations: Adopting a Participant-Centred Approach to Maximize Participant Retention","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Mental Health Association; University of Ottawa","funders":"","keywords":"Interview; Attrition; Participant observation; Psychology; Applied psychology; Investment (military); Medical education; Social psychology; Medicine; Sociology","score_opus":0.9454488731941052,"score_gpt":0.6050153259743052,"score_spread":0.3404335472198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030240","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109169394,0.0014904949,0.44628587,0.009728139,0.00075176934,0.41401538,0.00030300874,0.0008628281,0.017393012],"genre_scores_gemma":[0.1555472,0.00049878244,0.58760375,0.0015595952,0.00014211625,0.2535721,0.00006943751,0.00008316497,0.0009238596],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3548291,0.5930945,0.022239583,0.0056696157,0.02105355,0.0031136486],"domain_scores_gemma":[0.5526016,0.3150714,0.023074578,0.039926145,0.05910266,0.01022365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.5691479,0.0016445615,0.0022441924,0.004523512,0.007832068,0.007505304,0.005005651,0.003755897,0.0042243884],"category_scores_gemma":[0.47468078,0.0018220328,0.0017402902,0.0033199275,0.0052327667,0.0061034253,0.008178057,0.0038583751,0.0012150754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049680993,0.009510919,0.024353884,0.013866437,0.00066130265,0.00077750284,0.10926953,0.0031526426,0.015568658,0.015340245,0.013433186,0.78909755],"study_design_scores_gemma":[0.038533006,0.080905765,0.16669841,0.04675826,0.0030387458,0.002068086,0.17124155,0.037580427,0.11035032,0.112202026,0.22853248,0.0020909458],"about_ca_topic_score_codex":0.0025294481,"about_ca_topic_score_gemma":0.008134464,"teacher_disagreement_score":0.5691479,"about_ca_system_score_codex":0.0069223274,"about_ca_system_score_gemma":0.03539768,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4367030244","doi":"10.3138/cjpe.0015.012","title":"Reflections on Program Evaluation, 35 Years on","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Program evaluation; Psychology; Statistics; Mathematics","score_opus":0.6401574684201251,"score_gpt":0.6365197505771939,"score_spread":0.0036377178429312096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030244","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026566786,0.24886297,0.00063402863,0.72064906,0.011821008,0.000021269901,0.0001459319,0.000045765228,0.01755429],"genre_scores_gemma":[0.028188147,0.5717323,0.0041715405,0.29776093,0.019921849,0.00019538047,0.0004258901,0.00027348788,0.07733043],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97800463,0.011430721,0.0014368161,0.0007458776,0.0070191347,0.0013628252],"domain_scores_gemma":[0.9330597,0.03785126,0.002015421,0.0018424831,0.020811027,0.0044200616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033732332,0.00085120986,0.0009399882,0.0055447537,0.004000844,0.00963539,0.0021848714,0.009011797,0.021888409],"category_scores_gemma":[0.098682344,0.00055155205,0.0007946032,0.008216534,0.009523821,0.012226305,0.0057982397,0.010019344,0.004127162],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041206273,0.000035002875,0.00018820925,0.00042134683,0.000010302866,0.00004303506,0.0006173525,0.00012672035,0.000031790707,0.013321467,0.8781398,0.107023746],"study_design_scores_gemma":[0.0000124393355,0.000014076821,0.0008877593,0.002337611,0.000007836074,0.000036416375,0.0010517063,0.000024658748,0.00004172328,0.008183042,0.98738724,0.000015520873],"about_ca_topic_score_codex":0.09703814,"about_ca_topic_score_gemma":0.15890811,"teacher_disagreement_score":0.09703814,"about_ca_system_score_codex":0.01628014,"about_ca_system_score_gemma":0.02459967,"threshold_uncertainty_score":0.19294667},"labels":[],"label_agreement":null},{"id":"W4367030246","doi":"10.3138/cjpe.0019.006","title":"Creating Inclusive Workplaces: Employing People with Psychiatric Disabilities in Evaluation and Research in Community Mental Health","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Mental health; Equity (law); Rigour; Psychology; Psychiatry; Public relations; Political science","score_opus":0.4735733748112833,"score_gpt":0.5352069297284419,"score_spread":0.06163355491715855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030246","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65764976,0.004443742,0.19616237,0.06158138,0.0010202584,0.02183644,0.00034259446,0.0006008748,0.056362595],"genre_scores_gemma":[0.7852359,0.0010431836,0.19232064,0.00364766,0.00015463572,0.015483927,0.000102794686,0.000032873802,0.0019784023],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.73926115,0.24020126,0.0069958926,0.0015829161,0.008502033,0.0034567574],"domain_scores_gemma":[0.8213657,0.10949944,0.012227427,0.018789921,0.022823164,0.015294366],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2430438,0.0003878599,0.00060553406,0.0035274553,0.008901387,0.009639609,0.002242167,0.002667557,0.0032232255],"category_scores_gemma":[0.21706158,0.00086659135,0.00088656944,0.0020225018,0.0053595807,0.0071003474,0.026394125,0.0030973593,0.0006326995],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009513283,0.0064758286,0.03892985,0.0021939455,0.00017181678,0.0007371521,0.11246221,0.0014444318,0.0023164696,0.027284335,0.013735862,0.79329675],"study_design_scores_gemma":[0.0032449923,0.010022885,0.12819102,0.01348172,0.00069672463,0.0021673455,0.45539287,0.013338021,0.017356716,0.17231068,0.18303488,0.0007621402],"about_ca_topic_score_codex":0.0029591997,"about_ca_topic_score_gemma":0.010519503,"teacher_disagreement_score":0.2430438,"about_ca_system_score_codex":0.00558006,"about_ca_system_score_gemma":0.027679821,"threshold_uncertainty_score":0.9334618},"labels":[],"label_agreement":null},{"id":"W4367030253","doi":"10.3138/cjpe.25.001","title":"Gauging Alignments: An Ethnographically Informed Method for Process Evaluation in a Community-Based Intervention","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Lethbridge","funders":"","keywords":"Operationalization; Psychological intervention; Process (computing); Intervention (counseling); Field (mathematics); Ethnography; Computer science; Psychology; Knowledge management; Sociology; Epistemology","score_opus":0.7205975325689408,"score_gpt":0.7426925408260218,"score_spread":0.022095008257080995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030253","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33402392,0.00033497188,0.5639075,0.001254027,0.00020423392,0.062539816,0.0011665171,0.0008969212,0.035672016],"genre_scores_gemma":[0.29355317,0.00019013422,0.6460681,0.0002819184,0.000025140558,0.057581574,0.00023884408,0.00011377863,0.0019473454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.822384,0.16132122,0.0048240814,0.0040244944,0.006042995,0.001403201],"domain_scores_gemma":[0.8272617,0.13253982,0.008666957,0.014605049,0.015280587,0.0016458972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09933407,0.0017770504,0.0009640675,0.007132685,0.005587198,0.0047176727,0.002703375,0.0014344341,0.005567282],"category_scores_gemma":[0.11881563,0.0010229343,0.0009113972,0.0049900077,0.0061595123,0.004161218,0.0064171846,0.0023691708,0.00074913475],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013784673,0.0036286619,0.026755175,0.0029603709,0.00015798457,0.0008339067,0.41784063,0.0035809493,0.018595764,0.03180533,0.0046751443,0.4877877],"study_design_scores_gemma":[0.0033711854,0.010000568,0.07959407,0.007136636,0.0006674463,0.0009952568,0.6100451,0.044812143,0.051722955,0.089117326,0.101267695,0.0012696628],"about_ca_topic_score_codex":0.0047260653,"about_ca_topic_score_gemma":0.011265511,"teacher_disagreement_score":0.09933407,"about_ca_system_score_codex":0.0051691066,"about_ca_system_score_gemma":0.012483149,"threshold_uncertainty_score":0.5253351},"labels":[],"label_agreement":null},{"id":"W4367030268","doi":"10.3138/cjpe.0019.009","title":"The Use of the Multnomah Community Ability Scale as a Program Evaluation Tool","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Schizophrenia research and treatment","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Ottawa; University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Scale (ratio); Reliability (semiconductor); Mental health; Psychology; Mental illness; Relevance (law); Program evaluation; Measure (data warehouse); Applied psychology; Psychiatry; Computer science; Data mining","score_opus":0.23256051274039477,"score_gpt":0.43300053836600133,"score_spread":0.20044002562560656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9645395,0.00085985224,0.002922622,0.00094754196,0.00013330903,0.00437737,0.0026660818,0.00016517594,0.02338861],"genre_scores_gemma":[0.9864889,0.0002507467,0.00781298,0.00008909336,0.00003256018,0.0027064509,0.0011828109,0.0000122788,0.0014240928],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99400336,0.0023557644,0.00062027754,0.00017267067,0.0025536173,0.00029423297],"domain_scores_gemma":[0.9905703,0.0024844243,0.0018267182,0.000258046,0.003677648,0.0011828857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007255325,0.00028828962,0.0006121306,0.0027747748,0.00075432804,0.0008581353,0.0006468496,0.00026696842,0.0029289075],"category_scores_gemma":[0.017059015,0.00013340551,0.00063441624,0.0011663022,0.0003983004,0.00069249223,0.0011401909,0.00086117804,0.00032365613],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072158186,0.002111352,0.73863786,0.00042070838,0.0002755452,0.00018281616,0.0013515076,0.0007035582,0.0007662542,0.00076549384,0.011479081,0.24258429],"study_design_scores_gemma":[0.00016981064,0.0011830203,0.992035,0.0001793765,0.000051910516,0.0000954065,0.00062388007,0.001757722,0.00059827033,0.00023726092,0.0030417263,0.000026530952],"about_ca_topic_score_codex":0.012248922,"about_ca_topic_score_gemma":0.03018047,"teacher_disagreement_score":0.012248922,"about_ca_system_score_codex":0.0014291009,"about_ca_system_score_gemma":0.0034995752,"threshold_uncertainty_score":0.03837031},"labels":[],"label_agreement":null},{"id":"W4367030275","doi":"10.3138/cjpe.025.007","title":"Nick L. Smith &amp; Paul R. Brandon (Éds.). (2008). <i>Fundamental Issues in Evaluation</i> . New-York: Guilford, 266 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.35888501749321366,"score_gpt":0.5087863772677234,"score_spread":0.1499013597745097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030275","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027281934,0.95318127,0.0033729484,0.020199735,0.003549626,0.00003055867,0.00039516,0.00015273361,0.018845163],"genre_scores_gemma":[0.0034314906,0.95138067,0.0041316333,0.0016862247,0.0017791748,0.000039612416,0.00024869433,0.00008497578,0.037217587],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988663,0.0003044512,0.000103467806,0.000113501555,0.0005536234,0.000058648002],"domain_scores_gemma":[0.99602675,0.002137483,0.00027556674,0.000083978455,0.0011503288,0.0003258609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034960783,0.0022674862,0.0015430106,0.0027974956,0.0010384431,0.0039610774,0.0015229413,0.0028650123,0.039102186],"category_scores_gemma":[0.006123753,0.0014734511,0.0005002698,0.0044078487,0.0015263166,0.0071879053,0.0010244221,0.002408113,0.028085783],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003788987,0.000025472968,0.00033677637,0.0012589503,0.000014760024,0.00003721468,0.0002612209,0.00021590636,0.000106440944,0.0022869385,0.6904423,0.30497605],"study_design_scores_gemma":[0.000018597892,0.00004134154,0.0018223565,0.0030934326,0.00005565909,0.00034777346,0.000595522,0.00025241432,0.00042877832,0.008418081,0.9848904,0.00003550311],"about_ca_topic_score_codex":0.03255333,"about_ca_topic_score_gemma":0.09606973,"teacher_disagreement_score":0.039102186,"about_ca_system_score_codex":0.0022103123,"about_ca_system_score_gemma":0.0051011373,"threshold_uncertainty_score":0.1308099},"labels":[],"label_agreement":null},{"id":"W4367030280","doi":"10.3138/cjpe.025.008","title":"R. Bickel. (2007). <i>Multilevel Analysis for Applied Research: It’s Just Regression!</i> New York, NY: Guilford, 355 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Diverse Educational Innovations Studies","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Multilevel model; Regression analysis; Regression; Psychology; Regional science; Sociology; Statistics; Mathematics; Psychoanalysis","score_opus":0.6609894723349435,"score_gpt":0.45691838204747054,"score_spread":0.204071090287473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030280","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031355382,0.22810504,0.599121,0.06375045,0.019117856,0.0012500209,0.029056484,0.015930891,0.040532753],"genre_scores_gemma":[0.04151678,0.08897994,0.7844599,0.009031449,0.003947219,0.0050498,0.010690519,0.021524003,0.0348004],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9834674,0.009845404,0.001500182,0.0014005849,0.0034031994,0.00038322905],"domain_scores_gemma":[0.8127475,0.13932005,0.0044930554,0.0090474775,0.033047717,0.0013442977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036403585,0.0054225596,0.004238519,0.009395558,0.0040403395,0.005466793,0.004100173,0.004046413,0.05554266],"category_scores_gemma":[0.16835587,0.0071763895,0.004479547,0.016392743,0.005036651,0.005812598,0.0039894767,0.012346718,0.03751777],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001539196,0.00006303824,0.0014103439,0.0014933154,0.00030974613,0.000101739,0.00068079296,0.001796679,0.00018534334,0.019547364,0.70523596,0.26902175],"study_design_scores_gemma":[0.00044991582,0.00018437867,0.019413246,0.010335134,0.0013311408,0.0006111918,0.0013007479,0.009718535,0.0027586902,0.18489575,0.768171,0.0008303112],"about_ca_topic_score_codex":0.060893666,"about_ca_topic_score_gemma":0.07998928,"teacher_disagreement_score":0.060893666,"about_ca_system_score_codex":0.00383683,"about_ca_system_score_gemma":0.0079356665,"threshold_uncertainty_score":0.19252282},"labels":[],"label_agreement":null},{"id":"W4367030286","doi":"10.3138/cjpe.25.005","title":"Managing Evaluataion: Responding to Common Problems with a 10-Step Process","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Centers for Disease Control and Prevention","keywords":"Conceptualization; Process (computing); Stakeholder; Unit (ring theory); Public sector; Relation (database); Business; Process management; Program evaluation; Knowledge management; Management science; Public relations; Sociology; Psychology; Computer science; Political science; Economics; Public administration","score_opus":0.2596048059938968,"score_gpt":0.5263633695337143,"score_spread":0.26675856353981753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030286","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12416125,0.0020649445,0.6609525,0.13679838,0.0012146084,0.005674545,0.000098729775,0.0022519364,0.0667831],"genre_scores_gemma":[0.36718163,0.0011522373,0.60030943,0.0076569957,0.00021452273,0.0062432354,0.00017112543,0.00042725602,0.016643578],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6514503,0.28825524,0.012989446,0.007828985,0.032764863,0.006711126],"domain_scores_gemma":[0.59919757,0.26307985,0.02487104,0.030508012,0.066819705,0.015523912],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2811746,0.0016530133,0.001075801,0.004586817,0.012543349,0.020007074,0.0085645635,0.008646193,0.0057410016],"category_scores_gemma":[0.28694367,0.0017976707,0.0013749191,0.003304091,0.023167528,0.020064035,0.025849458,0.015219478,0.0020697422],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044160336,0.0017495024,0.017095858,0.0029526036,0.00015836844,0.0015726209,0.25003397,0.006613582,0.0032035864,0.25917324,0.030372426,0.42663255],"study_design_scores_gemma":[0.00047142382,0.0016930505,0.010702738,0.0066829287,0.00017278874,0.0021037706,0.19348629,0.038674857,0.00799692,0.37986097,0.3575155,0.0006387458],"about_ca_topic_score_codex":0.0066921664,"about_ca_topic_score_gemma":0.011893517,"teacher_disagreement_score":0.2811746,"about_ca_system_score_codex":0.025434695,"about_ca_system_score_gemma":0.084332116,"threshold_uncertainty_score":0.8864397},"labels":[],"label_agreement":null},{"id":"W4367030289","doi":"10.3138/cjpe.025.001","title":"Putting God in the Logic Model: Developing a National Framework for the Evaluation of Faith-Based Organizations","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Religion, Society, and Development","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Wilfrid Laurier University; Centre for Community Based Research","funders":"","keywords":"Faith; Scrutiny; Centrality; Sociology; Psychological intervention; Epistemology; Political science; Law; Psychology; Philosophy","score_opus":0.2012507351051212,"score_gpt":0.4513111432402284,"score_spread":0.2500604081351072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030289","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03539226,0.0043487083,0.4358283,0.16279191,0.0008543542,0.003962861,0.00027550483,0.00027218089,0.35627395],"genre_scores_gemma":[0.5717633,0.00094537763,0.41465068,0.005797246,0.00006456899,0.0032338975,0.0000994965,0.00005735665,0.003388173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.81895065,0.1581454,0.005592245,0.003147676,0.011373417,0.0027906417],"domain_scores_gemma":[0.8739599,0.075702734,0.0047931443,0.008261034,0.032615844,0.0046673147],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2104787,0.00082598015,0.0014865396,0.009584838,0.013083463,0.019335223,0.0038761601,0.0043175383,0.003275896],"category_scores_gemma":[0.110902086,0.0006244349,0.0013101564,0.004299292,0.050271112,0.019691236,0.009812132,0.0065554865,0.00040137352],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032760698,0.000084355976,0.0017948167,0.00036995733,0.000025878679,0.00006473993,0.014863874,0.000915931,0.00010853412,0.95192146,0.0030586624,0.02675902],"study_design_scores_gemma":[0.000119590586,0.00020498941,0.003691383,0.0053781723,0.00013492431,0.00016457748,0.056687795,0.009736319,0.0007795022,0.84135205,0.081638776,0.000111853944],"about_ca_topic_score_codex":0.088434964,"about_ca_topic_score_gemma":0.17124435,"teacher_disagreement_score":0.2104787,"about_ca_system_score_codex":0.08240669,"about_ca_system_score_gemma":0.15026811,"threshold_uncertainty_score":0.97362036},"labels":[],"label_agreement":null},{"id":"W4367030294","doi":"10.3138/cjpe.0019.008","title":"Inside the Black Box: Challenges in Implementation Evaluation of Community Mental Health Case Management Programs","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychiatric care and mental health services","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Toronto; Canadian Mental Health Association; St. Michael's Hospital","funders":"","keywords":"Assertive community treatment; Fidelity; General partnership; Mental health; Context (archaeology); Case management; Assertiveness; Process (computing); Scale (ratio); Mental illness; Agency (philosophy); Psychology; Process management; Applied psychology; Knowledge management; Medical education; Computer science; Business; Medicine; Psychiatry; Social psychology; Sociology","score_opus":0.34120571754707946,"score_gpt":0.515833388829458,"score_spread":0.1746276712823785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42651033,0.016980177,0.32812393,0.112617284,0.0031022949,0.061149612,0.0011821537,0.002107784,0.04822642],"genre_scores_gemma":[0.6879026,0.0014395409,0.27196023,0.006088808,0.0003360437,0.030495783,0.00030692638,0.0003184374,0.0011515591],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.19273226,0.7105023,0.027755087,0.006387386,0.058506973,0.0041161086],"domain_scores_gemma":[0.124622725,0.73116887,0.023492614,0.032634046,0.0806527,0.0074292063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.7149213,0.0016865598,0.004371168,0.0053107645,0.0069851526,0.016716393,0.009236988,0.0052851406,0.0034274533],"category_scores_gemma":[0.7645617,0.0020529178,0.0029001613,0.0054395255,0.010037825,0.018781047,0.010835347,0.0076646158,0.00087068556],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002519711,0.0049359733,0.049750015,0.0070931953,0.000984609,0.00023762535,0.045407817,0.005827199,0.0008504499,0.017308902,0.012673915,0.8524106],"study_design_scores_gemma":[0.00881338,0.04468118,0.29281354,0.10463537,0.0020633896,0.0017038743,0.17267181,0.12464215,0.012343916,0.11040985,0.12307359,0.0021480548],"about_ca_topic_score_codex":0.0191775,"about_ca_topic_score_gemma":0.021648742,"teacher_disagreement_score":0.7149213,"about_ca_system_score_codex":0.025164198,"about_ca_system_score_gemma":0.057693753,"threshold_uncertainty_score":0.35155284},"labels":[],"label_agreement":null},{"id":"W4367030296","doi":"10.3138/cjpe.025.009","title":"D.J. Treiman. (2009). <i>Quantitative Data Analysis: Doing Social Research to Test Ideas.</i> San Francisco, CA: Jossey-Bass.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Research Methods and Applications","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bass (fish); Psychology; Sociology; Fishery; Biology","score_opus":0.5524727847371994,"score_gpt":0.6475592487572489,"score_spread":0.0950864640200495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030296","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042678304,0.37685108,0.2788087,0.15810892,0.019997176,0.0033142292,0.00828485,0.004503564,0.14586358],"genre_scores_gemma":[0.05837609,0.38235933,0.44427148,0.02201111,0.0033799966,0.007309187,0.0041381945,0.003082774,0.07507173],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9824532,0.0087201,0.0024181553,0.0007382828,0.0054378645,0.00023242479],"domain_scores_gemma":[0.8495384,0.09773965,0.0059945798,0.005136767,0.0395627,0.0020280047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05345254,0.0020619722,0.0015068421,0.008916742,0.0055380603,0.006153937,0.002863276,0.0031337868,0.022336395],"category_scores_gemma":[0.10184742,0.003729041,0.0014340545,0.00819558,0.0072017307,0.008746695,0.0025459633,0.009935696,0.016114634],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007549285,0.000079847276,0.0016361534,0.0033922782,0.00006111195,0.00017446453,0.0050773867,0.00029006563,0.000549292,0.017863294,0.5951985,0.375602],"study_design_scores_gemma":[0.0001108595,0.00020222977,0.013928016,0.018538997,0.00030756253,0.00079615397,0.007944414,0.000754625,0.0025290237,0.057015892,0.897564,0.00030823683],"about_ca_topic_score_codex":0.0396709,"about_ca_topic_score_gemma":0.10263081,"teacher_disagreement_score":0.05345254,"about_ca_system_score_codex":0.0043237293,"about_ca_system_score_gemma":0.015048628,"threshold_uncertainty_score":0.28268743},"labels":[],"label_agreement":null},{"id":"W4367030299","doi":"10.3138/cjpe.25.004","title":"Jugement crédible en évaluation de programme : définition et conditions requises","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Viewpoints; Argumentation theory; Valuation (finance); Coherence (philosophical gambling strategy); Management science; Psychology; Quality (philosophy); Sociology; Epistemology; Business; Economics; Philosophy; Mathematics; Accounting","score_opus":0.4673144395102768,"score_gpt":0.5733540275195889,"score_spread":0.10603958800931207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030299","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.288871,0.009469324,0.52057874,0.056817092,0.0007159407,0.014769424,0.00047939227,0.00045994058,0.10783919],"genre_scores_gemma":[0.8152835,0.0011785292,0.17510736,0.00081111985,0.0002527373,0.006100713,0.00023924261,0.000049861417,0.0009770365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6971689,0.20275392,0.033584554,0.010502016,0.051181607,0.0048089875],"domain_scores_gemma":[0.27700692,0.59785,0.04321802,0.02303786,0.0539307,0.004956513],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23962875,0.0010492501,0.0020612658,0.0038850633,0.005266835,0.01670891,0.0030029693,0.009813621,0.004926057],"category_scores_gemma":[0.52592283,0.0011353007,0.0009931485,0.0030963728,0.026095493,0.023989886,0.010197319,0.0082632275,0.00073844544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012119701,0.0013775573,0.024138307,0.0073570046,0.00013123399,0.0019018133,0.06947345,0.0060448516,0.0070448415,0.7184053,0.004949204,0.15796453],"study_design_scores_gemma":[0.0011534315,0.0031465068,0.039074518,0.017296458,0.0003286629,0.0052709533,0.07386509,0.04626368,0.04001469,0.65188473,0.120802075,0.0008992118],"about_ca_topic_score_codex":0.0022312265,"about_ca_topic_score_gemma":0.0021029557,"teacher_disagreement_score":0.23962875,"about_ca_system_score_codex":0.009496669,"about_ca_system_score_gemma":0.022895904,"threshold_uncertainty_score":0.93767315},"labels":[],"label_agreement":null},{"id":"W4367157587","doi":"10.3138/cjpe.36.3.423","title":"Peer Reviewers for Volume 36 and Manuscripts Submitted in 2021 / Examinateurs des manuscrits du volume 36 et des manuscrits soumis en 2021","year":2022,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Medical Research and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Art; Physics","score_opus":0.14104167154593525,"score_gpt":0.390689681782057,"score_spread":0.24964801023612174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367157587","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014362865,0.019146489,0.0074726488,0.13988343,0.66080785,0.010499874,0.015266149,0.0046609594,0.12789974],"genre_scores_gemma":[0.030613754,0.015283749,0.018387452,0.01754471,0.1393966,0.004885038,0.009429201,0.0035622725,0.7608973],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97368,0.0041965167,0.0038371119,0.0016714284,0.014918564,0.0016962899],"domain_scores_gemma":[0.68245745,0.015885385,0.009302714,0.0067230784,0.26089126,0.02474009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023097407,0.002018013,0.0029519603,0.011961386,0.005529102,0.011364736,0.0022907723,0.0049414826,0.21864697],"category_scores_gemma":[0.11188565,0.0009668662,0.0020586036,0.0056211906,0.0013341754,0.003536076,0.0030607777,0.0031420859,0.13545875],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003755033,0.00007496756,0.0013100049,0.0008386954,0.00004269177,0.00020740308,0.00014634912,0.00004951808,0.00071409094,0.0005255561,0.9419079,0.0538074],"study_design_scores_gemma":[0.00017134286,0.00015326228,0.0049073473,0.0006094126,0.000056422217,0.0002449769,0.00040067386,0.0002053138,0.000889214,0.00097574334,0.99133706,0.000049174425],"about_ca_topic_score_codex":0.0049803318,"about_ca_topic_score_gemma":0.0148274265,"teacher_disagreement_score":0.21864697,"about_ca_system_score_codex":0.0028876623,"about_ca_system_score_gemma":0.023470793,"threshold_uncertainty_score":0.731447},"labels":[],"label_agreement":null},{"id":"W4384703998","doi":"10.3138/cjpe.75786","title":"Behind the Virtual Curtain: Techniques to Bring the CAE Principles to Life","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Work (physics); Engineering management; Computer science; Engineering; Engineering ethics; Mechanical engineering","score_opus":0.45754876663050736,"score_gpt":0.5220303242972517,"score_spread":0.06448155766674435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384703998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013682574,0.000523312,0.9122544,0.009552168,0.0003423158,0.0011573598,0.00003920519,0.0007816333,0.061666988],"genre_scores_gemma":[0.17986591,0.0004121936,0.8065255,0.0009790732,0.00006421638,0.0011828131,0.00004578557,0.0003471677,0.010577349],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9396692,0.048322435,0.0017237801,0.0025283399,0.0066827694,0.0010735242],"domain_scores_gemma":[0.92045194,0.055961527,0.0022032247,0.0131959645,0.0069281445,0.0012591941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043300882,0.0009965929,0.0006119699,0.0048615267,0.008481457,0.013606749,0.0028606183,0.0032554064,0.0063977856],"category_scores_gemma":[0.080872715,0.0009458146,0.0012167171,0.002317341,0.024344467,0.016508192,0.013071782,0.0062122364,0.0016452756],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076146534,0.00026280014,0.0012098057,0.0005416993,0.000038094207,0.00046656866,0.14674173,0.001721763,0.0028907538,0.61280954,0.0089956755,0.22424538],"study_design_scores_gemma":[0.00009158258,0.00032074694,0.0012959503,0.0011501912,0.0000543706,0.0012378397,0.08402114,0.009980778,0.007950417,0.43153206,0.46218124,0.00018367481],"about_ca_topic_score_codex":0.0030486132,"about_ca_topic_score_gemma":0.0063081924,"teacher_disagreement_score":0.043300882,"about_ca_system_score_codex":0.0040066647,"about_ca_system_score_gemma":0.0069841905,"threshold_uncertainty_score":0.22899967},"labels":[],"label_agreement":null},{"id":"W4384704009","doi":"10.3138/cjpe.75471","title":"Doing the Inner Work for Sustainable Practices","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mindset; Work (physics); Sociology; Grounded theory; Reflective practice; Engineering ethics; Psychology; Epistemology; Public relations; Pedagogy; Qualitative research; Social science; Political science; Engineering","score_opus":0.46181610888955293,"score_gpt":0.5772504504403074,"score_spread":0.1154343415507545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704009","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032896485,0.009827822,0.19918856,0.30972728,0.006691965,0.00097207096,0.0000921636,0.0007393064,0.4398644],"genre_scores_gemma":[0.733602,0.008682368,0.1708067,0.034543503,0.0013000936,0.0014724799,0.00009717273,0.00088132394,0.048614524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8736375,0.10173652,0.0026515967,0.003476143,0.014442765,0.0040555466],"domain_scores_gemma":[0.85521805,0.0958932,0.0059169712,0.016081106,0.017035367,0.009855398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08620828,0.0012214949,0.00123157,0.0032296896,0.020196285,0.04180485,0.002705671,0.0067887907,0.012378641],"category_scores_gemma":[0.083425894,0.0010106234,0.0015615374,0.0023773795,0.06011745,0.026003813,0.028867792,0.0152964685,0.003401054],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055147117,0.00040841263,0.0023689773,0.0011417745,0.00008269694,0.0004288551,0.20697002,0.0007566025,0.0009671484,0.58054376,0.045003463,0.16127317],"study_design_scores_gemma":[0.00003298732,0.00019252686,0.0011687198,0.003586837,0.0000722462,0.0005644477,0.12147985,0.00063893426,0.0018337223,0.2672217,0.6030712,0.00013671299],"about_ca_topic_score_codex":0.006135495,"about_ca_topic_score_gemma":0.011188477,"teacher_disagreement_score":0.08620828,"about_ca_system_score_codex":0.012914715,"about_ca_system_score_gemma":0.04615595,"threshold_uncertainty_score":0.45591837},"labels":[],"label_agreement":null},{"id":"W4384704011","doi":"10.3138/cjpe.74373","title":"Building Capacity With Evaluation Standards and Guidelines in Prince Edward Island: Responding to Academics’ “Call to Action”","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Government (linguistics); Process (computing); Action (physics); Capacity building; Public relations; Political science; Resource (disambiguation); Public administration; Business; Sociology; Computer science; Law","score_opus":0.422866600441089,"score_gpt":0.5731474583533296,"score_spread":0.1502808579122406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704011","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02222889,0.0066269618,0.028359488,0.9041465,0.0020616,0.0020091862,0.00007167401,0.0003962621,0.034099452],"genre_scores_gemma":[0.3728612,0.013032928,0.39586705,0.1820149,0.0010901854,0.0048167226,0.0004073704,0.00041628903,0.029493455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.70612216,0.2048449,0.027071472,0.0058596157,0.045475,0.010626839],"domain_scores_gemma":[0.3560893,0.3174069,0.025942337,0.037076194,0.2331691,0.030316126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.37710905,0.0007766522,0.0011058805,0.006146379,0.017960127,0.02510639,0.008301705,0.013310692,0.0024822426],"category_scores_gemma":[0.34402335,0.0018058384,0.0012332769,0.0044248058,0.025021378,0.015058421,0.027319212,0.02437482,0.0011483156],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011844744,0.0009518553,0.015520112,0.0030346974,0.0001537848,0.0024917,0.13541482,0.0039209053,0.0024907785,0.17393371,0.31876555,0.3432037],"study_design_scores_gemma":[0.00013561142,0.0002812249,0.013410406,0.010310459,0.00008060391,0.00083969976,0.11920225,0.0032188566,0.003340724,0.07564934,0.7730136,0.0005173018],"about_ca_topic_score_codex":0.20752802,"about_ca_topic_score_gemma":0.357684,"teacher_disagreement_score":0.935634,"about_ca_system_score_codex":0.06436601,"about_ca_system_score_gemma":0.39682817,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4384704021","doi":"10.3138/cjpe.76349","title":"Sustainability-Ready Evaluation: A Call to Action","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustainability; Nexus (standard); Call to action; Work (physics); Action (physics); Sustainability science; Environmental resource management; Business; Sustainability organizations; Environmental planning; Political science; Computer science; Engineering; Ecology; Marketing; Geography; Economics","score_opus":0.5953134200335379,"score_gpt":0.6226408964927189,"score_spread":0.027327476459180988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704021","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035574535,0.009286715,0.0046644723,0.9780294,0.0038181522,0.00010901707,0.00002372856,0.0001673186,0.0035454873],"genre_scores_gemma":[0.046713118,0.028432723,0.073660895,0.8336502,0.009620207,0.0011502982,0.00024076174,0.0004441969,0.006087637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5569977,0.31049633,0.020453338,0.012415177,0.08443131,0.015206262],"domain_scores_gemma":[0.23639418,0.5403627,0.015614744,0.028726771,0.1026893,0.076212265],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.47655994,0.0026374464,0.0063250065,0.0068225944,0.016423509,0.03952872,0.011889372,0.050506614,0.013898084],"category_scores_gemma":[0.4634505,0.0018376757,0.0060335337,0.005496797,0.0584407,0.054259703,0.03205206,0.08239473,0.0034328261],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002383213,0.0007080132,0.0018778481,0.0032331848,0.00020890133,0.0003364424,0.0078092264,0.0010796812,0.0004210241,0.11997579,0.6620186,0.20209289],"study_design_scores_gemma":[0.0002388752,0.00025106638,0.0020215514,0.013279169,0.00012163305,0.00037786487,0.015713962,0.0011513082,0.00041565925,0.22223616,0.7438359,0.0003568543],"about_ca_topic_score_codex":0.030877324,"about_ca_topic_score_gemma":0.04381654,"teacher_disagreement_score":0.47655994,"about_ca_system_score_codex":0.043432917,"about_ca_system_score_gemma":0.29931867,"threshold_uncertainty_score":0.6454948},"labels":[],"label_agreement":null},{"id":"W4384704058","doi":"10.3138/cjpe.75486","title":"Creating and Implementing an Indigenous Evaluation Framework Process With Minnesota Tribes","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Process (computing); Resource (disambiguation); Traditional knowledge; Work (physics); Sociology; Best practice; Culturally appropriate; Public relations; Political science; Computer science; Engineering; Gerontology; Law; Medicine; Ecology","score_opus":0.07244851493116858,"score_gpt":0.44289296833628083,"score_spread":0.37044445340511223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39291614,0.0016162246,0.30176142,0.09051997,0.0019141249,0.035202745,0.00033777097,0.0011826695,0.17454892],"genre_scores_gemma":[0.6228465,0.00064680155,0.327676,0.00562107,0.0001408636,0.012535139,0.0001719834,0.00026288815,0.030098835],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.855968,0.1192467,0.00431324,0.0040219002,0.010767552,0.0056825355],"domain_scores_gemma":[0.88530713,0.04070573,0.0032891906,0.0099225165,0.043982353,0.016793136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25680813,0.00053309696,0.0005352599,0.0027384262,0.024411822,0.01195894,0.0032760145,0.0021697609,0.0039966223],"category_scores_gemma":[0.09909655,0.0008810196,0.0006781426,0.0015343066,0.009280479,0.0061521726,0.01490436,0.0057954993,0.00075850345],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013524672,0.0013183283,0.008581574,0.0003074993,0.000047208963,0.00131599,0.7371607,0.0021299873,0.0026067812,0.047869172,0.021777669,0.17674981],"study_design_scores_gemma":[0.00011867871,0.0007324031,0.011282238,0.0017813373,0.000060387134,0.00038105526,0.6305253,0.005200293,0.0035904902,0.02782314,0.31825027,0.00025445435],"about_ca_topic_score_codex":0.10917771,"about_ca_topic_score_gemma":0.33085784,"teacher_disagreement_score":0.25680813,"about_ca_system_score_codex":0.042052675,"about_ca_system_score_gemma":0.15873237,"threshold_uncertainty_score":0.9164879},"labels":[],"label_agreement":null},{"id":"W4384704066","doi":"10.3138/cjpe.38.1.ed-fr","title":"Un mot de la rédactrice","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Psychology","score_opus":0.11514319283525193,"score_gpt":0.38527159884555906,"score_spread":0.27012840601030713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704066","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030926159,0.012323106,0.0064204484,0.2505767,0.032736402,0.0001701708,0.00036931646,0.0004458445,0.6938653],"genre_scores_gemma":[0.06956082,0.010983279,0.0074175005,0.06694469,0.0116184745,0.00040540026,0.00047087704,0.0009975871,0.83160144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97544676,0.008909223,0.00088545383,0.0024079198,0.010146784,0.002203781],"domain_scores_gemma":[0.96812826,0.007614315,0.0013425505,0.003988659,0.014790974,0.004135268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013477585,0.0008716294,0.0007106999,0.0023298452,0.009841094,0.01662104,0.0021216765,0.0057946565,0.081416994],"category_scores_gemma":[0.046047848,0.0006543825,0.0008250496,0.0026244211,0.010033259,0.015179279,0.011112745,0.013991794,0.029517911],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030773837,0.000031909007,0.00057654275,0.00035512555,0.000008019662,0.00020593744,0.007251605,0.000080842474,0.0003458117,0.25919017,0.63268,0.09924332],"study_design_scores_gemma":[0.0000029970129,0.000012010469,0.00035151656,0.0003073242,0.0000029128382,0.0001441334,0.0016155128,0.00003740039,0.00015827239,0.006113195,0.9912411,0.000013525437],"about_ca_topic_score_codex":0.013717164,"about_ca_topic_score_gemma":0.017148968,"teacher_disagreement_score":0.081416994,"about_ca_system_score_codex":0.00854625,"about_ca_system_score_gemma":0.023516707,"threshold_uncertainty_score":0.272367},"labels":[],"label_agreement":null},{"id":"W4384704137","doi":"10.3138/cjpe.76737","title":"<i>Thematic Analysis: A Practical Guide</i> , by Virginia Braun and Victoria Clarke","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Educator Training and Historical Pedagogy","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thematic map; Geography; Cartography","score_opus":0.20504419063999343,"score_gpt":0.4944815391531979,"score_spread":0.28943734851320446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704137","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031039205,0.06786045,0.52438045,0.228302,0.032659873,0.017077466,0.003857763,0.005626974,0.11713116],"genre_scores_gemma":[0.010825994,0.05129959,0.72972053,0.048479583,0.0040847696,0.021701196,0.002447621,0.0043566823,0.12708408],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95747596,0.030329363,0.002578513,0.0024072763,0.0066320007,0.000576847],"domain_scores_gemma":[0.94324535,0.03759671,0.002334365,0.0023888513,0.01236263,0.0020721238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053477336,0.0023876126,0.0021358898,0.005984314,0.007987556,0.0130386595,0.0046550683,0.0051283906,0.015319081],"category_scores_gemma":[0.068714246,0.0030629684,0.0014889984,0.008115556,0.009776104,0.014600892,0.008624178,0.018253004,0.01589188],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032680102,0.00006341883,0.00012780826,0.0011509373,0.000016021053,0.00036640634,0.02948845,0.00037791493,0.0008159383,0.038291954,0.8304487,0.0988198],"study_design_scores_gemma":[0.000008823421,0.000017445169,0.00009281389,0.0017319301,0.000002776569,0.00031845,0.005130886,0.00025822857,0.00016999783,0.014007572,0.9782146,0.000046479872],"about_ca_topic_score_codex":0.010998032,"about_ca_topic_score_gemma":0.01546396,"teacher_disagreement_score":0.053477336,"about_ca_system_score_codex":0.008148865,"about_ca_system_score_gemma":0.021815438,"threshold_uncertainty_score":0.28281856},"labels":[],"label_agreement":null},{"id":"W4384704143","doi":"10.3138/cjpe.71619","title":"How to Conduct a Metaevaluation?: A Metaevaluation Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Strengths and weaknesses; Computer science; Evaluation methods; Quality (philosophy); Process (computing); Management science; Process management; Psychology; Reliability engineering; Social psychology; Business; Engineering","score_opus":0.718641825237931,"score_gpt":0.625746580813898,"score_spread":0.09289524442403296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704143","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008512108,0.086389825,0.72615564,0.10269904,0.01327352,0.047096666,0.0016725032,0.0036611897,0.010539576],"genre_scores_gemma":[0.042027358,0.008288886,0.910902,0.006850825,0.0010013707,0.029494552,0.00019043486,0.0006393413,0.0006052293],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.20118618,0.6808654,0.07364676,0.01334003,0.02995046,0.0010110479],"domain_scores_gemma":[0.10407138,0.7660106,0.028252834,0.05536739,0.043625455,0.0026723556],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73589355,0.0056881206,0.016567249,0.023653269,0.0051441235,0.01873817,0.01031617,0.010666465,0.008334951],"category_scores_gemma":[0.8568293,0.0067315823,0.023323044,0.015301704,0.010111398,0.020891467,0.008308283,0.0138868755,0.002551945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037234193,0.0006951511,0.00872676,0.18181618,0.10635383,0.0010080608,0.024327809,0.009681293,0.0033492194,0.07576649,0.090260774,0.49429107],"study_design_scores_gemma":[0.009671102,0.0023873202,0.0060161403,0.28314972,0.0641422,0.0017693358,0.006718431,0.04947226,0.009313372,0.36335212,0.20209791,0.0019100746],"about_ca_topic_score_codex":0.0035197856,"about_ca_topic_score_gemma":0.0045403475,"teacher_disagreement_score":0.26410645,"about_ca_system_score_codex":0.011770397,"about_ca_system_score_gemma":0.030556781,"threshold_uncertainty_score":0.32569033},"labels":[],"label_agreement":null},{"id":"W4384704152","doi":"10.3138/cjpe.76738","title":"<i>Evaluating and Valuing in Social Research</i> , by Thomas A. Schwandt and Emily F. Gates","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Psychology; Positive economics; Economics","score_opus":0.6880176902655514,"score_gpt":0.6452034549058989,"score_spread":0.04281423535965245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704152","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064779416,0.15401174,0.006029264,0.795745,0.019726936,0.000072391165,0.00008408653,0.00011526822,0.02356743],"genre_scores_gemma":[0.04923505,0.4403208,0.03762157,0.30244738,0.046175625,0.00052133406,0.0002215826,0.00058028655,0.12287637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98163086,0.01014774,0.0011369677,0.0010188054,0.0056482884,0.00041735003],"domain_scores_gemma":[0.94162714,0.04119348,0.0021203628,0.001350489,0.010295504,0.0034129173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031491786,0.0010741466,0.0009500997,0.003951888,0.0044515445,0.012235989,0.00097489747,0.0054662125,0.0035120426],"category_scores_gemma":[0.05435523,0.00066581176,0.0007253627,0.004194047,0.013842647,0.013622803,0.0034632145,0.009902462,0.0024197719],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023426644,0.000017200311,0.000646208,0.0003715912,0.00002051374,0.000061017217,0.0012222277,0.00017013164,0.00019848433,0.040557787,0.9011478,0.05556376],"study_design_scores_gemma":[0.00001119497,0.000033592518,0.0012609564,0.0014708404,0.000018288058,0.0002673507,0.0018877214,0.0005541447,0.00039068828,0.08813342,0.905909,0.00006273988],"about_ca_topic_score_codex":0.016247496,"about_ca_topic_score_gemma":0.05561706,"teacher_disagreement_score":0.031491786,"about_ca_system_score_codex":0.0057221865,"about_ca_system_score_gemma":0.011813149,"threshold_uncertainty_score":0.16654646},"labels":[],"label_agreement":null},{"id":"W4384704212","doi":"10.3138/cjpe.77058-fr","title":"Nos racines et nos liens : une célébration de bons remèdes en évaluation autochtone","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Forestry; Geography","score_opus":0.385499950579361,"score_gpt":0.5506690169872253,"score_spread":0.16516906640786427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704212","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049440876,0.10410572,0.013003888,0.61071557,0.01884759,0.00023821677,0.00020547939,0.00031461785,0.20312808],"genre_scores_gemma":[0.64954436,0.06893246,0.027368162,0.062309925,0.0075141997,0.00047749106,0.00035763488,0.00053330604,0.18296252],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95566714,0.025727237,0.0014682837,0.0012810319,0.014121688,0.0017346862],"domain_scores_gemma":[0.9264641,0.036549173,0.003180574,0.0041919407,0.021759285,0.007854957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05801743,0.00038446282,0.000556481,0.0018642233,0.0045073186,0.01061994,0.00076429016,0.0032591328,0.008093248],"category_scores_gemma":[0.06788648,0.0003349402,0.0005308464,0.0018877857,0.0074374774,0.006683639,0.0070043295,0.0075803897,0.0012024868],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031817236,0.00024592938,0.0033916235,0.0016482072,0.00006494239,0.00047487972,0.045838073,0.00025427403,0.0021288206,0.11655709,0.34283593,0.48624212],"study_design_scores_gemma":[0.000022034834,0.00019222652,0.005410658,0.002680049,0.00002738427,0.00043797996,0.015658407,0.00027326477,0.0009927228,0.01139131,0.96285164,0.00006236892],"about_ca_topic_score_codex":0.0120759,"about_ca_topic_score_gemma":0.052670117,"teacher_disagreement_score":0.05801743,"about_ca_system_score_codex":0.010515027,"about_ca_system_score_gemma":0.019099794,"threshold_uncertainty_score":0.30682915},"labels":[],"label_agreement":null},{"id":"W4384704269","doi":"10.3138/cjpe.75518","title":"Reclaiming Our Narratives: An Indigenous Evaluation Framework for Urban American Indian/Alaska Native Communities","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Indigenous; Sovereignty; Narrative; Traditional knowledge; Decolonization; Sociology; Colonialism; Assertion; Politics; Political science; Law; Ecology","score_opus":0.13130153433392538,"score_gpt":0.45866090809758886,"score_spread":0.3273593737636635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704269","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15380275,0.015713131,0.14853513,0.28525916,0.0022333767,0.005351227,0.00030220725,0.00037148932,0.38843155],"genre_scores_gemma":[0.8706245,0.004716229,0.09511076,0.009929415,0.0002323809,0.0040190844,0.00013646267,0.00020288114,0.0150283575],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.78969824,0.18911327,0.004368978,0.0029956985,0.007395428,0.006428446],"domain_scores_gemma":[0.9099733,0.061952632,0.0035282194,0.0034183047,0.014710242,0.0064172726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18040176,0.0015129073,0.0010262433,0.008024654,0.03547854,0.025405321,0.0060894703,0.0048628026,0.0030627935],"category_scores_gemma":[0.07908553,0.0010312608,0.0011485136,0.0035340153,0.076044254,0.022758482,0.026704028,0.009997634,0.00041678047],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019474004,0.000068145026,0.001306594,0.00032652967,0.000016459657,0.00040556764,0.81015974,0.00029998942,0.00016655878,0.16351412,0.0039351196,0.019781668],"study_design_scores_gemma":[0.000014063209,0.000042113035,0.00079703645,0.0018125518,0.000033494845,0.00015959927,0.8472521,0.00046082938,0.00038463844,0.058667526,0.09032481,0.00005124948],"about_ca_topic_score_codex":0.09201069,"about_ca_topic_score_gemma":0.13104406,"teacher_disagreement_score":0.18040176,"about_ca_system_score_codex":0.057376496,"about_ca_system_score_gemma":0.09763417,"threshold_uncertainty_score":0.9540671},"labels":[],"label_agreement":null},{"id":"W4384704276","doi":"10.3138/cjpe.77058-en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Sociology; Political science; Engineering ethics; Environmental ethics; Medicine; Engineering; Philosophy; Biology; Ecology","score_opus":0.32934335382480695,"score_gpt":0.5403537153913232,"score_spread":0.2110103615665162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704276","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023072952,0.031309508,0.011601224,0.6364505,0.010412597,0.00017519579,0.000029876463,0.00017577267,0.2867723],"genre_scores_gemma":[0.7971361,0.017557962,0.021010691,0.082590625,0.007067809,0.0003571037,0.0000287694,0.00037892855,0.07387201],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.93717045,0.047717724,0.0013226969,0.0016499468,0.009614033,0.0025252646],"domain_scores_gemma":[0.9277114,0.0523948,0.0030281185,0.0038088558,0.007041654,0.0060152505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06698744,0.00045405896,0.0006648891,0.0024038123,0.022697309,0.027672004,0.001889884,0.0069679446,0.0067238105],"category_scores_gemma":[0.0708657,0.0004678917,0.00045602478,0.001880668,0.06601474,0.017659454,0.018238017,0.012358215,0.0008102649],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041990206,0.00008145909,0.00050945487,0.00056778005,0.000020133082,0.00038591537,0.30703503,0.000090044196,0.0004960202,0.51399577,0.07659627,0.1001802],"study_design_scores_gemma":[0.000015191615,0.0000771747,0.0010460854,0.0014997742,0.000023002249,0.0003910647,0.15233633,0.00018642317,0.0006019163,0.13159479,0.7121693,0.00005888845],"about_ca_topic_score_codex":0.010448182,"about_ca_topic_score_gemma":0.037890572,"teacher_disagreement_score":0.06698744,"about_ca_system_score_codex":0.016707877,"about_ca_system_score_gemma":0.028050799,"threshold_uncertainty_score":0.35426766},"labels":[],"label_agreement":null},{"id":"W4384704290","doi":"10.3138/cjpe.71436","title":"Methods to Make Sense of Resilience: Lessons From Participant Coded Micronarratives","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Sustainability and Climate Change Governance","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Livelihood; Psychological resilience; Community resilience; Narrative; Resilience (materials science); Participant observation; Climate change; Environmental resource management; Scale (ratio); Baseline (sea); Sociology; Environmental planning; Geography; Political science; Psychology; Social science; Social psychology; Ecology; Resource (disambiguation); Computer science; Environmental science","score_opus":0.2422532846471531,"score_gpt":0.46578582645173255,"score_spread":0.22353254180457946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704290","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4146321,0.0023942257,0.40920272,0.029240675,0.0011226987,0.019774817,0.002235838,0.00044701665,0.12094991],"genre_scores_gemma":[0.6688712,0.0010695352,0.27584314,0.002172366,0.000084760635,0.031376876,0.0007050445,0.0004137257,0.019463403],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.89863205,0.0885143,0.002507715,0.0033535545,0.0050188075,0.0019735713],"domain_scores_gemma":[0.83553654,0.120185494,0.0045899884,0.014158285,0.022219805,0.0033099852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.113790445,0.0011670009,0.0006440888,0.0043011396,0.013005394,0.0066464976,0.0048622256,0.0022005946,0.012254242],"category_scores_gemma":[0.14083065,0.0008310233,0.0006588575,0.0042503085,0.018626029,0.011462075,0.017607184,0.0040635346,0.001164367],"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":[0.00008219103,0.00010633104,0.0015117864,0.000409803,0.000010021027,0.00030253278,0.9318032,0.00015306663,0.0006811053,0.02249355,0.0023258892,0.040120434],"study_design_scores_gemma":[0.00006934304,0.00009991495,0.0016687299,0.0012931243,0.0000180179,0.0003200475,0.8693935,0.0009344908,0.0025198488,0.038017996,0.08558686,0.00007812718],"about_ca_topic_score_codex":0.014602031,"about_ca_topic_score_gemma":0.03388825,"teacher_disagreement_score":0.113790445,"about_ca_system_score_codex":0.011614768,"about_ca_system_score_gemma":0.017730145,"threshold_uncertainty_score":0.6017886},"labels":[],"label_agreement":null},{"id":"W4384704291","doi":"10.3138/cjpe.38.1.ed-en","title":"Editor’s Remarks","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.3016607384097375,"score_gpt":0.5419447489581198,"score_spread":0.24028401054838233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704291","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000085379965,0.002224633,0.00028975957,0.1405941,0.8403657,0.000050735922,0.00024846502,0.00022862248,0.015912585],"genre_scores_gemma":[0.0026788446,0.0044749565,0.0010449672,0.2659414,0.5134832,0.00021649725,0.00048024912,0.0005609736,0.21111888],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9902024,0.00096109754,0.00085557875,0.0017004744,0.0050277626,0.0012526686],"domain_scores_gemma":[0.96969664,0.0050286613,0.0015040626,0.0018989602,0.01730104,0.0045706644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008796125,0.0017800558,0.0015397011,0.0025814665,0.004401504,0.012516652,0.0047790622,0.013515113,0.1538858],"category_scores_gemma":[0.058198765,0.0007411869,0.0023608746,0.0019453542,0.0023223658,0.0069226297,0.004077528,0.014372692,0.10136002],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008368158,0.000006237374,0.000023046865,0.00005090818,0.0000019994295,0.000040239665,0.000022016317,0.000011555231,0.00003091674,0.00072614755,0.99377453,0.005304018],"study_design_scores_gemma":[0.0000062285476,0.000005435315,0.0000753971,0.00009700606,0.0000020435195,0.000046779285,0.00004421373,0.000022557111,0.00005061526,0.000509451,0.9991334,0.0000069525363],"about_ca_topic_score_codex":0.0021830322,"about_ca_topic_score_gemma":0.0039777127,"teacher_disagreement_score":0.1538858,"about_ca_system_score_codex":0.00359109,"about_ca_system_score_gemma":0.008573257,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4384704311","doi":"10.3138/cjpe.76031","title":"<i>Ethics for Evaluation. Beyond “Doing No Harm” to “Tackling Bad” and “Doing Good”</i> , par Rob van den Berg, Penny Hawkins et Nicoletta Stame (dir.)","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Harm; Psychology; Social psychology","score_opus":0.2641401555920312,"score_gpt":0.5229258898039616,"score_spread":0.2587857342119304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704311","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006091165,0.10783412,0.0016058763,0.8480071,0.024554444,0.00004670236,0.00009184448,0.000084194304,0.017714785],"genre_scores_gemma":[0.011541122,0.09038875,0.008678679,0.7676393,0.07018544,0.0006785678,0.00022481024,0.00047787075,0.050185487],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.90246725,0.05833368,0.0055180336,0.0033511107,0.027517447,0.0028124906],"domain_scores_gemma":[0.87121165,0.08855741,0.0050502317,0.005006727,0.025361506,0.004812379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.073643945,0.0014203192,0.0021259594,0.0020571356,0.0046385424,0.013827482,0.0022652077,0.018447088,0.009137097],"category_scores_gemma":[0.11462553,0.000938415,0.00128714,0.0021585731,0.021798154,0.012670794,0.0054725255,0.024158409,0.0071480973],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015898422,0.000005942098,0.00007333773,0.00027798922,0.000011516981,0.000024066007,0.000367466,0.000024039602,0.000043401596,0.033165377,0.9482549,0.017736062],"study_design_scores_gemma":[0.000021667598,0.000017716027,0.0006969647,0.0021804087,0.0000143927555,0.00016856544,0.00064220896,0.00010913128,0.00011175026,0.07716455,0.91884273,0.000029885861],"about_ca_topic_score_codex":0.028200548,"about_ca_topic_score_gemma":0.05304781,"teacher_disagreement_score":0.073643945,"about_ca_system_score_codex":0.012778717,"about_ca_system_score_gemma":0.023771334,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4390063387","doi":"10.3138/cjpe-2023-0009","title":"Employing Mixed-Methods Citation Analysis to Investigate Transnational Influence in Evaluation Theory","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citation; Affordance; Co-citation; Citation analysis; Equity (law); Epistemology; Sociology; Computer science; Management science; Psychology; Political science; Library science; Cognitive psychology; Engineering","score_opus":0.42274354534197994,"score_gpt":0.6040932728385231,"score_spread":0.18134972749654316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12618099,0.00989934,0.7923341,0.0067610913,0.0015316913,0.010907754,0.0018239546,0.00060081936,0.049960308],"genre_scores_gemma":[0.3933167,0.0025136296,0.57617325,0.0011200251,0.00046557136,0.021426084,0.0008930529,0.00025399897,0.0038377417],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6889658,0.23874813,0.023197496,0.008993659,0.03847578,0.0016191197],"domain_scores_gemma":[0.25213492,0.62223977,0.030118829,0.036217425,0.058219124,0.0010699545],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2476312,0.0011919768,0.002332145,0.030821659,0.0060146665,0.013776649,0.003076709,0.0027150153,0.0058843144],"category_scores_gemma":[0.50415045,0.000701426,0.0025040992,0.03755616,0.004917977,0.011504993,0.0077567147,0.0027916792,0.00059560145],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038077496,0.0005317583,0.0501776,0.008582706,0.0018312423,0.0004592865,0.08268506,0.004750225,0.0020005347,0.4054655,0.0066138995,0.43652138],"study_design_scores_gemma":[0.0005353122,0.0011853417,0.041602746,0.012329736,0.0022380468,0.00065789674,0.06964785,0.050228905,0.012949731,0.68998796,0.117911056,0.0007254616],"about_ca_topic_score_codex":0.0044964585,"about_ca_topic_score_gemma":0.00803627,"teacher_disagreement_score":0.9691783,"about_ca_system_score_codex":0.008115518,"about_ca_system_score_gemma":0.012962691,"threshold_uncertainty_score":0.92780465},"labels":[],"label_agreement":null},{"id":"W4390063458","doi":"10.3138/cjpe-2023-0023","title":"The “What” and “Why” of (Un)Ethical Evaluation Practice: A Meta-Narrative Review and Ethical Awareness Framework","year":2023,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Ontario Council of University Libraries; Wilfrid Laurier University; University of Toronto; University Health Network; Centre for Addiction and Mental Health; The Wilson Centre; York University","funders":"","keywords":"Engineering ethics; Reflexivity; Beneficence; Meta-ethics; Stewardship (theology); Deliberation; Stakeholder; Psychology; Nursing ethics; Sociology; Autonomy; Political science; Public relations; Social science","score_opus":0.7245374058454952,"score_gpt":0.6765867511534138,"score_spread":0.047950654692081374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063458","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011061417,0.8294502,0.056110647,0.07829619,0.0026382427,0.011993276,0.0010411083,0.000088681336,0.00932033],"genre_scores_gemma":[0.29041356,0.4848204,0.14075823,0.027161263,0.0014210102,0.0530932,0.0007680722,0.00011038348,0.0014538341],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.6074957,0.3076602,0.055922788,0.007294475,0.019207794,0.0024190655],"domain_scores_gemma":[0.44408044,0.48440802,0.03317902,0.011733053,0.024708102,0.0018912805],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34336,0.0018515731,0.004646402,0.024987329,0.0046408856,0.012952799,0.0038519588,0.0043970016,0.0027591623],"category_scores_gemma":[0.506155,0.0020114905,0.006513261,0.014687553,0.011677904,0.01825727,0.008315381,0.004800319,0.00033747635],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005089406,0.00008497132,0.00573511,0.4977213,0.0067092762,0.00070865126,0.076059006,0.0015389833,0.0006986641,0.17374495,0.012370493,0.22411954],"study_design_scores_gemma":[0.0001767906,0.00013284161,0.0018350324,0.80400586,0.007672096,0.0005276971,0.024439482,0.0011264035,0.00090135913,0.06326648,0.09579551,0.0001204844],"about_ca_topic_score_codex":0.0073636086,"about_ca_topic_score_gemma":0.018844433,"teacher_disagreement_score":0.995603,"about_ca_system_score_codex":0.02568808,"about_ca_system_score_gemma":0.062551856,"threshold_uncertainty_score":0.809754},"labels":[],"label_agreement":null},{"id":"W4390063483","doi":"10.3138/cjpe.75810","title":"Community-Based Evaluation When Localizing Sustainable Development Goals","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Community Based Research","funders":"","keywords":"Participatory evaluation; Stakeholder; Sustainable development; Citizen journalism; Key (lock); Process management; Evaluation methods; Sustainable community; Community development; Business; Environmental resource management; Environmental planning; Knowledge management; Management science; Computer science; Political science; Public relations; Public administration; Economics; Engineering; Geography","score_opus":0.5017879788631601,"score_gpt":0.5574306116824358,"score_spread":0.05564263281927573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063483","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047360644,0.0039529474,0.24631105,0.028229222,0.0024951454,0.011547023,0.00026451002,0.00073395035,0.6591056],"genre_scores_gemma":[0.725036,0.0015736177,0.23674431,0.0043232497,0.00025179447,0.0091190385,0.00020915722,0.00029298276,0.022449784],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7447476,0.22490402,0.004109832,0.0032447777,0.019128732,0.0038650807],"domain_scores_gemma":[0.877948,0.076693036,0.0037039083,0.0063953437,0.031178838,0.0040808804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14157102,0.0009797567,0.0015005799,0.007479331,0.009482139,0.014080372,0.003664196,0.0034355514,0.012808788],"category_scores_gemma":[0.14738116,0.0006338369,0.0007927767,0.0062082843,0.0078113154,0.011687049,0.014502434,0.005359352,0.0015575665],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000478791,0.0014787205,0.008059889,0.0025611697,0.00015455407,0.00093534833,0.059264213,0.007203913,0.0018689517,0.38958737,0.068869166,0.45953795],"study_design_scores_gemma":[0.00054398674,0.0014956448,0.008768565,0.0087213395,0.00023548998,0.0007426141,0.1623068,0.022102475,0.006105167,0.27148384,0.51711357,0.00038046247],"about_ca_topic_score_codex":0.018350193,"about_ca_topic_score_gemma":0.057957698,"teacher_disagreement_score":0.14157102,"about_ca_system_score_codex":0.014000605,"about_ca_system_score_gemma":0.025866332,"threshold_uncertainty_score":0.748708},"labels":[],"label_agreement":null},{"id":"W4390063549","doi":"10.3138/cjpe-2023-0031","title":"Process Evaluation of a Cooking Circle Program in the Arctic: Developing the Mukluk Logic Model and Identifying Key Enablers and Barriers for Program Implementation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Studies and Ecology","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo; Centre hospitalier de l'Université Laval; University of Ottawa; Government of Northwest Territories; Université Laval; Inuvialuit Regional Corporation","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Sustainability; Logic model; Conceptualization; Context (archaeology); Process (computing); Program evaluation; Process management; Consistency (knowledge bases); Program Design Language; Business; Computer science; Knowledge management; Environmental resource management; Sociology; Political science; Geography; Ecology; Environmental science","score_opus":0.33331312870332336,"score_gpt":0.5400006065959154,"score_spread":0.20668747789259206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8893147,0.0009435838,0.046409953,0.0042175115,0.00009156528,0.016442874,0.00022839455,0.00016993703,0.0421814],"genre_scores_gemma":[0.9028946,0.0008486589,0.08724146,0.00040251194,0.000009610578,0.0058002723,0.00013319783,0.000027383237,0.0026422464],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9555992,0.03312088,0.0011981503,0.0011383501,0.006479039,0.0024644025],"domain_scores_gemma":[0.9693788,0.015629506,0.002230197,0.0010326704,0.010083164,0.0016455997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054780688,0.0006828845,0.0005076015,0.0019289725,0.006278182,0.0055189827,0.0016302739,0.00076949206,0.001472024],"category_scores_gemma":[0.03699361,0.00034497224,0.0007431464,0.0015873362,0.0032564804,0.0024620886,0.004151867,0.0013314018,0.00016827446],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021974426,0.0074122683,0.086460136,0.006081124,0.00024308224,0.00076233724,0.2616224,0.017296221,0.011305066,0.03407622,0.0030480756,0.56949574],"study_design_scores_gemma":[0.0012413812,0.013989412,0.122138835,0.008925436,0.0011150445,0.000373128,0.64511836,0.051621497,0.045307826,0.01889554,0.09070236,0.0005712183],"about_ca_topic_score_codex":0.19658647,"about_ca_topic_score_gemma":0.34526932,"teacher_disagreement_score":0.8034135,"about_ca_system_score_codex":0.04732092,"about_ca_system_score_gemma":0.11045884,"threshold_uncertainty_score":0.39088446},"labels":[],"label_agreement":null},{"id":"W4390063608","doi":"10.3138/cjpe-2023-0042","title":"Indigenous Feminist Evaluation Methods: A Case Study in “My Two Aunties”","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Transformative learning; Scholarship; Assertion; Sociology; Colonialism; Feminist theory; Gender studies; Feminism; Epistemology; Political science; Pedagogy; Computer science; Law; Ecology; Philosophy","score_opus":0.19855657898280643,"score_gpt":0.5274372629225236,"score_spread":0.32888068393971714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88451064,0.0018291905,0.011477001,0.027624344,0.00047164081,0.002678854,0.000100638004,0.00007638203,0.07123128],"genre_scores_gemma":[0.9563144,0.0012935741,0.0118365,0.0035725788,0.00011979045,0.00240595,0.000043599997,0.00008858659,0.024324989],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.94986767,0.04184217,0.00071698526,0.001107119,0.0033636857,0.0031024169],"domain_scores_gemma":[0.97091246,0.020220889,0.0013949819,0.0012860677,0.0033329756,0.0028525053],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04544966,0.0005755899,0.0007283894,0.0016552836,0.024320513,0.0048309295,0.0027792393,0.0040897457,0.0052621723],"category_scores_gemma":[0.041075025,0.0005677793,0.00056339306,0.0020217781,0.0114168,0.0036564018,0.009134874,0.0056524663,0.00049339473],"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":[0.00009557861,0.0008121207,0.0032616449,0.00038439358,0.000012568898,0.0046504484,0.9260256,0.00017928443,0.00063968735,0.019777061,0.0052771545,0.038884405],"study_design_scores_gemma":[0.000028746052,0.0004527172,0.003196674,0.00053198234,0.00001346852,0.0012700546,0.9259592,0.00027460154,0.00086295133,0.0026747535,0.06470162,0.000033281507],"about_ca_topic_score_codex":0.029428175,"about_ca_topic_score_gemma":0.07805699,"teacher_disagreement_score":0.9545503,"about_ca_system_score_codex":0.01371096,"about_ca_system_score_gemma":0.0132479435,"threshold_uncertainty_score":0.24036366},"labels":[],"label_agreement":null},{"id":"W4390063624","doi":"10.3138/cjpe-2023-0024","title":"Arts-Based Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Lawson Foundation","keywords":"The arts; Recreation; Arts in education; Painting; Narrative; Psychology; Sociology; Visual arts; Political science; Art","score_opus":0.6412074581239966,"score_gpt":0.6406298731733805,"score_spread":0.0005775849506161057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063624","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032420505,0.004355025,0.106200896,0.014105797,0.0054968256,0.12834051,0.008275332,0.0018449816,0.6989601],"genre_scores_gemma":[0.33206072,0.0064845304,0.24558158,0.009908572,0.0013471505,0.24400285,0.00749339,0.0016180205,0.15150316],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79908806,0.12491151,0.013199331,0.0056340946,0.05214822,0.00501876],"domain_scores_gemma":[0.73654777,0.08096803,0.009195303,0.022701982,0.14042054,0.010166422],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14480875,0.0011981027,0.0015979185,0.0061436472,0.0046769367,0.008376084,0.0027474419,0.0020045359,0.07553879],"category_scores_gemma":[0.2318682,0.00061316445,0.0021890618,0.0045715137,0.0035865903,0.003958546,0.0069171865,0.0032253067,0.010247461],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026303064,0.0022230814,0.0058059054,0.0057632923,0.00029301425,0.00019552566,0.0118648885,0.0018664398,0.0014453398,0.055464566,0.17751451,0.7349331],"study_design_scores_gemma":[0.0011914143,0.002560633,0.014708828,0.010292799,0.00027254416,0.00017607618,0.008756045,0.0017764097,0.0039694747,0.02195301,0.93413365,0.00020910043],"about_ca_topic_score_codex":0.008315633,"about_ca_topic_score_gemma":0.014095524,"teacher_disagreement_score":0.85519123,"about_ca_system_score_codex":0.015589697,"about_ca_system_score_gemma":0.034937024,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4390063627","doi":"10.3138/cjpe.75803","title":"Contribution Analysis of a Complex System During Disruptions","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outreach; Occupational safety and health; Agriculture; Business; Coronavirus disease 2019 (COVID-19); Environmental planning; Environmental resource management; Political science; Environmental health; Geography; Environmental science; Medicine","score_opus":0.4378081056136442,"score_gpt":0.5552920873869361,"score_spread":0.11748398177329195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6784731,0.00030160954,0.29252642,0.001765005,0.00012433376,0.0019089844,0.0013771243,0.00053602806,0.022987356],"genre_scores_gemma":[0.9414455,0.00012278493,0.055964913,0.00005261083,0.000019786003,0.00043338875,0.0004717534,0.00005296716,0.0014364483],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98369944,0.009070542,0.0006598336,0.0015269303,0.0038660634,0.0011772469],"domain_scores_gemma":[0.9633159,0.02241633,0.0035622634,0.002095573,0.007311131,0.0012988079],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01938093,0.00095410243,0.00074376207,0.0041885995,0.0016607083,0.0041971267,0.0013859338,0.00079282845,0.003684851],"category_scores_gemma":[0.052002504,0.000404602,0.001086998,0.0032165041,0.0019469274,0.0034490235,0.003964271,0.0012764327,0.00030373054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009922856,0.0007770748,0.14231399,0.0012538845,0.00088450767,0.0009807663,0.009865769,0.46859947,0.0057537025,0.14009802,0.0065143825,0.22196612],"study_design_scores_gemma":[0.00009565707,0.001163555,0.06346249,0.0003588281,0.00043829807,0.00023593691,0.010518336,0.80901635,0.0050697722,0.09383502,0.015661094,0.00014469707],"about_ca_topic_score_codex":0.013340485,"about_ca_topic_score_gemma":0.009601681,"teacher_disagreement_score":0.9806191,"about_ca_system_score_codex":0.005130705,"about_ca_system_score_gemma":0.006094052,"threshold_uncertainty_score":0.10249734},"labels":[],"label_agreement":null},{"id":"W4393862188","doi":"10.3138/cjpe-2024-0012","title":"Strengthening Evaluation Capacity Building Practice Through Competition: The Max Bell School of Public Policy’s Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta; University of Ottawa; Queen's University; McGill University","funders":"","keywords":"Competition (biology); Capacity building; Political science; Architectural engineering; Economics; Engineering; Economic growth","score_opus":0.6298851995534387,"score_gpt":0.5347281576265688,"score_spread":0.09515704192686991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393862188","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018660055,0.0036189076,0.003089697,0.9365113,0.0018590259,0.00012381792,0.000033424574,0.0000563354,0.03604733],"genre_scores_gemma":[0.7046121,0.00541571,0.023099735,0.19781286,0.0017977699,0.0007449627,0.00011384528,0.00030768436,0.06609542],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9493087,0.029873606,0.00082292367,0.002985268,0.006194028,0.0108154],"domain_scores_gemma":[0.9159973,0.0330655,0.0015083306,0.002742958,0.0108969025,0.035789046],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07587067,0.0004503823,0.00064755743,0.001390879,0.031969804,0.020076497,0.0034332534,0.012796468,0.0077442387],"category_scores_gemma":[0.045209788,0.0010096172,0.00059354294,0.001663967,0.022109155,0.010940903,0.017377635,0.024687389,0.0008638354],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009990208,0.0006467568,0.0035110447,0.00017009661,0.000017239316,0.00071395887,0.035515998,0.000742666,0.000604395,0.34817812,0.5427296,0.067070186],"study_design_scores_gemma":[0.000058154503,0.00010112501,0.0031717464,0.000454933,0.0000052572072,0.000148892,0.03618359,0.0013064807,0.00073931634,0.04282874,0.9148789,0.00012279578],"about_ca_topic_score_codex":0.14345501,"about_ca_topic_score_gemma":0.31799272,"teacher_disagreement_score":0.9487244,"about_ca_system_score_codex":0.051275633,"about_ca_system_score_gemma":0.13593572,"threshold_uncertainty_score":0.40124726},"labels":[],"label_agreement":null},{"id":"W4393901164","doi":"10.3138/cjpe-2024-0003","title":"Evaluation Capacity Building: Experiential Learning Through Community–University Collaboratives","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University; Queen's University; University of Alberta","funders":"","keywords":"Experiential learning; Capacity building; Experiential education; Psychology; Sociology; Knowledge management; Mathematics education; Computer science; Political science","score_opus":0.5508950277399596,"score_gpt":0.5316824930199557,"score_spread":0.019212534720003838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23737967,0.0016254392,0.44919023,0.023047475,0.0009818305,0.0055561108,0.00017372021,0.0023013398,0.27974415],"genre_scores_gemma":[0.69530153,0.0011903585,0.28828812,0.0013713244,0.00022205955,0.0025497412,0.00016356181,0.00016738196,0.010745951],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9738565,0.02102875,0.0005102328,0.0011135846,0.0021798147,0.0013111426],"domain_scores_gemma":[0.90747017,0.07200187,0.0019549145,0.0057757664,0.0035351529,0.009262089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0355126,0.00094934955,0.00062165677,0.0019074325,0.003678694,0.008752865,0.0043646153,0.0019570505,0.011631048],"category_scores_gemma":[0.053628396,0.00046866902,0.0007026266,0.0014688099,0.0057085506,0.0064912946,0.016592477,0.0032200164,0.0017784009],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000292101,0.009922393,0.0041500153,0.0012246222,0.00010809511,0.00071594684,0.063868456,0.008970422,0.0032256134,0.08422958,0.031930655,0.7913622],"study_design_scores_gemma":[0.0010747619,0.003029648,0.009227813,0.004285633,0.000148082,0.0015045851,0.11526455,0.028947162,0.012035039,0.44637844,0.3776572,0.00044712925],"about_ca_topic_score_codex":0.0010324031,"about_ca_topic_score_gemma":0.002660933,"teacher_disagreement_score":0.0355126,"about_ca_system_score_codex":0.002978201,"about_ca_system_score_gemma":0.011016766,"threshold_uncertainty_score":0.18781078},"labels":[],"label_agreement":null},{"id":"W4393901296","doi":"10.3138/cjpe-2024-0001","title":"Capturing Evaluation Capacity: Findings from a Mapping of Evaluation Capacity Instruments","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Rubric; Face validity; Construct validity; Content validity; Reliability (semiconductor); Concurrent validity; Construct (python library); Adaptation (eye); Psychology; Computer science; Applied psychology; Internal consistency; Process management; Psychometrics; Engineering; Clinical psychology","score_opus":0.5637636910939985,"score_gpt":0.48089635624878085,"score_spread":0.08286733484521763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8890694,0.017466733,0.04066558,0.0031469075,0.00013547121,0.0012250056,0.00075324083,0.00009830143,0.04743936],"genre_scores_gemma":[0.9714831,0.0056928047,0.020400662,0.0003202748,0.000037693582,0.0010074602,0.00038207197,0.00006332239,0.00061261957],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.92350733,0.047136445,0.008091351,0.0029315387,0.016550144,0.0017831607],"domain_scores_gemma":[0.40714118,0.5084608,0.021697149,0.014699378,0.04614264,0.0018588497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09469199,0.0006442162,0.0008044346,0.022958312,0.002309329,0.005989609,0.0019940075,0.0009337167,0.0019861157],"category_scores_gemma":[0.3468906,0.00071560714,0.0011707046,0.022799524,0.004636295,0.010230894,0.009891407,0.0018922206,0.0002411776],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022688675,0.0002513933,0.30129436,0.0058155423,0.00025380732,0.00042019432,0.17307746,0.0017499834,0.00079215807,0.023492865,0.0022228258,0.49040252],"study_design_scores_gemma":[0.00008768668,0.0006492882,0.55522305,0.015466968,0.0006145834,0.0018572985,0.31427592,0.0052963253,0.0044028694,0.028170887,0.07370554,0.00024961622],"about_ca_topic_score_codex":0.0078198835,"about_ca_topic_score_gemma":0.0066520968,"teacher_disagreement_score":0.09469199,"about_ca_system_score_codex":0.007494883,"about_ca_system_score_gemma":0.014041549,"threshold_uncertainty_score":0.5007851},"labels":[],"label_agreement":null},{"id":"W4393901340","doi":"10.3138/cjpe-2024-0006","title":"Meeting the Challenge: How the City of Kingston Is Working to Propel Evaluation Growth","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Ottawa; Kingston Health Sciences Centre; McGill University; Queen's University","funders":"","keywords":"Regional science; Engineering ethics; Sociology; Engineering","score_opus":0.5229101328012221,"score_gpt":0.5202649908847802,"score_spread":0.00264514191644194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901340","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03928022,0.0044979304,0.009209186,0.8288305,0.002626258,0.000296552,0.00013559534,0.00042839153,0.11469541],"genre_scores_gemma":[0.6307279,0.0048648827,0.035956953,0.11046222,0.0005528259,0.00059083046,0.00023109303,0.00088865135,0.21572456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95394135,0.020372337,0.0016401722,0.0038497194,0.011503359,0.008693142],"domain_scores_gemma":[0.92178303,0.020346163,0.0020806887,0.0056152516,0.02297489,0.027199987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035549123,0.0006660542,0.00088779314,0.0016767987,0.044767626,0.042862102,0.005928787,0.014445489,0.012655211],"category_scores_gemma":[0.053152766,0.0018105496,0.0011809247,0.0027001926,0.035991635,0.013309553,0.031582236,0.015625149,0.0028979613],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022204341,0.00020022967,0.008403778,0.00066182093,0.0000723121,0.0027356136,0.12749113,0.0019911714,0.0011980269,0.30072582,0.44783166,0.1084664],"study_design_scores_gemma":[0.000028077562,0.000057043326,0.0025868432,0.00039634094,0.000019259276,0.00020948546,0.07144813,0.00054079096,0.00076147326,0.015510909,0.90825856,0.00018300612],"about_ca_topic_score_codex":0.6963897,"about_ca_topic_score_gemma":0.84317505,"teacher_disagreement_score":0.6963897,"about_ca_system_score_codex":0.108688965,"about_ca_system_score_gemma":0.27155668,"threshold_uncertainty_score":0.78859735},"labels":[],"label_agreement":null},{"id":"W4393901348","doi":"10.3138/cjpe-2024-0014","title":"Exploring the Edges: Identifying the Next Generation of Evaluation Capacity Building Research and Practice Through Adjacency","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Adjacency list; Computer science; Data science; Algorithm","score_opus":0.9617855589426995,"score_gpt":0.6449060188564266,"score_spread":0.31687954008627284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901348","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06375046,0.22720198,0.20070234,0.21389836,0.0023862482,0.0011667088,0.0005083172,0.0005005656,0.28988498],"genre_scores_gemma":[0.73321867,0.106468804,0.13792133,0.014768368,0.0008200643,0.0013378956,0.00035268068,0.0003075385,0.004804769],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95402735,0.036795292,0.0015470268,0.0017331347,0.0039662733,0.0019308092],"domain_scores_gemma":[0.7541959,0.21387702,0.005707671,0.0081322715,0.014652942,0.0034342017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06498821,0.00081468874,0.0014777037,0.010860264,0.0042450065,0.022003818,0.0031278385,0.0036503319,0.009543638],"category_scores_gemma":[0.11811044,0.00062311476,0.0011893893,0.014129751,0.022546854,0.04080113,0.010844146,0.005259924,0.0008950419],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077614066,0.000091084315,0.0034584354,0.0072357645,0.00008961994,0.00019627846,0.027574584,0.0008323827,0.00030273123,0.62071896,0.007982606,0.33143997],"study_design_scores_gemma":[0.000035018376,0.00012545838,0.0031212284,0.02521388,0.0001769002,0.00018838976,0.064432204,0.0020019715,0.0008281801,0.5895485,0.31426418,0.0000640764],"about_ca_topic_score_codex":0.008546238,"about_ca_topic_score_gemma":0.012495663,"teacher_disagreement_score":0.06498821,"about_ca_system_score_codex":0.010611823,"about_ca_system_score_gemma":0.02694483,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4393901512","doi":"10.3138/cjpe-2024-0002","title":"Evaluation Literacy and Use in Community Organizations: Insights and Implications for Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Australian Government","keywords":"Capacity building; Literacy; Business; Capacity development; Environmental planning; Environmental resource management; Sociology; Economic growth; Economics; Pedagogy; Geography","score_opus":0.43190576373339495,"score_gpt":0.5397514135621242,"score_spread":0.10784564982872924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8817055,0.0021695152,0.013040141,0.045297723,0.0000663377,0.0003842022,0.00007963174,0.000056349334,0.057200696],"genre_scores_gemma":[0.99683136,0.00032214643,0.00177202,0.00055391766,0.00001322392,0.00010654857,0.000015103444,0.000007938602,0.00037777753],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.90167356,0.07794315,0.0029768902,0.0021778482,0.008240784,0.006987865],"domain_scores_gemma":[0.6826192,0.2612278,0.014581277,0.007941375,0.021885518,0.011744775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08244675,0.0002591108,0.0006177742,0.0050114254,0.005807629,0.012858959,0.0018075376,0.0017523709,0.0032209512],"category_scores_gemma":[0.17586276,0.00047031936,0.0004536315,0.0035572099,0.016049143,0.011806732,0.010671856,0.0028137339,0.00013150644],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012827307,0.00094899,0.22072513,0.0007362517,0.00006788276,0.0007100408,0.4848116,0.00075195957,0.00053405616,0.079659246,0.0033371395,0.2075894],"study_design_scores_gemma":[0.000042869036,0.0002519761,0.14701208,0.0022543997,0.00004134554,0.00045491394,0.72319686,0.0034542396,0.0010892684,0.084999904,0.037050147,0.00015188554],"about_ca_topic_score_codex":0.03567411,"about_ca_topic_score_gemma":0.034812834,"teacher_disagreement_score":0.08244675,"about_ca_system_score_codex":0.015021124,"about_ca_system_score_gemma":0.03197841,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4393902965","doi":"10.3138/cjpe-2024-0004","title":"Developing Evaluation Capacity Building Competencies: Participant Reflections From the Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University; University of Waterloo; University of Alberta","funders":"","keywords":"Capacity building; Capacity development; Psychology; Business; Environmental resource management; Environmental science; Economic growth; Economics","score_opus":0.8696201595344439,"score_gpt":0.5799551477667225,"score_spread":0.2896650117677214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393902965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8987003,0.00071764307,0.010554799,0.062514365,0.0014201645,0.0009766342,0.00016746655,0.00012632928,0.024822326],"genre_scores_gemma":[0.9696973,0.0006756545,0.006922972,0.008464115,0.00030966123,0.00073015894,0.00010156021,0.00018748028,0.012911115],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9588882,0.03007218,0.0008589815,0.001570779,0.0037684913,0.004841317],"domain_scores_gemma":[0.9227225,0.04596205,0.0025645236,0.0023517653,0.012923058,0.013476213],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.039620884,0.0012551394,0.0010285474,0.0015886198,0.018299794,0.011754838,0.004321632,0.008394639,0.0028397432],"category_scores_gemma":[0.099796444,0.0011629515,0.00084628386,0.0008236015,0.015087784,0.0070476267,0.013859469,0.016628798,0.0005804612],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008087114,0.00050498743,0.0030452013,0.00010399452,0.0000106211055,0.0031189835,0.96287614,0.0003442855,0.0008801348,0.0047806874,0.009930288,0.014323774],"study_design_scores_gemma":[0.000018470377,0.00023705659,0.0008856237,0.00015924685,0.000006036342,0.0009963831,0.9332724,0.00063195836,0.0007226864,0.0018529871,0.061135825,0.00008135985],"about_ca_topic_score_codex":0.014673248,"about_ca_topic_score_gemma":0.033849444,"teacher_disagreement_score":0.9603791,"about_ca_system_score_codex":0.0077572656,"about_ca_system_score_gemma":0.013095696,"threshold_uncertainty_score":0.2095378},"labels":[],"label_agreement":null},{"id":"W4393902987","doi":"10.3138/cjpe-2024-0005","title":"Learning From Evaluation Data: Discoveries From the Inaugural Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Alberta; McGill University; Queen's University","funders":"","keywords":"Data science; Computer science","score_opus":0.7100870622061499,"score_gpt":0.544183741665453,"score_spread":0.1659033205406969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393902987","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118403025,0.015797198,0.13590592,0.61350024,0.002334021,0.00063634716,0.00046061794,0.00018284595,0.112779796],"genre_scores_gemma":[0.8451725,0.008659849,0.11102644,0.017466674,0.0013340934,0.00092544046,0.00039377456,0.0002211419,0.014800167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.84471774,0.1231408,0.0038669691,0.0038870182,0.02062017,0.0037672978],"domain_scores_gemma":[0.5326445,0.38847512,0.010293319,0.026862841,0.033160422,0.008563727],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20144314,0.0005201411,0.0010175039,0.0031141972,0.0098073995,0.022303596,0.0041696127,0.0057409415,0.0032246339],"category_scores_gemma":[0.31297934,0.0006214331,0.00069697184,0.0037248977,0.024698595,0.02947956,0.017329773,0.0141616175,0.0005492344],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000991452,0.00022311011,0.010796703,0.00070177903,0.000037532966,0.001325524,0.11136183,0.0011604981,0.00045467695,0.6306852,0.044248827,0.19890504],"study_design_scores_gemma":[0.00005105589,0.00016131089,0.0052463133,0.0031261167,0.00002831587,0.0015074264,0.10258782,0.005989801,0.0018718933,0.42997128,0.44925466,0.00020395828],"about_ca_topic_score_codex":0.0073320875,"about_ca_topic_score_gemma":0.020945149,"teacher_disagreement_score":0.79855686,"about_ca_system_score_codex":0.012623997,"about_ca_system_score_gemma":0.023173643,"threshold_uncertainty_score":0.9847628},"labels":[],"label_agreement":null},{"id":"W4396691899","doi":"10.3138/cjpe.38.3.ed-fr","title":"Un mot de la rédactrice","year":2024,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.0851767379731989,"score_gpt":0.3805536059568216,"score_spread":0.29537686798362267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396691899","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030639651,0.02583735,0.013714365,0.37253106,0.059585612,0.0002663022,0.000392217,0.0006398522,0.5239693],"genre_scores_gemma":[0.06435735,0.02185473,0.014725791,0.09956036,0.01813542,0.0005458982,0.0006094733,0.0012788696,0.7789321],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96932375,0.01263477,0.0011378366,0.0030688674,0.011817273,0.0020174675],"domain_scores_gemma":[0.96563643,0.009933796,0.0019027276,0.0035958118,0.014536105,0.00439516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016125979,0.0013660359,0.0010589497,0.0025183535,0.009765036,0.02288273,0.0025348787,0.0067217574,0.055385966],"category_scores_gemma":[0.05448787,0.0008720455,0.0011684853,0.0030403188,0.010904184,0.020885991,0.012616571,0.014998677,0.027797079],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005073606,0.000041450225,0.00063398253,0.00049352983,0.0000149875295,0.0001490721,0.007707393,0.00012208906,0.00040295077,0.26551193,0.61101824,0.11385366],"study_design_scores_gemma":[0.00000459868,0.000019802654,0.00032031574,0.0003547449,0.0000043844934,0.00015035922,0.0019491696,0.000059478916,0.00015962227,0.013191772,0.98376656,0.000019122721],"about_ca_topic_score_codex":0.009354728,"about_ca_topic_score_gemma":0.011223067,"teacher_disagreement_score":0.055385966,"about_ca_system_score_codex":0.0095344605,"about_ca_system_score_gemma":0.019056149,"threshold_uncertainty_score":0.1852845},"labels":[],"label_agreement":null},{"id":"W4396707487","doi":"10.3138/cjpe-2024-0013","title":"Concluding Remarks: A Bright Future for Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Engineering ethics; Management science; Capacity building; Computer science; Political science; Engineering; Law","score_opus":0.4634754320822916,"score_gpt":0.5450116204168327,"score_spread":0.08153618833454113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396707487","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006204403,0.018572418,0.007850468,0.9224487,0.038810313,0.000063692816,0.00015606728,0.00012910675,0.011348865],"genre_scores_gemma":[0.085298434,0.088239536,0.06568425,0.58763134,0.11134194,0.0007973304,0.00094311876,0.00047606142,0.059587944],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98730683,0.0064778584,0.0008415846,0.0016818028,0.002558873,0.0011331424],"domain_scores_gemma":[0.914128,0.04489955,0.0021060058,0.0037052324,0.029801255,0.005359938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025736397,0.0009618904,0.0011087275,0.0021676929,0.0040164134,0.010909965,0.0029146327,0.008466253,0.022639332],"category_scores_gemma":[0.07034361,0.00035982975,0.0012914846,0.0022153207,0.0068864184,0.013252246,0.0060981777,0.015758567,0.005911492],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084503,0.000051295126,0.0004946905,0.0007564777,0.00002036907,0.00018856922,0.0015288847,0.000642277,0.00016580077,0.2338003,0.7089694,0.05329748],"study_design_scores_gemma":[0.000031639524,0.00003638715,0.0004722562,0.0022722157,0.000016587404,0.00012312293,0.0045555136,0.0006965324,0.00020010072,0.2726234,0.71891946,0.000052874773],"about_ca_topic_score_codex":0.0055979993,"about_ca_topic_score_gemma":0.0076663275,"teacher_disagreement_score":0.9938481,"about_ca_system_score_codex":0.0061518867,"about_ca_system_score_gemma":0.014579263,"threshold_uncertainty_score":0.1361087},"labels":[],"label_agreement":null},{"id":"W4396707874","doi":"10.3138/cjpe-2024-0011","title":"The Science and Practice of Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Capacity building; Architectural engineering; Political science; Engineering","score_opus":0.5353283803429555,"score_gpt":0.5759095146980391,"score_spread":0.04058113435508359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396707874","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004224902,0.09376705,0.1997741,0.43513358,0.007005127,0.0006272723,0.0002712058,0.0005097597,0.25868705],"genre_scores_gemma":[0.53504556,0.14984511,0.2168636,0.053496923,0.012169232,0.0032394852,0.00041091882,0.0007024028,0.028226865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8252289,0.12934607,0.0066937055,0.008517646,0.02689114,0.0033224558],"domain_scores_gemma":[0.65843385,0.27340668,0.00971584,0.025679559,0.026813237,0.005950893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12929353,0.0012413391,0.0020171576,0.008898812,0.006406261,0.022535581,0.0041674986,0.007301299,0.008567111],"category_scores_gemma":[0.23011988,0.0009262312,0.0012010393,0.006901446,0.062005762,0.017126124,0.012621686,0.013347994,0.0022218833],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001708497,0.00005105643,0.0010151058,0.001084739,0.00004411164,0.00005548882,0.002214625,0.002172962,0.00006229109,0.8393046,0.034055967,0.119921915],"study_design_scores_gemma":[0.000020823,0.000027662656,0.00051867554,0.0029785954,0.000016451044,0.00007085233,0.0019348424,0.0015079025,0.00022886095,0.8366691,0.15598121,0.00004514377],"about_ca_topic_score_codex":0.013394916,"about_ca_topic_score_gemma":0.009266643,"teacher_disagreement_score":0.12929353,"about_ca_system_score_codex":0.01922513,"about_ca_system_score_gemma":0.04646703,"threshold_uncertainty_score":0.6837777},"labels":[],"label_agreement":null},{"id":"W4396708036","doi":"10.3138/cjpe.38.3.ed-en","title":"Editor’s Remarks","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.23986684550211407,"score_gpt":0.53726516308728,"score_spread":0.29739831758516594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396708036","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000117729855,0.0012976934,0.00027106417,0.27884552,0.7151528,0.000034912373,0.00016591839,0.00018330112,0.0039309715],"genre_scores_gemma":[0.0027442607,0.0022972352,0.0014049334,0.5225047,0.42751756,0.00014260804,0.00015263582,0.00022324495,0.043012783],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98421025,0.0015883875,0.0018555686,0.0028716857,0.008078022,0.0013962236],"domain_scores_gemma":[0.93159527,0.015008644,0.0037959921,0.003607217,0.03964638,0.0063466257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013787447,0.0017643084,0.0020207681,0.0021483523,0.0041083978,0.009009464,0.0052717235,0.020522304,0.031075437],"category_scores_gemma":[0.1135676,0.0009338653,0.0032997192,0.00167464,0.0031355554,0.0055564684,0.003326765,0.024090575,0.030889269],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001582202,0.0000069029325,0.000045003504,0.000051301296,0.0000050773224,0.000089622125,0.000027517382,0.000019469026,0.000041269857,0.00049185223,0.99643564,0.0027705317],"study_design_scores_gemma":[0.000017452254,0.000014854993,0.00020683413,0.00018051494,0.000009421172,0.00018103386,0.00008806687,0.00006478415,0.00019083713,0.0009021307,0.99812084,0.000023218432],"about_ca_topic_score_codex":0.0027335433,"about_ca_topic_score_gemma":0.005247001,"teacher_disagreement_score":0.031075437,"about_ca_system_score_codex":0.0040393015,"about_ca_system_score_gemma":0.008104122,"threshold_uncertainty_score":0.10395771},"labels":[],"label_agreement":null},{"id":"W4401363419","doi":"10.3138/cjpe-2023-0038","title":"Interactive Voice Response Technology as a Data Collection Tool Compared to a Household Survey: What We Learned","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Red Cross Society","funders":"","keywords":"Data collection; Computer science; Human–computer interaction; Interactive voice response; Data science; Psychology; Multimedia; Telecommunications; Statistics; Mathematics","score_opus":0.23152952426087353,"score_gpt":0.4168476999135069,"score_spread":0.18531817565263337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363419","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06632977,0.43908182,0.052204274,0.39288545,0.017621353,0.0024564257,0.0005872692,0.0005450505,0.028288618],"genre_scores_gemma":[0.39238298,0.36297792,0.15460637,0.06982104,0.0114833005,0.0036339187,0.00045792645,0.0006088056,0.004027809],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.860476,0.11097596,0.0066676955,0.0050745476,0.014097438,0.0027083189],"domain_scores_gemma":[0.48914707,0.44733432,0.0068756593,0.007401359,0.04296523,0.0062764543],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17540476,0.0011597836,0.002053985,0.0028641284,0.0020893486,0.015491914,0.0043064626,0.0045297043,0.0047840686],"category_scores_gemma":[0.28165025,0.00092485204,0.0014236186,0.0045537287,0.008805368,0.017238058,0.0047135954,0.009749529,0.00090960745],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046976763,0.00061563216,0.009084023,0.01569258,0.0002809823,0.0002481001,0.015621819,0.00044250442,0.0003996284,0.012718346,0.021166073,0.92326045],"study_design_scores_gemma":[0.00097653683,0.008111367,0.056199208,0.21197285,0.0017174039,0.002073835,0.12067977,0.011517852,0.0042075077,0.04620217,0.5352694,0.001072066],"about_ca_topic_score_codex":0.04188179,"about_ca_topic_score_gemma":0.048704855,"teacher_disagreement_score":0.8245952,"about_ca_system_score_codex":0.011612502,"about_ca_system_score_gemma":0.016626755,"threshold_uncertainty_score":0.9276401},"labels":[],"label_agreement":null},{"id":"W4401363439","doi":"10.3138/cjpe.39.1.ed-en","title":"Editor’s Remarks","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"History; Psychoanalysis; Psychology","score_opus":0.0638490808465071,"score_gpt":0.443443992212459,"score_spread":0.3795949113659519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363439","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012073218,0.0018636193,0.00012282,0.41217175,0.58092755,0.000032212956,0.000107851374,0.000071914976,0.00458157],"genre_scores_gemma":[0.0017575567,0.0013802833,0.00043139717,0.6972625,0.25323686,0.00008578208,0.00005155814,0.00007300421,0.04572107],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9811959,0.0018872855,0.0019791848,0.002802789,0.009804634,0.0023302287],"domain_scores_gemma":[0.93278486,0.016014932,0.0048540737,0.0032043108,0.033521432,0.009620384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016451903,0.0017351247,0.002791232,0.0027100092,0.0055537526,0.010961629,0.005189073,0.04226977,0.031883072],"category_scores_gemma":[0.13095033,0.0012742268,0.003525495,0.0021149737,0.0038276967,0.0037418087,0.0029213377,0.039566495,0.024126295],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001500489,0.000006308279,0.00004878067,0.000033542517,0.000008808714,0.000091464375,0.000019911642,0.000012983916,0.00002559106,0.00042964934,0.9974546,0.0018535441],"study_design_scores_gemma":[0.00004588209,0.000013755153,0.00043503332,0.00021239025,0.000027691733,0.00015660287,0.000103283164,0.00006741987,0.00011097459,0.00086629693,0.9979266,0.000034095927],"about_ca_topic_score_codex":0.016056456,"about_ca_topic_score_gemma":0.037209325,"teacher_disagreement_score":0.04226977,"about_ca_system_score_codex":0.008339114,"about_ca_system_score_gemma":0.015421836,"threshold_uncertainty_score":0.10665947},"labels":[],"label_agreement":null},{"id":"W4401363452","doi":"10.3138/cjpe.39.1.rr-en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Engineering ethics; Traditional medicine; Sociology; History; Anthropology; Medicine; Engineering; Biology; Ecology","score_opus":0.27093444104940484,"score_gpt":0.5361930289587907,"score_spread":0.2652585879093859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363452","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011303669,0.0085727135,0.009732161,0.8985923,0.0050343713,0.00009686953,0.000014295507,0.00011628069,0.06653729],"genre_scores_gemma":[0.7460185,0.00637482,0.0282598,0.18690795,0.0057032323,0.00033181757,0.000020501833,0.000559947,0.025823466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8077952,0.15205006,0.0032096219,0.0038737496,0.025387574,0.007683639],"domain_scores_gemma":[0.7225865,0.19285914,0.008611209,0.012989411,0.031533178,0.031420562],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20288971,0.00083768845,0.0013638657,0.0036540087,0.030951979,0.034882836,0.0033698573,0.012713026,0.007898909],"category_scores_gemma":[0.20618215,0.00091556803,0.00083801453,0.0022061823,0.09621005,0.02563544,0.027199326,0.03419904,0.0008567333],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017078596,0.00024140363,0.002012983,0.00079341244,0.000144006,0.00036704514,0.14290832,0.00044305835,0.0006248738,0.5803258,0.116099074,0.15586926],"study_design_scores_gemma":[0.00013526018,0.00018155218,0.0028237298,0.0030441668,0.00014907253,0.0004130247,0.088457406,0.0008538334,0.0011159221,0.3614156,0.5412124,0.0001981135],"about_ca_topic_score_codex":0.03746832,"about_ca_topic_score_gemma":0.12080796,"teacher_disagreement_score":0.20288971,"about_ca_system_score_codex":0.028442614,"about_ca_system_score_gemma":0.07181547,"threshold_uncertainty_score":0.9829789},"labels":[],"label_agreement":null},{"id":"W4401363543","doi":"10.3138/cjpe-2023-0021","title":"Breaking the Mould? Expanding our Conceptualization of Evaluator Competencies","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Conceptualization; Psychology; Engineering ethics; Sociology; Computer science; Engineering; Artificial intelligence","score_opus":0.40402035861867575,"score_gpt":0.5589097674439346,"score_spread":0.15488940882525887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363543","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06614591,0.020524682,0.19444998,0.16429174,0.0011171341,0.00050491816,0.00015545345,0.00031080507,0.5524995],"genre_scores_gemma":[0.9308405,0.0056894403,0.040820207,0.01232349,0.000244786,0.00044115004,0.00006490639,0.00011276388,0.009462711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9801601,0.014165964,0.00065112,0.0010666891,0.0024172831,0.0015387615],"domain_scores_gemma":[0.96814805,0.021328434,0.0019888913,0.0019298426,0.0045112413,0.0020935482],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025766736,0.0008074378,0.00061692717,0.0062123425,0.004324614,0.011685484,0.0025635348,0.00446967,0.0051899147],"category_scores_gemma":[0.02947758,0.00037806242,0.0008564236,0.0031663447,0.04693924,0.019488167,0.0062551806,0.00651124,0.0006193305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000141636265,0.00004309234,0.0019477776,0.00013988893,0.000008733217,0.00008225521,0.017193593,0.0006698922,0.00011344617,0.96305424,0.0020397804,0.014693255],"study_design_scores_gemma":[0.00003355373,0.0001237302,0.005549936,0.0022140224,0.000034862383,0.00039442233,0.029177882,0.0051866444,0.00050913607,0.7863842,0.17030206,0.000089590256],"about_ca_topic_score_codex":0.02317343,"about_ca_topic_score_gemma":0.017417831,"teacher_disagreement_score":0.97423327,"about_ca_system_score_codex":0.012207822,"about_ca_system_score_gemma":0.017915733,"threshold_uncertainty_score":0.13626915},"labels":[],"label_agreement":null},{"id":"W4401363556","doi":"10.3138/cjpe-2024-0026","title":"In Memoriam: Dr. Michael Scriven","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Advances in Oncology and Radiotherapy","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Evaluation Society","funders":"","keywords":"Philosophy; Theology; Art; Sociology","score_opus":0.07351575945754125,"score_gpt":0.4722924449047715,"score_spread":0.3987766854472303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363556","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023888635,0.0029161202,0.00059109664,0.64985836,0.34286055,0.000046684578,0.000287051,0.00015322385,0.0030480283],"genre_scores_gemma":[0.0066025727,0.0063879914,0.0011612441,0.5838418,0.3338179,0.00021321334,0.0002856074,0.00020422952,0.06748547],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996487,0.0005812844,0.00035455567,0.00053689594,0.0017771864,0.0002630345],"domain_scores_gemma":[0.95118964,0.010230196,0.002145771,0.0010911558,0.029142812,0.0062004263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056835595,0.00094025966,0.0017495737,0.0010727491,0.0019404229,0.0046966067,0.0023431813,0.006664959,0.023664845],"category_scores_gemma":[0.078315035,0.0004404633,0.0009888102,0.0005958842,0.0016515519,0.0034502104,0.0021722927,0.019146657,0.017361382],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012120544,0.00000448402,0.000061088926,0.000025666119,0.000004390243,0.0001101658,0.000033407603,0.000018106863,0.00001671047,0.00019909088,0.9963916,0.0031231567],"study_design_scores_gemma":[0.000028198234,0.000021615493,0.00045671972,0.0002454139,0.000019538775,0.00086900307,0.00031504707,0.00016234192,0.0001728518,0.0013657262,0.9963128,0.00003083796],"about_ca_topic_score_codex":0.0068810363,"about_ca_topic_score_gemma":0.0104076415,"teacher_disagreement_score":0.023664845,"about_ca_system_score_codex":0.0038874093,"about_ca_system_score_gemma":0.0074118525,"threshold_uncertainty_score":0.07916677},"labels":[],"label_agreement":null},{"id":"W4401363915","doi":"10.3138/cjpe-2024-0008","title":"Nora F. Murphy Johnson &amp; A. Rafael Johnson (2021). <i>Creative Evaluation and Engagement Essentials (Vol. 1)</i>","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Art; Art history","score_opus":0.3043823667836116,"score_gpt":0.5217967985992583,"score_spread":0.21741443181564674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363915","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005771068,0.06904334,0.0051694037,0.49662334,0.047356408,0.00021296862,0.0018431462,0.0016758406,0.37749848],"genre_scores_gemma":[0.0048448923,0.02478462,0.0038071454,0.035241496,0.0030387922,0.00012761979,0.0004916347,0.00042822497,0.92723554],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99729484,0.0003873268,0.00011052076,0.0002853268,0.0017220215,0.00019980819],"domain_scores_gemma":[0.9867775,0.0019268172,0.0006355738,0.00031032308,0.0071090837,0.0032407385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049182405,0.0007720411,0.0004093134,0.0018844994,0.0024090689,0.00501148,0.0011535535,0.003194001,0.21097259],"category_scores_gemma":[0.014730925,0.0004543967,0.000339399,0.0010354394,0.0010142298,0.0020606597,0.0020438002,0.0030641218,0.13558045],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056163717,0.000004911869,0.00006562169,0.000041196763,5.8823355e-7,0.000014906541,0.000031502783,0.000010170788,0.00003498642,0.001017239,0.96055406,0.038219165],"study_design_scores_gemma":[0.00000273229,0.0000041425055,0.00022495042,0.00016535821,0.0000015151404,0.000046132078,0.000091467824,0.000027576842,0.000053258358,0.0007837006,0.99859446,0.0000047068042],"about_ca_topic_score_codex":0.03528408,"about_ca_topic_score_gemma":0.11383477,"teacher_disagreement_score":0.21097259,"about_ca_system_score_codex":0.0029435782,"about_ca_system_score_gemma":0.014666342,"threshold_uncertainty_score":0.7057736},"labels":[],"label_agreement":null},{"id":"W4401363950","doi":"10.3138/cjpe-2024-0010","title":"On the (In)Comparability of Indigenous Community-Based Research Within University Merit Systems","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Comparability; Indigenous; Sociology; Geography; Political science; Mathematics","score_opus":0.32184069009545846,"score_gpt":0.45493570356606344,"score_spread":0.13309501347060498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6023684,0.0097065065,0.043404948,0.052578382,0.0015994672,0.00089539815,0.00066560274,0.00019046383,0.28859082],"genre_scores_gemma":[0.98889345,0.00085151114,0.005454088,0.0015926729,0.00024097381,0.0003214291,0.00011349898,0.00005065591,0.0024816713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8499665,0.10660748,0.006855781,0.006859869,0.024487559,0.005222736],"domain_scores_gemma":[0.7748933,0.14300576,0.019215314,0.026483854,0.032131203,0.004270654],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19219726,0.0002848977,0.0010670532,0.0076966085,0.009200715,0.020655578,0.0026524893,0.0017767138,0.0062121777],"category_scores_gemma":[0.31371465,0.00031430367,0.00064856914,0.0069206003,0.023189278,0.013990319,0.014792446,0.0026933302,0.00037632583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039050065,0.00018822131,0.095660396,0.0012563426,0.00040489537,0.00020657691,0.24122252,0.00086327735,0.0012250633,0.44512516,0.0056446935,0.20781243],"study_design_scores_gemma":[0.000099593504,0.00096983195,0.23959084,0.0059063113,0.000495328,0.00045713942,0.28987592,0.0036809335,0.0038318988,0.34342536,0.111427076,0.0002397814],"about_ca_topic_score_codex":0.023292722,"about_ca_topic_score_gemma":0.030980675,"teacher_disagreement_score":0.9902404,"about_ca_system_score_codex":0.009759629,"about_ca_system_score_gemma":0.015934676,"threshold_uncertainty_score":0.99616456},"labels":[],"label_agreement":null},{"id":"W4401363971","doi":"10.3138/cjpe-2024-0126","title":"Reinhard Stockmann, Wolfgang Meyer, &amp; Laszlo Szentmarjay. (Eds.) (2022). <i>The Institutionalisation of Evaluation in the Americas</i>","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Institutionalisation; Political science; Sociology; Humanities; Philosophy; Law","score_opus":0.31244695241803505,"score_gpt":0.5200390598074937,"score_spread":0.2075921073894586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363971","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006329949,0.881645,0.0055580046,0.06968524,0.009042106,0.000034982157,0.0009402979,0.00033023002,0.032131057],"genre_scores_gemma":[0.0049157985,0.9379292,0.0042087855,0.0024656653,0.00238978,0.000057075154,0.0008264421,0.00021005998,0.046997305],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982717,0.00040306264,0.00013657486,0.00018000703,0.00085789943,0.00015067843],"domain_scores_gemma":[0.99651897,0.0016519852,0.00040009816,0.000090711306,0.00083881174,0.00049947685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00428438,0.002093399,0.0012942188,0.0030633758,0.00068381935,0.004656281,0.0011389203,0.0025174555,0.02927123],"category_scores_gemma":[0.005615013,0.00096385635,0.0005638868,0.0043357424,0.0011913106,0.005678961,0.0017524577,0.0026055523,0.028853627],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003231346,0.000012725121,0.0002820885,0.0005403519,0.000010689253,0.000033779157,0.000099630466,0.00025830782,0.00006547855,0.0036088158,0.70587313,0.28918278],"study_design_scores_gemma":[0.000010254008,0.000010886621,0.0010128699,0.0014782009,0.00002577105,0.0001364778,0.0002639036,0.0003638315,0.00022722116,0.004236377,0.99221295,0.000021235312],"about_ca_topic_score_codex":0.032824017,"about_ca_topic_score_gemma":0.068855554,"teacher_disagreement_score":0.032824017,"about_ca_system_score_codex":0.0034385677,"about_ca_system_score_gemma":0.008445871,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4401363982","doi":"10.3138/cjpe-2023-0025","title":"E-Eval: Learnings from a Community-Based Evaluation Capacity Building Initiative","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Concordia University of Edmonton; University of Alberta","funders":"","keywords":"Capacity building; Geography; Forestry; Political science","score_opus":0.6622962955102082,"score_gpt":0.5664147753741403,"score_spread":0.09588152013606788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363982","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12771551,0.003181993,0.25991455,0.22004232,0.0023368266,0.0045655537,0.00048457473,0.005309656,0.37644908],"genre_scores_gemma":[0.45205992,0.0027596396,0.47591445,0.014444303,0.0005224096,0.0017926791,0.00072550523,0.00087335677,0.050907712],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97755903,0.015379541,0.000502741,0.00085723883,0.0036180427,0.0020834252],"domain_scores_gemma":[0.92873055,0.03701036,0.0015020637,0.006025978,0.007265002,0.019466124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051616725,0.0007639679,0.00048751058,0.0021495833,0.006810698,0.011186235,0.004356618,0.0025447384,0.009014778],"category_scores_gemma":[0.04871233,0.0004864262,0.0005985584,0.0014481139,0.0114187915,0.0066231624,0.018558946,0.005902904,0.002013147],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018325774,0.0034610035,0.0051214704,0.00059561647,0.00003605642,0.0007314919,0.043614473,0.0017924535,0.0021327466,0.0681294,0.120068155,0.75413394],"study_design_scores_gemma":[0.00027287204,0.0010361095,0.007920133,0.0024408838,0.000052445514,0.0007759136,0.07232662,0.0067688297,0.0055871857,0.11923619,0.7833171,0.00026577222],"about_ca_topic_score_codex":0.021559758,"about_ca_topic_score_gemma":0.09229816,"teacher_disagreement_score":0.051616725,"about_ca_system_score_codex":0.010022248,"about_ca_system_score_gemma":0.037131857,"threshold_uncertainty_score":0.2729786},"labels":[],"label_agreement":null},{"id":"W4401364057","doi":"10.3138/cjpe-2024-0024","title":"What Can Be Accomplished in 25 Years: In Memoriam of Dr. Stafford Hood","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Genealogy; History","score_opus":0.20618281051872753,"score_gpt":0.5059913778199284,"score_spread":0.29980856730120087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364057","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014047419,0.014748944,0.00025741462,0.83249974,0.15020134,0.000018174629,0.00004165617,0.000036810907,0.0020553546],"genre_scores_gemma":[0.0046337144,0.022919023,0.0011032919,0.82191885,0.12487085,0.00015142302,0.000089974536,0.00020167942,0.024111193],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9821895,0.006329564,0.0011345702,0.0017192867,0.0068940492,0.0017331399],"domain_scores_gemma":[0.9435291,0.017671077,0.0016626884,0.0016775231,0.01957992,0.015879728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027481109,0.0015485641,0.002144102,0.0013486146,0.010859096,0.016119216,0.003273961,0.011193616,0.006794364],"category_scores_gemma":[0.07018784,0.000848759,0.0015616853,0.0013080069,0.009749754,0.015699243,0.008114966,0.05379877,0.0050432747],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008796555,0.000014544565,0.000050440358,0.000034640907,0.0000042606503,0.00006431486,0.00064994,0.0000095732985,0.000018482957,0.00096966967,0.9923052,0.0058702095],"study_design_scores_gemma":[0.00001219384,0.000025215746,0.00025227736,0.0006013532,0.00000979583,0.0002556853,0.0033805755,0.000031480897,0.000057670553,0.0025097146,0.9928213,0.000042820473],"about_ca_topic_score_codex":0.025882157,"about_ca_topic_score_gemma":0.05657672,"teacher_disagreement_score":0.027481109,"about_ca_system_score_codex":0.011956522,"about_ca_system_score_gemma":0.024532756,"threshold_uncertainty_score":0.14533573},"labels":[],"label_agreement":null},{"id":"W4401364183","doi":"10.3138/cjpe.39.1.rr-fr","title":"Nos racines et nos liens : une célébration de bons remèdes en évaluation autochtone","year":2024,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Mathematics; Art","score_opus":0.08810190095737296,"score_gpt":0.4216578946619128,"score_spread":0.3335559937045398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364183","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015936906,0.027655153,0.0037124625,0.92797506,0.015237113,0.00017233759,0.00005190803,0.00007335455,0.009185655],"genre_scores_gemma":[0.63305646,0.0307518,0.032617357,0.247818,0.01205,0.0019266213,0.00018267066,0.00057833706,0.04101865],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.82792014,0.124903016,0.008428407,0.0037507736,0.027669989,0.0073276693],"domain_scores_gemma":[0.63060534,0.25788462,0.010979674,0.01572138,0.055636387,0.029172646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18752429,0.0008208143,0.0016213416,0.0022347737,0.013937703,0.016741335,0.0023995086,0.015108837,0.0045668026],"category_scores_gemma":[0.3020597,0.0009497671,0.001464497,0.0017705576,0.020054111,0.0134895425,0.017217489,0.027530897,0.0004949376],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011498345,0.0014204553,0.006780217,0.0037263485,0.00029933013,0.002152903,0.10695461,0.001266759,0.0026088774,0.15019879,0.33377904,0.38966274],"study_design_scores_gemma":[0.00037057683,0.0006013435,0.011083483,0.014081147,0.0001740416,0.0023692253,0.046714835,0.0020515241,0.0013989419,0.028141929,0.8927348,0.00027813812],"about_ca_topic_score_codex":0.051624116,"about_ca_topic_score_gemma":0.16420278,"teacher_disagreement_score":0.18752429,"about_ca_system_score_codex":0.031461667,"about_ca_system_score_gemma":0.07410282,"threshold_uncertainty_score":0.9917351},"labels":[],"label_agreement":null},{"id":"W4401364631","doi":"10.3138/cjpe-2023-0020","title":"Developing an Evaluation Training Program for Community-Based Organizations: A Participatory Curriculum Development Approach","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Training (meteorology); Curriculum; Citizen journalism; Curriculum development; Medical education; Sociology; Computer science; Political science; Pedagogy; Geography; Medicine","score_opus":0.6931025557856326,"score_gpt":0.5773742074883836,"score_spread":0.11572834829724898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25755304,0.0006591489,0.5581634,0.014281086,0.00067085365,0.09211191,0.0003906835,0.0014071603,0.07476268],"genre_scores_gemma":[0.22218822,0.00045419656,0.73954827,0.0008105942,0.00006756363,0.027211696,0.00022589958,0.000081423714,0.009412191],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9827574,0.012136254,0.0006178157,0.00083791954,0.002358785,0.0012917059],"domain_scores_gemma":[0.97331595,0.012131163,0.0013954521,0.001745312,0.0057857656,0.005626409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048630133,0.0005862885,0.0004519549,0.0019831792,0.004055655,0.003362257,0.003279817,0.001189728,0.0038707],"category_scores_gemma":[0.032046735,0.00048115067,0.00047547414,0.0015200647,0.0020418358,0.001830257,0.0062394673,0.0024922856,0.00065542985],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021347946,0.0136443395,0.0060508233,0.0014971398,0.000035293295,0.00044719572,0.027431112,0.010095748,0.006682014,0.028414812,0.01856223,0.8869259],"study_design_scores_gemma":[0.0020045023,0.014097571,0.036973305,0.0063636275,0.00019615938,0.0011994547,0.09436358,0.049067732,0.036080852,0.07577614,0.68349034,0.00038686825],"about_ca_topic_score_codex":0.0030500104,"about_ca_topic_score_gemma":0.0068719904,"teacher_disagreement_score":0.048630133,"about_ca_system_score_codex":0.0075842002,"about_ca_system_score_gemma":0.041008055,"threshold_uncertainty_score":0.2571838},"labels":[],"label_agreement":null},{"id":"W4401364750","doi":"10.3138/cjpe-2023-0047","title":"Expert Panels in Evaluation: An Update From the Field Using the DATA Model","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Canada; Agriculture and Agri-Food Canada; University of Prince Edward Island","funders":"","keywords":"Field (mathematics); Computer science; Data science; Mathematics","score_opus":0.7706233405746606,"score_gpt":0.6311445631645073,"score_spread":0.13947877741015335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364750","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00503366,0.2774172,0.22550593,0.42705095,0.014845936,0.00062068994,0.00020309247,0.00044881596,0.04887371],"genre_scores_gemma":[0.14956503,0.34798592,0.38132223,0.092614904,0.01025962,0.0025385043,0.00028066392,0.0011694655,0.014263591],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7291032,0.19784197,0.020256942,0.010642719,0.039835233,0.0023199592],"domain_scores_gemma":[0.44598296,0.44122025,0.01023254,0.030342268,0.067476355,0.0047455416],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30023992,0.0016037204,0.0033427814,0.010289632,0.0060179657,0.023763029,0.006758878,0.01438147,0.0030016503],"category_scores_gemma":[0.2507205,0.0024672437,0.0021249612,0.017749256,0.03490743,0.03573415,0.012350663,0.020360379,0.002289358],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001392231,0.00014504677,0.0025302721,0.004032015,0.00011671775,0.00036692785,0.017305864,0.0027695836,0.00027478195,0.41000316,0.0741525,0.48816392],"study_design_scores_gemma":[0.000044007073,0.000091893984,0.001053423,0.015425316,0.00008357576,0.0005706418,0.006682848,0.0034664304,0.00049398403,0.13010608,0.84176826,0.00021352507],"about_ca_topic_score_codex":0.02274985,"about_ca_topic_score_gemma":0.023731139,"teacher_disagreement_score":0.30023992,"about_ca_system_score_codex":0.024763832,"about_ca_system_score_gemma":0.028807197,"threshold_uncertainty_score":0.86292875},"labels":[],"label_agreement":null},{"id":"W4401364911","doi":"10.3138/cjpe-2024-0023","title":"Marthe Hurteau &amp; Thomas Archibald (Eds.). (2023). <i>Practical Wisdom for an Ethical Evaluation Practice</i> .","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Environmental ethics; Engineering ethics; Engineering","score_opus":0.4952909679291251,"score_gpt":0.6140363416331979,"score_spread":0.11874537370407279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364911","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023230925,0.67721105,0.004967244,0.232201,0.029362861,0.000052204392,0.0008826858,0.0003260339,0.054764524],"genre_scores_gemma":[0.004352564,0.79683447,0.007989452,0.021183936,0.011143982,0.00012692543,0.0008400927,0.00044874474,0.15707986],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995765,0.0010762672,0.0003213179,0.00029411472,0.0023361177,0.00020718202],"domain_scores_gemma":[0.98700434,0.0062310006,0.0009255966,0.00034287162,0.003997851,0.0014982801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008763719,0.0020250732,0.0014498159,0.0025296912,0.0016762513,0.0072230836,0.0016925008,0.005513163,0.04374592],"category_scores_gemma":[0.015186624,0.0012228779,0.00084882986,0.0039214245,0.0024221232,0.0061338954,0.0024726642,0.0060855467,0.0462999],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012463754,0.0000072829575,0.00009656742,0.0002836672,0.0000053063877,0.000029018503,0.0000954532,0.000094327195,0.000034354794,0.0026280882,0.879915,0.1167984],"study_design_scores_gemma":[0.0000066403095,0.000007120005,0.00032854962,0.0016730923,0.000011176606,0.000118207616,0.0002523552,0.00015845738,0.00010464378,0.005253489,0.9920684,0.000017927436],"about_ca_topic_score_codex":0.043770935,"about_ca_topic_score_gemma":0.12042789,"teacher_disagreement_score":0.043770935,"about_ca_system_score_codex":0.004791787,"about_ca_system_score_gemma":0.018513247,"threshold_uncertainty_score":0.1463446},"labels":[],"label_agreement":null},{"id":"W4401365084","doi":"10.3138/cjpe.39.1.ed-fr","title":"Un mot de la rédactrice","year":2024,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Geography","score_opus":0.0851767379731989,"score_gpt":0.3805536059568216,"score_spread":0.29537686798362267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401365084","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01587235,0.01441935,0.07976245,0.17871644,0.05985437,0.000894985,0.006960841,0.0113215875,0.63219756],"genre_scores_gemma":[0.09553312,0.0086315395,0.054840647,0.022846336,0.015529778,0.0012034659,0.0059847427,0.0062044337,0.789226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97131807,0.011250799,0.0011985577,0.0024071503,0.012604696,0.0012207706],"domain_scores_gemma":[0.9615207,0.010262906,0.0014988862,0.0036542916,0.021464385,0.0015988231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014926452,0.0020989748,0.001582721,0.0036662787,0.0063358406,0.016318798,0.0020016027,0.0049952334,0.097375706],"category_scores_gemma":[0.04813528,0.0010582871,0.0019290266,0.0030348918,0.0036149034,0.009202715,0.004444916,0.011762524,0.037298385],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005233755,0.00020023684,0.0016398389,0.0008433422,0.00006399228,0.0006234752,0.002837901,0.0009681686,0.0036844932,0.13673215,0.54349554,0.30838746],"study_design_scores_gemma":[0.000056015793,0.000039143943,0.0010280292,0.00023023777,0.0000141721175,0.00036678402,0.00063856685,0.00052231015,0.0013363108,0.004432176,0.9912874,0.00004876698],"about_ca_topic_score_codex":0.09008972,"about_ca_topic_score_gemma":0.055059113,"teacher_disagreement_score":0.097375706,"about_ca_system_score_codex":0.011194371,"about_ca_system_score_gemma":0.011748214,"threshold_uncertainty_score":0.32575417},"labels":[],"label_agreement":null},{"id":"W4401380024","doi":"10.3138/cjpe-2024-0025","title":"In Memoriam : Dr Michael Scriven","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Advances in Oncology and Radiotherapy","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Evaluation Society","funders":"","keywords":"Art; Philosophy","score_opus":0.06950805959103097,"score_gpt":0.4698868799706733,"score_spread":0.40037882037964234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401380024","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017846341,0.0021082284,0.00024856094,0.63593787,0.35863253,0.00003311192,0.00015243921,0.0000638241,0.0026449587],"genre_scores_gemma":[0.004290259,0.0038124507,0.0006753459,0.6290209,0.29271328,0.00016160082,0.00015502662,0.00011597876,0.06905512],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943784,0.00090227823,0.00060650404,0.0007352833,0.0027565828,0.00062091707],"domain_scores_gemma":[0.9338809,0.012842662,0.0036214823,0.0017635184,0.03738062,0.010510844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072152372,0.0011831068,0.0022489694,0.001596277,0.0033162395,0.007027074,0.003195928,0.013771091,0.026448557],"category_scores_gemma":[0.11231494,0.00060812663,0.0014644155,0.00090518856,0.0026021171,0.0035016595,0.00416396,0.027616268,0.018395122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007769753,0.0000053023327,0.000114501934,0.00002322163,0.000006159225,0.00015194467,0.0000316645,0.000017025848,0.000010455455,0.00021070376,0.99684453,0.0025768282],"study_design_scores_gemma":[0.00002939391,0.000016595148,0.00061035354,0.00029622347,0.000025867284,0.00080640236,0.0004908395,0.00013921582,0.00008461738,0.0013022615,0.99616504,0.000033177876],"about_ca_topic_score_codex":0.015159191,"about_ca_topic_score_gemma":0.029564094,"teacher_disagreement_score":0.026448557,"about_ca_system_score_codex":0.008568597,"about_ca_system_score_gemma":0.015029064,"threshold_uncertainty_score":0.08847922},"labels":[],"label_agreement":null},{"id":"W4401380030","doi":"10.3138/cjpe-2023-0040","title":"Using Dedoose to “Quantitize” Qualitative Data in Mixed Method Analysis: A Case Analysis","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Technology Adoption and User Behaviour","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Qualitative analysis; Computer science; Qualitative research; Sociology","score_opus":0.7511361533249208,"score_gpt":0.6609219567685167,"score_spread":0.09021419655640406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401380030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017186524,0.0041334596,0.9346295,0.020869063,0.0011471392,0.005956963,0.00014803426,0.00067131396,0.015257957],"genre_scores_gemma":[0.049779344,0.0026242079,0.93658346,0.0022968375,0.00015587178,0.006177828,0.000053981596,0.0003293907,0.001999165],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7457976,0.2169194,0.012158229,0.0027141355,0.0213427,0.0010679449],"domain_scores_gemma":[0.53786254,0.41368935,0.008352756,0.013497017,0.025611086,0.0009872828],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2305397,0.0010156392,0.001255964,0.0066119344,0.004232399,0.008476085,0.0030229276,0.0028994954,0.0018363476],"category_scores_gemma":[0.24062254,0.0013658609,0.0015742262,0.005789335,0.007907628,0.0074397097,0.007195849,0.004323912,0.0007142683],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021717059,0.00044550825,0.007874468,0.0079669105,0.00019913059,0.002954868,0.12239099,0.003927448,0.006508774,0.20353746,0.041672602,0.6023047],"study_design_scores_gemma":[0.00023164463,0.0014928747,0.008348442,0.017876433,0.00027527008,0.008972373,0.07522983,0.031570047,0.018043019,0.11753086,0.7196639,0.0007653055],"about_ca_topic_score_codex":0.003646531,"about_ca_topic_score_gemma":0.012386473,"teacher_disagreement_score":0.2305397,"about_ca_system_score_codex":0.005437535,"about_ca_system_score_gemma":0.00668381,"threshold_uncertainty_score":0.94888157},"labels":[],"label_agreement":null},{"id":"W4405365781","doi":"10.3138/cjpe.38.2.rr-fr","title":"Introduction à la deuxième section « Nos racines et nos liens »","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Education, sociology, and vocational training","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Section (typography); Computer science","score_opus":0.3637926478787051,"score_gpt":0.5189570241948082,"score_spread":0.15516437631610308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365781","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062238225,0.09080779,0.024235785,0.49424767,0.19239427,0.0006090337,0.003366523,0.0006318419,0.18748324],"genre_scores_gemma":[0.06701355,0.10207407,0.036038034,0.21777765,0.08907218,0.0024088721,0.004653334,0.0010082292,0.47995415],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945622,0.0022601937,0.00040522535,0.0005988514,0.0016230546,0.0005504483],"domain_scores_gemma":[0.97708124,0.009730105,0.00083005487,0.0005269323,0.010496605,0.0013350626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072027775,0.00055978564,0.00066085043,0.0019952613,0.003969145,0.0066549308,0.0012100805,0.003666538,0.039486695],"category_scores_gemma":[0.019769255,0.00034425175,0.0007229049,0.0016252657,0.0028985129,0.002577691,0.0022520155,0.006273225,0.006022765],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007966797,0.00007593304,0.0010016626,0.0011971229,0.000015794963,0.00012602173,0.0031982244,0.00016077279,0.0008230386,0.086594075,0.8146366,0.09209118],"study_design_scores_gemma":[0.000004512853,0.000011542739,0.0008110519,0.0005644554,0.0000046488476,0.00005876249,0.00051703176,0.00002956218,0.00009886498,0.002244024,0.99564505,0.000010580885],"about_ca_topic_score_codex":0.07287319,"about_ca_topic_score_gemma":0.1385907,"teacher_disagreement_score":0.07287319,"about_ca_system_score_codex":0.007146638,"about_ca_system_score_gemma":0.016830996,"threshold_uncertainty_score":0.144898},"labels":[],"label_agreement":null},{"id":"W4405365784","doi":"10.3138/cjpe.76851","title":"Veronica G. Thomas and Patricia B. Campbell (2021). <i>Evaluation in today’s world: Respecting diversity, improving quality, and promoting usability</i>","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diversity (politics); Usability; Quality (philosophy); Sociology; Library science; Computer science; Philosophy; Anthropology; Epistemology; Human–computer interaction","score_opus":0.3843085190255128,"score_gpt":0.5217906207117903,"score_spread":0.1374821016862775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365784","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034464535,0.091317646,0.004329474,0.8082964,0.067567766,0.00012475421,0.0005430198,0.0003693695,0.027107101],"genre_scores_gemma":[0.0144632645,0.16524069,0.014885659,0.4052234,0.033675317,0.00044956553,0.0010943309,0.0008783893,0.36408943],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99199355,0.001722513,0.0005037431,0.0005108032,0.004938164,0.00033111192],"domain_scores_gemma":[0.9557156,0.008940619,0.0016903151,0.0006342095,0.028093582,0.0049257353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013393101,0.0010896495,0.000636806,0.0037545946,0.0031192002,0.006663633,0.0019427533,0.0067827296,0.021878788],"category_scores_gemma":[0.04430683,0.000712149,0.0005744844,0.0027305163,0.0026689922,0.0044501033,0.0025724738,0.009164117,0.020428058],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009046163,0.0000060376346,0.00019856535,0.00009808281,0.0000022278593,0.00002448488,0.0001535568,0.000021907996,0.00006290094,0.001241395,0.96347505,0.03470678],"study_design_scores_gemma":[0.0000080052205,0.0000113937385,0.0008241705,0.00083489297,0.000007791017,0.00009483873,0.00033921914,0.000056945337,0.00014405062,0.002260371,0.99539655,0.000021697324],"about_ca_topic_score_codex":0.087425664,"about_ca_topic_score_gemma":0.21460631,"teacher_disagreement_score":0.087425664,"about_ca_system_score_codex":0.004695218,"about_ca_system_score_gemma":0.020613506,"threshold_uncertainty_score":0.17383355},"labels":[],"label_agreement":null},{"id":"W4405365834","doi":"10.3138/cjpe-2023-0022","title":"Une collaboration recherche-pratique pour améliorer l’organisation des services aux enfants ayant un retard de développement","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Family and Disability Support Research","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais; Cégep de l'Outaouais","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.3230178159040422,"score_gpt":0.5181626233987924,"score_spread":0.19514480749475016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365834","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1770179,0.0558945,0.11335572,0.592627,0.0026655144,0.002135023,0.0011984054,0.00049996265,0.054605987],"genre_scores_gemma":[0.70810616,0.036296602,0.22972703,0.010212576,0.0006850902,0.0017555661,0.00092040404,0.00021136511,0.012085228],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8583529,0.11184744,0.0040006936,0.0037436802,0.015362612,0.0066927746],"domain_scores_gemma":[0.8058445,0.12551469,0.012549547,0.010418684,0.030839426,0.014833201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14369982,0.00085305056,0.001201553,0.0039493702,0.008870701,0.0136493165,0.0037035472,0.0035608625,0.004303452],"category_scores_gemma":[0.1296663,0.00072579656,0.0015338346,0.005463673,0.009639495,0.009769123,0.008751421,0.008832924,0.0008908195],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046399745,0.0016184209,0.06496104,0.005751916,0.00032754746,0.001374943,0.18053192,0.0051842867,0.005355923,0.16608375,0.04578663,0.5225596],"study_design_scores_gemma":[0.00034102108,0.001710286,0.0661618,0.010244038,0.00020578258,0.0008382444,0.3569355,0.0038886468,0.0073068053,0.042609356,0.50940067,0.00035786311],"about_ca_topic_score_codex":0.38031542,"about_ca_topic_score_gemma":0.39496306,"teacher_disagreement_score":0.38031542,"about_ca_system_score_codex":0.053972833,"about_ca_system_score_gemma":0.21814075,"threshold_uncertainty_score":0.7599664},"labels":[],"label_agreement":null},{"id":"W4405365835","doi":"10.3138/cjpe-2023-0036","title":"The Evaluation and Research of the Somatic Archaeology Model <sup>©</sup>","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Cultural Heritage Management and Preservation","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Archaeology; Somatic cell; Environmental science; History; Chemistry","score_opus":0.52334230746563,"score_gpt":0.41824368714025206,"score_spread":0.10509862032537798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365835","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15268686,0.04128707,0.030405559,0.19127654,0.008425851,0.0021540637,0.0010547945,0.00020707783,0.57250214],"genre_scores_gemma":[0.8454883,0.04369901,0.034884308,0.023517868,0.0022462371,0.003014724,0.00094879966,0.0002576328,0.045943163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.990272,0.006522808,0.00038213911,0.00035173667,0.0021157481,0.0003555468],"domain_scores_gemma":[0.94014055,0.03755633,0.0029472248,0.0030851897,0.0137196,0.002551097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022616755,0.0003934437,0.00032064415,0.0017203374,0.0035014001,0.010736737,0.0015952695,0.0014138065,0.010313954],"category_scores_gemma":[0.048531286,0.00022444632,0.0005389654,0.0021132333,0.0085409265,0.0058091767,0.0043704375,0.0028561687,0.0017380508],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023909629,0.00040505707,0.020697864,0.0018272272,0.000034479926,0.00053394714,0.03694559,0.00057480903,0.0007692444,0.44518507,0.10149131,0.3912963],"study_design_scores_gemma":[0.000047492416,0.0006788632,0.0323923,0.010911586,0.00009823358,0.0011451247,0.23533037,0.0031517008,0.00228144,0.069009885,0.6448574,0.000095645075],"about_ca_topic_score_codex":0.008535981,"about_ca_topic_score_gemma":0.012631626,"teacher_disagreement_score":0.022616755,"about_ca_system_score_codex":0.007919293,"about_ca_system_score_gemma":0.015346674,"threshold_uncertainty_score":0.11961031},"labels":[],"label_agreement":null},{"id":"W4405365838","doi":"10.3138/cjpe-2023-0027","title":"A Conversational Approach to Learning About Learning: Embedded Indigenous Evaluation and Communities of Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Yukon University; University of Manitoba; Saskatchewan Health Authority; Vancouver Island University","funders":"","keywords":"Indigenous; Computer science; Psychology; Mathematics education; Sociology; Ecology","score_opus":0.23476152038788015,"score_gpt":0.47532930408291163,"score_spread":0.24056778369503148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365838","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13251172,0.0068336674,0.37455213,0.09524889,0.0018447181,0.0041117775,0.00018643257,0.0005434891,0.38416722],"genre_scores_gemma":[0.8952025,0.0016291307,0.078540914,0.004054309,0.0001907728,0.0027799571,0.000057798054,0.00017908939,0.017365532],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.87555325,0.114307046,0.001246884,0.00204063,0.004414466,0.002437794],"domain_scores_gemma":[0.9052405,0.078560226,0.002491665,0.0036814553,0.005139584,0.004886601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06440585,0.0010064902,0.0010183011,0.004259851,0.02215892,0.022912588,0.0044632116,0.0065063154,0.006731685],"category_scores_gemma":[0.056726243,0.00079483114,0.00080876995,0.0029697856,0.055247676,0.021546755,0.025120301,0.009203411,0.000737747],"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":[0.00003990654,0.000090227324,0.0004118747,0.00038327655,0.000014218263,0.00044566902,0.84864116,0.00023178496,0.00031780486,0.12865606,0.0018886974,0.018879348],"study_design_scores_gemma":[0.000043358825,0.00011583589,0.0006408823,0.001612313,0.000029983525,0.00054668623,0.7518303,0.001267011,0.00090769405,0.12924628,0.11368125,0.00007851793],"about_ca_topic_score_codex":0.010976161,"about_ca_topic_score_gemma":0.014898531,"teacher_disagreement_score":0.06440585,"about_ca_system_score_codex":0.0157662,"about_ca_system_score_gemma":0.018661072,"threshold_uncertainty_score":0.3406148},"labels":[],"label_agreement":null},{"id":"W4405365972","doi":"10.3138/cjpe.76834","title":"Gail Vallance Barrington &amp; Beverly Triana-Tremain. (2022). <i>Evaluation time: A practical guide for evaluation</i>","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Environmental science","score_opus":0.4077939034852666,"score_gpt":0.576833651242932,"score_spread":0.16903974775766534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365972","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067039224,0.03231973,0.010417665,0.1415208,0.01123694,0.00034533752,0.0050231298,0.006212419,0.79225355],"genre_scores_gemma":[0.0021355464,0.007523026,0.004113244,0.011704055,0.00046603804,0.00014272,0.00069876446,0.0010896315,0.97212696],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998607,0.0002507186,0.00006213744,0.00018752826,0.0007663155,0.00012642633],"domain_scores_gemma":[0.9949477,0.00078818854,0.00021931398,0.0001873732,0.0026102252,0.0012472002],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002427078,0.0009765672,0.00058962003,0.0016405352,0.0020900925,0.0038320683,0.0013078669,0.0025500352,0.4066858],"category_scores_gemma":[0.0077409237,0.0007345291,0.00039027559,0.0012585992,0.00083619356,0.002543273,0.0020530792,0.0034857122,0.29929104],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073712463,0.0000045220354,0.000037837668,0.000025639167,6.0585637e-7,0.000014641269,0.000024957873,0.000014790718,0.000036945337,0.00043833084,0.96858907,0.030805258],"study_design_scores_gemma":[0.0000035986097,0.000003796075,0.00018301455,0.00009756531,0.0000013400281,0.00002967322,0.000074312804,0.000043861324,0.00005152728,0.0003620213,0.9991437,0.000005467704],"about_ca_topic_score_codex":0.048329853,"about_ca_topic_score_gemma":0.14751734,"teacher_disagreement_score":0.4066858,"about_ca_system_score_codex":0.002044566,"about_ca_system_score_gemma":0.0064940234,"threshold_uncertainty_score":0.8462907},"labels":[],"label_agreement":null},{"id":"W4405365997","doi":"10.3138/cjpe.38.2.ed-fr","title":"Un mot de la rédactrice","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.11514319283525193,"score_gpt":0.38527159884555906,"score_spread":0.27012840601030713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365997","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015735187,0.014683609,0.077660754,0.18048926,0.060411263,0.0009001743,0.0069641354,0.0110815875,0.6320741],"genre_scores_gemma":[0.09548527,0.008808615,0.054027464,0.02298319,0.015652576,0.0012124529,0.0059522563,0.0060997447,0.7897784],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9711174,0.011267655,0.001214673,0.0024019592,0.012769003,0.0012293428],"domain_scores_gemma":[0.9608431,0.010352881,0.0015191379,0.003683932,0.02197671,0.001624213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015023522,0.002085078,0.0015823699,0.003714673,0.0063316394,0.016370298,0.0020028604,0.0049965656,0.09706946],"category_scores_gemma":[0.04850366,0.0010515578,0.001916292,0.0030759152,0.0036132312,0.009165806,0.0044404212,0.011682445,0.03716339],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051501126,0.00019821785,0.0016324739,0.0008344225,0.000063017746,0.0006136689,0.002808066,0.00095100846,0.0036115062,0.1346868,0.54688835,0.30719748],"study_design_scores_gemma":[0.000055495027,0.0000389294,0.0010363294,0.00023096857,0.000013998007,0.0003619141,0.0006378709,0.0005090131,0.0013061771,0.0043694954,0.9913914,0.00004840039],"about_ca_topic_score_codex":0.09251535,"about_ca_topic_score_gemma":0.05651768,"teacher_disagreement_score":0.09706946,"about_ca_system_score_codex":0.011344027,"about_ca_system_score_gemma":0.011959272,"threshold_uncertainty_score":0.32472968},"labels":[],"label_agreement":null},{"id":"W4405366000","doi":"10.3138/cjpe-2023-0011","title":"When we say evaluation, it isn’t the same thing","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Computer science","score_opus":0.5162236582112425,"score_gpt":0.5551123995560459,"score_spread":0.03888874134480336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366000","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025130128,0.019081129,0.01829192,0.87380034,0.029828642,0.00009830744,0.00019938636,0.00040436914,0.055783],"genre_scores_gemma":[0.22159886,0.020883197,0.05062499,0.6335914,0.018909879,0.00046013514,0.00031545045,0.001454995,0.052161038],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8496429,0.07492574,0.00746906,0.006093839,0.055280983,0.006587491],"domain_scores_gemma":[0.756927,0.09090502,0.008659824,0.015332735,0.109731495,0.018443905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.066145055,0.0010173013,0.0026423,0.0039058528,0.008180827,0.02217061,0.0024649492,0.009255661,0.012111769],"category_scores_gemma":[0.22431158,0.00074818474,0.0016376129,0.0038990595,0.030261738,0.018341405,0.005145923,0.021999374,0.004564168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017688863,0.00019022245,0.004435049,0.0021024153,0.0004211408,0.00015754873,0.0059138555,0.0005338745,0.0009776347,0.197485,0.64918,0.13842641],"study_design_scores_gemma":[0.00010910455,0.00018752957,0.004178975,0.005497089,0.00025644942,0.0004889585,0.011765316,0.00060572446,0.0017847439,0.17053318,0.80430573,0.00028722425],"about_ca_topic_score_codex":0.047212634,"about_ca_topic_score_gemma":0.048095886,"teacher_disagreement_score":0.066145055,"about_ca_system_score_codex":0.013835319,"about_ca_system_score_gemma":0.026914103,"threshold_uncertainty_score":0.3498127},"labels":[],"label_agreement":null},{"id":"W4405366071","doi":"10.3138/cjpe.38.2.rr-en","title":"Introduction to 2nd Roots and Relations Section","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Plant Molecular Biology Research","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Section (typography); Geology; Computer science","score_opus":0.08111006797874254,"score_gpt":0.33464356837323284,"score_spread":0.2535335003944903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366071","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002480368,0.02251123,0.0502313,0.035586264,0.033914715,0.0007695129,0.011497929,0.0043100403,0.83869857],"genre_scores_gemma":[0.009588256,0.01334547,0.016524473,0.0057135485,0.0056521213,0.00023757847,0.0043781525,0.0012410564,0.9433194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990656,0.00008731039,0.000051404724,0.00015460064,0.00047139992,0.00016973521],"domain_scores_gemma":[0.99635136,0.00061625394,0.00013285791,0.00020793565,0.0022368047,0.00045473618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016863823,0.0010253696,0.00062477123,0.0028219903,0.0021834602,0.0038387873,0.0013662968,0.0015739475,0.24538666],"category_scores_gemma":[0.0034955782,0.0005785432,0.00070627197,0.0020209546,0.0010010117,0.0027784558,0.0015405979,0.0028677026,0.08044182],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038701794,0.000048902002,0.00057732774,0.00025669142,0.0000028260652,0.00009078184,0.0001644496,0.00031659516,0.0009291398,0.030765966,0.77928334,0.18752524],"study_design_scores_gemma":[0.0000023243308,0.000008556906,0.0008671709,0.000112903515,0.0000018028239,0.00005668571,0.00005463741,0.000069335976,0.0002126224,0.0041639092,0.9944423,0.000007776276],"about_ca_topic_score_codex":0.11163734,"about_ca_topic_score_gemma":0.2046975,"teacher_disagreement_score":0.24538666,"about_ca_system_score_codex":0.0068118465,"about_ca_system_score_gemma":0.012122504,"threshold_uncertainty_score":0.82090014},"labels":[],"label_agreement":null},{"id":"W4405366141","doi":"10.3138/cjpe.38.2.ed-en","title":"Editor’s Remarks","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Computer science","score_opus":0.08631146171931367,"score_gpt":0.44821129325792025,"score_spread":0.3618998315386066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366141","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000119412995,0.001873331,0.00012024426,0.41039166,0.5826468,0.000032262844,0.000109481545,0.000070688286,0.0046361405],"genre_scores_gemma":[0.0017618249,0.0014222517,0.00043447103,0.6957009,0.25361544,0.000087419336,0.000052822044,0.00007344841,0.046851408],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98093665,0.0018759676,0.0019987575,0.0027986472,0.010037717,0.0023522477],"domain_scores_gemma":[0.93047756,0.016210133,0.004857307,0.0032766175,0.03526481,0.009913556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016648497,0.0017340239,0.0028201444,0.0027733676,0.0055975,0.011036536,0.005240216,0.04201716,0.03179858],"category_scores_gemma":[0.13241698,0.0012728495,0.0035215942,0.0022090392,0.0038544207,0.0037604584,0.0028955953,0.039445233,0.024062648],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001455141,0.0000063007337,0.000048633836,0.000032510427,0.000008456808,0.000087069246,0.000019388497,0.000012617973,0.000023867804,0.00043072752,0.9974974,0.0018184684],"study_design_scores_gemma":[0.000045406436,0.000013469664,0.0004364263,0.00021001551,0.000027005939,0.00015257142,0.00010357293,0.00006697006,0.000106501655,0.00085405394,0.99795014,0.000033838747],"about_ca_topic_score_codex":0.017278155,"about_ca_topic_score_gemma":0.039980255,"teacher_disagreement_score":0.04201716,"about_ca_system_score_codex":0.008620999,"about_ca_system_score_gemma":0.016131017,"threshold_uncertainty_score":0.10637683},"labels":[],"label_agreement":null},{"id":"W4405366177","doi":"10.3138/cjpe-2023-0012","title":"Examining Youth Sector Stakeholders’ Experiences in an Online Program Evaluation Certificate","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"York University; Youth Research and Evaluation eXchange; Brock University","funders":"","keywords":"Certificate; Business; Public relations; Political science; Computer science","score_opus":0.9339822613619181,"score_gpt":0.581308825436659,"score_spread":0.3526734359252591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99568343,0.000041256248,0.0003790722,0.0006125177,0.000014887872,0.000052481377,0.000024274237,0.000009273104,0.0031829518],"genre_scores_gemma":[0.99812275,0.00007687419,0.00035481644,0.00013278046,0.000008120194,0.00003513758,0.00003696292,0.0000062775835,0.0012263057],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9914657,0.004836141,0.00023605481,0.00024325665,0.0012241598,0.0019947882],"domain_scores_gemma":[0.9858796,0.003956203,0.0018975018,0.00043302847,0.0022379218,0.005595733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0117739085,0.00023253335,0.00031224883,0.0007839358,0.0048004836,0.0037468798,0.000747078,0.00078543427,0.0034231674],"category_scores_gemma":[0.019629885,0.00034022055,0.0003693357,0.0006280554,0.0020608343,0.0016190499,0.005496688,0.0017911956,0.00039083313],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032827203,0.0016168985,0.34672916,0.00019400401,0.000024222361,0.0023683456,0.5648835,0.00033876137,0.0034473308,0.0020261535,0.0047509125,0.07329241],"study_design_scores_gemma":[0.00002072819,0.00092073344,0.14268845,0.00021183825,0.000017135311,0.0006805037,0.8312362,0.0005366674,0.0012590168,0.00040012613,0.021979962,0.00004858416],"about_ca_topic_score_codex":0.015711583,"about_ca_topic_score_gemma":0.03500631,"teacher_disagreement_score":0.015711583,"about_ca_system_score_codex":0.0039807423,"about_ca_system_score_gemma":0.0064201313,"threshold_uncertainty_score":0},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"incentives","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W4406258567","doi":"10.3138/cjpe-2023-0055","title":"Reporting Lines of Inquiry: Documenting Evaluations and Making Values Explicit","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Documentation; Set (abstract data type); Dimension (graph theory); Key (lock); Computer science; Value (mathematics); Quality (philosophy); Action (physics); Psychology; Epistemology; Mathematics","score_opus":0.5936105233649892,"score_gpt":0.6283661788620908,"score_spread":0.03475565549710158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406258567","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04289404,0.010931687,0.6361092,0.2110438,0.004247466,0.007873851,0.000998773,0.0027021489,0.08319902],"genre_scores_gemma":[0.27538952,0.0057102945,0.68598145,0.012157073,0.000991657,0.011494432,0.00068562553,0.0011651777,0.006424734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.30931938,0.55766237,0.059537664,0.009514831,0.059001345,0.0049644704],"domain_scores_gemma":[0.13670272,0.5087624,0.07417081,0.07213219,0.20082092,0.0074109808],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52772695,0.0022004617,0.0020927757,0.0182822,0.012343835,0.035002906,0.0069723614,0.007804138,0.0034235173],"category_scores_gemma":[0.76572984,0.0024793702,0.0017233808,0.012792211,0.02316189,0.042575423,0.020424476,0.013308338,0.0022000796],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024579896,0.00022541147,0.012460104,0.0038935095,0.00019273837,0.0004802304,0.24021716,0.0018400154,0.0021602057,0.19644538,0.07074088,0.47109857],"study_design_scores_gemma":[0.00022317572,0.0004037292,0.008800494,0.025434272,0.0002427992,0.00047296658,0.16120853,0.0056480756,0.0073435213,0.31960765,0.46982452,0.0007902253],"about_ca_topic_score_codex":0.014511304,"about_ca_topic_score_gemma":0.018539991,"teacher_disagreement_score":0.47227305,"about_ca_system_score_codex":0.03052623,"about_ca_system_score_gemma":0.07475299,"threshold_uncertainty_score":0.5823968},"labels":[],"label_agreement":null},{"id":"W4406258628","doi":"10.3138/cjpe-2024-0028","title":"Theory-of-Change Visuals: Using Diagrams, Metaphors, and Symbols to Communicate Complex Ideas and Get Buy-In","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Context (archaeology); Creativity; Field (mathematics); Stakeholder; Dynamism; Sociology; Epistemology; Psychology; Public relations; Social psychology","score_opus":0.7625487198627899,"score_gpt":0.6027241267009266,"score_spread":0.15982459316186337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406258628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040019017,0.003994293,0.7238265,0.036270794,0.0024629994,0.0012713876,0.0007098267,0.0037349146,0.18771024],"genre_scores_gemma":[0.4730385,0.002457308,0.4999357,0.0032721933,0.0003220011,0.0020273565,0.00048410016,0.0010122213,0.017450554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98497677,0.012426271,0.00032738317,0.0006184738,0.0013255149,0.0003255329],"domain_scores_gemma":[0.9670933,0.024667336,0.0014653695,0.0035576385,0.0023086201,0.0009077495],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015514692,0.0022198511,0.0005494381,0.005753631,0.0027971177,0.014228209,0.002833268,0.0031267519,0.011491616],"category_scores_gemma":[0.043959953,0.0007870327,0.0016450516,0.0025525568,0.014071286,0.01812332,0.0078556845,0.0039056763,0.0022256477],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023125975,0.00025529723,0.0022246165,0.0024243337,0.000098221346,0.00069402077,0.167818,0.0045840507,0.004075405,0.5755515,0.042313688,0.19972965],"study_design_scores_gemma":[0.00018097168,0.0003174208,0.0015344908,0.0028724466,0.000119476346,0.0011329482,0.06239934,0.011565631,0.0034637402,0.39279175,0.5233902,0.00023166143],"about_ca_topic_score_codex":0.0021770846,"about_ca_topic_score_gemma":0.0031064467,"teacher_disagreement_score":0.9844853,"about_ca_system_score_codex":0.004433618,"about_ca_system_score_gemma":0.0037095994,"threshold_uncertainty_score":0.0820505},"labels":[],"label_agreement":null},{"id":"W4406259049","doi":"10.3138/cjpe-2024-0034","title":"Old Knowledge, New Tools: Applying an Indigenous Approach to Social Network Analysis","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Honour; Traditional knowledge; Social network analysis; Work (physics); Indigenous education; Value (mathematics); Scale (ratio); Process (computing); Sociology; Data science; Computer science; Geography; Social science; Engineering; Cartography; Archaeology; Ecology; Social capital","score_opus":0.42867378272941575,"score_gpt":0.5489013155159965,"score_spread":0.12022753278658077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406259049","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1979797,0.002056442,0.67305887,0.018658884,0.00035467482,0.0026086508,0.00036137403,0.00052025646,0.10440121],"genre_scores_gemma":[0.58410686,0.0016244734,0.40525228,0.00079598074,0.00009245344,0.0020068449,0.000108795786,0.00012786432,0.005884444],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94905865,0.04504607,0.0010026976,0.001165686,0.0029481014,0.000778742],"domain_scores_gemma":[0.93292576,0.055108204,0.0023683514,0.0037851457,0.004683628,0.0011288244],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.055932824,0.00069470354,0.0006490926,0.0073656305,0.007049325,0.009958641,0.0020148484,0.0008490458,0.0033821177],"category_scores_gemma":[0.05687179,0.00059922907,0.00056925317,0.0043328777,0.011048298,0.009799142,0.008472531,0.0026257082,0.00028148017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006164993,0.00022043439,0.018008543,0.0008826437,0.0001658712,0.000420098,0.51832783,0.0017492202,0.0009384611,0.21509874,0.0025602987,0.24156627],"study_design_scores_gemma":[0.000046943955,0.00024626634,0.018829668,0.001877111,0.00017116123,0.00037276556,0.5660007,0.018056097,0.0015802775,0.29653153,0.096144654,0.0001428786],"about_ca_topic_score_codex":0.039683636,"about_ca_topic_score_gemma":0.06866172,"teacher_disagreement_score":0.9929507,"about_ca_system_score_codex":0.00838345,"about_ca_system_score_gemma":0.011238921,"threshold_uncertainty_score":0.29580456},"labels":[],"label_agreement":null},{"id":"W4406259107","doi":"10.3138/cjpe-2024-0039","title":"Indigenous Data Sovereignty: Applying It By, With, For, and Through Indigenous Evaluators and Evaluations","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Aotearoa; Sovereignty; Alliance; Political science; Traditional knowledge; Human rights; Indigenous rights; Declaration; Law; Sociology; Public administration; Economic growth; Politics","score_opus":0.13022562831437404,"score_gpt":0.4388837017283193,"score_spread":0.30865807341394524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406259107","genre_codex":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032211423,0.026673824,0.1503302,0.5362551,0.009309891,0.0038982367,0.0002221985,0.00070405944,0.240395],"genre_scores_gemma":[0.7317826,0.0154745225,0.1746184,0.050405394,0.0025038205,0.0045879325,0.00022000851,0.0009687043,0.01943867],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4129169,0.51830494,0.014294668,0.0075925277,0.039072324,0.00781865],"domain_scores_gemma":[0.39177895,0.4451201,0.013809337,0.03171624,0.100242734,0.017332619],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47447002,0.0011118292,0.0021400738,0.009501146,0.018751161,0.03895966,0.0050309934,0.006292674,0.0054909172],"category_scores_gemma":[0.48991632,0.00087825913,0.0011226989,0.0074048615,0.06188083,0.034502257,0.030589715,0.015109453,0.0008043315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080905724,0.0002044785,0.004627561,0.0026763058,0.00017057681,0.00024409033,0.34452718,0.0006278472,0.00046151676,0.36990514,0.04603683,0.23043768],"study_design_scores_gemma":[0.00006724903,0.00019882349,0.002670395,0.0131809525,0.00014142152,0.00020372722,0.34243107,0.0013384243,0.0010966246,0.25039396,0.38807788,0.00019945476],"about_ca_topic_score_codex":0.031390186,"about_ca_topic_score_gemma":0.047350287,"teacher_disagreement_score":0.98124886,"about_ca_system_score_codex":0.037033655,"about_ca_system_score_gemma":0.12706791,"threshold_uncertainty_score":0.64807206},"labels":[],"label_agreement":null},{"id":"W4406276209","doi":"10.3138/cjpe-2024-0037","title":"Continuing the Evaluation Journey: Sharing the Lunaape Seven Directions Medicine Wheel (7DMW™) Model","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Engineering ethics; Engineering","score_opus":0.29473198926177535,"score_gpt":0.5316997553062507,"score_spread":0.23696776604447534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406276209","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021506049,0.0074261576,0.17477886,0.6148273,0.0031437043,0.0014361782,0.0001198401,0.00049113866,0.1762708],"genre_scores_gemma":[0.5765756,0.008120943,0.31745908,0.047484707,0.0005859169,0.004589335,0.0001768652,0.0005265601,0.044480972],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7610369,0.20159903,0.0056405063,0.0044284286,0.021412715,0.0058824406],"domain_scores_gemma":[0.8955025,0.05296336,0.00365412,0.0092241345,0.026212791,0.012443104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18409997,0.0008895895,0.0014471015,0.007962281,0.021933436,0.04030265,0.004827829,0.008289595,0.0053876354],"category_scores_gemma":[0.11745955,0.0014425967,0.0017855868,0.0044459705,0.07154242,0.03402827,0.03554533,0.013996677,0.0015268734],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045430665,0.00019085698,0.0022257655,0.00054244086,0.0000404553,0.00019638696,0.07412109,0.00082009454,0.00014211572,0.7686006,0.035952963,0.11712196],"study_design_scores_gemma":[0.00007085614,0.00021370333,0.0015727425,0.0033956307,0.00005212431,0.00025679386,0.120199576,0.0024180063,0.00046735074,0.5100619,0.36110938,0.00018187387],"about_ca_topic_score_codex":0.05234242,"about_ca_topic_score_gemma":0.09801443,"teacher_disagreement_score":0.959754,"about_ca_system_score_codex":0.04024604,"about_ca_system_score_gemma":0.130083,"threshold_uncertainty_score":0.97362536},"labels":[],"label_agreement":null},{"id":"W4406530177","doi":"10.3138/cjpe-2024-0015","title":"Photovoice as a Participatory Evaluation Method: Evaluating a Collective Kitchen Program in Northern Ontario","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Participatory Visual Research Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Lethbridge; Cambrian College","funders":"","keywords":"Photovoice; Citizen journalism; Participatory evaluation; Sociology; Environmental planning; Geography; Computer science; Social science; Art; Visual arts; World Wide Web","score_opus":0.7917015056043963,"score_gpt":0.6991385768057358,"score_spread":0.09256292879866057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406530177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91265833,0.0008461861,0.0069506997,0.0020196561,0.00013266326,0.02386397,0.00055099465,0.00013328934,0.05284421],"genre_scores_gemma":[0.9361296,0.0010147775,0.023169586,0.00060447975,0.000041868694,0.019605216,0.00036390428,0.0000764427,0.018994171],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97297317,0.01686863,0.00050763687,0.0012339101,0.0050895005,0.0033270437],"domain_scores_gemma":[0.98301053,0.0060721706,0.0012463509,0.0010178884,0.006302228,0.0023507914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026352428,0.00079364557,0.00075435353,0.0011651714,0.010988145,0.0026315476,0.0021579857,0.0012572842,0.004372914],"category_scores_gemma":[0.020679144,0.0005683716,0.00079299125,0.0015474485,0.0039816727,0.0012494309,0.003560602,0.0011632822,0.00030574654],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005122138,0.012360969,0.04417451,0.0061299317,0.0003944668,0.00209184,0.4700639,0.0061879507,0.015185413,0.009253413,0.013184567,0.41585085],"study_design_scores_gemma":[0.0037596556,0.025852423,0.20253746,0.0037133337,0.0007346923,0.00029245968,0.51576596,0.0044148415,0.019579172,0.0044176043,0.21851867,0.00041372934],"about_ca_topic_score_codex":0.69218004,"about_ca_topic_score_gemma":0.90841365,"teacher_disagreement_score":0.30781996,"about_ca_system_score_codex":0.060428597,"about_ca_system_score_gemma":0.09543656,"threshold_uncertainty_score":0.61926556},"labels":[],"label_agreement":null},{"id":"W4406530357","doi":"10.3138/cjpe-2023-0017","title":"Conditions favorables à l’engagement communautaire : évaluation participative de l’adaptation culturelle d’un programme de développement des filles au Sénégal, Afrique","year":2024,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Poverty, Education, and Child Welfare","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.16969731398257917,"score_gpt":0.40967625978078825,"score_spread":0.23997894579820908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406530357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97195274,0.0007233344,0.0039718146,0.0014600653,0.0000999933,0.008063873,0.0004074596,0.000043146178,0.013277651],"genre_scores_gemma":[0.96739846,0.0006646346,0.008722002,0.00036614182,0.000031227803,0.019378725,0.00020455422,0.000025177485,0.0032091255],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9400218,0.048255205,0.002402508,0.0019186346,0.0048297853,0.0025720573],"domain_scores_gemma":[0.94425654,0.033463355,0.0047665024,0.0027481262,0.011600361,0.003165082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05914672,0.00080016744,0.0010616796,0.0017800998,0.0052111945,0.004630459,0.0014250252,0.0012692623,0.004589899],"category_scores_gemma":[0.07231251,0.0005990752,0.0010953116,0.001897004,0.0039692526,0.0020161432,0.0057166764,0.001615402,0.00039565476],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032549063,0.005228594,0.041356694,0.0053508277,0.00045136723,0.00055297394,0.672058,0.0010864219,0.004349882,0.0048621166,0.0027757627,0.2586725],"study_design_scores_gemma":[0.0022145668,0.014859857,0.22103384,0.0059927343,0.001006817,0.00023352716,0.6685417,0.0012446167,0.0124747,0.005595183,0.06647274,0.00032969168],"about_ca_topic_score_codex":0.023382958,"about_ca_topic_score_gemma":0.044997945,"teacher_disagreement_score":0.05914672,"about_ca_system_score_codex":0.010848434,"about_ca_system_score_gemma":0.02855173,"threshold_uncertainty_score":0.31280148},"labels":[],"label_agreement":null},{"id":"W4406530370","doi":"10.3138/cjpe-2023-0026","title":"Foundations for a Utopia: Can Evaluation Contribute to Achieving a Better World, and How?","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique; Government of Canada; Government of Nova Scotia; University of Victoria","funders":"","keywords":"Utopia; Environmental ethics; Sociology; Aesthetics; Philosophy; History; Art history","score_opus":0.3634329391642527,"score_gpt":0.5449652074120074,"score_spread":0.1815322682477547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406530370","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03570582,0.021200782,0.051813424,0.73556894,0.0035997839,0.0014619216,0.00006792151,0.0001565887,0.15042472],"genre_scores_gemma":[0.8854755,0.011164039,0.05183281,0.04201609,0.00083281455,0.0015589629,0.00006471175,0.00018384852,0.0068712644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.634052,0.32869932,0.0054996596,0.0037008016,0.01924721,0.008801058],"domain_scores_gemma":[0.6656628,0.23825292,0.01474239,0.015629625,0.04659794,0.019114347],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3260036,0.0008437125,0.0017864098,0.006003351,0.014618038,0.030058142,0.002807123,0.005854269,0.0052344673],"category_scores_gemma":[0.29076907,0.00078170793,0.0014351535,0.0040627085,0.063989244,0.033211738,0.018000454,0.009864269,0.0008186451],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029610324,0.00035229878,0.008084489,0.0031094365,0.00014201953,0.00044014843,0.101890646,0.00077174895,0.00064085756,0.5798726,0.03513248,0.2692672],"study_design_scores_gemma":[0.00015253898,0.0004062705,0.006394986,0.01424446,0.0001457946,0.0003745367,0.18136269,0.0016934598,0.001626009,0.5591308,0.23422477,0.00024379484],"about_ca_topic_score_codex":0.017247329,"about_ca_topic_score_gemma":0.022877675,"teacher_disagreement_score":0.3260036,"about_ca_system_score_codex":0.03553464,"about_ca_system_score_gemma":0.11164228,"threshold_uncertainty_score":0.83115757},"labels":[],"label_agreement":null},{"id":"W4406530380","doi":"10.3138/cjpe-2023-0050","title":"From Spreadsheets to Scalability: Databases as a Next Step for Non-Profits","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Cambrian College; University of Lethbridge","funders":"","keywords":"Scalability; Database; Computer science","score_opus":0.24928049497698818,"score_gpt":0.41249852362480666,"score_spread":0.16321802864781848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406530380","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28095096,0.02122456,0.0929452,0.33040044,0.00308295,0.0030001886,0.0016660437,0.0038416,0.26288807],"genre_scores_gemma":[0.76091444,0.014704542,0.16617005,0.020596307,0.0008660543,0.0012912266,0.0012974528,0.0012161765,0.03294368],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9558894,0.02285912,0.0016051863,0.0012477322,0.016796965,0.0016016638],"domain_scores_gemma":[0.9180665,0.042943384,0.0038971594,0.007383609,0.019796882,0.007912468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042128284,0.00054583146,0.00044895647,0.0029798567,0.0019591276,0.018841272,0.0023329596,0.0015111449,0.010155335],"category_scores_gemma":[0.07743946,0.00036338597,0.0004240042,0.004653248,0.0033862623,0.015701327,0.0069068074,0.003062607,0.0013176347],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004352161,0.0007222701,0.008200777,0.0010878058,0.00008974171,0.0001392841,0.0052658366,0.0014352637,0.0019976401,0.17112802,0.06592874,0.74356943],"study_design_scores_gemma":[0.00035546123,0.0022903718,0.015904883,0.0045750397,0.00016735982,0.00040721273,0.031292323,0.00748458,0.013001004,0.15339763,0.7709371,0.00018711119],"about_ca_topic_score_codex":0.007126012,"about_ca_topic_score_gemma":0.005732586,"teacher_disagreement_score":0.042128284,"about_ca_system_score_codex":0.007421608,"about_ca_system_score_gemma":0.0153022725,"threshold_uncertainty_score":0.22279829},"labels":[],"label_agreement":null},{"id":"W4406938295","doi":"10.3138/cjpe.39.2.01.en","title":"Editors’ Remarks","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Research Methods and Ethics","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.39665271964067156,"score_gpt":0.6107709316613831,"score_spread":0.21411821202071152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938295","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013474752,0.0013496776,0.00016309801,0.6334527,0.35998976,0.000043196724,0.00014231468,0.0000836037,0.0046408977],"genre_scores_gemma":[0.0019949083,0.0009339753,0.0006387116,0.8055031,0.16023813,0.00021083868,0.00006194533,0.00009305846,0.03032542],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9548166,0.006766196,0.005429682,0.0061856234,0.022306662,0.0044952207],"domain_scores_gemma":[0.820142,0.057738923,0.0133809475,0.009189871,0.07896804,0.020580253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039339475,0.0016131657,0.0030448313,0.003010714,0.0058135125,0.01552524,0.006949973,0.04295618,0.038029414],"category_scores_gemma":[0.2886062,0.0013719192,0.0035089783,0.002795622,0.0066871694,0.0064201066,0.005298441,0.045364227,0.027774375],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001848373,0.000007844865,0.00007103603,0.000068662426,0.000011369222,0.00006046859,0.00007483405,0.000015283402,0.00001982041,0.0013316786,0.9962107,0.002109938],"study_design_scores_gemma":[0.000061069615,0.000017640657,0.00039847745,0.0004462002,0.000034248653,0.00010736209,0.0002820552,0.00007719892,0.00013402905,0.0020790733,0.9963207,0.000041937838],"about_ca_topic_score_codex":0.009783673,"about_ca_topic_score_gemma":0.016694399,"teacher_disagreement_score":0.04295618,"about_ca_system_score_codex":0.009654183,"about_ca_system_score_gemma":0.020840768,"threshold_uncertainty_score":0.20804948},"labels":[],"label_agreement":null},{"id":"W4406938301","doi":"10.3138/cjpe.39.2.rr-fr","title":"Introduction à la section Nos racines et nos liens","year":2024,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychoanalysis and Psychopathology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Section (typography); Computer science","score_opus":0.10059640209803446,"score_gpt":0.46827933993461274,"score_spread":0.3676829378365783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938301","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004326842,0.107802846,0.0216017,0.33475366,0.17828716,0.00072316476,0.0057641976,0.00091937056,0.34582108],"genre_scores_gemma":[0.04409472,0.107309185,0.036180336,0.113707185,0.105367675,0.0018815796,0.0068730377,0.00087589445,0.5837104],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961671,0.0014843078,0.00041422056,0.0004226172,0.0012042022,0.00030755613],"domain_scores_gemma":[0.98671794,0.005562128,0.00066187535,0.00038969042,0.0058065755,0.0008617738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067381025,0.0006970758,0.0007247332,0.001764127,0.002655281,0.0045132297,0.0011831389,0.0034635665,0.063764594],"category_scores_gemma":[0.015260469,0.00044248518,0.0008830303,0.0010117785,0.001898328,0.0023628573,0.0014690295,0.005635652,0.012909896],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115778515,0.00012836931,0.0015070441,0.0012641837,0.000016803579,0.00025615082,0.00087656436,0.00025165535,0.0006894275,0.107752495,0.7658459,0.12129563],"study_design_scores_gemma":[0.0000039640454,0.000013130942,0.000678551,0.00041140243,0.0000033814379,0.00011854025,0.00011510909,0.00003176629,0.00005684684,0.0029118895,0.99564785,0.000007530907],"about_ca_topic_score_codex":0.04616786,"about_ca_topic_score_gemma":0.06891772,"teacher_disagreement_score":0.063764594,"about_ca_system_score_codex":0.006146467,"about_ca_system_score_gemma":0.013922357,"threshold_uncertainty_score":0.21331382},"labels":[],"label_agreement":null},{"id":"W4406938302","doi":"10.3138/cjpe-2023-0005","title":"Developing a Community of Practice (CoP) on Monitoring, Evaluation, and Learning (MEL) in a Global Network of Women’s Funds","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Psychology; Medical education; Medicine","score_opus":0.38552297080082165,"score_gpt":0.5674184361961859,"score_spread":0.18189546539536428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938302","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06691878,0.0064182864,0.4186742,0.24340934,0.0027096379,0.020097949,0.00019722014,0.0007613839,0.2408132],"genre_scores_gemma":[0.4855354,0.0029517405,0.46222988,0.018526211,0.000475657,0.008166457,0.00015770008,0.00034111558,0.021615867],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.83222646,0.1256193,0.004505072,0.009927964,0.019512776,0.0082084],"domain_scores_gemma":[0.82277,0.09087933,0.007755242,0.014215822,0.036194507,0.028185116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20985156,0.0009683555,0.0009608032,0.007183861,0.023570688,0.018793741,0.0060168137,0.0105988635,0.0056823012],"category_scores_gemma":[0.13172023,0.0013729315,0.0011384988,0.0038994316,0.03864786,0.015598496,0.03460039,0.011599363,0.001088626],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006666984,0.0008107817,0.004061303,0.0014442255,0.000060686154,0.0011744035,0.23699981,0.0025234432,0.0016680388,0.331918,0.034031518,0.3852411],"study_design_scores_gemma":[0.00014687185,0.0005327503,0.004611596,0.0068158545,0.00003403807,0.00080772134,0.1331752,0.0032620796,0.0019194866,0.11834056,0.7301085,0.0002453373],"about_ca_topic_score_codex":0.03668919,"about_ca_topic_score_gemma":0.064752586,"teacher_disagreement_score":0.20985156,"about_ca_system_score_codex":0.038570613,"about_ca_system_score_gemma":0.21983981,"threshold_uncertainty_score":0.9743937},"labels":[],"label_agreement":null},{"id":"W4406938306","doi":"10.3138/cjpe.39.2.01.fr","title":"Un mot de la rédactrice","year":2024,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.0851767379731989,"score_gpt":0.3805536059568216,"score_spread":0.29537686798362267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938306","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01587235,0.01441935,0.07976245,0.17871644,0.05985437,0.000894985,0.006960841,0.0113215875,0.63219756],"genre_scores_gemma":[0.09553312,0.0086315395,0.054840647,0.022846336,0.015529778,0.0012034659,0.0059847427,0.0062044337,0.789226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97131807,0.011250799,0.0011985577,0.0024071503,0.012604696,0.0012207706],"domain_scores_gemma":[0.9615207,0.010262906,0.0014988862,0.0036542916,0.021464385,0.0015988231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014926452,0.0020989748,0.001582721,0.0036662787,0.0063358406,0.016318798,0.0020016027,0.0049952334,0.097375706],"category_scores_gemma":[0.04813528,0.0010582871,0.0019290266,0.0030348918,0.0036149034,0.009202715,0.004444916,0.011762524,0.037298385],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005233755,0.00020023684,0.0016398389,0.0008433422,0.00006399228,0.0006234752,0.002837901,0.0009681686,0.0036844932,0.13673215,0.54349554,0.30838746],"study_design_scores_gemma":[0.000056015793,0.000039143943,0.0010280292,0.00023023777,0.0000141721175,0.00036678402,0.00063856685,0.00052231015,0.0013363108,0.004432176,0.9912874,0.00004876698],"about_ca_topic_score_codex":0.09008972,"about_ca_topic_score_gemma":0.055059113,"teacher_disagreement_score":0.097375706,"about_ca_system_score_codex":0.011194371,"about_ca_system_score_gemma":0.011748214,"threshold_uncertainty_score":0.32575417},"labels":[],"label_agreement":null},{"id":"W4406938309","doi":"10.3138/cjpe.39.2.rr-en","title":"Introduction to the Roots and Relations Section","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Plant Molecular Biology Research","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Section (typography); Geology; History; Computer science","score_opus":0.061750821460284946,"score_gpt":0.3265941244688644,"score_spread":0.26484330300857944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938309","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001311922,0.029544307,0.038001806,0.049739253,0.022883754,0.0006167263,0.0065594823,0.002319819,0.8490229],"genre_scores_gemma":[0.012439215,0.03431592,0.024653504,0.010088537,0.0066691334,0.0003399649,0.0040838066,0.001071833,0.90633816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989324,0.0001461009,0.0000745391,0.00013995594,0.00055051997,0.0001564277],"domain_scores_gemma":[0.9961423,0.0009372465,0.00014293824,0.00018875499,0.0020990665,0.00048973976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024192147,0.00087830436,0.0005243289,0.0027932145,0.0021057744,0.0042228843,0.0014009846,0.0015702561,0.17631832],"category_scores_gemma":[0.004075865,0.0005028347,0.00058773,0.0028652588,0.0015558434,0.003178136,0.0015753823,0.0032763674,0.06129027],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017540457,0.00003655327,0.00041566516,0.00020173787,0.0000021329456,0.00004942564,0.00016370889,0.00018690577,0.00044979798,0.057160567,0.7932558,0.14806014],"study_design_scores_gemma":[0.0000014897347,0.00000462876,0.0005573888,0.00010573357,0.0000012055315,0.000027972448,0.000068929694,0.000041614046,0.00007646436,0.0044068303,0.99470276,0.00000491116],"about_ca_topic_score_codex":0.15594782,"about_ca_topic_score_gemma":0.24282227,"teacher_disagreement_score":0.17631832,"about_ca_system_score_codex":0.007328351,"about_ca_system_score_gemma":0.014421457,"threshold_uncertainty_score":0.5898435},"labels":[],"label_agreement":null},{"id":"W4406938312","doi":"10.3138/cjpe-2024-0035","title":"Planting the Seed: Learning From Co-Constructing Program Theory Within an Urban Indigenous Context","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sowing; Indigenous; Context (archaeology); Agroforestry; Mathematics education; Geography; Psychology; Environmental science; Agronomy; Biology; Ecology; Archaeology","score_opus":0.06319006244665473,"score_gpt":0.3768876901932238,"score_spread":0.31369762774656906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4728301,0.001478625,0.26779717,0.032218393,0.00066426786,0.011728984,0.00015361769,0.0004909148,0.21263802],"genre_scores_gemma":[0.7474371,0.001137162,0.23720674,0.001465753,0.000039313607,0.0041802768,0.000101544836,0.00019056225,0.008241468],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9155696,0.074744515,0.00099731,0.0015344218,0.00436674,0.002787306],"domain_scores_gemma":[0.92001104,0.060161076,0.0018677221,0.0069648093,0.007250026,0.0037454125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.083732426,0.0010615719,0.00095034955,0.0029421442,0.010804842,0.011828745,0.0042355414,0.0017777188,0.0041514924],"category_scores_gemma":[0.07947259,0.00072995154,0.0007962411,0.002221102,0.018131336,0.011167522,0.015326914,0.004583033,0.00058923237],"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":[0.000090354224,0.0017021453,0.005611715,0.0009470401,0.000051183077,0.0006538912,0.69234866,0.00144189,0.0012287665,0.07740838,0.0054118754,0.21310407],"study_design_scores_gemma":[0.00011940414,0.0011045806,0.0034119184,0.0026500328,0.00014796392,0.00028539158,0.8086844,0.003870436,0.0038158942,0.07897625,0.0968288,0.00010495896],"about_ca_topic_score_codex":0.026636671,"about_ca_topic_score_gemma":0.08061385,"teacher_disagreement_score":0.083732426,"about_ca_system_score_codex":0.02030533,"about_ca_system_score_gemma":0.05276395,"threshold_uncertainty_score":0.44282466},"labels":[],"label_agreement":null},{"id":"W4406938315","doi":"10.3138/cjpe-2024-0027","title":"Artificial Intelligence in Program Evaluation: Insights and Applications","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Artificial intelligence; Data science","score_opus":0.38402557388508574,"score_gpt":0.5251154718170555,"score_spread":0.1410898979319698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938315","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018812826,0.08762235,0.25027922,0.3382049,0.0019778062,0.0008517828,0.0003363885,0.00047350494,0.3014413],"genre_scores_gemma":[0.63503385,0.07559445,0.24852648,0.020187711,0.0030071384,0.0018691656,0.0002880841,0.00024230902,0.015250835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93679523,0.050597683,0.002422902,0.001223423,0.007673943,0.0012867482],"domain_scores_gemma":[0.8209012,0.15745667,0.0038914247,0.0045691705,0.011426195,0.0017552926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051453862,0.0011778657,0.0011042356,0.008733541,0.0028550567,0.015081812,0.0020894888,0.0047164867,0.0040591774],"category_scores_gemma":[0.08380797,0.00063452445,0.00086867274,0.010347652,0.012011644,0.011548979,0.004550138,0.005001157,0.0006458813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047367837,0.00012183951,0.004148901,0.0010606998,0.00005253592,0.00031451424,0.0023560266,0.0058409087,0.0001299363,0.7698612,0.021463877,0.19460215],"study_design_scores_gemma":[0.00002644377,0.00008700679,0.0028274828,0.003203733,0.00003289612,0.00030366052,0.0038326539,0.01678997,0.0003596841,0.868836,0.10363283,0.00006760663],"about_ca_topic_score_codex":0.0067759193,"about_ca_topic_score_gemma":0.007984122,"teacher_disagreement_score":0.051453862,"about_ca_system_score_codex":0.009899233,"about_ca_system_score_gemma":0.0097528715,"threshold_uncertainty_score":0.27211726},"labels":[],"label_agreement":null},{"id":"W4413187217","doi":"10.3138/cjpe-2023-0049","title":"Intersections between Participatory Evaluation and Social Pedagogy When Assessing Socio-Educational Projects","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Sociology; Pedagogy; Political science","score_opus":0.6169192173815058,"score_gpt":0.6321641301355303,"score_spread":0.015244912754024509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27045658,0.0071747447,0.55892646,0.010623,0.00084729353,0.0200657,0.00030034335,0.00026467422,0.13134126],"genre_scores_gemma":[0.79846096,0.00127532,0.17922759,0.0006494825,0.00008126552,0.018458012,0.00008387083,0.00007230987,0.0016911678],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.3460022,0.5937834,0.016550066,0.006128681,0.033765506,0.0037702925],"domain_scores_gemma":[0.43300733,0.48378262,0.027493995,0.018991461,0.033091165,0.0036333988],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.35197943,0.0016688887,0.0022461796,0.013120537,0.009920041,0.014403562,0.0030025868,0.0024727902,0.0036166129],"category_scores_gemma":[0.3894767,0.0012729646,0.0015064368,0.012216789,0.030599365,0.013411626,0.016596796,0.002830798,0.00032805122],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004925078,0.0005241446,0.052220006,0.007222512,0.00048788023,0.00081319344,0.40680623,0.003909304,0.0017683591,0.25655055,0.0027008727,0.26650438],"study_design_scores_gemma":[0.0003599124,0.0019342883,0.046065968,0.009085024,0.00046836774,0.0011523141,0.46847144,0.011319657,0.0044164374,0.350407,0.10593695,0.0003826395],"about_ca_topic_score_codex":0.0049919616,"about_ca_topic_score_gemma":0.010565543,"teacher_disagreement_score":0.35197943,"about_ca_system_score_codex":0.010697728,"about_ca_system_score_gemma":0.033780634,"threshold_uncertainty_score":0.7991247},"labels":[],"label_agreement":null},{"id":"W4413187222","doi":"10.3138/cjpe-2024-0041","title":"Implantation dans une région québécoise de pratiques centrées sur le rétablissement en milieux résidentiels en santé mentale soutenue par l’évaluation émancipatrice","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Bishop's University; Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"","keywords":"Humanities; Art","score_opus":0.11955512879476453,"score_gpt":0.4320808889566393,"score_spread":0.3125257601618748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8103764,0.007646801,0.0081429165,0.0635359,0.0007306593,0.0007651878,0.0006294639,0.00012744486,0.10804528],"genre_scores_gemma":[0.95436937,0.0025246579,0.0058594407,0.0046659233,0.00005298952,0.00058571633,0.00017568676,0.000059239992,0.031706948],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9924428,0.0044523454,0.00018215433,0.0005508511,0.0011491689,0.0012226528],"domain_scores_gemma":[0.98534817,0.003074893,0.00073257706,0.00077300885,0.0060786232,0.0039926753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011622461,0.00033187258,0.00070712226,0.000758197,0.00899466,0.0045568706,0.0011580995,0.0010186888,0.010161261],"category_scores_gemma":[0.013596672,0.00030805598,0.0005033958,0.0013078887,0.004782554,0.002507063,0.0046235607,0.002950299,0.00083087286],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066508044,0.0005949443,0.114296794,0.0015978281,0.00023642117,0.0012396962,0.45583662,0.00081073045,0.0048831613,0.050576694,0.042232648,0.32702938],"study_design_scores_gemma":[0.00016185598,0.0009080237,0.3022029,0.0041568032,0.0003008978,0.00036960022,0.3260221,0.0010740809,0.002370542,0.0072328127,0.35500363,0.00019677095],"about_ca_topic_score_codex":0.8049899,"about_ca_topic_score_gemma":0.92395645,"teacher_disagreement_score":0.19501013,"about_ca_system_score_codex":0.044250004,"about_ca_system_score_gemma":0.14479235,"threshold_uncertainty_score":0.39231712},"labels":[],"label_agreement":null},{"id":"W4413187223","doi":"10.3138/cjpe.39.3.rr-fr","title":"Introduction à la section Nos racines et nos liens","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychoanalysis and Psychopathology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Section (typography); Philosophy; Computer science","score_opus":0.08024736689894285,"score_gpt":0.4662046988581395,"score_spread":0.3859573319591966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187223","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004382743,0.10895378,0.021734038,0.33261806,0.17704831,0.0007307957,0.0057554217,0.00091976335,0.3478571],"genre_scores_gemma":[0.04458215,0.10876502,0.03649927,0.112291254,0.10480443,0.0018835971,0.0068021812,0.00086827733,0.5835038],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962125,0.0014625918,0.00041054998,0.0004167282,0.0011942253,0.00030345187],"domain_scores_gemma":[0.98685974,0.0054774317,0.00065535674,0.00038493454,0.0057678157,0.0008546864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066762385,0.000691025,0.0007204734,0.00175832,0.0026246721,0.0044789347,0.001172474,0.0034209203,0.06336565],"category_scores_gemma":[0.015089229,0.00043793998,0.0008750416,0.0010071674,0.0018820988,0.0023314618,0.0014520164,0.005559352,0.012658535],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011648096,0.00012955746,0.0015265287,0.0012717107,0.000016943313,0.00025773555,0.0008795816,0.0002549016,0.0006979593,0.108512715,0.7625253,0.1238107],"study_design_scores_gemma":[0.000003984809,0.000013259903,0.00069172547,0.00041228958,0.000003385607,0.00012009288,0.00011496988,0.000032128,0.00005721789,0.0029163822,0.99562705,0.0000075572975],"about_ca_topic_score_codex":0.046602868,"about_ca_topic_score_gemma":0.069945686,"teacher_disagreement_score":0.06336565,"about_ca_system_score_codex":0.0061540557,"about_ca_system_score_gemma":0.013862579,"threshold_uncertainty_score":0.21197921},"labels":[],"label_agreement":null},{"id":"W4413187227","doi":"10.3138/cjpe.39.3.rr-en","title":"Introduction to the Roots and Relations Section","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Plant Molecular Biology Research","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Section (typography); Geology; History; Computer science; Operating system","score_opus":0.04839155616159236,"score_gpt":0.32469390913832463,"score_spread":0.2763023529767323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187227","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013060552,0.029877907,0.037456796,0.05045795,0.022883695,0.00061326235,0.006376503,0.0022746867,0.8487532],"genre_scores_gemma":[0.012665179,0.03489674,0.024683522,0.010189105,0.0066858497,0.00033919545,0.0039531006,0.0010504224,0.90553683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890935,0.00014856305,0.00007613315,0.00014114605,0.0005659214,0.00015899865],"domain_scores_gemma":[0.99607855,0.0009449212,0.00014495537,0.00019034227,0.0021438946,0.0004972793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024413723,0.0008693803,0.0005220484,0.0028150291,0.0021179838,0.00425587,0.0013983279,0.0015710038,0.17330776],"category_scores_gemma":[0.0041274736,0.00049914356,0.0005821341,0.002892267,0.001577782,0.0031490359,0.0015710905,0.0032617364,0.059326462],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017196642,0.00003616286,0.0004132018,0.00020105304,0.0000021312833,0.000049410908,0.00016567028,0.00018633436,0.00044246626,0.05776949,0.7917913,0.14892554],"study_design_scores_gemma":[0.0000014830329,0.000004593155,0.00056071253,0.00010676192,0.0000012069224,0.000027987368,0.000069996815,0.000041806023,0.000075909265,0.0044424646,0.9946621,0.000004960198],"about_ca_topic_score_codex":0.16177006,"about_ca_topic_score_gemma":0.25196272,"teacher_disagreement_score":0.17330776,"about_ca_system_score_codex":0.0074979668,"about_ca_system_score_gemma":0.014764487,"threshold_uncertainty_score":0.57977223},"labels":[],"label_agreement":null},{"id":"W4413187250","doi":"10.3138/cjpe-2024-0045","title":"L’utilisation des évaluations par l’analyse thématique : le cas d’Anciens Combattants Canada (ACC)","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Political science","score_opus":0.2822294590102694,"score_gpt":0.49894638162417587,"score_spread":0.21671692261390646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57321286,0.0148204,0.02274739,0.022854744,0.00063726393,0.0012349879,0.0029367055,0.00026285183,0.36129275],"genre_scores_gemma":[0.96772486,0.0025604044,0.011510463,0.0008471511,0.000038616014,0.00035491717,0.0004646793,0.000067252666,0.016431594],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9665069,0.013901242,0.0011693723,0.0014631449,0.014762247,0.0021971373],"domain_scores_gemma":[0.944142,0.017996782,0.0032589794,0.0015650556,0.031161852,0.0018753451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022029664,0.00069695327,0.00074914336,0.004421009,0.0060319635,0.010664101,0.0012250971,0.00090182124,0.0050529097],"category_scores_gemma":[0.048101075,0.0003568228,0.00070600444,0.0070273275,0.004210815,0.0023415857,0.0030023386,0.0017707169,0.00053453003],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006820366,0.00028291615,0.15570499,0.0028542727,0.0005097811,0.0006336966,0.13093618,0.0040470525,0.0019251815,0.072138146,0.03550653,0.59477925],"study_design_scores_gemma":[0.000091424656,0.0006187049,0.40641907,0.0071303113,0.00077794486,0.0005719062,0.19265753,0.010154847,0.004873327,0.016755154,0.35946396,0.0004859439],"about_ca_topic_score_codex":0.84112656,"about_ca_topic_score_gemma":0.8991262,"teacher_disagreement_score":0.94377863,"about_ca_system_score_codex":0.05622135,"about_ca_system_score_gemma":0.08123536,"threshold_uncertainty_score":0.40791637},"labels":[],"label_agreement":null},{"id":"W4413187252","doi":"10.3138/cjpe.39.3.ed-fr","title":"Un mot de la rédactrice","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.06542518342593938,"score_gpt":0.3783976160849991,"score_spread":0.3129724326590597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187252","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015814805,0.014480012,0.07885102,0.1793849,0.059695955,0.00090362586,0.0069639226,0.0111918235,0.6327139],"genre_scores_gemma":[0.09596264,0.008705667,0.054863617,0.022953076,0.015481423,0.0012119173,0.005985287,0.0061468743,0.78868943],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9712026,0.011277675,0.0012093919,0.0023977037,0.012689709,0.0012230037],"domain_scores_gemma":[0.96107274,0.0103059225,0.0015095149,0.0036894209,0.021811564,0.0016107904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0150338495,0.0020751958,0.0015681776,0.0036890516,0.0063001923,0.016252931,0.001998966,0.004955495,0.09647052],"category_scores_gemma":[0.048446607,0.0010450751,0.0019051579,0.0030447764,0.003603461,0.009134096,0.004432997,0.011601566,0.03689801],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005162252,0.00019815646,0.0016447924,0.00083673844,0.0000629706,0.0006144731,0.0028333447,0.0009523973,0.003644181,0.13518493,0.5451056,0.30840632],"study_design_scores_gemma":[0.000055020333,0.000038786657,0.0010324969,0.00023064723,0.0000139884005,0.00036269467,0.0006386705,0.0005130389,0.0013187042,0.0043977057,0.99134994,0.000048193957],"about_ca_topic_score_codex":0.091196194,"about_ca_topic_score_gemma":0.055972528,"teacher_disagreement_score":0.09647052,"about_ca_system_score_codex":0.011263832,"about_ca_system_score_gemma":0.011903559,"threshold_uncertainty_score":0.322726},"labels":[],"label_agreement":null},{"id":"W4413187255","doi":"10.3138/cjpe-2025-0007","title":"Kwayâtisiwin (“We Prepare”): Understanding the Methods of Preparation for Evaluating Nêhiyawak-based Research","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.5463508103977922,"score_gpt":0.6224705137179819,"score_spread":0.07611970332018969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1512395,0.009730862,0.4393096,0.113170035,0.0030693868,0.024604239,0.0005559145,0.0012381992,0.2570823],"genre_scores_gemma":[0.48813614,0.0031820452,0.46214688,0.0065408,0.00010687097,0.014335396,0.00014502593,0.0005092804,0.024897521],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9014818,0.07888268,0.004242291,0.0023878175,0.010274263,0.0027311307],"domain_scores_gemma":[0.87888193,0.08002009,0.0068216273,0.009269723,0.020990139,0.00401652],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12225027,0.00086912763,0.0008333232,0.004296423,0.012573275,0.017225003,0.0028624947,0.0029539217,0.004651181],"category_scores_gemma":[0.15488139,0.0009898272,0.0007204754,0.0037346894,0.03133595,0.010355669,0.010977936,0.005082732,0.00083770556],"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":[0.00019840758,0.00020804052,0.0077360636,0.0023823413,0.00006263561,0.0006078873,0.5435819,0.00060670666,0.0027960814,0.19530958,0.014910998,0.2315993],"study_design_scores_gemma":[0.00013995598,0.00037482788,0.013511431,0.007077655,0.00016707867,0.000493563,0.46523714,0.0015577442,0.0062350426,0.12118344,0.38374004,0.00028208637],"about_ca_topic_score_codex":0.058983967,"about_ca_topic_score_gemma":0.16210428,"teacher_disagreement_score":0.87774974,"about_ca_system_score_codex":0.02545709,"about_ca_system_score_gemma":0.07337511,"threshold_uncertainty_score":0.64652896},"labels":[],"label_agreement":null},{"id":"W4413187257","doi":"10.3138/cjpe-2025-0009","title":"Walking With Our Relatives: Co-Designing an Anishinaabe-Led Evaluation Approach","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program 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":true,"route_about_ca":false,"ca_institutions":"Research Manitoba","funders":"","keywords":"Genealogy; History; Geography","score_opus":0.686476612639038,"score_gpt":0.6948117451606552,"score_spread":0.008335132521617217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55422145,0.004292394,0.1810278,0.08447914,0.0028828857,0.027559487,0.00027577614,0.0009664174,0.14429471],"genre_scores_gemma":[0.80680025,0.0015514394,0.14890262,0.009229047,0.00013709742,0.013103855,0.00012798776,0.0003650806,0.019782647],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8112645,0.17547074,0.00205931,0.0027428144,0.0038682022,0.0045943223],"domain_scores_gemma":[0.93754154,0.033137348,0.0018300331,0.0033819345,0.011991337,0.012117782],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08926096,0.0007961288,0.0009357383,0.0021361327,0.019800147,0.010004466,0.003662313,0.0025604262,0.009144681],"category_scores_gemma":[0.08391577,0.0010332026,0.0009491032,0.0012577628,0.010016879,0.008486904,0.014065366,0.006196175,0.001738525],"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":[0.00034731315,0.002587125,0.0050841025,0.0013600608,0.000069544614,0.002626899,0.7748851,0.0010487118,0.0020085191,0.023099754,0.01909859,0.16778435],"study_design_scores_gemma":[0.00014041342,0.00068768015,0.0012505548,0.0013913868,0.00006410822,0.0004838947,0.8351974,0.00096749904,0.0013083409,0.013825551,0.14458795,0.000095205476],"about_ca_topic_score_codex":0.008951934,"about_ca_topic_score_gemma":0.030914906,"teacher_disagreement_score":0.91073906,"about_ca_system_score_codex":0.014932489,"about_ca_system_score_gemma":0.037894756,"threshold_uncertainty_score":0.4720627},"labels":[],"label_agreement":null},{"id":"W4413187259","doi":"10.3138/cjpe.39.3.ed-en","title":"Editor’s Remarks","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Philosophy","score_opus":0.04911871370871162,"score_gpt":0.4412405066259155,"score_spread":0.3921217929172039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187259","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012049363,0.0018812898,0.00012235004,0.4059659,0.5870936,0.000032455853,0.00010870857,0.00007144672,0.0046038204],"genre_scores_gemma":[0.0017802985,0.0014215925,0.00044195968,0.6905605,0.25903,0.00008689864,0.0000525515,0.000073365845,0.046552815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9810357,0.0018916421,0.0020034215,0.0027939812,0.009946009,0.002329146],"domain_scores_gemma":[0.9314802,0.016121063,0.004889782,0.003251394,0.034481082,0.00977652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016520126,0.0017269029,0.0027953614,0.0027434547,0.0055254223,0.010914212,0.0051850034,0.041697543,0.031891182],"category_scores_gemma":[0.13163888,0.0012632428,0.0035059084,0.0021531077,0.0038185006,0.003722706,0.00289171,0.039171148,0.0241082],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000150014,0.0000063606485,0.00004894069,0.000033696993,0.000008762966,0.00009067785,0.00001976815,0.000012855739,0.000025131005,0.00042939073,0.9974356,0.0018738076],"study_design_scores_gemma":[0.000045630906,0.000013694429,0.00043694582,0.00021342572,0.000027559308,0.00015696572,0.00010305132,0.000067399465,0.0001096916,0.0008541223,0.9979377,0.000033899047],"about_ca_topic_score_codex":0.016485322,"about_ca_topic_score_gemma":0.038454704,"teacher_disagreement_score":0.041697543,"about_ca_system_score_codex":0.008436065,"about_ca_system_score_gemma":0.01562878,"threshold_uncertainty_score":0.10668671},"labels":[],"label_agreement":null},{"id":"W4413187262","doi":"10.3138/cjpe-2025-0008","title":"Responsibility to All Relations: Indigenous 
Evaluation of an AI/AN Public Health Workforce Development Program","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Career Development and Diversity","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Workforce; Workforce development; Public health; Political science; Public relations; Economic growth; Sociology; Engineering ethics; Engineering; Nursing; Medicine; Economics; Law","score_opus":0.2819711151035477,"score_gpt":0.47544962715717404,"score_spread":0.19347851205362632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73531675,0.0027507977,0.008353664,0.023078429,0.0013495676,0.027681105,0.00060432736,0.00023801638,0.20062743],"genre_scores_gemma":[0.94777083,0.0020192168,0.017494258,0.0047458475,0.00019973618,0.014664416,0.0002808106,0.00007160052,0.01275318],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9063013,0.07008814,0.0024400908,0.0015548415,0.013682671,0.005932982],"domain_scores_gemma":[0.95532495,0.015536233,0.002629409,0.0026775184,0.016400287,0.0074315816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06792218,0.0005028136,0.0005566279,0.0015813351,0.008322576,0.0035915663,0.0025764205,0.0011258792,0.0053136293],"category_scores_gemma":[0.063427866,0.00035754216,0.0010832435,0.0013197685,0.0038745685,0.0026006536,0.008208823,0.0032153486,0.00040040776],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004145217,0.032697234,0.028814351,0.008019912,0.0007664371,0.00056882243,0.16015497,0.0031404,0.0030104253,0.03309617,0.016722681,0.7088633],"study_design_scores_gemma":[0.00962333,0.07278067,0.18139681,0.012305208,0.0025868528,0.00048774682,0.38291582,0.004790155,0.014721075,0.01768552,0.30016452,0.00054234214],"about_ca_topic_score_codex":0.10190571,"about_ca_topic_score_gemma":0.17792368,"teacher_disagreement_score":0.10190571,"about_ca_system_score_codex":0.02155277,"about_ca_system_score_gemma":0.105019055,"threshold_uncertainty_score":0.35921115},"labels":[],"label_agreement":null},{"id":"W4413187265","doi":"10.3138/cjpe-2024-0020","title":"Recognizing the Need for a Trauma-Informed Approach in the Evaluation of an Indigenous Program in British Columbia","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Indigenous; Psychology; Biology; Ecology","score_opus":0.10552904188995195,"score_gpt":0.4214811029662174,"score_spread":0.31595206107626544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.796042,0.0038129943,0.010271225,0.07928078,0.00069919904,0.011054324,0.00024970708,0.00017704064,0.098412775],"genre_scores_gemma":[0.9581153,0.002038632,0.017136497,0.009424337,0.00005464196,0.0059848772,0.000080823076,0.000087811466,0.007077129],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9492348,0.036629617,0.0014435577,0.0008459395,0.0062757754,0.0055703274],"domain_scores_gemma":[0.94514257,0.025056921,0.00197022,0.0021443013,0.016128113,0.009557847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04698001,0.0004975515,0.0006145706,0.0019159646,0.024059983,0.0109581975,0.0033479899,0.0018399172,0.0054890844],"category_scores_gemma":[0.06071722,0.000546633,0.00036538704,0.0025230523,0.009716383,0.0035301868,0.010570214,0.0075789196,0.00030823756],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047998445,0.00243909,0.025420472,0.0035163532,0.00018983615,0.0029053977,0.73655343,0.0018202342,0.003914186,0.017915022,0.01744949,0.18739653],"study_design_scores_gemma":[0.00010738652,0.00086661696,0.038509544,0.0040150555,0.000128927,0.00031382774,0.8883066,0.00088368,0.0014018746,0.006181094,0.059119944,0.00016551714],"about_ca_topic_score_codex":0.7527262,"about_ca_topic_score_gemma":0.941893,"teacher_disagreement_score":0.2472738,"about_ca_system_score_codex":0.07195761,"about_ca_system_score_gemma":0.2634068,"threshold_uncertainty_score":0.52209145},"labels":[],"label_agreement":null},{"id":"W4413187340","doi":"10.3138/cjpe-2024-0033","title":"How Do Municipal Policy- and Decision-Makers Evaluate the Impact of Their Policies? Insights from the City of Regina in Saskatchewan, Canada","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Public Health Ontario; Saskatchewan Health; University of Toronto; Saskatchewan Science Centre; Saskatchewan Health Authority; University of Regina","funders":"","keywords":"Political science; Public administration; Environmental planning; Geography","score_opus":0.14757668733566243,"score_gpt":0.46834605433322624,"score_spread":0.3207693669975638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9338609,0.0024166733,0.00069520884,0.015811447,0.00005184519,0.0003493555,0.00060333667,0.000040304978,0.046171036],"genre_scores_gemma":[0.9909469,0.0015104514,0.00091586163,0.0010642064,0.0000036887122,0.00008347163,0.00017009789,0.000020777275,0.0052845376],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98995614,0.004825072,0.00027543528,0.0005525977,0.0014974814,0.0028933513],"domain_scores_gemma":[0.98774105,0.0042869938,0.00068284426,0.00046351162,0.0043025543,0.0025231785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007912976,0.00047607502,0.00061126484,0.0016947638,0.020283109,0.009048322,0.0027858193,0.00090103754,0.0028301345],"category_scores_gemma":[0.012540621,0.00046696176,0.00041080976,0.0050141914,0.008229184,0.0018515448,0.0051000435,0.0020960255,0.0002986299],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044393077,0.0005471034,0.2857155,0.00094664184,0.00029298844,0.004342849,0.49555767,0.005667396,0.002465993,0.03844932,0.03637726,0.12919329],"study_design_scores_gemma":[0.000030338566,0.000069228256,0.14242409,0.0007710536,0.000090813206,0.00011891437,0.80318296,0.0013529664,0.0005390358,0.002493452,0.04879295,0.00013427096],"about_ca_topic_score_codex":0.99644023,"about_ca_topic_score_gemma":0.998838,"teacher_disagreement_score":0.21656834,"about_ca_system_score_codex":0.21656834,"about_ca_system_score_gemma":0.29814252,"threshold_uncertainty_score":0.9086697},"labels":[],"label_agreement":null},{"id":"W4413187342","doi":"10.3138/cjpe-2024-0016","title":"Development of a Volunteer Transportation Program to Support Age-Friendly Rural Communities","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Migration, Aging, and Tourism Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Volunteer; Transport engineering; Business; Environmental planning; Economic growth; Engineering; Geography; Economics; Ecology; Biology","score_opus":0.07512296391410477,"score_gpt":0.39573546599595383,"score_spread":0.32061250208184905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187342","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7619022,0.00059775606,0.022033673,0.010805977,0.0004399556,0.11634079,0.0016158574,0.00048648604,0.08577733],"genre_scores_gemma":[0.8326383,0.0011275444,0.11047361,0.0017115929,0.00004914557,0.042759914,0.00087793946,0.000052585292,0.010309397],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9858085,0.008193401,0.0003469274,0.00035033395,0.0029709854,0.0023298704],"domain_scores_gemma":[0.98503554,0.0017168093,0.0006511869,0.0005045377,0.0057978583,0.0062940195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017908335,0.0004157654,0.00034410867,0.0014871391,0.005368806,0.002987319,0.002036296,0.00077040587,0.0032698042],"category_scores_gemma":[0.015113912,0.00028852004,0.0004220309,0.0010986438,0.0012398799,0.0011168895,0.003989755,0.00134113,0.0002753497],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016655585,0.022278585,0.048796088,0.003542748,0.00015573276,0.001159227,0.042778146,0.009790208,0.0059048,0.019076211,0.034403574,0.8104492],"study_design_scores_gemma":[0.004363688,0.046889197,0.24560477,0.005549246,0.0005257632,0.0007179478,0.24238873,0.018740349,0.015757915,0.009984264,0.409144,0.00033400077],"about_ca_topic_score_codex":0.18339196,"about_ca_topic_score_gemma":0.41476578,"teacher_disagreement_score":0.8166081,"about_ca_system_score_codex":0.016256927,"about_ca_system_score_gemma":0.14735271,"threshold_uncertainty_score":0.364649},"labels":[],"label_agreement":null},{"id":"W4413187352","doi":"10.3138/cjpe-2024-0036","title":"Relational Systems and the Principles of Self-Determination, Reciprocity, and Mutual Benefit: Enacting Indigenous Ways of Knowing in the Evaluation of an Indigenous Health Research Network in the Province of British Columbia, Canada","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Royal Roads University; Simon Fraser University","funders":"","keywords":"Indigenous; Reciprocity (cultural anthropology); Sociology; Public relations; Psychology; Political science; Social science; Ecology","score_opus":0.1425181304911122,"score_gpt":0.39970848931565606,"score_spread":0.2571903588245439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46625265,0.122511834,0.059234392,0.1771314,0.001015765,0.003968313,0.00025501248,0.00017964198,0.16945101],"genre_scores_gemma":[0.9556118,0.015531943,0.023962054,0.0022323611,0.00005060764,0.00087004405,0.000035348967,0.00004914397,0.0016567477],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.73845047,0.23360734,0.005327148,0.002207392,0.017021457,0.0033862866],"domain_scores_gemma":[0.7046531,0.24767284,0.009231271,0.006521986,0.027352776,0.0045679826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24224727,0.00051376695,0.0010741067,0.005602442,0.013721654,0.01738296,0.0027828366,0.0014392622,0.0013941933],"category_scores_gemma":[0.21276905,0.0007247004,0.00076386606,0.005230593,0.030304257,0.010617236,0.010816628,0.0041479967,0.000091046466],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110701985,0.00012518102,0.011181066,0.006443343,0.0005628134,0.000245929,0.67290837,0.0008946238,0.00028101233,0.08109743,0.0041425293,0.22200702],"study_design_scores_gemma":[0.00009782674,0.00024498577,0.022798236,0.028303219,0.0013719664,0.0002040569,0.79698724,0.0016237408,0.0012414439,0.06734124,0.07954085,0.00024515146],"about_ca_topic_score_codex":0.57615405,"about_ca_topic_score_gemma":0.7826603,"teacher_disagreement_score":0.42384595,"about_ca_system_score_codex":0.07872548,"about_ca_system_score_gemma":0.18783808,"threshold_uncertainty_score":0.934444},"labels":[],"label_agreement":null},{"id":"W4413187357","doi":"10.3138/cjpe-2024-0017","title":"Constats sur l’implantation de pratiques évaluatives en lien avec une nouvelle offre de services individuelle et de groupe basée sur la présence attentive sensible au trauma","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Psychoanalysis and Psychopathology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; Université du Québec à Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.08983140988866319,"score_gpt":0.4273849840174259,"score_spread":0.33755357412876275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9289572,0.003222635,0.014118302,0.022663236,0.0009049338,0.0013527207,0.00030293452,0.00018593187,0.028292056],"genre_scores_gemma":[0.97920907,0.0011565975,0.011470613,0.0021936942,0.000090919064,0.0014207195,0.00010174502,0.000051063806,0.0043055783],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9534546,0.028235478,0.0035456207,0.002003742,0.010178511,0.0025819677],"domain_scores_gemma":[0.69909483,0.21439585,0.025527757,0.010981681,0.040177576,0.009822347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.055898294,0.00041956492,0.0005381785,0.0013565038,0.0030635102,0.0034952876,0.0014655084,0.001277509,0.004955906],"category_scores_gemma":[0.21382195,0.00060929393,0.00084879785,0.0011759071,0.004000491,0.0040558036,0.004098847,0.004244393,0.0006394598],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00227466,0.0015388792,0.24915437,0.0026171366,0.00043306907,0.00041699555,0.30186212,0.0004936634,0.004546006,0.010059573,0.0060504954,0.42055303],"study_design_scores_gemma":[0.0003550816,0.004900834,0.70003194,0.0046732943,0.0004480069,0.0005540341,0.22062021,0.0015864784,0.005755307,0.009096845,0.051778417,0.00019952969],"about_ca_topic_score_codex":0.013862072,"about_ca_topic_score_gemma":0.022918215,"teacher_disagreement_score":0.9861379,"about_ca_system_score_codex":0.006164646,"about_ca_system_score_gemma":0.022615789,"threshold_uncertainty_score":0.295622},"labels":[],"label_agreement":null},{"id":"W4413819327","doi":"10.3138/cjpe-2024-0040","title":"Reconstructing Baseline: A Case Study from Nepal","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Baseline (sea); Geography; History; Political science; Law","score_opus":0.10085433679400654,"score_gpt":0.3260660034665272,"score_spread":0.22521166667252066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413819327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9444362,0.0007357952,0.008677963,0.00941653,0.00012743789,0.00052602415,0.001178105,0.000105627965,0.034796204],"genre_scores_gemma":[0.9647545,0.0013349584,0.01706755,0.0022313765,0.000043344775,0.00038021972,0.00079152634,0.00010373258,0.013292708],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9975414,0.0013607863,0.000111481444,0.00020021012,0.0003115823,0.00047460676],"domain_scores_gemma":[0.9950293,0.002629101,0.00035632442,0.00047599155,0.00090038986,0.00060892064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033615287,0.00047651428,0.00039134838,0.0010441571,0.0063366336,0.0026125184,0.002023215,0.002815657,0.004683754],"category_scores_gemma":[0.01216437,0.00028378566,0.0004238195,0.0017212674,0.0022600568,0.0024965948,0.003540424,0.00295992,0.0005825898],"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":[0.00027301983,0.0022644235,0.1692564,0.0011311088,0.00010798608,0.11526008,0.42944402,0.0050059063,0.0019222881,0.03688694,0.03228208,0.20616579],"study_design_scores_gemma":[0.000031134685,0.0006733727,0.06953698,0.0015621901,0.00006582236,0.023761446,0.7153344,0.0044478173,0.0021411642,0.013431036,0.16887459,0.00014001959],"about_ca_topic_score_codex":0.060267825,"about_ca_topic_score_gemma":0.13542414,"teacher_disagreement_score":0.060267825,"about_ca_system_score_codex":0.0033328244,"about_ca_system_score_gemma":0.0050902585,"threshold_uncertainty_score":0.119834065},"labels":[],"label_agreement":null},{"id":"W4413972820","doi":"10.3138/cjpe-2024-0044","title":"Taking Stock of Contribution Analysis: Reflecting on the Past to Inform the Future","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stock (firearms); Geography; Data science; Computer science; Archaeology","score_opus":0.3492271650557068,"score_gpt":0.5756301893170004,"score_spread":0.2264030242612936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413972820","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011659554,0.16782555,0.0667215,0.6850156,0.0094373245,0.00023605821,0.00021991141,0.00027086778,0.058613654],"genre_scores_gemma":[0.39149353,0.26939666,0.21107952,0.10107428,0.009934347,0.000994439,0.00045429327,0.0009930193,0.014579948],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8770228,0.091062374,0.0045630396,0.0043952325,0.019697282,0.003259263],"domain_scores_gemma":[0.6387846,0.24999152,0.0120822415,0.016775275,0.07189567,0.010470697],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2206747,0.0015127301,0.002026008,0.011588768,0.009222863,0.031404614,0.005110443,0.0063444325,0.0064558634],"category_scores_gemma":[0.27000168,0.0007254363,0.0015416669,0.012226771,0.025791885,0.061132416,0.010637129,0.0120174065,0.0018939099],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012935157,0.00011649555,0.007156039,0.0043166257,0.00018400107,0.00021464074,0.031443227,0.00082809996,0.0004275241,0.4027951,0.066085055,0.48630384],"study_design_scores_gemma":[0.000027356371,0.000092142596,0.0033856179,0.014780559,0.00013826387,0.00029141392,0.04171317,0.0016300309,0.0008908977,0.45701042,0.47988135,0.00015881417],"about_ca_topic_score_codex":0.022371314,"about_ca_topic_score_gemma":0.04176387,"teacher_disagreement_score":0.97939366,"about_ca_system_score_codex":0.020606311,"about_ca_system_score_gemma":0.038917724,"threshold_uncertainty_score":0.9610469},"labels":[],"label_agreement":null},{"id":"W47101223","doi":"10.3138/cjpe.0015.003","title":"Predictors of Educator’s Valuing of Systematic Inquiry in Schools","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Ottawa","funders":"","keywords":"Psychology; Variance (accounting); Relevance (law); Exploratory research; Medical education; Value (mathematics); Medicine; Sociology; Social science","score_opus":0.3838212522965732,"score_gpt":0.506814129178217,"score_spread":0.12299287688164379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W47101223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998548,0.00008412321,0.00018273837,0.00021367337,0.000005013862,0.000013404362,0.000025811181,0.0000042745373,0.0009230237],"genre_scores_gemma":[0.99952185,0.00006759311,0.00017769831,0.00003416757,0.0000035135079,0.000008552326,0.00002533562,0.0000016346871,0.00015968822],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9929919,0.0034480921,0.0008494226,0.00030376794,0.0018741991,0.0005325785],"domain_scores_gemma":[0.8952266,0.05177227,0.028607085,0.003098314,0.012441037,0.008854679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0109656835,0.00013979408,0.00026526974,0.0015555567,0.0006980893,0.0022404268,0.00042192123,0.0007267608,0.0026721773],"category_scores_gemma":[0.058970425,0.00029861112,0.00029972405,0.0009045549,0.0011863135,0.00097224937,0.0012440438,0.0013166644,0.0003379522],"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":[0.00008498404,0.00015525284,0.9811998,0.000085244275,0.00002625855,0.0001184935,0.009723896,0.00007293861,0.0004947356,0.00012478794,0.00018607968,0.0077274283],"study_design_scores_gemma":[0.0000156177,0.00032116438,0.96303856,0.00015910788,0.000026000287,0.00033831195,0.032593027,0.00063373445,0.00061773387,0.00031570008,0.0019136686,0.000027363141],"about_ca_topic_score_codex":0.0020231428,"about_ca_topic_score_gemma":0.0031989126,"teacher_disagreement_score":0.0109656835,"about_ca_system_score_codex":0.0009148808,"about_ca_system_score_gemma":0.0015879748,"threshold_uncertainty_score":0.057992816},"labels":[],"label_agreement":null},{"id":"W56576167","doi":"10.3138/cjpe.017.003","title":"Evaluation and Municipal Urban Planning: Practice and Prospects","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Government (linguistics); Urban planning; Local government; Scale (ratio); Environmental planning; Evaluation methods; Comprehensive planning; Public administration; Process management; Management science; Business; Environmental resource management; Political science; Geography; Engineering; Economics; Civil engineering","score_opus":0.4565580453517729,"score_gpt":0.5429851099364679,"score_spread":0.08642706458469496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W56576167","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046849687,0.36260676,0.017632298,0.38426894,0.0010680235,0.00033510503,0.00011838053,0.00024077647,0.18688007],"genre_scores_gemma":[0.824522,0.14418377,0.012949543,0.006331715,0.0007028301,0.0001911725,0.0000812023,0.000046971596,0.010990669],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9826413,0.012053691,0.0004928758,0.00049906556,0.0029126345,0.0014004231],"domain_scores_gemma":[0.9553182,0.023894481,0.0023672606,0.001811914,0.012093755,0.0045142947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03140705,0.00033184918,0.00050764624,0.0025840166,0.0032188473,0.0069238287,0.0012840562,0.0020021047,0.006133611],"category_scores_gemma":[0.031922482,0.00027407813,0.00024711623,0.0051583485,0.012178617,0.0035464126,0.004192289,0.0016582411,0.0003296514],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014488035,0.00016686221,0.016113976,0.0024623836,0.000039219616,0.0004149827,0.010193189,0.0027876038,0.00016872662,0.12921314,0.053339392,0.7849556],"study_design_scores_gemma":[0.00012355797,0.00021121383,0.058289163,0.012302851,0.000062808176,0.0007576347,0.03437266,0.0038526242,0.0007026174,0.13770382,0.75149554,0.00012551821],"about_ca_topic_score_codex":0.24120292,"about_ca_topic_score_gemma":0.21258889,"teacher_disagreement_score":0.24120292,"about_ca_system_score_codex":0.02987247,"about_ca_system_score_gemma":0.045430355,"threshold_uncertainty_score":0.47959793},"labels":[],"label_agreement":null},{"id":"W573730680","doi":"10.3138/cjpe.0014.001","title":"Editor’s Introduction to the Issue","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Qualitative Research Methods and Ethics","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"History; Environmental ethics; Philosophy","score_opus":0.2589604495269632,"score_gpt":0.5718811616512326,"score_spread":0.3129207121242694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W573730680","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004438787,0.0011524081,0.000108253655,0.06733877,0.9303074,0.000020568546,0.000038662176,0.000023969998,0.00096544524],"genre_scores_gemma":[0.00072187296,0.0023325812,0.0003011963,0.08589375,0.8962385,0.000057225938,0.00005460047,0.000046451023,0.014353789],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924419,0.0012793182,0.0010676807,0.00083515764,0.0036888807,0.0006870976],"domain_scores_gemma":[0.94089407,0.016847901,0.0027432072,0.0016927718,0.030949317,0.0068727196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013228958,0.0034138898,0.0035793127,0.0039012288,0.0038615507,0.0083162235,0.0052223844,0.02137005,0.026294926],"category_scores_gemma":[0.051503163,0.0012887211,0.0038207555,0.0019030157,0.0025332347,0.0048554656,0.0018507068,0.022699311,0.0116300825],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039164654,0.000026095631,0.0000604928,0.00013796389,0.0000140731745,0.00007457072,0.00001144441,0.000021289026,0.000044619523,0.00025687515,0.9950046,0.004308895],"study_design_scores_gemma":[0.00007414209,0.000044913817,0.00086838263,0.0005439193,0.000067810535,0.00019939883,0.000093597366,0.00023768272,0.00017415476,0.00096536794,0.99669635,0.000034285356],"about_ca_topic_score_codex":0.003970793,"about_ca_topic_score_gemma":0.008253046,"teacher_disagreement_score":0.026294926,"about_ca_system_score_codex":0.0031513793,"about_ca_system_score_gemma":0.005893873,"threshold_uncertainty_score":0.08796525},"labels":[],"label_agreement":null},{"id":"W6045406","doi":"10.3138/cjpe.24.004","title":"Interrater Reliability in Content Analysis of Healthcare Service Quality Using Montreal’s Conceptual Framework","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"Universitetet i Bergen; Thomas Jefferson University","keywords":"Inter-rater reliability; Generalizability theory; Kappa; Reliability (semiconductor); Psychology; Cohen's kappa; Statistics; Content analysis; Service (business); Service quality; Health care; Applied psychology; Mathematics; Business; Sociology; Power (physics); Rating scale; Marketing; Political science","score_opus":0.6590834155962562,"score_gpt":0.5276751899838836,"score_spread":0.13140822561237253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6045406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67563134,0.00080713123,0.29730222,0.000518628,0.00018770953,0.0042506773,0.00052053394,0.00033379783,0.020448003],"genre_scores_gemma":[0.9299256,0.00008774073,0.06729871,0.000031837768,0.000022387982,0.0022022799,0.00015068622,0.000031557272,0.00024907297],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.725482,0.20635486,0.01678991,0.00764047,0.04138356,0.0023492961],"domain_scores_gemma":[0.58672535,0.3049687,0.018253576,0.018208098,0.070567995,0.0012763013],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18311888,0.00083472783,0.0010368351,0.012833145,0.0024151178,0.0031103804,0.0019238024,0.000720951,0.0011236977],"category_scores_gemma":[0.37690362,0.0006913517,0.0015748289,0.008886381,0.0057435874,0.0033359162,0.005726599,0.0012290066,0.00019431874],"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":[0.0013926327,0.0003597905,0.49420774,0.0022753451,0.0016368992,0.00026529594,0.14092636,0.013194446,0.0066573946,0.056221362,0.0035010665,0.27936167],"study_design_scores_gemma":[0.00042709275,0.0018722194,0.6256357,0.002235966,0.0009629348,0.00065453624,0.06804198,0.18889344,0.019407667,0.07249421,0.018590834,0.0007835984],"about_ca_topic_score_codex":0.014968796,"about_ca_topic_score_gemma":0.016480908,"teacher_disagreement_score":0.8168811,"about_ca_system_score_codex":0.007209409,"about_ca_system_score_gemma":0.0075561716,"threshold_uncertainty_score":0.9684368},"labels":[],"label_agreement":null},{"id":"W78612901","doi":"10.3138/cjpe.0017.008","title":"Defining the Benefits, Outputs, and Knowledge Elements of Program Evaluation","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Process (computing); Program evaluation; Process management; Knowledge management; Raising (metalworking); Evaluation methods; Participatory evaluation; Management science; Business; Computer science; Public relations; Political science; Engineering; Public administration","score_opus":0.346987607917928,"score_gpt":0.5305338923085439,"score_spread":0.18354628439061588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W78612901","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28839305,0.008270262,0.15548937,0.11354276,0.00049763813,0.004024823,0.0008344074,0.00044211347,0.42850563],"genre_scores_gemma":[0.95676965,0.0012701111,0.037674204,0.0010460209,0.00008376011,0.0009204914,0.00013274234,0.000047760954,0.0020552373],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75299156,0.17561646,0.010111173,0.002346446,0.052275356,0.0066590984],"domain_scores_gemma":[0.63307923,0.26172096,0.01662575,0.012868807,0.06738993,0.008315417],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17492023,0.00087684946,0.00078128197,0.006862215,0.005430491,0.01640041,0.0015392693,0.0026094636,0.0029456473],"category_scores_gemma":[0.2593578,0.00060288457,0.00087143877,0.0044193976,0.009627891,0.011764242,0.011160446,0.0035827563,0.00036541006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007538963,0.00067205867,0.06643864,0.0063911118,0.00033528713,0.0005037031,0.030474532,0.0064533534,0.002201977,0.30954486,0.009875242,0.5663554],"study_design_scores_gemma":[0.00031657607,0.0014619022,0.1568156,0.021288756,0.0010713396,0.0008159307,0.07849305,0.019029194,0.021826215,0.50759,0.19094868,0.00034278532],"about_ca_topic_score_codex":0.014013875,"about_ca_topic_score_gemma":0.025445256,"teacher_disagreement_score":0.9782882,"about_ca_system_score_codex":0.021711836,"about_ca_system_score_gemma":0.048438266,"threshold_uncertainty_score":0.9250777},"labels":[],"label_agreement":null},{"id":"W79165327","doi":"10.3138/cjpe.018.001","title":"They’re Happy, but Did They Make a Difference? Applying Kirkpatrick’s Framework to the Evaluation of a National Leadership Program","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Formative assessment; Process (computing); Program evaluation; Leadership development; Psychology; Investment (military); Management science; Process management; Medical education; Political science; Business; Computer science; Public relations; Pedagogy; Engineering; Public administration; Medicine","score_opus":0.3557958721915049,"score_gpt":0.43434497165714075,"score_spread":0.07854909946563587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W79165327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39864352,0.005319128,0.1570966,0.10640343,0.0009275795,0.013706266,0.00028214362,0.0002061674,0.31741515],"genre_scores_gemma":[0.9087812,0.0009091906,0.080257244,0.002278438,0.000030316067,0.004652699,0.00005309676,0.00003664174,0.0030011763],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.72965646,0.23636146,0.004463406,0.0024914888,0.022273943,0.0047532013],"domain_scores_gemma":[0.93078274,0.04484203,0.004200274,0.0019197877,0.015565793,0.002689229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13050812,0.0009376201,0.0012668999,0.0057736626,0.010152666,0.011400085,0.003644972,0.0027139438,0.0032017832],"category_scores_gemma":[0.100021414,0.0005541301,0.0011655831,0.0031138565,0.016952785,0.009591647,0.009304842,0.0044696974,0.00039427276],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060536904,0.0033623422,0.024425298,0.003665946,0.00026287895,0.001223537,0.17067374,0.0053944793,0.0012414699,0.33198354,0.021851324,0.43530998],"study_design_scores_gemma":[0.0008187901,0.0035830827,0.04144494,0.011570486,0.0003938804,0.0014462046,0.54051113,0.027393904,0.0069590556,0.23683101,0.12847711,0.0005705239],"about_ca_topic_score_codex":0.022813397,"about_ca_topic_score_gemma":0.037865177,"teacher_disagreement_score":0.13050812,"about_ca_system_score_codex":0.033574324,"about_ca_system_score_gemma":0.05238308,"threshold_uncertainty_score":0.69020116},"labels":[],"label_agreement":null}]}