{"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9523183,0.0022524304,0.00006087974,0.017931439,0.0010570389,0.00349104,0.0000068634827,0.000011157039,0.022870824],"genre_scores_gemma":[0.9927648,0.00010327374,0.0036158871,0.0004308155,0.0005773424,0.00063466234,0.00007881122,0.00001267037,0.001781772],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99485517,0.0015376512,0.0006789335,0.00019438047,0.0022675125,0.0004663543],"domain_scores_gemma":[0.9966885,0.00008059564,0.00035746774,0.00014300137,0.0021319068,0.00059855805],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017095614,0.00013352823,0.00016485383,0.00034503735,0.000521828,0.00023914086,0.00024914,0.00013134014,0.022994954],"category_scores_gemma":[0.000832479,0.00014333667,0.00006691027,0.0006770488,0.0001109993,0.00046601568,0.0000039418774,0.00019420248,0.000035779423],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000026823436,0.0003198671,0.029474678,0.000008790739,0.000038032864,0.0000028836591,0.05755685,0.0044035325,0.000018956585,0.0009980423,0.07492097,0.83223057],"study_design_scores_gemma":[0.0024822606,0.00014934812,0.60278887,0.00023282615,0.00017125395,0.000006653832,0.011484921,0.0050052,0.000042411113,0.011008442,0.36632133,0.00030652288],"about_ca_topic_score_codex":0.0857375,"about_ca_topic_score_gemma":0.5607854,"teacher_disagreement_score":0.8319241,"about_ca_system_score_codex":0.014853986,"about_ca_system_score_gemma":0.07652766,"threshold_uncertainty_score":0.98892784},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928038,0.00020936938,0.00040125847,0.00091886934,0.00030948053,0.00083841034,0.000007919993,0.00001484862,0.004496038],"genre_scores_gemma":[0.99445486,0.000011660831,0.0049230196,0.00022062336,0.00029858446,0.000050537023,0.0000047544777,0.000012235736,0.000023750319],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9916697,0.005954528,0.00046181725,0.00009656567,0.0013731418,0.0004442095],"domain_scores_gemma":[0.99648225,0.00068582076,0.00034388105,0.00022424337,0.0015884874,0.0006753092],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.015772363,0.00009138769,0.00022144211,0.00044697223,0.0018291405,0.00006211382,0.00039702636,0.00013309458,0.00029048655],"category_scores_gemma":[0.0109795695,0.000092933566,0.00012200127,0.0006876716,0.0005269948,0.00028506698,0.000009740895,0.0007609885,0.000013640016],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009640532,0.0005534779,0.04477562,0.000018805138,0.0002651587,0.00007774121,0.38973215,0.0006374043,0.0031609861,0.0011447098,0.0017954389,0.5577421],"study_design_scores_gemma":[0.005382899,0.010947295,0.49028483,0.0009382054,0.0009910619,0.000076051,0.06620654,0.0048402855,0.016642135,0.06560951,0.3368353,0.0012458939],"about_ca_topic_score_codex":0.073827855,"about_ca_topic_score_gemma":0.13510273,"teacher_disagreement_score":0.5564962,"about_ca_system_score_codex":0.0012535264,"about_ca_system_score_gemma":0.013379118,"threshold_uncertainty_score":0.99947035},"labels":[],"label_agreement":null},{"id":"W14092155","doi":"10.3138/cjpe.018.003","title":"Balancing Ethical Principles in Evaluation: A Case Study","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Neglect; Engineering ethics; Politics; Indigenous; Ethical decision; Ethical issues; Ethical code; Political science; Public relations; Psychology; Sociology; Law; Engineering","score_opus":0.5803079388152322,"score_gpt":0.5911604505217036,"score_spread":0.01085251170647139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W14092155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99082863,0.00026528197,0.0002958871,0.0011297342,0.0008278991,0.0023476207,0.0000013253033,0.000005645399,0.0042979666],"genre_scores_gemma":[0.99745315,0.0000015923196,0.0020038434,0.00021198692,0.00009186349,0.00016894589,0.0000019350937,0.000009543282,0.000057150704],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98916966,0.0041672713,0.0016099624,0.0003083575,0.0043962253,0.0003485209],"domain_scores_gemma":[0.99345493,0.00048630557,0.0007016309,0.0003905687,0.0044822665,0.00048428244],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.097543,0.00014661787,0.0003072087,0.0011273955,0.0002483656,0.00044979778,0.00032838952,0.00015148488,0.0035729127],"category_scores_gemma":[0.017930117,0.00011646579,0.00010265616,0.0014756593,0.000070716254,0.00049347273,0.000010358769,0.00062361796,0.00005050762],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012396595,0.00018604836,0.50701976,0.0000033768574,0.000029899433,0.00057777885,0.009866308,0.021048248,0.00000548264,0.0007365697,0.0004000125,0.46011415],"study_design_scores_gemma":[0.008355482,0.0022806372,0.42706475,0.00012296515,0.00034881776,0.005566809,0.090087235,0.41918325,0.000048138867,0.0109780105,0.03544289,0.00052102853],"about_ca_topic_score_codex":0.0011661276,"about_ca_topic_score_gemma":0.17299503,"teacher_disagreement_score":0.45959312,"about_ca_system_score_codex":0.0010264902,"about_ca_system_score_gemma":0.013871942,"threshold_uncertainty_score":0.99733794},"labels":[],"label_agreement":null},{"id":"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":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99162406,0.0010174183,0.00019750369,0.003688443,0.0005100036,0.0026913108,0.000012178399,0.000006931495,0.00025217835],"genre_scores_gemma":[0.99857175,0.000004953116,0.00073686044,0.000106622334,0.00022062036,0.00030507118,0.00003732253,0.000015282045,0.0000014848831],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98652375,0.011302407,0.0007954911,0.00011780835,0.000951777,0.000308784],"domain_scores_gemma":[0.9942176,0.000940782,0.00092088815,0.00025608897,0.0033943835,0.00027030046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025981758,0.00013993992,0.00039810393,0.00017107643,0.0009431532,0.0001093058,0.00031775277,0.0001859234,0.000024846096],"category_scores_gemma":[0.0046149213,0.00008795748,0.00006985549,0.00048687804,0.0003201669,0.00040470398,0.00002457746,0.0012620266,0.0000011678703],"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":[0.00002036379,0.000080636026,0.65313053,0.000019579245,0.00005187229,9.0561093e-7,0.10722866,0.00028260078,0.000010224137,0.00035508547,0.000012103722,0.23880744],"study_design_scores_gemma":[0.001427687,0.00017232791,0.64264244,0.00037933054,0.0002640315,3.8546924e-7,0.33654448,0.0032684687,0.0000171745,0.014812854,0.00037602487,0.00009477913],"about_ca_topic_score_codex":0.13065496,"about_ca_topic_score_gemma":0.507889,"teacher_disagreement_score":0.37723404,"about_ca_system_score_codex":0.0010291632,"about_ca_system_score_gemma":0.008727018,"threshold_uncertainty_score":0.9968926},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22951438,0.010306709,0.00014824898,0.69633263,0.00807758,0.003260268,0.0000019622478,0.000041275212,0.052316967],"genre_scores_gemma":[0.9921705,0.00009310715,0.004693201,0.00025218536,0.0014031478,0.0001419533,0.000009123729,0.000010287804,0.0012264539],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957868,0.0021925073,0.00038037417,0.00013525717,0.0011199535,0.00038511027],"domain_scores_gemma":[0.99549615,0.00015644009,0.00019766248,0.00012848487,0.0032418917,0.00077936007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01879025,0.00007165042,0.00012369767,0.0006217026,0.00026102306,0.00021413498,0.00016835154,0.000112825124,0.0002862735],"category_scores_gemma":[0.005576923,0.00007307179,0.000040923558,0.0008987371,0.00031133278,0.00053741765,0.000005312744,0.0004965991,0.000104665756],"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":[0.000025568897,0.00025015522,0.027741887,0.000009541142,0.000017344055,0.0000029649489,0.1486322,0.000019305497,0.0000033383171,0.0023917214,0.3561388,0.4647672],"study_design_scores_gemma":[0.00030128306,0.00009833312,0.009658315,0.000045820714,0.000019178276,0.000012502202,0.19145462,0.00001521605,0.0000013072606,0.0039503146,0.79437494,0.000068165406],"about_ca_topic_score_codex":0.06325325,"about_ca_topic_score_gemma":0.59849864,"teacher_disagreement_score":0.76265615,"about_ca_system_score_codex":0.0026249136,"about_ca_system_score_gemma":0.03990464,"threshold_uncertainty_score":0.9655382},"labels":[],"label_agreement":null},{"id":"W1490602178","doi":"10.3138/cjpe.0028.005","title":"A Professional Grounding and History of the Development and Formal Use of Evaluator Competencies","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Viewpoints; Credentialing; Engineering ethics; Value (mathematics); Professional association; Field (mathematics); Foundation (evidence); Professional development; Psychology; Political science; Sociology; Pedagogy; Public relations; Engineering; Computer science; Social science; Law","score_opus":0.39851549563026134,"score_gpt":0.4680725057001939,"score_spread":0.06955701006993253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490602178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972078,0.00047347244,0.00041240518,0.00037208907,0.00077779446,0.00046345955,0.0000015523182,0.0000013902713,0.0002900378],"genre_scores_gemma":[0.9914935,0.000003557874,0.008165202,0.00006982547,0.00003314269,0.000015593778,0.0000012932861,0.00000389175,0.00021397306],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966415,0.0005461826,0.0008401165,0.00010627956,0.0017187638,0.00014714221],"domain_scores_gemma":[0.9966117,0.000375993,0.000935033,0.00014882977,0.0017438403,0.00018458746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014703625,0.0000784705,0.00020210067,0.00031699255,0.00014275951,0.000060899743,0.00020123128,0.000045147535,0.00018360106],"category_scores_gemma":[0.002625795,0.000047842113,0.000049443366,0.00020185641,0.00022244331,0.00064530846,0.000030935662,0.00011306833,9.573965e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021211858,0.000027878763,0.17504327,0.000023525643,0.000023388937,1.5964446e-7,0.007321842,0.00016179019,0.00027992052,0.0016933694,0.00090998213,0.81449366],"study_design_scores_gemma":[0.0007983416,0.00027414647,0.8656971,0.00017030787,0.000064901484,0.000022093473,0.0015822303,0.04331083,0.00021403203,0.0017634028,0.08601237,0.00009024481],"about_ca_topic_score_codex":0.00014166378,"about_ca_topic_score_gemma":0.0052625253,"teacher_disagreement_score":0.8144034,"about_ca_system_score_codex":0.00034348806,"about_ca_system_score_gemma":0.006019714,"threshold_uncertainty_score":0.99961525},"labels":[],"label_agreement":null},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018616322,0.97321373,0.0006892736,0.004612012,0.00094421,0.020262394,0.000117751006,0.0000083703535,0.00013366068],"genre_scores_gemma":[0.000963637,0.99409944,0.0022095873,0.00039145257,0.00028139705,0.0018902518,0.000110507106,0.00003442926,0.000019297215],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9770094,0.0140734725,0.0066926586,0.00020618862,0.0012988774,0.0007193867],"domain_scores_gemma":[0.9814976,0.0009931073,0.013065869,0.0005133277,0.003359902,0.00057022774],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05778972,0.00025634287,0.0019050954,0.0008203111,0.0007890927,0.000018176934,0.0006260421,0.00017154655,0.0014562749],"category_scores_gemma":[0.007360358,0.00018305678,0.00065226975,0.0013550917,0.00043353773,0.00034616402,0.00004400105,0.0008879217,0.000029057337],"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":[5.398449e-7,0.000033567732,0.000051317813,0.19636038,0.000048812355,1.114732e-7,0.0016367561,0.0000013806771,3.1307206e-8,0.00028147985,0.00055943197,0.80102617],"study_design_scores_gemma":[0.0003874985,0.0003872594,0.00040663683,0.84298515,0.0017808998,0.000027758819,0.000550012,0.00003291992,1.8508103e-7,0.00050852046,0.15277648,0.00015669706],"about_ca_topic_score_codex":0.003432831,"about_ca_topic_score_gemma":0.033390384,"teacher_disagreement_score":0.80086946,"about_ca_system_score_codex":0.0018746322,"about_ca_system_score_gemma":0.053313218,"threshold_uncertainty_score":0.9994565},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825568,0.0026360922,0.000995877,0.0050094486,0.0023398488,0.0028121485,0.000005006285,0.000006866466,0.003637875],"genre_scores_gemma":[0.99733824,0.000007731987,0.0016363292,0.00023993038,0.00046109874,0.0002093993,0.000005783524,0.00001315698,0.0000883145],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97850215,0.0062176166,0.0019308786,0.00022039509,0.01267289,0.0004560923],"domain_scores_gemma":[0.97983736,0.0008476868,0.0022332226,0.0007934531,0.015951522,0.0003367521],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17275204,0.00017655084,0.00029406222,0.00039082018,0.00067151035,0.00034356827,0.00086531555,0.00011200776,0.0038565958],"category_scores_gemma":[0.023309542,0.00009501661,0.00029602705,0.0018127494,0.00022402736,0.0014707368,0.000036765592,0.00033204517,0.000079874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021557238,0.00008615927,0.08393175,0.0000038323724,0.00007338699,6.993813e-8,0.0042101704,0.030742887,0.00062218314,0.0011302126,0.0027772547,0.87640053],"study_design_scores_gemma":[0.0012810957,0.0003334343,0.5114548,0.00004366725,0.001016052,0.000030471761,0.0025939445,0.46123654,0.0018211835,0.01312138,0.00692505,0.00014234812],"about_ca_topic_score_codex":0.00031294007,"about_ca_topic_score_gemma":0.004348504,"teacher_disagreement_score":0.8762582,"about_ca_system_score_codex":0.0008936226,"about_ca_system_score_gemma":0.009686183,"threshold_uncertainty_score":0.99705404},"labels":[],"label_agreement":null},{"id":"W1496927098","doi":"","title":"Barbier, J. C., & Hawkins, P. (Eds.). (2012). Evaluation Cultures: Sense-making in Complex Times","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sense (electronics); Psychology; Chemistry; Physical chemistry","score_opus":0.32864005862634,"score_gpt":0.529181536959155,"score_spread":0.20054147833281505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496927098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.914903,0.008910811,0.0015984819,0.014815374,0.0029088103,0.009682803,0.000021180613,0.000051038347,0.04710854],"genre_scores_gemma":[0.9939196,0.000040220028,0.0046179937,0.0005782025,0.0002643181,0.00021824153,0.00004736465,0.0000170257,0.0002970487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915931,0.0015893616,0.0016300856,0.0003466024,0.004336669,0.0005041455],"domain_scores_gemma":[0.99121916,0.00031459957,0.0010649067,0.00043042013,0.0064892694,0.00048164793],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024165379,0.0002210271,0.00038885177,0.0013459219,0.00030302702,0.00094940653,0.000518145,0.00015177,0.030361231],"category_scores_gemma":[0.0044165393,0.0001717881,0.0001661787,0.0012811847,0.000118183714,0.0019855385,0.000021396174,0.00036428872,0.00066091947],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009964975,0.000054719938,0.011434986,0.000004850131,0.000024608727,0.000005259016,0.0015215726,0.006644245,0.00014191386,0.00026641885,0.04408773,0.9358037],"study_design_scores_gemma":[0.0019968052,0.00036515563,0.34669542,0.00012593446,0.000116869436,0.0000881908,0.0024428787,0.46290538,0.00004815057,0.027714426,0.1571759,0.00032488737],"about_ca_topic_score_codex":0.0015049927,"about_ca_topic_score_gemma":0.040194746,"teacher_disagreement_score":0.93547887,"about_ca_system_score_codex":0.00083022326,"about_ca_system_score_gemma":0.0054051992,"threshold_uncertainty_score":0.9773192},"labels":[],"label_agreement":null},{"id":"W1506594705","doi":"10.3138/cjpe.0028.003","title":"Introduction to Professionalizing Evaluation: A Global Perspective on Evaluator Competencies","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Psychology; Sociology; Pedagogy; Knowledge management; Computer science; Artificial intelligence","score_opus":0.26065355762357273,"score_gpt":0.5437613801430642,"score_spread":0.28310782251949146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506594705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82943976,0.00063550955,0.0062538562,0.11480531,0.009398197,0.006551008,0.000025088515,0.000050906612,0.032840375],"genre_scores_gemma":[0.99011713,0.000001619837,0.0060318424,0.001099587,0.0023049777,0.00023156502,0.000014960596,0.000012905387,0.00018541994],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9885592,0.0025102177,0.0011632051,0.00049473473,0.0068667596,0.00040591945],"domain_scores_gemma":[0.9822205,0.00034558133,0.0008504243,0.00053579477,0.015265293,0.0007824491],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046336632,0.00021927194,0.0003650954,0.00085105485,0.00048745642,0.0005200027,0.0006269352,0.00010645261,0.0055493354],"category_scores_gemma":[0.022129538,0.00016803588,0.00018092348,0.0017106251,0.00010542567,0.0007015944,0.000024497795,0.0002757392,0.0005686378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000098235614,0.00010424194,0.0065263347,0.0000039875863,0.000051114548,0.0000012874799,0.0022933409,0.025187591,0.00007105719,0.02251467,0.037663065,0.9054851],"study_design_scores_gemma":[0.0034216421,0.004145266,0.2093225,0.00021000231,0.00039618183,0.00010756963,0.01480557,0.29891855,0.00021001066,0.118458845,0.34941664,0.0005872393],"about_ca_topic_score_codex":0.00038356776,"about_ca_topic_score_gemma":0.010318208,"teacher_disagreement_score":0.9048978,"about_ca_system_score_codex":0.003893956,"about_ca_system_score_gemma":0.008777533,"threshold_uncertainty_score":0.9999299},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1514004023","doi":"10.3138/cjpe.025.006","title":"An Alternative to the Traditional Literature Review","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Disk formatting; Process (computing); Information needs; Work (physics); Computer science; Process management; Outcome (game theory); Risk analysis (engineering); Knowledge management; Management science; Business; World Wide Web; Engineering; Economics","score_opus":0.4147867432021777,"score_gpt":0.5561090360664662,"score_spread":0.14132229286428855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514004023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6817788,0.017477175,0.0045924615,0.25378057,0.015407288,0.009382184,0.00020432363,0.000034293244,0.01734295],"genre_scores_gemma":[0.98912746,0.00015710876,0.0044206227,0.004960286,0.0010529949,0.00011789927,0.00003693544,0.000007559005,0.00011913254],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99621165,0.0005451065,0.00062965875,0.0001615148,0.0022777144,0.00017435678],"domain_scores_gemma":[0.99434376,0.00017877214,0.0004110885,0.00036366846,0.004126364,0.0005763293],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019197132,0.00009187188,0.00015506925,0.00035304506,0.0002388567,0.0006036566,0.0007974832,0.000047794707,0.004248781],"category_scores_gemma":[0.0033017008,0.000052070296,0.000103408864,0.0009291824,0.000055400822,0.00077420275,0.0000052874607,0.0004082433,0.00013253636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005488483,0.0000330403,0.0011698585,0.000006291658,0.000012499586,0.000005708258,0.0013640013,0.00065200066,0.00006444093,0.0026796716,0.034010712,0.9599963],"study_design_scores_gemma":[0.00053896604,0.00095202593,0.086873494,0.0006139081,0.000101839956,0.00030561793,0.00040949686,0.02981995,0.000085603504,0.02678906,0.853308,0.00020199682],"about_ca_topic_score_codex":0.000066651606,"about_ca_topic_score_gemma":0.019739572,"teacher_disagreement_score":0.9597943,"about_ca_system_score_codex":0.00009996898,"about_ca_system_score_gemma":0.002920967,"threshold_uncertainty_score":0.9981476},"labels":[],"label_agreement":null},{"id":"W1517551366","doi":"10.3138/cjpe.028.005","title":"Learning Circles for Advanced Professional Development in Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Public Health Agency of Canada; Health Canada","funders":"","keywords":"Professional development; Context (archaeology); Process (computing); Quality (philosophy); Psychology; Professional learning community; Collaborative learning; Knowledge management; Medical education; Pedagogy; Computer science; Medicine","score_opus":0.36610878492078347,"score_gpt":0.5580433458244787,"score_spread":0.1919345609036952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517551366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991002,0.00029327843,0.0008963874,0.0018455794,0.0013112174,0.003793273,0.0000010278667,0.000006746619,0.0008504765],"genre_scores_gemma":[0.9862302,0.0000028199283,0.011879522,0.000103235296,0.00009854919,0.0012465403,0.00003083081,0.000010365897,0.00039792494],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947668,0.00073370873,0.0012239476,0.0002278046,0.00272247,0.00032527602],"domain_scores_gemma":[0.9918566,0.0004033296,0.0007874163,0.00015325107,0.0064859483,0.0003134755],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02674914,0.00012008246,0.00022637114,0.00090876664,0.00027293336,0.00030257722,0.00033372745,0.0000856285,0.003300318],"category_scores_gemma":[0.007047738,0.00009623528,0.00008339116,0.0006366906,0.00004264221,0.0010634463,0.000010777642,0.00022766678,0.00010560339],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012406359,0.000040500996,0.028110398,0.000004534222,0.000009305485,3.2094002e-7,0.0017774027,0.013257513,0.00014000024,0.000067480316,0.0009935666,0.95558655],"study_design_scores_gemma":[0.003122929,0.0005185013,0.57187057,0.00015076082,0.000038829374,0.000009874915,0.00458243,0.34150413,0.00035628682,0.015344328,0.06227862,0.00022273372],"about_ca_topic_score_codex":0.00014051682,"about_ca_topic_score_gemma":0.010273616,"teacher_disagreement_score":0.9553638,"about_ca_system_score_codex":0.00084200915,"about_ca_system_score_gemma":0.010480989,"threshold_uncertainty_score":0.9976108},"labels":[],"label_agreement":null},{"id":"W1547906511","doi":"10.3138/cjpe.0028.008","title":"Evaluator Competencies: The South African Government Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Presidency; Context (archaeology); Institution; Process (computing); Political science; Computer science; Geography","score_opus":0.27171115503889426,"score_gpt":0.4784742502509596,"score_spread":0.20676309521206532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1547906511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661425,0.00034910833,0.005624685,0.0073208804,0.0020232867,0.0016000702,0.000011248182,0.000014439017,0.016913803],"genre_scores_gemma":[0.9968649,0.0000026102853,0.0019378857,0.0005800732,0.00028113765,0.000103872226,0.0000016988665,0.000008658168,0.0002191518],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99172586,0.0011307588,0.0009748143,0.00022737004,0.005608813,0.0003323861],"domain_scores_gemma":[0.99527,0.0005202429,0.00094287575,0.00052967126,0.0022402962,0.0004969074],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026771361,0.00013883944,0.00023248456,0.0001869687,0.00045267472,0.0005932868,0.0009982089,0.000052178046,0.0030095556],"category_scores_gemma":[0.0072633186,0.00008091856,0.00015187215,0.00072213425,0.0002281765,0.00044975246,0.000023361525,0.00021417247,0.00014073601],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017611937,0.000031698695,0.032934353,0.0000021443684,0.000024215968,0.0000013948304,0.015806882,0.0039311163,0.000049003458,0.0016370735,0.002954001,0.9426105],"study_design_scores_gemma":[0.0011839968,0.0009564426,0.16144046,0.000045517332,0.00012216499,0.00004344007,0.03366141,0.29841024,0.00016538729,0.008112582,0.49559736,0.00026100254],"about_ca_topic_score_codex":0.0002065372,"about_ca_topic_score_gemma":0.005722884,"teacher_disagreement_score":0.9423495,"about_ca_system_score_codex":0.0005617798,"about_ca_system_score_gemma":0.0029617655,"threshold_uncertainty_score":0.99790186},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9241723,0.0012045642,0.06174582,0.0012396887,0.0011465194,0.010187822,0.00000899024,0.000059781567,0.00023456133],"genre_scores_gemma":[0.91435593,8.864173e-7,0.08364623,0.00016642768,0.00041414384,0.0007522863,0.0006219638,0.00003441338,0.000007738465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99631274,0.0013842724,0.0005571548,0.000162032,0.0012182518,0.00036556835],"domain_scores_gemma":[0.9934226,0.00012603836,0.00050876726,0.00037652216,0.0044392277,0.0011268134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013946765,0.00017866783,0.0003190731,0.00036681053,0.00016989654,0.00013296751,0.0002176418,0.00022422326,0.000046916583],"category_scores_gemma":[0.004089118,0.00016808505,0.0001768246,0.0004236968,0.00009314123,0.00045998825,0.000005322212,0.000556049,0.000006490659],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036876663,0.00045239966,0.006229554,0.00013785562,0.00009415091,0.000009287272,0.0024026213,0.0006986204,0.00013474416,0.00028277116,0.00038914965,0.9888001],"study_design_scores_gemma":[0.05301387,0.09764613,0.07074743,0.0067223525,0.008114447,0.000719486,0.009417444,0.46367714,0.008599498,0.24736528,0.032256376,0.0017205655],"about_ca_topic_score_codex":0.00045086755,"about_ca_topic_score_gemma":0.00708839,"teacher_disagreement_score":0.9870795,"about_ca_system_score_codex":0.0014380462,"about_ca_system_score_gemma":0.008373085,"threshold_uncertainty_score":0.99724853},"labels":[],"label_agreement":null},{"id":"W1558175818","doi":"10.3138/cjpe.028.002","title":"The Reciprocal Relationship between Implementation Theory and Program Theory in Assisting Program Design and Decision-Making","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reciprocal; Management science; Program Design Language; Interpretation (philosophy); Computer science; Decision theory; Focus (optics); Development theory; Theory of change; Epistemology; Sociology; Software engineering; Mathematics; Engineering; Economics; Programming language","score_opus":0.3607936961203019,"score_gpt":0.5650848166150938,"score_spread":0.20429112049479192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558175818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96794367,0.0012596272,0.023437733,0.001131988,0.00025981257,0.0056207874,0.0000021188175,0.000024262632,0.00031999705],"genre_scores_gemma":[0.94183874,0.000017200027,0.057206858,0.000057676603,0.00010569651,0.0007376913,0.000005750385,0.0000135016035,0.000016866154],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99348485,0.002894716,0.0013600474,0.00029796403,0.0015481613,0.0004142812],"domain_scores_gemma":[0.98637223,0.010697199,0.0008518075,0.00024632763,0.0014864744,0.00034596806],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05975969,0.00016686326,0.00024118922,0.00062708877,0.00076490256,0.0016661251,0.00034666003,0.000109843924,0.0002799919],"category_scores_gemma":[0.013369642,0.000109425106,0.00006258076,0.00087894505,0.00024967288,0.0011099634,0.000031270425,0.00036832117,0.000015184812],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025059111,0.000016614968,0.26071057,0.0000024842595,0.000011977442,9.963957e-7,0.00078048866,0.00013780763,0.0000010076087,0.002127491,0.00014888447,0.7360366],"study_design_scores_gemma":[0.00056228344,0.00049536175,0.6680868,0.000096124284,0.00005075847,0.000017947814,0.003913773,0.018236047,0.00000307402,0.30727673,0.0011572742,0.00010377932],"about_ca_topic_score_codex":0.00012298177,"about_ca_topic_score_gemma":0.0044204416,"teacher_disagreement_score":0.7359328,"about_ca_system_score_codex":0.00030245422,"about_ca_system_score_gemma":0.0018381677,"threshold_uncertainty_score":0.9993702},"labels":[],"label_agreement":null},{"id":"W1559496221","doi":"10.3138/cjpe.28.005","title":"Neutral Assessment of the National Research Council Canada Evaluation Function","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique; National Research Council Canada","funders":"","keywords":"Treasury; Function (biology); Government (linguistics); Research council; Public administration; Political science; Public relations; Accounting; Business; Law","score_opus":0.7595030484590533,"score_gpt":0.59285100163704,"score_spread":0.1666520468220133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1559496221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9370078,0.00029677153,0.00024367654,0.0106896795,0.0030869017,0.0038713065,0.000018075672,0.000004896038,0.044780903],"genre_scores_gemma":[0.9983985,0.0000029390426,0.0005531764,0.00030206272,0.0002454915,0.00024089821,0.0000055569167,0.000008468025,0.00024294779],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9661093,0.0024089257,0.0012826703,0.0002379479,0.029602014,0.0003591781],"domain_scores_gemma":[0.87890935,0.0005457408,0.00089047686,0.00029501642,0.11904572,0.0003137271],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12750128,0.000121477744,0.00021513164,0.00046222517,0.00047226792,0.0003812719,0.0007250073,0.00008507197,0.0058550206],"category_scores_gemma":[0.02127089,0.00007953943,0.00012580138,0.0015920843,0.00017448554,0.0008336924,0.000025307867,0.00044279706,0.00002738401],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000017301225,0.000108891785,0.050641254,0.000011827228,0.000090905676,5.8301924e-7,0.0007014079,0.051119145,0.00042746065,0.0033533713,0.3371784,0.55634946],"study_design_scores_gemma":[0.00084448856,0.000298619,0.6398241,0.00004153229,0.000069523536,0.000012139046,0.0011658731,0.2611075,0.0000868081,0.029097388,0.06735183,0.000100238125],"about_ca_topic_score_codex":0.27538505,"about_ca_topic_score_gemma":0.94555926,"teacher_disagreement_score":0.67017424,"about_ca_system_score_codex":0.013623818,"about_ca_system_score_gemma":0.22176318,"threshold_uncertainty_score":0.99505377},"labels":[],"label_agreement":null},{"id":"W1570565511","doi":"10.3138/cjpe.27.007","title":"Funnell, S. C., and Rogers, P. J. (2011). <i>Purposeful Program Theory.</i> San Francisco, CA: Jossey-Bass. 550 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bass (fish); Psychology; Fishery; Biology","score_opus":0.24747467403425955,"score_gpt":0.4667965692241588,"score_spread":0.21932189518989925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570565511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94051665,0.027369635,0.0028285503,0.005193455,0.00466042,0.0055853734,0.000045175708,0.00007903758,0.013721698],"genre_scores_gemma":[0.9922119,0.00010553411,0.005987073,0.00051822595,0.0005898173,0.00019102063,0.000027196655,0.000027515294,0.0003417412],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99360406,0.001152315,0.0013250543,0.00033739334,0.0027898927,0.00079130393],"domain_scores_gemma":[0.9941518,0.00043913882,0.0010240566,0.00049666007,0.0024067063,0.0014816732],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029777812,0.00028097525,0.00045157562,0.0007577295,0.00044683376,0.0007934796,0.0005723688,0.00018342979,0.0085403845],"category_scores_gemma":[0.0020338648,0.00021212733,0.00017520672,0.0006829256,0.00028192505,0.0017194418,0.000030799638,0.0004410407,0.00042495326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028822718,0.00012233776,0.06384842,0.000009514851,0.000054053708,0.0000055810006,0.0014258894,0.00013437336,0.0000420358,0.0007089689,0.024316993,0.909303],"study_design_scores_gemma":[0.0024091532,0.0015771047,0.28764936,0.00009180417,0.0003896477,0.0002710002,0.0036298751,0.011170452,0.00030760083,0.0149074225,0.676993,0.0006035415],"about_ca_topic_score_codex":0.00029411778,"about_ca_topic_score_gemma":0.006117131,"teacher_disagreement_score":0.90869945,"about_ca_system_score_codex":0.00035750234,"about_ca_system_score_gemma":0.002994394,"threshold_uncertainty_score":0.99904794},"labels":[],"label_agreement":null},{"id":"W1588229591","doi":"10.3138/cjpe.30.1.105","title":"Sharon Brisolara, Denise Seigart, &amp; Saumitra SenGupta (Eds.). (2014). <i>Feminist Evaluation and Research: Theory and Practice.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sociology; Theology; Philosophy","score_opus":0.6285746015045411,"score_gpt":0.6044724397125063,"score_spread":0.024102161792034837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588229591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9379916,0.021233473,0.0015288709,0.012470287,0.0017415965,0.0042559556,0.000031004307,0.000026788293,0.020720394],"genre_scores_gemma":[0.9921243,0.00018324365,0.006197829,0.00056471047,0.00037487596,0.000090898604,0.000028791608,0.000021993523,0.00041332707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98324734,0.008290576,0.0011732801,0.000463446,0.0063163596,0.00050900556],"domain_scores_gemma":[0.9833058,0.0026642608,0.0008519712,0.0004967732,0.011306648,0.0013745201],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20733808,0.00019564187,0.00031794756,0.0010357104,0.00051608105,0.0014734821,0.0004307545,0.00016224188,0.0010107408],"category_scores_gemma":[0.053575754,0.00015992048,0.000075615855,0.0008157087,0.00043664116,0.0017162864,0.00005338549,0.0005710387,0.00017271713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023293414,0.000067465706,0.0080909785,0.000008018314,0.000049433544,0.000009528453,0.008955169,0.00032385465,0.00008488313,0.00095914945,0.036448974,0.9447696],"study_design_scores_gemma":[0.0038871225,0.0015160562,0.024402313,0.00012331335,0.00049225165,0.00095062534,0.022884214,0.032655083,0.00006966918,0.07894593,0.83365595,0.0004174871],"about_ca_topic_score_codex":0.0005388154,"about_ca_topic_score_gemma":0.009860488,"teacher_disagreement_score":0.94435215,"about_ca_system_score_codex":0.00054366543,"about_ca_system_score_gemma":0.010140692,"threshold_uncertainty_score":0.9999025},"labels":[],"label_agreement":null},{"id":"W1591702131","doi":"10.3138/cjpe.28.002","title":"To Case Study or Not to Case Study: Our Experience with the Canadian Government’s Evaluation Practices and the Use of Case Studies as an Evaluation Methodology for First Nations Programs","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Case study research; Work (physics); Public relations; Comparative case; Value (mathematics); Political science; Psychology; Business; Marketing; Engineering","score_opus":0.8529623701720311,"score_gpt":0.6548419671908232,"score_spread":0.19812040298120792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1591702131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9573239,0.00008722442,0.00039489067,0.011691123,0.00042446068,0.030031702,0.000019294432,0.0000066550156,0.00002072614],"genre_scores_gemma":[0.9816571,0.000003157354,0.00823546,0.00052307826,0.00012630966,0.009365786,0.0000048367842,0.000021635344,0.00006266864],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98592323,0.0069124647,0.0014319639,0.0005799444,0.0046883384,0.00046405743],"domain_scores_gemma":[0.97613716,0.004511821,0.002026687,0.00078359514,0.015638463,0.000902267],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06953911,0.00029016566,0.0005130657,0.0007706098,0.0024980519,0.0015782819,0.0004826821,0.000082123566,0.0002122654],"category_scores_gemma":[0.05241201,0.00015168088,0.00008350944,0.0017156664,0.00021548822,0.0020470314,0.00004930092,0.00023928648,0.000007729383],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049932336,0.00043087572,0.020894423,0.000013091936,0.00042153645,0.001279246,0.264108,0.015010726,0.000003785824,0.00007642123,0.0007305972,0.696532],"study_design_scores_gemma":[0.0043933927,0.008173476,0.006905623,0.000038523893,0.0015711557,0.020134231,0.8394762,0.11721876,0.000011833974,0.00018849106,0.0016459246,0.00024234806],"about_ca_topic_score_codex":0.42574567,"about_ca_topic_score_gemma":0.9970624,"teacher_disagreement_score":0.69628966,"about_ca_system_score_codex":0.0014385787,"about_ca_system_score_gemma":0.007953458,"threshold_uncertainty_score":0.9994582},"labels":[],"label_agreement":null},{"id":"W1594257894","doi":"10.3138/cjpe.23.003","title":"Reframing Evaluation: Defining an Indigenous Evaluation Framework","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognitive reframing; Indigenous; Traditional knowledge; Focus group; Common ground; Sociology; Public relations; Political science; Engineering ethics; Psychology; Engineering; Social psychology; Anthropology; Ecology","score_opus":0.396733003676957,"score_gpt":0.552227878522765,"score_spread":0.15549487484580798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594257894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9838338,0.0024886692,0.0033724585,0.0007311968,0.0021983793,0.0028617538,0.0000096037575,0.00002705073,0.0044770846],"genre_scores_gemma":[0.9794262,0.00002905847,0.01921723,0.0003187683,0.0005447072,0.0002830508,0.00009365455,0.00002850955,0.000058832764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98321295,0.0031676001,0.0019695074,0.00051777344,0.010528704,0.00060347194],"domain_scores_gemma":[0.9810528,0.00060452166,0.0017087096,0.0007943672,0.014908279,0.0009313123],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07245219,0.00027363116,0.00044934405,0.0015225584,0.0011889397,0.0006292202,0.0009150127,0.0002739923,0.008595575],"category_scores_gemma":[0.016429527,0.00023582413,0.00021223616,0.0018826234,0.00019531064,0.0021857934,0.000021591834,0.0005971259,0.00028063555],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022613933,0.00008495262,0.03465482,0.0000029002297,0.00004113437,0.000010910337,0.013490658,0.020558959,0.000019560815,0.00035578271,0.00076892995,0.9299888],"study_design_scores_gemma":[0.0029245117,0.001940261,0.2955871,0.00018039207,0.0006329354,0.00059994886,0.007993684,0.6049691,0.00014065817,0.06572765,0.018678201,0.00062559836],"about_ca_topic_score_codex":0.0005223277,"about_ca_topic_score_gemma":0.008125919,"teacher_disagreement_score":0.9293632,"about_ca_system_score_codex":0.0017303753,"about_ca_system_score_gemma":0.025611255,"threshold_uncertainty_score":0.9923107},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["sts"],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W1594443358","doi":"10.3138/cjpe.027.002","title":"Research on Evaluation: A Needs Assessment","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Psychology; Survey research; Engineering ethics; Management science; Sociology; Applied psychology; Engineering","score_opus":0.7833440326357193,"score_gpt":0.6849524617018541,"score_spread":0.09839157093386519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594443358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8563039,0.0013305342,0.0007642173,0.008681882,0.004203503,0.003315702,0.000007656716,0.000015551783,0.12537709],"genre_scores_gemma":[0.9957566,0.00000809221,0.00238996,0.00027981214,0.0009232257,0.0002489675,0.000014368592,0.000014112289,0.00036483363],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9827187,0.003858387,0.0011765591,0.00020591597,0.01133779,0.0007026419],"domain_scores_gemma":[0.9852979,0.00091060955,0.0006316192,0.0005442426,0.011528704,0.001086911],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.15748209,0.00015182221,0.0002654825,0.002936783,0.00053879834,0.0006491278,0.0006902911,0.00012323735,0.012865041],"category_scores_gemma":[0.0051429947,0.00011351662,0.00015687302,0.002851841,0.00015058632,0.0012358662,0.000021887661,0.00062629755,0.0005924988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017175269,0.00015189614,0.04477359,0.000002554974,0.000032005868,0.0000014275106,0.001778282,0.0032154012,0.000019357181,0.0061797407,0.020454517,0.92337406],"study_design_scores_gemma":[0.002224075,0.0018813098,0.52186775,0.00010426188,0.00017037799,0.00006762116,0.013439269,0.09685926,0.00012897392,0.01783021,0.34512892,0.0002979787],"about_ca_topic_score_codex":0.00022226623,"about_ca_topic_score_gemma":0.0022425815,"teacher_disagreement_score":0.9230761,"about_ca_system_score_codex":0.0018759632,"about_ca_system_score_gemma":0.013326426,"threshold_uncertainty_score":0.9922671},"labels":[],"label_agreement":null},{"id":"W1594828522","doi":"","title":"The key functions of collaborative logic modeling: Insights from the British Columbia Early Childhood Dental Programs","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Documentation; General partnership; Logic model; Government (linguistics); Key (lock); Early childhood; Computer science; Knowledge management; Public relations; Political science; Process management; Psychology; Public administration; Business; Programming language; Developmental psychology","score_opus":0.20652292156545762,"score_gpt":0.41826608559438194,"score_spread":0.21174316402892432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594828522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909539,0.00360914,0.00070162734,0.0008663235,0.0012718947,0.0014677115,0.000027224909,0.0000069699468,0.0010951952],"genre_scores_gemma":[0.99840343,0.000033585795,0.0007566561,0.000107291555,0.0003571857,0.00011565982,0.000028839038,0.000009431153,0.0001879396],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954096,0.0009132915,0.0009770483,0.00015667816,0.002231909,0.00031148235],"domain_scores_gemma":[0.9941575,0.00042073254,0.00082723977,0.0003174707,0.0038892278,0.00038784507],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007147104,0.00009983339,0.00021045505,0.00008282742,0.0014787638,0.002942876,0.000527884,0.0000825168,0.0005081347],"category_scores_gemma":[0.0018418037,0.000071937095,0.00014499374,0.0010572232,0.00022228192,0.00087617704,0.000021347538,0.00026909084,0.000039305694],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011965947,0.00016402708,0.1989762,7.863421e-7,0.00010675544,0.0000015704832,0.00773501,0.001529809,0.000008587137,0.00017457087,0.00497416,0.7863166],"study_design_scores_gemma":[0.0012892223,0.00084949797,0.8684277,0.0000957409,0.00025481754,0.00005167888,0.024907097,0.044228587,0.00000897217,0.016914342,0.042765863,0.00020648068],"about_ca_topic_score_codex":0.021821758,"about_ca_topic_score_gemma":0.6984774,"teacher_disagreement_score":0.7861101,"about_ca_system_score_codex":0.00022684064,"about_ca_system_score_gemma":0.003724285,"threshold_uncertainty_score":0.9998212},"labels":[],"label_agreement":null},{"id":"W1596745603","doi":"10.3138/cjpe.027.005","title":"Bamberger, Michael, Rugh, Jim, and Mabry, Linda. (2012). <i>Real World Evaluation: Working Under Budget, Time, Data, and Political Constraints</i> (2nd ed.). Thousand Oaks, CA: Sage. 666 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Politics; Economic history; Media studies; Gerontology; Sociology; Political science; History; Medicine; Law","score_opus":0.18890778587147808,"score_gpt":0.45984872552332184,"score_spread":0.27094093965184374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1596745603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8429125,0.04741677,0.0051109176,0.02941402,0.008736129,0.007799847,0.00041124359,0.00008955003,0.058109038],"genre_scores_gemma":[0.9933839,0.00023870518,0.003613438,0.0007370612,0.0010252526,0.000049436087,0.00012610292,0.000029111941,0.0007970312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925921,0.0014085716,0.0013608801,0.00050362374,0.003217881,0.0009169581],"domain_scores_gemma":[0.9942109,0.0009088225,0.00078792847,0.0006506423,0.0017388182,0.0017028842],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03265146,0.00031137967,0.00049862,0.0008293639,0.0005014343,0.0010543627,0.000548204,0.00017768073,0.008355154],"category_scores_gemma":[0.0014649846,0.00025953326,0.00008728475,0.00074391736,0.0006180567,0.0019533406,0.000102423975,0.00047900976,0.00011270918],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003539172,0.00009390558,0.08623342,0.000012081596,0.000111555855,0.0000073702304,0.0006459382,0.00015844358,0.000047183134,0.0017226655,0.04817069,0.8627614],"study_design_scores_gemma":[0.0061735543,0.0005236868,0.32273987,0.00042756693,0.0015772614,0.00073880976,0.005286636,0.16388266,0.000110207104,0.010584729,0.48678285,0.0011721862],"about_ca_topic_score_codex":0.00052693166,"about_ca_topic_score_gemma":0.014460982,"teacher_disagreement_score":0.8615892,"about_ca_system_score_codex":0.0005673881,"about_ca_system_score_gemma":0.0048225243,"threshold_uncertainty_score":0.9999857},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3230795,0.03350804,0.54567343,0.018434273,0.009170489,0.06943771,0.0003495809,0.0001295888,0.0002173919],"genre_scores_gemma":[0.7697516,0.0008650708,0.21634147,0.007066143,0.0012766137,0.0021729197,0.0023339214,0.0000846857,0.000107545886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99508965,0.002259422,0.0011868264,0.00022749742,0.0007239761,0.0005126203],"domain_scores_gemma":[0.99305296,0.0005074723,0.0012148173,0.0001546975,0.0043002316,0.00076983863],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0056955996,0.00017869422,0.0003024284,0.00032603316,0.0016432825,0.000042606614,0.000108419474,0.00018301257,0.00062206795],"category_scores_gemma":[0.0008656693,0.00017543836,0.00004470855,0.00043540786,0.000095121366,0.00036021805,0.00000990044,0.00030967215,0.000023358896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023733688,0.00020360136,0.018544512,0.00083798025,0.00014251452,3.6990193e-7,0.03374646,0.0027342588,0.000038371105,0.0033942652,0.027049204,0.91307116],"study_design_scores_gemma":[0.0155342715,0.00556298,0.01428574,0.004027039,0.0006671638,0.000038791157,0.039013542,0.32763493,0.00019658783,0.024555773,0.56764627,0.00083690154],"about_ca_topic_score_codex":0.0011521281,"about_ca_topic_score_gemma":0.007842158,"teacher_disagreement_score":0.91223425,"about_ca_system_score_codex":0.0022382522,"about_ca_system_score_gemma":0.009458385,"threshold_uncertainty_score":0.99965644},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9498256,0.00038577276,0.00051178737,0.019800132,0.0010851569,0.004280826,0.000016286862,0.000043190426,0.02405129],"genre_scores_gemma":[0.9982048,0.000025578645,0.00026883237,0.00071249506,0.00045951887,0.00008446757,0.00012806761,0.000015400807,0.000100793746],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977683,0.00015774391,0.000501159,0.00020038028,0.0009591046,0.00041331086],"domain_scores_gemma":[0.9973659,0.000028837483,0.0006103802,0.00015225336,0.0018064374,0.000036189347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040657725,0.00020247654,0.00023027748,0.0005102508,0.00053208147,0.000546968,0.0004536136,0.0001729986,0.00028155712],"category_scores_gemma":[0.00043343526,0.00017194884,0.000092233335,0.0007654186,0.00019726041,0.001627951,0.000050215593,0.00039683102,0.00003456434],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051674102,0.00014829957,0.005506403,0.00012067189,0.000149987,0.000044279637,0.0028222864,0.00017466828,0.000015235627,0.0070306673,0.14283074,0.8411051],"study_design_scores_gemma":[0.0033998943,0.00018430616,0.3307025,0.00015004558,0.0007341012,0.000018614935,0.032810114,0.00998917,0.000030909745,0.009180592,0.6120745,0.0007252726],"about_ca_topic_score_codex":0.0017358544,"about_ca_topic_score_gemma":0.003601271,"teacher_disagreement_score":0.84037983,"about_ca_system_score_codex":0.00095004967,"about_ca_system_score_gemma":0.0008681978,"threshold_uncertainty_score":0.701187},"labels":[],"label_agreement":null},{"id":"W1611881142","doi":"10.3138/cjpe.30.1.64","title":"Exploring the Leadership Dimension of Developmental Evaluation: The Evaluator as a Servant-Leader","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Servant leadership; Situational ethics; Leadership development; Situated; Psychology; Servant; Dimension (graph theory); Adaptation (eye); Applied psychology; Knowledge management; Computer science; Public relations; Social psychology; Leadership style; Political science; Artificial intelligence; Software engineering","score_opus":0.8742798159456303,"score_gpt":0.541068240408882,"score_spread":0.3332115755367483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1611881142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9743785,0.0013387072,0.00015987935,0.0168748,0.0020215313,0.0022547753,0.0000033059835,0.000008662094,0.0029597855],"genre_scores_gemma":[0.9974394,0.000010654086,0.001221593,0.00060257956,0.0002761204,0.0002507102,0.000008867381,0.00001496504,0.00017509927],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9879959,0.0023611118,0.0013947608,0.00025461963,0.007609979,0.0003836323],"domain_scores_gemma":[0.98848534,0.0006575296,0.0010890061,0.00047113735,0.0087936185,0.000503385],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.067509554,0.00018820804,0.00029231986,0.00047405428,0.0004233911,0.00036562615,0.00096792344,0.0000658768,0.0016607019],"category_scores_gemma":[0.010696696,0.00010035661,0.00017062166,0.0013067363,0.00027027793,0.0012348951,0.00003674313,0.0003391315,0.00021427401],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073892224,0.00005642104,0.011533383,0.000006637216,0.00009016189,0.0000033189485,0.022064995,0.008344198,0.000099286604,0.00049314747,0.007891587,0.94934297],"study_design_scores_gemma":[0.0071023786,0.0025062705,0.19854136,0.00043526836,0.0011509687,0.0005642766,0.31739128,0.31547427,0.0030360064,0.023390796,0.12966952,0.0007376097],"about_ca_topic_score_codex":0.0005954907,"about_ca_topic_score_gemma":0.008308214,"teacher_disagreement_score":0.94860536,"about_ca_system_score_codex":0.00095750357,"about_ca_system_score_gemma":0.01982355,"threshold_uncertainty_score":0.9992519},"labels":[],"label_agreement":null},{"id":"W1658636278","doi":"10.3138/cjpe.0028.004","title":"Introduction à la professionnalisation de l’évaluation : perspective globale sur les compétences des évaluateurs","year":2014,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.2965364943297302,"score_gpt":0.4989688669957872,"score_spread":0.20243237266605696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1658636278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8552853,0.010967167,0.039899208,0.07422197,0.0083395075,0.0026699246,0.000026192944,0.000040556795,0.008550164],"genre_scores_gemma":[0.97425234,0.0002954483,0.020702057,0.00018279869,0.0026876456,0.00010884271,0.000042576146,0.000028666458,0.0016996408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9841292,0.010200477,0.0015548909,0.000496148,0.0029467384,0.0006725686],"domain_scores_gemma":[0.98224354,0.0008491164,0.0016114316,0.000397511,0.014125447,0.0007729414],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.069766246,0.0003264517,0.00047017366,0.0009883501,0.0009508865,0.0009910959,0.0005975593,0.0003500249,0.0050129863],"category_scores_gemma":[0.01833701,0.00029203846,0.00026922362,0.0015460822,0.0008669293,0.0020564776,0.000024083818,0.0006032789,0.00013886935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008586707,0.00017462276,0.019889234,0.000040791554,0.00007495707,0.0000032123717,0.010375401,0.020269105,0.00009228635,0.01466203,0.008267547,0.92606497],"study_design_scores_gemma":[0.0020723732,0.002354024,0.13636222,0.0006242412,0.00067834667,0.0002956116,0.024224788,0.44980037,0.00022276628,0.21409756,0.16881359,0.00045407997],"about_ca_topic_score_codex":0.011808013,"about_ca_topic_score_gemma":0.0664695,"teacher_disagreement_score":0.92561084,"about_ca_system_score_codex":0.0031223383,"about_ca_system_score_gemma":0.015265293,"threshold_uncertainty_score":0.99995315},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760506,0.00097071705,0.00064820354,0.0020520948,0.0007832614,0.00876655,0.000006080875,0.00002084734,0.010701627],"genre_scores_gemma":[0.99254495,0.000007231068,0.005767976,0.00046615058,0.00036823886,0.00062429195,0.000046420755,0.000014143468,0.00016062395],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99609435,0.0013549372,0.0006663783,0.00031578273,0.0011874578,0.0003811275],"domain_scores_gemma":[0.9971735,0.0000712301,0.00046304832,0.00028107673,0.001583581,0.00042757846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017342174,0.0002008066,0.00019637374,0.0005274426,0.00043854146,0.00022993644,0.00027749155,0.00010660028,0.00034473356],"category_scores_gemma":[0.0005776681,0.00014997882,0.00006248871,0.0005386153,0.000066732224,0.0003428853,0.000009698892,0.00026883054,0.00004288964],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018781207,0.00004748555,0.00040312012,0.0000037910843,0.000101505226,0.0000050827234,0.037399102,0.0012395093,0.00005455128,0.0011977206,0.0025583596,0.95680195],"study_design_scores_gemma":[0.005367289,0.004389231,0.8904018,0.00019822575,0.0009307844,0.00008451681,0.005254802,0.021958593,0.00010476581,0.009766259,0.061120722,0.00042302778],"about_ca_topic_score_codex":0.00013550623,"about_ca_topic_score_gemma":0.0017437545,"teacher_disagreement_score":0.95637894,"about_ca_system_score_codex":0.000620087,"about_ca_system_score_gemma":0.00048804385,"threshold_uncertainty_score":0.6115959},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85893136,0.016890595,0.091314055,0.0067676017,0.000768924,0.012031073,0.0000044769013,0.000038900744,0.013253042],"genre_scores_gemma":[0.9453751,0.00003810703,0.05374508,0.00003258929,0.00026445536,0.00016034338,0.0000015200725,0.000014095564,0.0003687113],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96378016,0.032943554,0.00048208234,0.00023560511,0.0019975964,0.000561027],"domain_scores_gemma":[0.9879221,0.0014622118,0.0002246231,0.00019471816,0.008571646,0.001624719],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13000378,0.000111416186,0.00028869198,0.0009188388,0.00090188085,0.00055138447,0.0003479343,0.00007868379,0.0004392636],"category_scores_gemma":[0.012104235,0.00009938134,0.00006347804,0.0012600963,0.000714916,0.0005516117,0.000026865657,0.0005122131,0.000044898785],"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":[0.000062603016,0.00029232437,0.010243292,0.0000067166047,0.00025819632,0.0006884043,0.17620194,0.00057265407,0.00004626918,0.0012479838,0.06313013,0.7472495],"study_design_scores_gemma":[0.0031673233,0.0059155975,0.0027393063,0.000067822126,0.0004023678,0.0003603138,0.7070971,0.021209463,0.000112537164,0.03387226,0.22457787,0.0004780347],"about_ca_topic_score_codex":0.06006487,"about_ca_topic_score_gemma":0.1763618,"teacher_disagreement_score":0.74677145,"about_ca_system_score_codex":0.001076443,"about_ca_system_score_gemma":0.011271776,"threshold_uncertainty_score":0.99621725},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99443513,0.00013578088,0.0005646181,0.0021040144,0.00076402654,0.0005599895,0.000004824366,0.000002862255,0.0014287361],"genre_scores_gemma":[0.9975237,0.0000033999577,0.0019972553,0.00020428166,0.00007704582,0.000020479718,0.0000021267053,0.000005929445,0.00016576743],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946891,0.001783333,0.0010163576,0.00014707584,0.0021482983,0.00021584526],"domain_scores_gemma":[0.9962227,0.0006618342,0.0007196767,0.00039034232,0.0018073245,0.00019812932],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035467044,0.00008869215,0.00023233243,0.00064533384,0.0001191595,0.00014880614,0.0006272635,0.000056752124,0.0025275978],"category_scores_gemma":[0.0034789434,0.000056456065,0.00012284199,0.0011047948,0.00014834011,0.00031474838,0.000016137174,0.0001865952,0.000028499468],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014490206,0.000070918635,0.2865972,0.0000066258694,0.0000176736,0.000002567411,0.0054339864,0.004673774,0.0012134586,0.0034921817,0.01087097,0.68747574],"study_design_scores_gemma":[0.00088087795,0.00069706334,0.6254288,0.00003264284,0.000016290604,0.000022332562,0.0010146908,0.0063165855,0.00031537062,0.007775457,0.35741737,0.00008251859],"about_ca_topic_score_codex":0.00069834053,"about_ca_topic_score_gemma":0.028779041,"teacher_disagreement_score":0.68739325,"about_ca_system_score_codex":0.00029489104,"about_ca_system_score_gemma":0.004113502,"threshold_uncertainty_score":0.99838424},"labels":[],"label_agreement":null},{"id":"W1688463168","doi":"10.3138/cjpe.30.1.99","title":"McDavid, J. C., Huse, I., &amp; Hawthorn, L. R. L. (2013). <i>Program Evaluation and Performance Measurement: An Introduction to Practice (2nd ed.).</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"SAGE; Psychology; Sociology; Library science; Computer science; Physics; Nuclear physics","score_opus":0.4454211636939176,"score_gpt":0.5224499535137422,"score_spread":0.07702878981982464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1688463168","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89109904,0.005220444,0.0066035036,0.07016871,0.0090706395,0.013540212,0.000018000957,0.00011233936,0.0041671433],"genre_scores_gemma":[0.95079774,0.00009349319,0.045068517,0.0008195569,0.0022017448,0.0007393796,0.00006743162,0.00003768024,0.0001744734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9865812,0.0022847499,0.0015846257,0.0006309751,0.008364446,0.0005540208],"domain_scores_gemma":[0.9701762,0.00015902352,0.0012264615,0.0007454481,0.025907904,0.0017849215],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.092325784,0.00029045698,0.00041062388,0.0011810751,0.0004404948,0.001333436,0.0005931676,0.00016223814,0.00092025683],"category_scores_gemma":[0.019842615,0.0002476252,0.00009339632,0.0014789508,0.00013699022,0.004159481,0.00003438337,0.00041925296,0.00022227477],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017054618,0.00016450194,0.00439332,0.000006834644,0.000040321436,0.0000013450942,0.0020325978,0.00831285,0.00004781897,0.00006958533,0.04668925,0.938071],"study_design_scores_gemma":[0.0017400312,0.0031942292,0.017640729,0.0000463701,0.00034451773,0.0001769117,0.0021053532,0.06597871,0.000062121595,0.0011785891,0.9072153,0.00031714325],"about_ca_topic_score_codex":0.00082128623,"about_ca_topic_score_gemma":0.028914152,"teacher_disagreement_score":0.9377539,"about_ca_system_score_codex":0.0014908459,"about_ca_system_score_gemma":0.008658291,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7880621,0.057588253,0.0005150308,0.1085399,0.030725589,0.004508326,0.000043499927,0.000030732903,0.009986546],"genre_scores_gemma":[0.9749714,0.00093099975,0.0028262942,0.0050363317,0.013758344,0.00007631981,0.000042355998,0.00005844945,0.002299495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99063075,0.0055932594,0.0012839029,0.00016137726,0.0008718105,0.0014588931],"domain_scores_gemma":[0.99262065,0.0007196042,0.0008733633,0.00027407974,0.001919676,0.0035926139],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027945027,0.00023441199,0.00046868774,0.00028477568,0.0006847585,0.000044810873,0.00027410442,0.0011976488,0.006912115],"category_scores_gemma":[0.006762088,0.00022177005,0.00022649988,0.0004957877,0.00018389571,0.00075771153,0.000015403011,0.0031508412,0.00054312876],"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":[0.000011093539,0.0001738538,0.08071266,0.00039660637,0.00011009105,0.000016967508,0.0971531,0.000017627473,0.000009412033,0.001392003,0.15134892,0.66865766],"study_design_scores_gemma":[0.0015279605,0.0005121463,0.12238609,0.0007879999,0.00046202386,0.00007545005,0.018308941,0.0012971115,0.000004534524,0.0004251658,0.85402423,0.00018832121],"about_ca_topic_score_codex":0.011442679,"about_ca_topic_score_gemma":0.02612233,"teacher_disagreement_score":0.70267534,"about_ca_system_score_codex":0.0028351448,"about_ca_system_score_gemma":0.023673525,"threshold_uncertainty_score":0.9991489},"labels":[],"label_agreement":null},{"id":"W1700780107","doi":"10.3138/cjpe.0028.006","title":"Evaluator Competencies: The Canadian Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Engineering ethics; Context (archaeology); Political science; Psychology; Sociology; Public relations; Management; Engineering; History; Law","score_opus":0.36189769178651315,"score_gpt":0.5260247839748239,"score_spread":0.16412709218831073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1700780107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91652256,0.00085300417,0.0021480932,0.025982305,0.0047823973,0.002723355,0.000013483178,0.00002222019,0.0469526],"genre_scores_gemma":[0.99634606,0.0000034015009,0.0016682553,0.0013213819,0.0003248088,0.0000882931,0.0000050138456,0.000009712614,0.00023306503],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936276,0.0011964686,0.00097487005,0.00022544443,0.003518889,0.000456721],"domain_scores_gemma":[0.9925585,0.00048556697,0.00064116635,0.0005516667,0.004682443,0.0010806737],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031174932,0.00014419107,0.00023345728,0.0006912653,0.00096278917,0.0009863564,0.001173106,0.000087475455,0.004890842],"category_scores_gemma":[0.00868959,0.00008814901,0.00014537784,0.0010004417,0.0002788492,0.0006024689,0.000012933352,0.0002878207,0.00030257294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006124753,0.000015275364,0.040434137,0.0000018261464,0.000020041616,0.0000029113935,0.0058868425,0.0035147497,0.000018814973,0.0036942847,0.009606996,0.936798],"study_design_scores_gemma":[0.000586992,0.00037094706,0.14086269,0.000028674576,0.000058016678,0.000061057486,0.00340962,0.18189299,0.00004260425,0.011544553,0.66096973,0.0001721335],"about_ca_topic_score_codex":0.07267068,"about_ca_topic_score_gemma":0.9269716,"teacher_disagreement_score":0.93662584,"about_ca_system_score_codex":0.0008618571,"about_ca_system_score_gemma":0.015880954,"threshold_uncertainty_score":0.9996606},"labels":[],"label_agreement":null},{"id":"W1701527280","doi":"","title":"King, J. A., & Stevahn, L. (2013). Interactive Evaluation Practice: Mastering the Interpersonal Dynamics of Program Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dynamics (music); Interpersonal communication; Psychology; Interpersonal relationship; Applied psychology; Social psychology; Pedagogy","score_opus":0.29701047840383554,"score_gpt":0.5445591158437647,"score_spread":0.24754863743992916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1701527280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92683095,0.0015826722,0.0051974915,0.02719356,0.004764677,0.020848418,0.000025196081,0.000040089573,0.013516963],"genre_scores_gemma":[0.9909401,0.000020182253,0.006720948,0.0002448648,0.0002881937,0.0015890903,0.000076689146,0.000026278996,0.00009363383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98559874,0.0035366276,0.0021295836,0.00043290987,0.0078038992,0.00049822096],"domain_scores_gemma":[0.9696128,0.0010738553,0.003229207,0.0006362311,0.025019346,0.00042860606],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05144329,0.00029279004,0.00043536827,0.0010085256,0.00037166633,0.0013537024,0.0009799715,0.00016480846,0.01067692],"category_scores_gemma":[0.01443191,0.00020248661,0.00027382877,0.0012727102,0.00026015218,0.004076652,0.00005735023,0.0005941084,0.00020010164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053788543,0.00015377047,0.0039314367,0.000009375816,0.00012790777,0.000001030336,0.003661172,0.008165937,0.00005703431,0.00017866533,0.0024613529,0.98119855],"study_design_scores_gemma":[0.0014753954,0.001144537,0.047944035,0.00016598414,0.000564154,0.00008472572,0.018048054,0.90927386,0.00006503767,0.0060080485,0.015011633,0.00021451521],"about_ca_topic_score_codex":0.0028140908,"about_ca_topic_score_gemma":0.030148966,"teacher_disagreement_score":0.98098403,"about_ca_system_score_codex":0.0021142934,"about_ca_system_score_gemma":0.007869059,"threshold_uncertainty_score":0.99968296},"labels":[],"label_agreement":null},{"id":"W1720965121","doi":"10.3138/cjpe.28.001","title":"Measuring Organizational Evaluation Capacity in the Canadian Federal Government","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Saint Paul University; Carleton University; École Nationale d'Administration Publique","funders":"","keywords":"Government (linguistics); Identification (biology); Organization development; Business; Evaluation methods; Organizational effectiveness; Organizational learning; Organizational identification; Public relations; Process management; Organizational commitment; Knowledge management; Political science; Computer science; Engineering","score_opus":0.5879919298116747,"score_gpt":0.4514966114809471,"score_spread":0.1364953183307276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1720965121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96937543,0.00016347649,0.00017823227,0.012695644,0.00082978647,0.0027482733,0.000009060739,0.000004392744,0.013995704],"genre_scores_gemma":[0.9976972,0.0000020508205,0.0010447514,0.0007699055,0.00020085777,0.00020690056,0.00001590529,0.0000093738045,0.000053080494],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98997384,0.0014660769,0.0009977651,0.00021529279,0.0069556595,0.00039136998],"domain_scores_gemma":[0.99312586,0.0002471033,0.00054846436,0.00030832842,0.0052393572,0.0005309196],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034078192,0.00014051955,0.00018818994,0.00053922815,0.0005719237,0.0013775311,0.0006910252,0.0000983563,0.008415329],"category_scores_gemma":[0.0062744627,0.000096590265,0.00008399943,0.0011660238,0.00008285926,0.0010360737,0.000008824198,0.00032009534,0.00023655027],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052069113,0.00006601281,0.36801237,0.0000036660288,0.00003054914,0.0000042802067,0.0051844027,0.01159351,0.000046744604,0.0014999626,0.008538914,0.6050144],"study_design_scores_gemma":[0.0008491836,0.00014267981,0.8455033,0.000028657709,0.000041643736,0.000045529454,0.002684727,0.122380644,0.00003949021,0.01958001,0.008557946,0.0001462025],"about_ca_topic_score_codex":0.13232444,"about_ca_topic_score_gemma":0.948618,"teacher_disagreement_score":0.81629354,"about_ca_system_score_codex":0.0035107515,"about_ca_system_score_gemma":0.013134344,"threshold_uncertainty_score":0.9996591},"labels":[],"label_agreement":null},{"id":"W1723825527","doi":"","title":"Contributing Factors to the Continued Blurring of Research and Evaluation: Strategies for Moving Forward","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Confusion; Terminology; Political science; Humanities; Psychology; Philosophy","score_opus":0.5525192653748852,"score_gpt":0.6023241883787067,"score_spread":0.049804923003821555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1723825527","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98349273,0.00027839927,0.009238467,0.003210124,0.000470454,0.0023918794,0.0000095015575,0.0000038514427,0.00090457755],"genre_scores_gemma":[0.99784285,0.0000017633306,0.0017261257,0.000050789604,0.00020373368,0.00012323058,0.0000063526973,0.00000719059,0.00003798495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944559,0.0010735667,0.0009121165,0.00019489261,0.0029941422,0.00036938462],"domain_scores_gemma":[0.985023,0.0021720764,0.0005987038,0.00025542246,0.011639814,0.0003109524],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09206989,0.00009541503,0.00025020813,0.00063317566,0.00054735946,0.0006758998,0.00042933342,0.00005897651,0.00020432434],"category_scores_gemma":[0.019291226,0.00006120194,0.000079827776,0.0007328683,0.00013383226,0.0005045364,0.00002489952,0.00018422236,0.0000041409457],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004635203,0.000024196546,0.053295493,0.000018179784,0.00004681656,2.2090423e-7,0.0072000017,0.013966802,0.00021300119,0.0064587733,0.0017563268,0.9169738],"study_design_scores_gemma":[0.0027099515,0.0024739606,0.23714213,0.00025189004,0.00017560388,0.000011640575,0.042325076,0.58124167,0.0009458035,0.091983415,0.04051334,0.00022554137],"about_ca_topic_score_codex":0.00039724528,"about_ca_topic_score_gemma":0.015078692,"teacher_disagreement_score":0.9167483,"about_ca_system_score_codex":0.00023272456,"about_ca_system_score_gemma":0.0036672093,"threshold_uncertainty_score":0.9889697},"labels":[],"label_agreement":null},{"id":"W1724770786","doi":"10.3138/cjpe.30.1.23","title":"Reflexivity in Evaluating an Aboriginal Women Heart Health Promotion Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"B.C. Women's Hospital & Health Centre","funders":"","keywords":"Reflexivity; Context (archaeology); Process (computing); Promotion (chess); Rework; Sociology; Power (physics); Psychology; Computer science; Political science; Social science","score_opus":0.6574517143601347,"score_gpt":0.6690681666853625,"score_spread":0.011616452325227788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1724770786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898873,0.0002455334,0.00023882133,0.0052304645,0.00088268175,0.0025039893,0.000004562412,0.000026610067,0.0009800423],"genre_scores_gemma":[0.97892886,0.000005345002,0.02003118,0.00026806726,0.0002868173,0.0003658955,0.000023422339,0.000015399402,0.0000750365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9903514,0.002829826,0.00161485,0.0003705458,0.0041680215,0.0006653506],"domain_scores_gemma":[0.992336,0.000108794426,0.0010940818,0.0004149587,0.004376627,0.0016695863],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0842098,0.00018116312,0.0004293545,0.0011682493,0.00021065501,0.00063363585,0.0005043781,0.00010084556,0.00068120926],"category_scores_gemma":[0.003290886,0.00014953622,0.00008381655,0.0016540266,0.000094813986,0.001812091,0.0000106653615,0.00039789386,0.00006560972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049633323,0.0003443919,0.056346968,0.000007845292,0.0000078684825,0.000003840615,0.0060884655,0.0038190568,0.00001567732,0.00018376335,0.000943326,0.93218917],"study_design_scores_gemma":[0.0057404544,0.029070377,0.34797975,0.0002620389,0.00004250948,0.00018401764,0.012537658,0.44239467,0.000046499757,0.0397419,0.12145916,0.0005409378],"about_ca_topic_score_codex":0.0015898745,"about_ca_topic_score_gemma":0.048774797,"teacher_disagreement_score":0.93164825,"about_ca_system_score_codex":0.003112326,"about_ca_system_score_gemma":0.029185064,"threshold_uncertainty_score":0.97631854},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1727891101","doi":"","title":"S. N. Hesse-Biber. (2010). Mixed Methods Research: Merging Theory with Practice. New York, NY: Guildford. 242 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Sociology; Information retrieval; Computer science","score_opus":0.7558464177977277,"score_gpt":0.634052245019063,"score_spread":0.12179417277866467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1727891101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29800794,0.06606645,0.28605396,0.122990474,0.025756769,0.014784735,0.000032243755,0.00020450098,0.18610293],"genre_scores_gemma":[0.76379395,0.000076098164,0.23180969,0.0005615311,0.0011336548,0.00010337666,0.000013466132,0.00004216533,0.0024660944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9840943,0.008182966,0.0012446824,0.00032887392,0.0052082334,0.000940895],"domain_scores_gemma":[0.98693144,0.0035876725,0.0012158124,0.0006990973,0.005867297,0.0016986794],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16947855,0.00022005514,0.00038762914,0.0015544608,0.0005842444,0.0009099912,0.0008894643,0.00014610282,0.004230434],"category_scores_gemma":[0.024021843,0.00015017741,0.00014829922,0.0022683947,0.00024797916,0.0027309724,0.00003746582,0.0007942582,0.00023125806],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008663866,0.000068307316,0.004157092,0.0000042721126,0.00008408856,0.000005843816,0.0036362577,0.0005239592,0.000054418768,0.0026903034,0.057015385,0.9316734],"study_design_scores_gemma":[0.0015985556,0.0009945132,0.033919524,0.00012816694,0.00031298888,0.0002446962,0.018073032,0.0058001885,0.0006185965,0.024429286,0.91354406,0.00033636764],"about_ca_topic_score_codex":0.0010128497,"about_ca_topic_score_gemma":0.008278984,"teacher_disagreement_score":0.93133706,"about_ca_system_score_codex":0.00073335896,"about_ca_system_score_gemma":0.0118340235,"threshold_uncertainty_score":0.99667984},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96758306,0.0013512081,0.0021204366,0.017977472,0.0007222543,0.006695205,0.00041339075,0.000012334268,0.003124659],"genre_scores_gemma":[0.99265647,0.000003205204,0.0058924053,0.00012705845,0.0006114522,0.00028423933,0.0000035876424,0.000012043831,0.00040953158],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986521,0.00023955083,0.00022096567,0.00007336729,0.00036605177,0.0004479446],"domain_scores_gemma":[0.99794316,0.0004954325,0.00040483155,0.000085941516,0.0006991933,0.00037143668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038717024,0.00007859188,0.00014138581,0.00008289005,0.0005774154,0.00017207347,0.00017072934,0.000058987538,0.000043429725],"category_scores_gemma":[0.0027733815,0.00005855243,0.00010743582,0.00022088335,0.00037332883,0.00070705806,0.0000022871952,0.00009396535,1.622997e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008334239,0.000074070194,0.015742872,0.00009487918,0.00014885045,3.947037e-7,0.08846341,0.000084414125,0.000011070507,0.045190945,0.008417979,0.8416878],"study_design_scores_gemma":[0.0011509244,0.0005773024,0.06760819,0.00022157733,0.00040868798,0.000013049099,0.10951725,0.0008094804,0.00013226803,0.004029039,0.81529254,0.00023970765],"about_ca_topic_score_codex":0.06906276,"about_ca_topic_score_gemma":0.33781847,"teacher_disagreement_score":0.84144807,"about_ca_system_score_codex":0.0005708616,"about_ca_system_score_gemma":0.0045054154,"threshold_uncertainty_score":0.9371364},"labels":[],"label_agreement":null},{"id":"W1731692312","doi":"10.3138/cjpe.023.010","title":"Professional Identity of Evaluators in Israel","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diversity (politics); Identity (music); Context (archaeology); Public relations; Professional association; Professional development; Political science; Publication; Sociology; Pedagogy; Law; Geography","score_opus":0.5165946088532868,"score_gpt":0.591396369755435,"score_spread":0.07480176090214818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1731692312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99498165,0.000386979,0.0002394747,0.0008648437,0.0011319966,0.00073221774,0.000004538316,0.0000029623898,0.0016553691],"genre_scores_gemma":[0.997711,0.000014034973,0.001844072,0.000094106974,0.00009185199,0.00003373078,0.000005145343,0.000006281554,0.00019979622],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9935228,0.0008191996,0.0014079206,0.0001705669,0.003840655,0.00023881393],"domain_scores_gemma":[0.99390656,0.00023069062,0.0012767614,0.0002512719,0.004007021,0.00032769778],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021700958,0.0001018093,0.0002923712,0.0012058287,0.00014803764,0.000064768035,0.0005260654,0.00008624579,0.0023626648],"category_scores_gemma":[0.0060066134,0.000078418096,0.00013555147,0.0013552338,0.00015957993,0.0012025138,0.00001598131,0.0002335529,0.000057154397],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027148848,0.000118266194,0.77717155,0.0000058761616,0.000015777463,0.000013702463,0.001813459,0.0025934288,0.0000841317,0.00094179506,0.0024764384,0.2147384],"study_design_scores_gemma":[0.0013471084,0.0003400268,0.95414096,0.000078068326,0.000030734212,0.00006859617,0.0017825165,0.025649356,0.00017552871,0.012397327,0.0038781913,0.00011158574],"about_ca_topic_score_codex":0.0012523024,"about_ca_topic_score_gemma":0.034479685,"teacher_disagreement_score":0.2146268,"about_ca_system_score_codex":0.00042564768,"about_ca_system_score_gemma":0.011557061,"threshold_uncertainty_score":0.9985493},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5565518,0.101162985,0.0033250558,0.18305494,0.012315931,0.01162755,0.00028848715,0.00011881994,0.1315544],"genre_scores_gemma":[0.995985,0.0007240142,0.0017808027,0.0001891443,0.00063748733,0.00004138064,0.000023222137,0.000014769671,0.00060423673],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99237955,0.0041027567,0.00063678017,0.00020271157,0.0019215938,0.00075663364],"domain_scores_gemma":[0.9964759,0.00062905473,0.0006200168,0.00038485348,0.0010652672,0.0008249492],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.050399814,0.0001364001,0.00028359634,0.00019859931,0.0007570193,0.000347188,0.0013459488,0.000111147674,0.0012767698],"category_scores_gemma":[0.00560699,0.00010079376,0.00011066559,0.00062301947,0.0011094221,0.0017093463,0.00008930217,0.00041733266,0.00004392834],"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":[0.000017380076,0.00012588142,0.01208139,0.000032371765,0.00014700361,0.000006163324,0.23547241,0.00004246432,0.000089431356,0.0024949224,0.08699981,0.6624908],"study_design_scores_gemma":[0.000646965,0.00034142693,0.029586796,0.00033307177,0.00019398432,0.00001200175,0.1285197,0.0006723164,0.0001105555,0.005916466,0.8333237,0.00034296612],"about_ca_topic_score_codex":0.035596386,"about_ca_topic_score_gemma":0.23218414,"teacher_disagreement_score":0.74632394,"about_ca_system_score_codex":0.0005825427,"about_ca_system_score_gemma":0.005079588,"threshold_uncertainty_score":0.9996362},"labels":[],"label_agreement":null},{"id":"W1746934302","doi":"10.3138/cjpe.0028.012","title":"Evaluator Competencies and Professionalizing the Field: Where Are We Now?","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Professionalization; Globe; Narrative; Field (mathematics); Core competency; Happening; Engineering ethics; Sociology; Epistemology; Pedagogy; Psychology; Management; Engineering; Social science; Linguistics; History; Philosophy","score_opus":0.27667815328718687,"score_gpt":0.51874720227499,"score_spread":0.24206904898780318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1746934302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.661557,0.0075194705,0.003806208,0.31475365,0.0033898423,0.002640774,0.000008162366,0.00002454613,0.0063003153],"genre_scores_gemma":[0.99577975,0.00010206976,0.0021107898,0.0012770781,0.00030693036,0.000053510415,0.0000018397059,0.000008042242,0.00036000935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99558544,0.0011082382,0.00069597765,0.00017314001,0.002208029,0.00022919157],"domain_scores_gemma":[0.99503845,0.0011835634,0.0007570415,0.0002833003,0.0024096526,0.0003279956],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020262536,0.00011406765,0.00021193699,0.0002988071,0.0004910763,0.00046541955,0.00045429647,0.00007229306,0.0016228047],"category_scores_gemma":[0.0034514957,0.00006473122,0.00008447996,0.00042517326,0.00011539815,0.00044991885,0.000023147282,0.00025713988,0.000046765832],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013325651,0.000018397664,0.07032406,0.000010817682,0.000021844942,0.0000014599445,0.0017240966,0.000585368,0.00002581445,0.0012867008,0.05593716,0.87005097],"study_design_scores_gemma":[0.00080454425,0.0004739039,0.115902685,0.00023001556,0.00008985761,0.00004401563,0.005221462,0.12490412,0.000043148444,0.021762721,0.7303718,0.00015173755],"about_ca_topic_score_codex":0.00012915608,"about_ca_topic_score_gemma":0.027589168,"teacher_disagreement_score":0.8698992,"about_ca_system_score_codex":0.000121379504,"about_ca_system_score_gemma":0.002199836,"threshold_uncertainty_score":0.9992899},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15284635,0.0022714182,0.7522113,0.018991282,0.00043477246,0.007420511,0.000049670358,0.00006446463,0.06571024],"genre_scores_gemma":[0.236042,0.00006085465,0.7629043,0.0000886287,0.00017079768,0.00040685007,0.000014104575,0.00001925324,0.0002932207],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97154886,0.025488615,0.0006078282,0.000337678,0.0013053383,0.000711692],"domain_scores_gemma":[0.98932177,0.004005852,0.00027316934,0.0002661682,0.004391607,0.0017414071],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13322388,0.00013626572,0.00029809366,0.0007968345,0.0012132232,0.00040920792,0.00051022985,0.00012806078,0.00027033294],"category_scores_gemma":[0.019406304,0.0001274161,0.000048431575,0.0012830718,0.00090861047,0.00050920306,0.000025985972,0.00046066457,0.000026965843],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020428646,0.000036304868,0.000030101677,0.000009294149,0.000018953995,4.738473e-7,0.038290255,0.000013124505,0.0014076345,0.30211353,0.0033790327,0.65468085],"study_design_scores_gemma":[0.0005158469,0.0014300124,0.0031645736,0.00006752401,0.000043287357,0.000002016674,0.135932,0.0007364781,0.00040378506,0.22219369,0.6352483,0.00026251475],"about_ca_topic_score_codex":0.012132841,"about_ca_topic_score_gemma":0.096815735,"teacher_disagreement_score":0.65441835,"about_ca_system_score_codex":0.00045713555,"about_ca_system_score_gemma":0.0037141563,"threshold_uncertainty_score":0.99444544},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91536313,0.0014649505,0.030387638,0.019860791,0.008992401,0.02251944,0.00038023194,0.00001938925,0.0010120387],"genre_scores_gemma":[0.9822046,0.0000020727186,0.015637826,0.0002443311,0.00046186135,0.0012163088,0.00011949363,0.000016734899,0.00009672683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912493,0.0008931622,0.001296657,0.00024293805,0.005928547,0.00038935174],"domain_scores_gemma":[0.976522,0.0007736501,0.0011628943,0.00038307058,0.020487754,0.0006705731],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.119444855,0.00016329235,0.00024617524,0.00035220975,0.0013298601,0.00042598275,0.0007535038,0.00014124392,0.00040877808],"category_scores_gemma":[0.007435805,0.00009033641,0.0002123744,0.0005808564,0.00015514059,0.0007293827,0.000011781632,0.00021362572,0.000004448323],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107924636,0.00004164055,0.0016850134,0.000010287489,0.00009495397,7.520438e-8,0.011813538,0.009294713,0.000022598553,0.0002789198,0.021058168,0.95559216],"study_design_scores_gemma":[0.0029041213,0.00083309517,0.028908325,0.000060016973,0.00035215862,0.000011223468,0.021144694,0.63838863,0.00029925597,0.013191081,0.2937275,0.00017991035],"about_ca_topic_score_codex":0.0047379625,"about_ca_topic_score_gemma":0.78774965,"teacher_disagreement_score":0.95541227,"about_ca_system_score_codex":0.0030097403,"about_ca_system_score_gemma":0.1187729,"threshold_uncertainty_score":0.99997026},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63851506,0.010896616,0.00024982626,0.2756734,0.031354245,0.0012097901,0.00002132872,0.000015328582,0.042064387],"genre_scores_gemma":[0.9849171,0.000491058,0.0038276927,0.00021749924,0.009197098,0.000030660947,0.00001419658,0.000014664428,0.0012900548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973172,0.0011683655,0.0004414872,0.00014889588,0.0005104385,0.00041361066],"domain_scores_gemma":[0.9958809,0.0002758885,0.0009793575,0.00022343121,0.0019610876,0.00067935494],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012539515,0.00012414568,0.00019023428,0.00014844994,0.0022747375,0.00045303075,0.00057054707,0.00021924837,0.00126772],"category_scores_gemma":[0.0073701823,0.0001363813,0.00014718235,0.0001433029,0.0017511062,0.0008057248,0.0000073754777,0.00031419905,0.00006095048],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019192605,0.00007374347,0.046946123,0.0000128351385,0.00009712145,0.0000067364167,0.028263146,0.000037672708,0.0000027039112,0.072431944,0.004070331,0.8480557],"study_design_scores_gemma":[0.00073279225,0.0002941128,0.29750833,0.00018918948,0.0003563296,0.000049269307,0.025723543,0.00083132,0.0000066186526,0.036290053,0.63777953,0.00023890415],"about_ca_topic_score_codex":0.013452414,"about_ca_topic_score_gemma":0.038210124,"teacher_disagreement_score":0.8478168,"about_ca_system_score_codex":0.00061583315,"about_ca_system_score_gemma":0.008102176,"threshold_uncertainty_score":0.99964523},"labels":[],"label_agreement":null},{"id":"W1758177958","doi":"10.3138/cjpe.29.3.86","title":"View from the Credentialing Board: Where We've Been and Where We're Going","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Northwest Territories; Barrie Urology Group","funders":"","keywords":"Credentialing; On board; Editorial board; Psychology; Engineering ethics; Medical education; Management; Computer science; Library science; Engineering; Medicine","score_opus":0.4342804105770348,"score_gpt":0.5121123250234277,"score_spread":0.07783191444639292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1758177958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7009358,0.15436551,0.0032217926,0.12756038,0.004674381,0.0029791538,0.000052645137,0.000036370897,0.0061739907],"genre_scores_gemma":[0.9925637,0.0011216986,0.004496711,0.0005207267,0.0007999169,0.000041853466,0.0000115951325,0.000018907494,0.00042487073],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99524385,0.0008757367,0.0008802396,0.00023664719,0.0024855512,0.00027795686],"domain_scores_gemma":[0.9957508,0.00041518823,0.0007117679,0.00032330208,0.0021411872,0.0006577716],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014447307,0.00014809848,0.00027014443,0.00022330701,0.00034069733,0.001218063,0.0005523192,0.00009423861,0.00210463],"category_scores_gemma":[0.0016557542,0.000095897274,0.00010244342,0.0004913503,0.00010654813,0.0008606438,0.000030650644,0.00028736974,0.0001258195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014683463,0.000013538648,0.028135052,0.000007573422,0.000044452878,0.0000062550644,0.006871191,0.0008475753,0.000013369211,0.000096705386,0.03992717,0.92402244],"study_design_scores_gemma":[0.0020040926,0.00048268164,0.026797026,0.00074960955,0.00030414914,0.000042211286,0.027142843,0.07422037,0.000030161604,0.021558415,0.84638494,0.0002835278],"about_ca_topic_score_codex":0.0017876322,"about_ca_topic_score_gemma":0.15782678,"teacher_disagreement_score":0.9237389,"about_ca_system_score_codex":0.00030990003,"about_ca_system_score_gemma":0.0041759685,"threshold_uncertainty_score":0.99981874},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9757148,0.0028783511,0.00018414768,0.008182096,0.0011572222,0.0030574198,0.000006139043,0.000019886955,0.008799944],"genre_scores_gemma":[0.99508953,0.00005169128,0.0017829445,0.00013150286,0.00049444905,0.00044588617,0.00003445026,0.000022155064,0.0019473995],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966641,0.0012716185,0.0006943069,0.0001631327,0.00056523154,0.00064160465],"domain_scores_gemma":[0.9953484,0.00027332173,0.00038044018,0.00021092118,0.0031510026,0.0006359217],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0064614285,0.00010403228,0.0001779019,0.000992897,0.00076614425,0.0001547071,0.0002204117,0.00016119055,0.0027862703],"category_scores_gemma":[0.002069142,0.00009722088,0.000049851573,0.0009434872,0.0001267553,0.0011965736,0.000011083095,0.00084065855,0.00021983353],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014396525,0.00021972178,0.08650059,0.00006736265,0.000042418964,0.0000046441182,0.035950623,0.00044581096,0.00018995965,0.00057980313,0.1366196,0.73936504],"study_design_scores_gemma":[0.0022803643,0.00075893616,0.41881052,0.0016689601,0.000088831075,0.000034811506,0.10365137,0.0100455005,0.000041342017,0.023836385,0.43823925,0.00054375967],"about_ca_topic_score_codex":0.014243975,"about_ca_topic_score_gemma":0.053425953,"teacher_disagreement_score":0.7388213,"about_ca_system_score_codex":0.0018380774,"about_ca_system_score_gemma":0.008935852,"threshold_uncertainty_score":0.9981253},"labels":[],"label_agreement":null},{"id":"W1767493202","doi":"","title":"The 5 Cs for innovating in evaluation: Lessons from the field","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Excellence; Courage; Coaching; Humanities; Political science; Sociology; Management; Art; Economics","score_opus":0.5293170350997406,"score_gpt":0.5948341961710625,"score_spread":0.06551716107132188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1767493202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7709296,0.0020506224,0.0032893845,0.21023566,0.0026689789,0.0066294475,0.000013298142,0.000008153687,0.004174906],"genre_scores_gemma":[0.99489844,0.000010634173,0.0024937526,0.0014726244,0.00035559165,0.00066324597,0.000012121581,0.000006899301,0.000086704385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956437,0.00078588387,0.0010327911,0.00016105798,0.0021074228,0.00026914504],"domain_scores_gemma":[0.9885219,0.00464954,0.0007307067,0.0003618914,0.005590657,0.00014531458],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03478024,0.00009406649,0.00014816849,0.00021163355,0.0005573776,0.0009869754,0.0007141387,0.000067372755,0.0019074812],"category_scores_gemma":[0.022350699,0.000049407783,0.00009040958,0.0008848711,0.000070393624,0.0005700022,0.000014215486,0.00024269728,0.000048424085],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006017097,0.000008869807,0.015049563,5.151868e-7,0.000012486088,1.6198634e-7,0.0008273089,0.0008907751,0.00001323154,0.0009852444,0.0275379,0.9546679],"study_design_scores_gemma":[0.0012957426,0.00028942447,0.3096844,0.000056844525,0.000061469465,0.0000043782356,0.0046412037,0.43540618,0.00007100738,0.119301274,0.12906657,0.00012152551],"about_ca_topic_score_codex":0.0027463413,"about_ca_topic_score_gemma":0.07745856,"teacher_disagreement_score":0.9545464,"about_ca_system_score_codex":0.00030134135,"about_ca_system_score_gemma":0.004691143,"threshold_uncertainty_score":0.9990049},"labels":[],"label_agreement":null},{"id":"W1769680758","doi":"10.3138/cjpe.29.3.70","title":"Launching the Credentialed Evaluator (CE) Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Credentialing; Credibility; Process (computing); Stakeholder; Corporate governance; Politics; Political science; Public relations; Business; Engineering ethics; Public administration; Process management; Management; Engineering management; Law; Computer science; Engineering; Economics","score_opus":0.6094119450625466,"score_gpt":0.5671337020641761,"score_spread":0.04227824299837046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769680758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9430896,0.0020462354,0.017930994,0.012171728,0.0049366374,0.0030488677,0.0000068436857,0.000027933422,0.016741129],"genre_scores_gemma":[0.99607307,0.0000039017054,0.0028416514,0.0002976402,0.00041646822,0.00005167833,0.000007891162,0.000010192861,0.00029752523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925676,0.0015539078,0.0010018975,0.00018128537,0.0044285925,0.00026672526],"domain_scores_gemma":[0.9910981,0.00035469086,0.00088549557,0.0003479372,0.006706581,0.00060716236],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05226286,0.00012035437,0.00019775279,0.00056886644,0.00033552325,0.0008829695,0.0007153524,0.000074592506,0.0022414445],"category_scores_gemma":[0.010249908,0.00007372851,0.00013414283,0.0009041427,0.00009814138,0.0009559852,0.000015731528,0.00023796425,0.00020427576],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026203064,0.000032444997,0.010418268,0.0000014463569,0.000035829282,0.0000042430092,0.0037607215,0.012159996,0.00005714811,0.0007842952,0.02308716,0.9496322],"study_design_scores_gemma":[0.0038169995,0.0012292113,0.07685768,0.000076958764,0.00038827598,0.00016949215,0.009786886,0.55481714,0.00033094105,0.08518075,0.26697597,0.00036970808],"about_ca_topic_score_codex":0.00044999752,"about_ca_topic_score_gemma":0.010230511,"teacher_disagreement_score":0.94926256,"about_ca_system_score_codex":0.0006172784,"about_ca_system_score_gemma":0.0112705985,"threshold_uncertainty_score":0.99867064},"labels":[],"label_agreement":null},{"id":"W1769901993","doi":"10.3138/cjpe.29.3.33","title":"A Made-in-Canada Credential: Developing an Evaluation Professional Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credential; Context (archaeology); Public relations; Political science; Process (computing); Service (business); Credentialing; Sociology; Business; Law; Marketing; Geography; Computer science","score_opus":0.6273699174603828,"score_gpt":0.566949663297369,"score_spread":0.06042025416301389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769901993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98645616,0.00039126605,0.0031397606,0.0031691382,0.0033142527,0.0019391099,0.000004652568,0.000007091765,0.0015785712],"genre_scores_gemma":[0.9929635,0.000002879657,0.0062706787,0.00026579504,0.0002081249,0.00014006802,0.000044529705,0.000012160276,0.00009228142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98933583,0.002012182,0.0013967034,0.0002818966,0.0066190455,0.00035434845],"domain_scores_gemma":[0.98921335,0.00019585484,0.00094187225,0.00027112654,0.008650867,0.00072691514],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04134887,0.00015282742,0.00026275704,0.0010037754,0.00017160345,0.00036754893,0.00055268814,0.0000876741,0.0018056348],"category_scores_gemma":[0.005319535,0.00012715034,0.00005791832,0.0012165277,0.000040847786,0.001693507,0.000014597065,0.00024402705,0.00003484086],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000037463848,0.000043294058,0.06534165,0.0000031577931,0.000014454356,0.000008898328,0.0016274354,0.025328629,0.00004050421,0.00036316246,0.0040249876,0.90316635],"study_design_scores_gemma":[0.0027140353,0.00036312992,0.35940024,0.00011048611,0.00007967413,0.00005347608,0.00826917,0.5896924,0.00020948457,0.0244212,0.014400416,0.00028628533],"about_ca_topic_score_codex":0.22928691,"about_ca_topic_score_gemma":0.97741014,"teacher_disagreement_score":0.9028801,"about_ca_system_score_codex":0.005771371,"about_ca_system_score_gemma":0.13170047,"threshold_uncertainty_score":0.9991068},"labels":[],"label_agreement":null},{"id":"W1773568500","doi":"10.3138/cjpe.0028.007","title":"Evaluator Competencies: The Aotearoa New Zealand Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Credentialing; Underpinning; Pedagogy; Set (abstract data type); Engineering ethics; Cultural competence; Sociology; Psychology; Medical education; Engineering; Computer science; Medicine; Gender studies","score_opus":0.27326673436579285,"score_gpt":0.4978504535242318,"score_spread":0.22458371915843894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1773568500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9601,0.00050744216,0.0032624237,0.024327734,0.0029190346,0.0017242897,0.0000038728344,0.000020559224,0.007134626],"genre_scores_gemma":[0.992255,0.0000065285267,0.0031381517,0.00078305404,0.00055100373,0.00004212911,0.0000035427267,0.000009693078,0.003210928],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99412745,0.0010179012,0.0009415319,0.00021195551,0.0033748616,0.00032631974],"domain_scores_gemma":[0.99503493,0.0005683614,0.00073250424,0.00049236574,0.002497347,0.00067446765],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022611402,0.00013340499,0.00023308567,0.00036111264,0.00034064412,0.0006817573,0.0009588725,0.00006542286,0.0042918627],"category_scores_gemma":[0.0066402755,0.000077745965,0.00014050744,0.00078268227,0.00017118709,0.00058937573,0.0000174055,0.00023828112,0.00022859505],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011136319,0.000015790807,0.02331101,9.8664e-7,0.000015102757,9.828595e-7,0.0074380725,0.0027453555,0.000041551233,0.00045945297,0.046281997,0.91967857],"study_design_scores_gemma":[0.0009977571,0.0005403476,0.09661956,0.000033332348,0.00006556979,0.000056166227,0.002278227,0.12262968,0.000073853334,0.028980656,0.7475715,0.00015330252],"about_ca_topic_score_codex":0.0016144427,"about_ca_topic_score_gemma":0.015463129,"teacher_disagreement_score":0.91952527,"about_ca_system_score_codex":0.00024426705,"about_ca_system_score_gemma":0.0062298966,"threshold_uncertainty_score":0.99940383},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048753317,0.0010177124,0.92818296,0.018177122,0.0010220123,0.002112791,0.00004923968,0.00006196814,0.0006228965],"genre_scores_gemma":[0.3825572,0.000016736405,0.61673844,0.0003536764,0.00016831732,0.00006176885,0.000049760216,0.000014049148,0.00004003611],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984563,0.00007858829,0.00036856395,0.0002935963,0.00046947683,0.0003334993],"domain_scores_gemma":[0.9973851,0.000042056505,0.00021471849,0.00089737325,0.00071750756,0.00074323534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016194509,0.00011051935,0.00013608538,0.00037901278,0.00021528597,0.0008154922,0.0018582651,0.000046197267,0.00010630261],"category_scores_gemma":[0.00022271191,0.00010249776,0.000038559545,0.0007719915,0.00004146163,0.0015452661,0.00009602058,0.00014987553,0.00007997597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.6335962e-7,0.0000210361,0.00013118697,0.0000027909118,0.000021093616,0.000003325123,0.00036031002,0.00019610187,0.00006126161,0.0053763236,0.04893087,0.9448953],"study_design_scores_gemma":[0.00083379535,0.0005832935,0.014490597,0.00017551445,0.000120142606,0.00018920781,0.00072473986,0.72411364,0.0001215156,0.04493378,0.21317035,0.0005433975],"about_ca_topic_score_codex":0.005273566,"about_ca_topic_score_gemma":0.007081229,"teacher_disagreement_score":0.9443519,"about_ca_system_score_codex":0.00019350577,"about_ca_system_score_gemma":0.0012977946,"threshold_uncertainty_score":0.79720896},"labels":[],"label_agreement":null},{"id":"W1782129283","doi":"","title":"ARTICLE 5: DISSEMINATION AND EARLY USE OF THE PARIS DECLARATION EVALUATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Champion; Declaration; Transparency (behavior); Stakeholder; Corporate governance; Politics; Stakeholder engagement; Public relations; Political science; Evaluation methods; Process management; Business; Management science; Engineering; Law","score_opus":0.4613107564983002,"score_gpt":0.5371820478652425,"score_spread":0.07587129136694226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1782129283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99560523,0.00059825875,0.00069676683,0.0011493635,0.00061868975,0.0010119502,0.0000031799148,0.000002772262,0.00031377096],"genre_scores_gemma":[0.998409,0.000009552693,0.0012995324,0.00004607872,0.00010977495,0.000043371223,0.0000035915857,0.00000581055,0.00007328899],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99533117,0.00097134744,0.00082858175,0.00011229434,0.0025542632,0.00020233271],"domain_scores_gemma":[0.9946276,0.0003815169,0.0009205871,0.00025575154,0.003543192,0.00027137407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020253738,0.00008565668,0.00015104513,0.00033198833,0.00020536529,0.0003013843,0.00018652507,0.000072069255,0.0005301494],"category_scores_gemma":[0.0059494046,0.000056088968,0.00008198868,0.00069565605,0.00010102409,0.0019656317,0.000013576004,0.00012966231,0.000010238524],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007889583,0.00003204475,0.4874599,0.0000019244874,0.000011288908,5.4170364e-8,0.0022952263,0.0006634039,0.00039092707,0.00034930362,0.00087632675,0.50791174],"study_design_scores_gemma":[0.00035483425,0.0001258529,0.9304673,0.00003555685,0.00013712623,0.000010734216,0.00052440836,0.0601847,0.0011780548,0.0020604078,0.0048562707,0.000064733256],"about_ca_topic_score_codex":0.00034353044,"about_ca_topic_score_gemma":0.0028324896,"teacher_disagreement_score":0.507847,"about_ca_system_score_codex":0.00024413728,"about_ca_system_score_gemma":0.0013321879,"threshold_uncertainty_score":0.7122423},"labels":[],"label_agreement":null},{"id":"W1782687918","doi":"10.3138/cjpe.027.001","title":"L’évaluateur éthiquement engagé: sur le sens et la pertinence d’un nouveau référentiel","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Meaning (existential); Commit; Neutrality; Subject (documents); Sociology; Epistemology; Psychology; Social psychology; Philosophy; Library science","score_opus":0.32017871900978256,"score_gpt":0.4955612199298118,"score_spread":0.17538250092002922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1782687918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97823346,0.0009901009,0.0022304303,0.008362999,0.0016539232,0.0010112815,0.000008576703,0.000018962755,0.0074902675],"genre_scores_gemma":[0.9927689,0.000036273,0.00590277,0.0006555574,0.00025751162,0.00006473492,0.000014476246,0.000016392283,0.0002833727],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927997,0.0023320944,0.0011488678,0.00022083132,0.002990616,0.00050786266],"domain_scores_gemma":[0.99430585,0.0005196949,0.000847791,0.0003682593,0.0031776899,0.0007806976],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.048080932,0.00018273029,0.0002730971,0.0004746725,0.00040670583,0.000627948,0.000497242,0.00011391792,0.0025598896],"category_scores_gemma":[0.0046998095,0.00014368028,0.00017479708,0.0006421796,0.000120150136,0.00146222,0.000027537644,0.00041938733,0.00016462678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019515292,0.00024544273,0.081964515,0.00000677675,0.000057324385,0.00000730766,0.009300447,0.002421528,0.00021175841,0.0018808715,0.006786475,0.89709806],"study_design_scores_gemma":[0.0028418726,0.00063239253,0.40037057,0.000120710734,0.00021324203,0.00025192296,0.005064973,0.08373912,0.0008479571,0.0062051243,0.4992233,0.0004888331],"about_ca_topic_score_codex":0.00081549,"about_ca_topic_score_gemma":0.00470478,"teacher_disagreement_score":0.8966092,"about_ca_system_score_codex":0.0002876096,"about_ca_system_score_gemma":0.008231035,"threshold_uncertainty_score":0.99835193},"labels":[],"label_agreement":null},{"id":"W1788049718","doi":"10.3138/cjpe.29.3.54","title":"The Development and Initial Validation of Competencies and Descriptors for Canadian Evaluation Practice","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Barrie Urology Group","funders":"","keywords":"Psychology; Medical education; Computer science; Medicine","score_opus":0.5926820838299982,"score_gpt":0.5503943550828988,"score_spread":0.04228772874709941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1788049718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862911,0.0016056435,0.0012469358,0.0053730947,0.0010938843,0.0022840668,0.00000968877,0.0000034212815,0.0020921328],"genre_scores_gemma":[0.98571754,0.000010032862,0.01393009,0.00010065897,0.00008656414,0.000105298685,0.000017341807,0.0000060821258,0.00002642177],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960951,0.0007106824,0.0008716945,0.00014506684,0.001962329,0.00021510724],"domain_scores_gemma":[0.9881629,0.00075801386,0.0007788375,0.00014221482,0.009561853,0.00059620524],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043922786,0.00009438348,0.00016143298,0.00047238704,0.00046316636,0.00045581744,0.00020094367,0.00006044584,0.000047098176],"category_scores_gemma":[0.017467503,0.00006588786,0.00003310546,0.00034691958,0.00014335405,0.0008496452,0.000009427393,0.000094735915,0.000002942593],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004115309,0.000012399821,0.008434552,0.00000444604,0.000035249806,4.427167e-7,0.0071563576,0.00071321963,0.00001227822,0.0008879027,0.0013649943,0.981337],"study_design_scores_gemma":[0.0048334277,0.0017911079,0.08849833,0.00011697696,0.00057934894,0.00013483148,0.059203394,0.16749951,0.0015812024,0.028413692,0.646953,0.0003952071],"about_ca_topic_score_codex":0.007592434,"about_ca_topic_score_gemma":0.4071365,"teacher_disagreement_score":0.9809418,"about_ca_system_score_codex":0.0005907952,"about_ca_system_score_gemma":0.020310659,"threshold_uncertainty_score":0.9990161},"labels":[],"label_agreement":null},{"id":"W1790388803","doi":"","title":"Hurteau, M., Houle, S., & Guillemette, F. (Éds.). (2012). L’évaluation de programme axée sur le jugement crédible. Québec, QC : Presses de l’Université du Québec, 200 pages","year":2013,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Physics; Mathematical physics; Economics; Accounting","score_opus":0.1689980442060935,"score_gpt":0.37409090493899916,"score_spread":0.20509286073290567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1790388803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47207505,0.087820746,0.007484293,0.41453037,0.0035851959,0.007878604,0.000055392647,0.000091246475,0.0064791045],"genre_scores_gemma":[0.95783883,0.006004789,0.021629116,0.0017182367,0.0015310268,0.0008027789,0.00012416553,0.00010763032,0.010243394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98992383,0.002487754,0.0020111345,0.00060402375,0.0034696707,0.0015035537],"domain_scores_gemma":[0.98649275,0.00070499926,0.001846507,0.0007236135,0.008361166,0.001870952],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.021179644,0.0005247872,0.0006672081,0.0012862678,0.00095733826,0.0017269647,0.0013288384,0.00037506653,0.055036884],"category_scores_gemma":[0.0051271995,0.00049734133,0.00043833334,0.0013812704,0.00044240215,0.0035522599,0.00008228754,0.0006726572,0.0008443813],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000024093679,0.00028487114,0.042855494,0.000040639276,0.00015822191,0.000017057355,0.0034033624,0.0056147673,0.000110896624,0.00008667276,0.3471255,0.60027844],"study_design_scores_gemma":[0.0026356718,0.001028281,0.2212999,0.00027319018,0.0006328621,0.00014744021,0.003909115,0.10579574,0.00019855332,0.003337642,0.6602398,0.00050181756],"about_ca_topic_score_codex":0.6276516,"about_ca_topic_score_gemma":0.8590168,"teacher_disagreement_score":0.5997766,"about_ca_system_score_codex":0.004555434,"about_ca_system_score_gemma":0.081709966,"threshold_uncertainty_score":0.9999336},"labels":[],"label_agreement":null},{"id":"W1793639688","doi":"","title":"Ryan, K. E., & Cousins, J. B. (Eds.). (2009). The Sage International Handbook of Educational Evaluation. Thousand Oaks, CA: Sage. 608 pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Sociology; Library science; Psychology; Computer science; Physics","score_opus":0.17227601125528205,"score_gpt":0.4771476743022029,"score_spread":0.3048716630469208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1793639688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6144475,0.1830024,0.011026323,0.09187676,0.037118714,0.012893677,0.00048461684,0.000048335707,0.049101707],"genre_scores_gemma":[0.993535,0.00048616,0.0023455983,0.0004819902,0.0012168309,0.00017378008,0.00009714338,0.00002042855,0.0016430626],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99111825,0.0012243993,0.0015784326,0.00024981247,0.005367028,0.00046205497],"domain_scores_gemma":[0.9908458,0.0008743944,0.0016150181,0.00050556933,0.0056011765,0.0005580491],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03157545,0.00021684314,0.00032981628,0.0007672578,0.00042554436,0.0004175744,0.00095404516,0.0001257134,0.022507554],"category_scores_gemma":[0.00589625,0.00014843294,0.00022628355,0.00083536387,0.000272102,0.0013548046,0.00003523854,0.00033658926,0.00019126572],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029242248,0.00018260108,0.0540803,0.0000058830924,0.00011687984,7.7720233e-7,0.0020447136,0.0031432167,0.000115776704,0.00042445862,0.059175927,0.8806802],"study_design_scores_gemma":[0.0026160027,0.0003349482,0.32395357,0.0002746121,0.0005413828,0.0001466403,0.0019866019,0.06330124,0.00044371394,0.010107063,0.5959004,0.00039379217],"about_ca_topic_score_codex":0.00041649738,"about_ca_topic_score_gemma":0.008238757,"teacher_disagreement_score":0.88028646,"about_ca_system_score_codex":0.00071957475,"about_ca_system_score_gemma":0.009908886,"threshold_uncertainty_score":0.99719685},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47591975,0.46161732,0.00036911614,0.04534342,0.011343696,0.0020382234,0.000008847694,0.000039937087,0.0033196595],"genre_scores_gemma":[0.97315997,0.0011018262,0.01380206,0.00021457176,0.010883481,0.00006270542,0.000010532932,0.000028989161,0.0007358413],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972573,0.00051177474,0.00057984074,0.00017439993,0.00045841423,0.0010182541],"domain_scores_gemma":[0.9961909,0.00007124878,0.00046135252,0.00031351103,0.0015578681,0.0014051244],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074416227,0.00017338859,0.00033521766,0.0005686395,0.00015431142,0.000055833152,0.00015450268,0.00025187046,0.00066123315],"category_scores_gemma":[0.008908848,0.00016244102,0.0001251193,0.0004593591,0.00041547243,0.0006474572,0.000009465817,0.0006570326,0.00006827642],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003961254,0.00014721173,0.10739151,0.00017710113,0.00011484139,0.000028350672,0.0015146277,0.000020720001,0.0001766833,0.0032945047,0.013636147,0.8734587],"study_design_scores_gemma":[0.0010660404,0.0018917086,0.31427595,0.0007052722,0.00089260744,0.0019583162,0.0026723386,0.00038905718,0.0023328846,0.0076787374,0.6659143,0.00022280052],"about_ca_topic_score_codex":0.0019499945,"about_ca_topic_score_gemma":0.0013598867,"teacher_disagreement_score":0.8732359,"about_ca_system_score_codex":0.0018487242,"about_ca_system_score_gemma":0.007261403,"threshold_uncertainty_score":0.99943954},"labels":[],"label_agreement":null},{"id":"W1826075361","doi":"10.3138/cjpe.22.007","title":"Participatory Impact Pathways Analysis: A Practical Application of Program Theory in Research-for-Development","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Logic model; Citizen journalism; Food security; Computer science; Poverty; Narrative; Theory of change; Management science; Knowledge management; Process management; Sociology; Business; Engineering; Economics; Economic growth; Social science","score_opus":0.815960147008348,"score_gpt":0.6979548155552535,"score_spread":0.11800533145309444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1826075361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9548617,0.00028468316,0.040286914,0.0005058593,0.00014225913,0.0031305542,0.0000060289094,0.000008852585,0.0007731308],"genre_scores_gemma":[0.9805804,0.0000029744892,0.018841403,0.000027651962,0.00007662437,0.00042455996,0.000021885586,0.000008829913,0.000015682926],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9926903,0.0013819669,0.0018437118,0.0002733814,0.0032567354,0.00055385137],"domain_scores_gemma":[0.99094075,0.0015363888,0.0009826467,0.00035973958,0.0056157066,0.0005647854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14730027,0.00012232988,0.00036439567,0.002815181,0.00017612746,0.0001823291,0.00038743071,0.00011985639,0.0003676154],"category_scores_gemma":[0.0082124,0.000091870876,0.00021804847,0.0034948168,0.00018922101,0.0004923323,0.000015227959,0.00032723122,0.000017776945],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000138129,0.00025186082,0.108076945,0.0000073473884,0.00011302966,0.0000035010542,0.0029257624,0.002346568,0.000077492434,0.0024206298,0.00019387911,0.88344485],"study_design_scores_gemma":[0.001252024,0.0013600072,0.8425184,0.000046928628,0.0002727489,0.000009805493,0.0048161433,0.10636667,0.00062225,0.02439897,0.018159667,0.00017637067],"about_ca_topic_score_codex":0.0002999508,"about_ca_topic_score_gemma":0.035373718,"teacher_disagreement_score":0.8832685,"about_ca_system_score_codex":0.0009958664,"about_ca_system_score_gemma":0.010924259,"threshold_uncertainty_score":0.9946829},"labels":[],"label_agreement":null},{"id":"W1836020270","doi":"","title":"ARTICLE 2: PREPARING, GOVERNING AND MANAGING THE PARIS DECLARATION EVALUATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credibility; Declaration; Stakeholder; Corporate governance; Joint (building); Process management; Stakeholder engagement; Quality (philosophy); Business; Public relations; Political science; Environmental resource management; Economics; Engineering; Law","score_opus":0.37383956162570414,"score_gpt":0.523925339424259,"score_spread":0.15008577779855486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1836020270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9816403,0.002954805,0.002702538,0.0027334772,0.0008498379,0.0012370948,0.0000016613578,0.000008599047,0.0078716865],"genre_scores_gemma":[0.9979579,0.000023469822,0.0013896888,0.00018977717,0.00027808695,0.00007551455,0.0000056170147,0.0000073317137,0.00007264747],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952787,0.0009671743,0.0007137076,0.00014493917,0.002592792,0.00030265373],"domain_scores_gemma":[0.99660724,0.00030143035,0.0006954179,0.00025706412,0.0017794608,0.00035935774],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.041642934,0.00009948691,0.00014082073,0.00027007758,0.0004478223,0.00059737393,0.00023781904,0.00005624954,0.0010165852],"category_scores_gemma":[0.003279526,0.000065880115,0.00006426364,0.0005004323,0.00007899624,0.0015418342,0.000018141269,0.00018588455,0.00006764111],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007970233,0.000018430328,0.16390926,0.00000192744,0.000019580999,1.902686e-7,0.003282625,0.0032336623,0.00004474957,0.0005212721,0.0025350095,0.8264253],"study_design_scores_gemma":[0.0006677435,0.00014458122,0.47867575,0.000028577144,0.00020288472,0.00004751246,0.0030779617,0.46066055,0.00012527968,0.0061088777,0.050145406,0.0001148701],"about_ca_topic_score_codex":0.00034012715,"about_ca_topic_score_gemma":0.0060267798,"teacher_disagreement_score":0.82631046,"about_ca_system_score_codex":0.00039386845,"about_ca_system_score_gemma":0.0015011667,"threshold_uncertainty_score":0.99989665},"labels":[],"label_agreement":null},{"id":"W183745815","doi":"10.3138/cjpe.0023.006","title":"Participatory Evaluation as Seen in a Vygotskian Framework","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interview; Categorization; Psychology; Citizen journalism; Participatory evaluation; Coding (social sciences); Medical education; Pedagogy; Applied psychology; Computer science; Sociology; Medicine","score_opus":0.567309139198488,"score_gpt":0.6135182252392328,"score_spread":0.04620908604074481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W183745815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98064154,0.0010619703,0.00074058975,0.0067750886,0.000910466,0.0017283844,0.0000024626393,0.000011109141,0.00812837],"genre_scores_gemma":[0.9962595,0.000011949873,0.002459546,0.00087833713,0.00022512724,0.00008479621,0.000008511976,0.000008121076,0.000064111664],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99231434,0.0014341546,0.0013707739,0.00023930949,0.004220153,0.00042128933],"domain_scores_gemma":[0.99456525,0.0003168487,0.00076892227,0.00040067165,0.0033420997,0.00060622324],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03944305,0.0001545448,0.0003007496,0.0012349257,0.0001671258,0.00031889966,0.0005173829,0.00015742551,0.005436751],"category_scores_gemma":[0.011244202,0.00012830428,0.00013577926,0.0015009101,0.00006840915,0.0009091181,0.000007062291,0.00038906327,0.00025491684],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022870781,0.00007222243,0.03246291,0.0000012477026,0.000010539889,0.000007907454,0.003546256,0.006475137,0.00002096871,0.0011755988,0.001393458,0.95481086],"study_design_scores_gemma":[0.0015420789,0.001137351,0.5932045,0.00014619582,0.000120380464,0.00003928577,0.0030038788,0.13650517,0.00009208657,0.24665907,0.01731039,0.00023963314],"about_ca_topic_score_codex":0.00035700144,"about_ca_topic_score_gemma":0.011639098,"teacher_disagreement_score":0.95457125,"about_ca_system_score_codex":0.0009145058,"about_ca_system_score_gemma":0.009518293,"threshold_uncertainty_score":0.9970845},"labels":[],"label_agreement":null},{"id":"W1841863553","doi":"","title":"ARTICLE 3: THE PARIS DECLARATION EVALUATION PROCESS AND METHODS","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Process (computing); Engineering ethics; Corporate governance; Process management; Perspective (graphical); Quality (philosophy); Management science; Political science; Computer science; Business; Engineering; Epistemology; Law","score_opus":0.516238008344546,"score_gpt":0.625758530785327,"score_spread":0.10952052244078092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1841863553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760802,0.0035279174,0.010005054,0.0049853665,0.0010189075,0.0017768985,0.0000016979623,0.00000797634,0.0025959928],"genre_scores_gemma":[0.99136865,0.0000146022,0.007896553,0.00024603726,0.00027991782,0.00014415226,0.000004889112,0.000007190412,0.000037990438],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9940564,0.0022056885,0.0008073423,0.00014605279,0.0024836692,0.0003008711],"domain_scores_gemma":[0.9943749,0.0004923781,0.0006743093,0.00025561143,0.0037692862,0.000433531],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.072847724,0.00010478913,0.00016566805,0.00032945364,0.00039479168,0.00048388183,0.00026706836,0.00007386537,0.0015690381],"category_scores_gemma":[0.006074889,0.00006401387,0.00006640521,0.00076687796,0.000109657325,0.0014934109,0.000010031554,0.00019566492,0.000040338364],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007804543,0.000026292519,0.079280496,0.0000020509974,0.00001668596,1.2301938e-7,0.0036512702,0.0012312246,0.000076332835,0.00038576583,0.0009201774,0.91440177],"study_design_scores_gemma":[0.0009915075,0.00027056155,0.5219434,0.000024263996,0.00033199647,0.00007108075,0.005697153,0.40985703,0.0010202419,0.027190944,0.032434523,0.00016730605],"about_ca_topic_score_codex":0.00013369304,"about_ca_topic_score_gemma":0.0022768024,"teacher_disagreement_score":0.91423446,"about_ca_system_score_codex":0.00025283385,"about_ca_system_score_gemma":0.0026580233,"threshold_uncertainty_score":0.99934363},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9650689,0.00050295575,0.00007162052,0.005638688,0.0017189974,0.0010353412,0.0000040330024,0.00000486711,0.025954604],"genre_scores_gemma":[0.9987738,0.0000072832713,0.00065882003,0.000049002996,0.0003549926,0.000021215155,0.0000071210497,0.0000034216334,0.00012431799],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99779046,0.0005313774,0.00036371098,0.000047692563,0.0010765924,0.00019014384],"domain_scores_gemma":[0.99753946,0.000052667947,0.00040669422,0.00007133986,0.001755416,0.00017443285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009382033,0.000045084165,0.00006561342,0.00011285369,0.00026271187,0.000054818516,0.00015390427,0.000055670233,0.00027865416],"category_scores_gemma":[0.0020853886,0.00003494288,0.00006089328,0.00029697068,0.00009644603,0.00048214514,0.000004292106,0.00008556845,0.000010111173],"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":[0.000059096204,0.00015315277,0.18051073,0.0000073424144,0.00009382829,5.259643e-7,0.048377194,0.0008134924,0.000534399,0.02918241,0.013385795,0.72688204],"study_design_scores_gemma":[0.00182008,0.00013280606,0.8529499,0.000118259355,0.00027339894,0.0000064896667,0.004009798,0.0055912817,0.0034780274,0.012714718,0.11872493,0.00018028783],"about_ca_topic_score_codex":0.002968804,"about_ca_topic_score_gemma":0.031651087,"teacher_disagreement_score":0.72670174,"about_ca_system_score_codex":0.00050334464,"about_ca_system_score_gemma":0.0030621267,"threshold_uncertainty_score":0.9860188},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6658881,0.1359373,0.005703164,0.18062812,0.0014215934,0.008469712,0.00036756668,0.000016644142,0.001567845],"genre_scores_gemma":[0.9913236,0.0006307956,0.0074586975,0.00025232724,0.00015134609,0.00012684288,0.000017519078,0.00001749177,0.000021385293],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9927577,0.0013503233,0.0051806173,0.00022248749,0.0001703936,0.00031852178],"domain_scores_gemma":[0.99152356,0.00045305895,0.006488575,0.00034136084,0.0008110979,0.00038236167],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05734207,0.00012516983,0.00073127006,0.000745978,0.00017431485,0.00009405928,0.00026982918,0.000087181215,0.00026218765],"category_scores_gemma":[0.006258871,0.00012244337,0.00017948366,0.00015351942,0.00021880308,0.0007565714,0.000016987793,0.00014829947,0.0000302245],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023307297,0.00044888302,0.0215159,0.0023572163,0.00094059267,5.585967e-7,0.038102377,0.0036819472,0.00002054701,0.18416981,0.008430418,0.74030846],"study_design_scores_gemma":[0.008983824,0.0039199325,0.3510506,0.0033988,0.000288233,0.00017044634,0.043478686,0.30507612,0.000049812228,0.25373933,0.028801115,0.0010431254],"about_ca_topic_score_codex":0.00977357,"about_ca_topic_score_gemma":0.016705452,"teacher_disagreement_score":0.7392653,"about_ca_system_score_codex":0.0009879317,"about_ca_system_score_gemma":0.0037412427,"threshold_uncertainty_score":0.99682045},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18555595,0.0021853552,0.30238184,0.44158384,0.007869515,0.017266717,0.00023423941,0.000070453556,0.04285209],"genre_scores_gemma":[0.93203974,0.0000037953996,0.0633811,0.001382278,0.0014645713,0.00032356504,0.0000997988,0.000019446787,0.0012856848],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99456465,0.00037249867,0.0010832986,0.00034431482,0.0031404858,0.000494759],"domain_scores_gemma":[0.9897596,0.00025945337,0.0005947204,0.0005087133,0.0059559653,0.0029215366],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014781953,0.00015457573,0.0002543003,0.00054295035,0.00016145867,0.00080985395,0.000754682,0.00008871367,0.001650048],"category_scores_gemma":[0.0066520236,0.00013184844,0.00014646031,0.0010284187,0.00003638949,0.0008758787,0.000026275799,0.00012517124,0.00020853517],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020047006,0.000028021597,0.0034565656,0.0000010503942,0.00003488673,3.4297355e-7,0.00070691854,0.0011668552,0.000004201627,0.021812107,0.1639288,0.8088402],"study_design_scores_gemma":[0.003295201,0.00050520484,0.09525937,0.000032869902,0.00023132827,0.000009182207,0.0016343337,0.018589607,0.00002263551,0.43075016,0.4494797,0.00019038767],"about_ca_topic_score_codex":0.0033606188,"about_ca_topic_score_gemma":0.02292435,"teacher_disagreement_score":0.8086498,"about_ca_system_score_codex":0.0019335665,"about_ca_system_score_gemma":0.020745873,"threshold_uncertainty_score":0.9992626},"labels":[],"label_agreement":null},{"id":"W1874375828","doi":"10.3138/cjpe.29.3.x","title":"Introduction à la professionnalisation de l’évaluation au Canada","year":2015,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.34891936041679567,"score_gpt":0.5163978479684853,"score_spread":0.16747848755168965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1874375828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.734942,0.006173278,0.009697753,0.18690994,0.039153397,0.0034245816,0.00004742557,0.00002314898,0.019628445],"genre_scores_gemma":[0.98249763,0.00004134249,0.006850231,0.00041714325,0.005556925,0.000097640615,0.00008428615,0.000025322808,0.004429454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98772997,0.005431334,0.0015218663,0.0003197183,0.0043769768,0.00062012067],"domain_scores_gemma":[0.98741823,0.00038747114,0.0014057956,0.00036710472,0.008909225,0.0015121835],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06386427,0.00023819236,0.00034473615,0.0006994692,0.00037120303,0.00051808165,0.0004689444,0.00026532417,0.003221341],"category_scores_gemma":[0.012989111,0.00021955774,0.00012448036,0.0012685395,0.00021253226,0.00155405,0.000017262186,0.0005398839,0.0000865591],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000039186838,0.00007093223,0.018632049,0.00001936536,0.00004498381,0.000014209979,0.005593382,0.030164,0.00001849374,0.0018019638,0.13913143,0.80447],"study_design_scores_gemma":[0.0015977576,0.0005725536,0.043932155,0.00019354545,0.00030731063,0.00030027417,0.007910865,0.13707899,0.00012459047,0.010564379,0.79715866,0.00025893335],"about_ca_topic_score_codex":0.7088732,"about_ca_topic_score_gemma":0.98135155,"teacher_disagreement_score":0.8042111,"about_ca_system_score_codex":0.010384981,"about_ca_system_score_gemma":0.2691125,"threshold_uncertainty_score":0.99768984},"labels":[],"label_agreement":null},{"id":"W18830643","doi":"10.3138/cjpe.026.001","title":"Advancing Empirical Scholarship to Further Develop Evaluation Theory and Practice","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Grounded theory; Context (archaeology); Development theory; Field (mathematics); Empirical research; Contingency; Epistemology; Sociology; Intersection (aeronautics); Contingency theory; Management science; Engineering ethics; Qualitative research; Knowledge management; Computer science; Social science; Political science; Economics","score_opus":0.580695406400756,"score_gpt":0.5966934622915074,"score_spread":0.015998055890751428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W18830643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95835876,0.0011522237,0.012184186,0.009083507,0.0012170443,0.0024928611,0.0000035847697,0.000016497663,0.015491336],"genre_scores_gemma":[0.9545121,0.000008134364,0.043626048,0.0015564202,0.00013059122,0.00008400523,0.000003412745,0.000012935748,0.00006631498],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99107146,0.004155572,0.00097298826,0.0002907674,0.003171006,0.00033821282],"domain_scores_gemma":[0.98735696,0.0012313337,0.0006682547,0.00029010285,0.009655432,0.00079791533],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12308104,0.00013874995,0.0002115006,0.0008215165,0.00024052465,0.000378912,0.00037496377,0.00009107417,0.0035454333],"category_scores_gemma":[0.07867451,0.00010810104,0.00005783772,0.0011407435,0.00007516366,0.001823277,0.000023330236,0.00026060297,0.0001565621],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121847406,0.0000388359,0.02729316,0.000001902025,0.000027836692,0.0000045341217,0.011401465,0.00024130885,0.000042896474,0.00065825914,0.0008976988,0.95927024],"study_design_scores_gemma":[0.0018349319,0.0014084749,0.76386946,0.000118944205,0.0003783461,0.00034879465,0.018395618,0.01073665,0.0002738029,0.10190985,0.100315034,0.00041010487],"about_ca_topic_score_codex":0.00011581395,"about_ca_topic_score_gemma":0.0070660547,"teacher_disagreement_score":0.95886016,"about_ca_system_score_codex":0.00053235533,"about_ca_system_score_gemma":0.007967063,"threshold_uncertainty_score":0.9976568},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98027587,0.010963205,0.002845211,0.003166593,0.00046683557,0.0018139175,0.000022485832,0.00005238949,0.00039349915],"genre_scores_gemma":[0.8500922,0.0003056052,0.14711611,0.000974791,0.0006201487,0.0007506505,0.000033821732,0.000037706563,0.000068995374],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933455,0.0044790134,0.00056977017,0.00020989579,0.00032484258,0.0010709909],"domain_scores_gemma":[0.99737716,0.00042960938,0.0004920923,0.00018863079,0.0005304028,0.0009821276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0152299665,0.00024653983,0.00029487588,0.0002986702,0.00019821379,0.00010420377,0.00033813104,0.00032376853,0.00034780696],"category_scores_gemma":[0.0005041114,0.00022416761,0.00014275021,0.00041076113,0.00013004847,0.00031243308,0.000017031678,0.0005629005,0.000009464698],"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":[0.00009638962,0.0005134648,0.08760039,0.00019310966,0.0002040861,0.000025515095,0.10539398,0.00005930308,0.0005000853,0.0006345855,0.0019380997,0.802841],"study_design_scores_gemma":[0.0036324947,0.0029474117,0.85231775,0.0006992245,0.0009930291,0.00083951803,0.09707928,0.0003660401,0.0015961914,0.010890212,0.027928459,0.00071041175],"about_ca_topic_score_codex":0.02030039,"about_ca_topic_score_gemma":0.0710493,"teacher_disagreement_score":0.8021306,"about_ca_system_score_codex":0.0017698589,"about_ca_system_score_gemma":0.003119113,"threshold_uncertainty_score":0.9862235},"labels":[],"label_agreement":null},{"id":"W1891772057","doi":"","title":"ARTICLE 1: THE PARIS DECLARATION ON AID EFFECTIVENESS: HISTORY AND SIGNIFICANCE","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Context (archaeology); Relevance (law); Harmonization; Diversity (politics); Accountability; Political science; Public administration; Law; History","score_opus":0.39254754268677033,"score_gpt":0.488255545621587,"score_spread":0.09570800293481668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1891772057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902515,0.0025377823,0.0010673284,0.0017073012,0.0010867747,0.00088807615,0.0000012739226,0.000005368167,0.0024545914],"genre_scores_gemma":[0.998901,0.000014391808,0.00042000067,0.00031400053,0.00020267695,0.0000724404,0.0000015739402,0.000005248925,0.00006866972],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99693125,0.0010529518,0.00042907213,0.00011122149,0.0012652951,0.00021021446],"domain_scores_gemma":[0.99756694,0.00061951653,0.00038296782,0.0002001995,0.0009122108,0.00031814855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021092167,0.0000796532,0.00012635412,0.00021925909,0.00019750936,0.00014956713,0.00018060699,0.00004737729,0.0007947814],"category_scores_gemma":[0.0018440083,0.00004906555,0.000053228163,0.00026448717,0.00010934445,0.00068984414,0.0000054715324,0.00016502124,0.00007163395],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004648256,0.00006220028,0.17700933,0.0000042193083,0.000021276759,8.613512e-7,0.002614927,0.0014084169,0.00028571408,0.0025409418,0.0064761452,0.8095295],"study_design_scores_gemma":[0.000696519,0.00046770694,0.79051197,0.000031236796,0.00006718476,0.000019777453,0.0008100391,0.01853297,0.0004947087,0.003573839,0.18468973,0.00010431328],"about_ca_topic_score_codex":0.00021068435,"about_ca_topic_score_gemma":0.0016761492,"teacher_disagreement_score":0.8094252,"about_ca_system_score_codex":0.000654661,"about_ca_system_score_gemma":0.0016434536,"threshold_uncertainty_score":0.8702299},"labels":[],"label_agreement":null},{"id":"W193071","doi":"10.3138/cjpe.17.006","title":"Developing an Evaluation Habit of Mind","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Habit; Accountability; Sustainability; Psychology; Political science; Sociology; Social psychology; Law","score_opus":0.6840143153944287,"score_gpt":0.5727226976961833,"score_spread":0.11129161769824536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W193071","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869411,0.00082448364,0.0023342634,0.0024525858,0.00094303436,0.0012369608,0.0000057679026,0.0000046372634,0.0052571944],"genre_scores_gemma":[0.98433673,0.000010414944,0.015231156,0.000101542435,0.00015811253,0.00003865218,0.00001195881,0.000008789544,0.00010261567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931573,0.0009862486,0.001342561,0.000215445,0.0040437584,0.00025466172],"domain_scores_gemma":[0.9902801,0.0001923993,0.001167115,0.0003438836,0.0076159057,0.00040058923],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027047213,0.00012206964,0.00026460827,0.00096495147,0.00017670366,0.0002582843,0.0005041179,0.00009143713,0.01233043],"category_scores_gemma":[0.004134873,0.000099318146,0.000114584705,0.001006828,0.00009670808,0.0011620821,0.000008937411,0.00015441427,0.00011182527],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058350365,0.000040488467,0.014100325,0.0000028923866,0.000017766472,0.0000012438761,0.001804494,0.002914849,0.000053380645,0.00031391412,0.0009203903,0.9798244],"study_design_scores_gemma":[0.0022482593,0.001048947,0.13231403,0.00010391226,0.0002124083,0.000059581347,0.0025474438,0.80464363,0.0008518737,0.016034957,0.039667703,0.00026726836],"about_ca_topic_score_codex":0.0002050906,"about_ca_topic_score_gemma":0.012636933,"teacher_disagreement_score":0.97955716,"about_ca_system_score_codex":0.0005813457,"about_ca_system_score_gemma":0.00451257,"threshold_uncertainty_score":0.9885724},"labels":[],"label_agreement":null},{"id":"W1951995802","doi":"10.3138/cjpe.027.004","title":"Propositions théoriques et pratiques pour l’évaluation de programmes en négligence","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec en Outaouais","funders":"Université de Montréal; Université du Québec en Outaouais; Université du Québec à Montréal","keywords":"Neglect; Fidelity; Valuation (finance); Psychological intervention; Psychology; Variety (cybernetics); Intervention (counseling); Sustainability; Program evaluation; Social psychology; Computer science; Political science; Business","score_opus":0.3343002875915336,"score_gpt":0.5692418239309505,"score_spread":0.2349415363394169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951995802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9421958,0.0014374173,0.027118284,0.015412911,0.0011062087,0.0029143733,0.000012308008,0.000053526805,0.009749211],"genre_scores_gemma":[0.94576216,0.000045991208,0.052802745,0.0003993823,0.00046791858,0.0002445577,0.000023533843,0.000014716778,0.00023897678],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99357045,0.0023972432,0.0010262087,0.0001876401,0.0023105838,0.0005078953],"domain_scores_gemma":[0.99397373,0.00047867285,0.0008211832,0.00028892767,0.0037483035,0.0006891892],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0413558,0.00016678631,0.00023817453,0.0006917299,0.00027995137,0.0006399518,0.0004510961,0.00013069459,0.0015031003],"category_scores_gemma":[0.005987529,0.00012854359,0.0001503691,0.00074743363,0.00008835352,0.0021322917,0.000015708609,0.0003116435,0.00010163827],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001287852,0.0001751142,0.13408089,0.000007447351,0.00003863311,0.0000022961235,0.012927565,0.0010825203,0.00027236078,0.0072659864,0.00444325,0.83969104],"study_design_scores_gemma":[0.0013709848,0.0016099276,0.719276,0.000216569,0.00035998784,0.00035584287,0.012216979,0.0730926,0.0040695304,0.077282794,0.109554134,0.00059463806],"about_ca_topic_score_codex":0.00045903848,"about_ca_topic_score_gemma":0.008150474,"teacher_disagreement_score":0.8390964,"about_ca_system_score_codex":0.00071851263,"about_ca_system_score_gemma":0.012349084,"threshold_uncertainty_score":0.9994097},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945734,0.00034339086,0.000015559675,0.0010373943,0.00016613654,0.0018941797,0.000003900848,0.000043864406,0.0019221712],"genre_scores_gemma":[0.9949766,0.00005373782,0.004489062,0.00025457633,0.00007266242,0.00008495476,0.000028031343,0.0000127066905,0.000027688087],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952326,0.0029440308,0.0009474121,0.00009198399,0.00038835325,0.00039564175],"domain_scores_gemma":[0.99578846,0.0002955937,0.0006263929,0.0002825679,0.0024684854,0.000538531],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.008411586,0.0001250456,0.0002846286,0.00028824926,0.0015977159,0.000044887878,0.00024065319,0.00016706984,0.00043245289],"category_scores_gemma":[0.00031419736,0.00012191289,0.000047306406,0.000319909,0.000067775225,0.00042656306,0.000022974808,0.00095230766,0.0000042235474],"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":[0.000029850364,0.00036174088,0.14756101,0.0035527006,0.000044406228,0.000005975522,0.095484,0.00003317785,0.000009659762,0.00008754476,0.00024117457,0.75258875],"study_design_scores_gemma":[0.0024975673,0.00092927157,0.9186218,0.0011714059,0.00020061668,0.000023777662,0.04118819,0.008819663,0.000012154726,0.008787853,0.017498352,0.00024936814],"about_ca_topic_score_codex":0.02098269,"about_ca_topic_score_gemma":0.06121977,"teacher_disagreement_score":0.77106076,"about_ca_system_score_codex":0.0015828509,"about_ca_system_score_gemma":0.008558056,"threshold_uncertainty_score":0.9997021},"labels":[],"label_agreement":null},{"id":"W1960015609","doi":"","title":"ARTICLE 7: LESSONS LEARNED AND THE CONTRIBUTIONS OF THE PARIS DECLARATION EVALUATION TO EVALUATION THEORY AND PRACTICE","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; General partnership; Stakeholder; Declaration of independence; Political science; Engineering ethics; Management; Public relations; Sociology; Engineering; Law; Economics","score_opus":0.4814292938080387,"score_gpt":0.5829727740956275,"score_spread":0.1015434802875888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960015609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9101662,0.004609041,0.0069774687,0.06975766,0.00093723513,0.0051537473,0.000016934942,0.000006101351,0.0023756009],"genre_scores_gemma":[0.99815935,0.000043736225,0.00084669783,0.0005366923,0.0001443742,0.000222226,0.000006368822,0.0000068153818,0.00003375225],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9846269,0.010198305,0.0010081126,0.000195192,0.0036532404,0.00031827952],"domain_scores_gemma":[0.9872946,0.0031232627,0.0010825275,0.0003781459,0.0077701877,0.00035129016],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17772475,0.00011668253,0.00022189377,0.00028510872,0.00062016695,0.0003346571,0.00026504748,0.00008491596,0.00047335206],"category_scores_gemma":[0.06991262,0.00006602547,0.00008639953,0.0008653775,0.00030143288,0.0014926995,0.00003709339,0.00021861082,0.000014608472],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024316598,0.00006696698,0.0075412085,0.0000030033195,0.00006498517,7.913851e-8,0.008319969,0.0038494978,0.0005005039,0.036225,0.0008914293,0.9422942],"study_design_scores_gemma":[0.0076347734,0.0004610959,0.4991877,0.000101339516,0.0024548718,0.00012989991,0.017841715,0.280705,0.0017142395,0.16496666,0.02453052,0.00027215676],"about_ca_topic_score_codex":0.00030081943,"about_ca_topic_score_gemma":0.0025241894,"teacher_disagreement_score":0.942022,"about_ca_system_score_codex":0.00038906393,"about_ca_system_score_gemma":0.0032610646,"threshold_uncertainty_score":0.9379219},"labels":[],"label_agreement":null},{"id":"W1968516213","doi":"10.3138/cjpe.29.2.67","title":"Positive Thinking Approaches to Evaluation and Program Perspectives","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Value (mathematics); Nothing; Management science; Yield (engineering); Psychology; Sociology; Computer science; Epistemology; Economics; Artificial intelligence; Philosophy","score_opus":0.5279838688003321,"score_gpt":0.5159939137242172,"score_spread":0.011989955076114889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968516213","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9528537,0.0013167482,0.007100212,0.014710015,0.0007713555,0.005568655,0.000006048685,0.000032175863,0.017641095],"genre_scores_gemma":[0.9787909,0.00000544106,0.020406378,0.00021480814,0.0002717011,0.00023040947,0.000010450893,0.00001199467,0.000057935147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938121,0.0013697738,0.0007558634,0.0003491377,0.003403202,0.00030994095],"domain_scores_gemma":[0.9941518,0.0003404289,0.0005662517,0.00027624745,0.0040459195,0.00061937474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037148044,0.00015903059,0.00026714342,0.00089556945,0.00038796742,0.0009504135,0.00039077224,0.000086050844,0.0005860477],"category_scores_gemma":[0.0067699347,0.00012372942,0.000097366,0.00084460696,0.00011658663,0.00078323367,0.00002309725,0.00021271354,0.00004193263],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015887385,0.000053043816,0.0068796463,0.000002466778,0.00002654236,5.731037e-7,0.010757599,0.0023219972,0.000010755137,0.004618143,0.00042100772,0.9748923],"study_design_scores_gemma":[0.001776503,0.0027966644,0.35188204,0.00014805609,0.00029769368,0.00007364943,0.018958779,0.52719307,0.00011166335,0.07574715,0.020643713,0.000370989],"about_ca_topic_score_codex":0.00023316228,"about_ca_topic_score_gemma":0.0072515956,"teacher_disagreement_score":0.97452134,"about_ca_system_score_codex":0.00051621336,"about_ca_system_score_gemma":0.0027869178,"threshold_uncertainty_score":0.9914587},"labels":[],"label_agreement":null},{"id":"W1973373172","doi":"10.3138/cjpe.29.1.118","title":"Evaluating Humanitarian Action in Real Time: Recent Practices, Challenges, and Innovations","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Accountability; Bridge (graph theory); Action (physics); Process management; Business; Computer science; Risk analysis (engineering); Political science; Sociology; Law","score_opus":0.7423398199910727,"score_gpt":0.610782611392342,"score_spread":0.13155720859873066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973373172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9657997,0.0014325205,0.00019181934,0.012062823,0.00085736666,0.0013525848,0.0000024651365,0.000015840067,0.018284917],"genre_scores_gemma":[0.991486,0.00064852886,0.0072004218,0.0001366399,0.0003108226,0.00006907357,0.000019802943,0.000012746731,0.00011595392],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99503565,0.0014614038,0.0011026176,0.00026095583,0.0018847554,0.0002546425],"domain_scores_gemma":[0.9937544,0.00058043975,0.0017887526,0.00026715652,0.0033417894,0.00026750157],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04204954,0.00012058322,0.00023512966,0.0011079069,0.00022822722,0.0003401719,0.0002636681,0.000099136625,0.001077243],"category_scores_gemma":[0.016112067,0.00010421884,0.000038148242,0.0008264993,0.000064741966,0.0011631175,0.000014588846,0.00029601203,0.000056477806],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000146353905,0.000037427802,0.0030688716,0.0000045002494,0.000010491868,0.0000010489921,0.0013828109,0.0006287749,0.00014583448,0.0019409931,0.00032548216,0.99243915],"study_design_scores_gemma":[0.0023485948,0.0016369164,0.51166326,0.00012200298,0.00011109178,0.000077581884,0.003337605,0.2933215,0.000040456867,0.040117715,0.14693607,0.00028722177],"about_ca_topic_score_codex":0.000791261,"about_ca_topic_score_gemma":0.07126598,"teacher_disagreement_score":0.9921519,"about_ca_system_score_codex":0.00049723766,"about_ca_system_score_gemma":0.0031508715,"threshold_uncertainty_score":0.9998359},"labels":[],"label_agreement":null},{"id":"W197622962","doi":"10.3138/cjpe.16.006","title":"Softly, Softly Catch the Monkey: Innovative Approaches to Measure Socially Sensitive and Complex Issues in Evaluation Research","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Respondent; Reliability (semiconductor); Measure (data warehouse); Psychology; Government (linguistics); Focus (optics); Research design; Management science; Knowledge management; Computer science; Data science; Applied psychology; Sociology; Engineering; Political science; Social science; Data mining","score_opus":0.8765369178333454,"score_gpt":0.6071075175501194,"score_spread":0.26942940028322604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W197622962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91809833,0.00062007055,0.00094201777,0.070605464,0.0003801281,0.004285957,0.000007716958,0.000008821932,0.0050514936],"genre_scores_gemma":[0.99617916,0.000020025389,0.0027245968,0.00041058895,0.00027040558,0.00020735028,0.000017404409,0.000013182778,0.00015727009],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98820215,0.0040938626,0.0010628537,0.00036915942,0.0057772803,0.0004946873],"domain_scores_gemma":[0.985811,0.0008278887,0.00048237285,0.00031635712,0.012195498,0.00036691286],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.089231774,0.00016708636,0.0003221543,0.0014022854,0.00060300704,0.00074123294,0.00050155784,0.00011742711,0.00045551758],"category_scores_gemma":[0.011014511,0.000116640775,0.00005981872,0.0040314095,0.00030309078,0.0006794963,0.00004164402,0.0005415292,0.000052516847],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006695125,0.00005212197,0.03018452,0.000002839743,0.00003278046,0.0000066146067,0.020572351,0.0034838498,0.00008087797,0.0012028335,0.005320245,0.938994],"study_design_scores_gemma":[0.0016550735,0.00080170645,0.731254,0.00010857281,0.00006633645,0.00006573484,0.040650357,0.15855819,0.00009715914,0.037761766,0.028710915,0.00027020014],"about_ca_topic_score_codex":0.0028216436,"about_ca_topic_score_gemma":0.1582799,"teacher_disagreement_score":0.9387238,"about_ca_system_score_codex":0.0010166377,"about_ca_system_score_gemma":0.009901623,"threshold_uncertainty_score":0.9973161},"labels":[],"label_agreement":null},{"id":"W1979608959","doi":"10.3138/cjpe.29.2.139","title":"Spaulding, D. T. (2014). <i>Program evaluation in practice: Core concepts and examples for discussion and analysis</i> (2nd ed.).","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Core (optical fiber); Psychology; Mathematics education; Computer science","score_opus":0.2714138296030427,"score_gpt":0.5558037051431876,"score_spread":0.28438987554014483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979608959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661616,0.0034715976,0.011605441,0.007847168,0.0010292192,0.008220849,0.00003058286,0.00002472461,0.001608794],"genre_scores_gemma":[0.97878826,0.00009819929,0.020119544,0.000251818,0.00017433672,0.00042654114,0.00007788916,0.000013101706,0.000050296927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994524,0.0011773442,0.0011836445,0.00043015394,0.0023244682,0.00036041636],"domain_scores_gemma":[0.993229,0.0010944162,0.001176424,0.00031348414,0.0036629539,0.0005237334],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042265426,0.00019192029,0.00044502097,0.0012120293,0.00029713917,0.00072891515,0.00026422937,0.00013661858,0.00055432075],"category_scores_gemma":[0.011375988,0.00012838865,0.0001245657,0.001012731,0.00017771173,0.0011796054,0.000021765507,0.00021727465,0.0000063646926],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004308046,0.000055845776,0.08831149,0.000007713578,0.000072309456,8.390016e-7,0.0010471055,0.0020229013,0.000024324387,0.0004657226,0.0017812314,0.90616745],"study_design_scores_gemma":[0.002667191,0.0011391591,0.24509616,0.00006521647,0.0012005612,0.00002909034,0.0028438873,0.5725437,0.000018043345,0.0089121265,0.16526063,0.00022422647],"about_ca_topic_score_codex":0.00051015744,"about_ca_topic_score_gemma":0.028923646,"teacher_disagreement_score":0.9059432,"about_ca_system_score_codex":0.0002949724,"about_ca_system_score_gemma":0.0019195237,"threshold_uncertainty_score":0.99695164},"labels":[],"label_agreement":null},{"id":"W1992090873","doi":"10.3138/cjpe.29.2.87","title":"The Utility of a Realist Evaluation Approach in Implementing and Evaluating Health Equity Policy","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Equity (law); Program evaluation; Public economics; Health policy; Program Design Language; Management science; Political science; Economics; Business; Economic growth; Public administration; Computer science; Health care","score_opus":0.6286769634684284,"score_gpt":0.6421045718362257,"score_spread":0.013427608367797328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992090873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96208906,0.0016334095,0.0048631146,0.00986119,0.00045335764,0.004005207,0.000013864914,0.00000830645,0.017072473],"genre_scores_gemma":[0.9949807,0.000019599667,0.004594288,0.00013960055,0.00014317875,0.00008673433,0.00001528573,0.0000073487413,0.0000132863315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9874682,0.0049228254,0.0022742858,0.00030738642,0.004478708,0.00054859277],"domain_scores_gemma":[0.99288416,0.000848428,0.0020018464,0.0004067232,0.003500488,0.00035837048],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21765892,0.00013000553,0.00034015058,0.0007187492,0.00054064416,0.00046250678,0.00047791196,0.00006504433,0.00020686092],"category_scores_gemma":[0.018293262,0.00008979254,0.00008997272,0.0011804741,0.00017821646,0.00045741443,0.000055653527,0.00025916638,0.0000019064586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015028214,0.00002668929,0.03756957,0.000012698565,0.000010298685,6.2624586e-8,0.0018063241,0.00075915386,0.0000117788595,0.0019904247,0.00034051525,0.9574575],"study_design_scores_gemma":[0.0009926595,0.00037833233,0.29183453,0.00004303335,0.00003052947,0.00000984603,0.0023997598,0.66953063,0.000009318124,0.031975348,0.0027281488,0.00006784831],"about_ca_topic_score_codex":0.0060629505,"about_ca_topic_score_gemma":0.06229206,"teacher_disagreement_score":0.9573896,"about_ca_system_score_codex":0.000658036,"about_ca_system_score_gemma":0.012359833,"threshold_uncertainty_score":0.99323916},"labels":[],"label_agreement":null},{"id":"W1998312778","doi":"10.3138/cjpe.29.1.87","title":"Toward a Definition of Evaluation Within the Canadian Context: Who Knew This Would Be So Difficult?","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada; Canadian Evaluation Society; University of Alberta","funders":"","keywords":"Scope (computer science); Presentation (obstetrics); Context (archaeology); Process (computing); Public relations; Psychology; Sociology; Computer science; Social psychology; Political science; History; Medicine","score_opus":0.40214964057962616,"score_gpt":0.47723035797279373,"score_spread":0.07508071739316757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998312778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8880248,0.0019175094,0.0017628265,0.05618901,0.0035702928,0.005495005,0.000063613945,0.000024568824,0.042952396],"genre_scores_gemma":[0.9968018,0.000008582756,0.0010780579,0.0015976952,0.00022440203,0.00012061209,0.000042294247,0.00001539343,0.00011118078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.991046,0.0019711903,0.0015937133,0.00028778997,0.0047044074,0.0003968919],"domain_scores_gemma":[0.98683476,0.00041912403,0.0016694326,0.000505216,0.0098079555,0.0007635057],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04370066,0.00020625287,0.0003957406,0.0009573403,0.0007037383,0.00077894336,0.0006544104,0.00026031447,0.003315985],"category_scores_gemma":[0.01223579,0.00013690375,0.000200939,0.0012587762,0.00031379948,0.0006886181,0.000014192629,0.0005574127,0.00008770836],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032460594,0.00004989979,0.010449235,0.000012851574,0.00007760853,0.0000025531235,0.011303892,0.00397962,0.00004529662,0.017406635,0.011627506,0.94501245],"study_design_scores_gemma":[0.0047617615,0.0021047462,0.16806246,0.00043451664,0.00092295575,0.00015396807,0.010337468,0.5363824,0.00044578296,0.11815404,0.1575697,0.0006702389],"about_ca_topic_score_codex":0.097979166,"about_ca_topic_score_gemma":0.8993084,"teacher_disagreement_score":0.9443422,"about_ca_system_score_codex":0.0011581569,"about_ca_system_score_gemma":0.021922711,"threshold_uncertainty_score":0.99759513},"labels":[],"label_agreement":null},{"id":"W2004772372","doi":"10.3138/cjpe.29.2.145","title":"Pawson, R. (2013). <i>The science of evaluation: A realist manifesto.</i>","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; University of Toronto","funders":"","keywords":"Manifesto; Philosophy; Epistemology; Sociology; Psychology; Political science; Law","score_opus":0.31751238103500456,"score_gpt":0.5079111319318299,"score_spread":0.19039875089682534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004772372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91929597,0.0014031162,0.0041973265,0.026350671,0.0042339847,0.003914512,0.000015036355,0.000018947598,0.040570457],"genre_scores_gemma":[0.99700755,0.000010711163,0.0022111246,0.00028539516,0.0002938545,0.00006693462,0.000005627837,0.000008393479,0.00011042166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896608,0.0012605425,0.0013670324,0.0002767927,0.0070774932,0.00035734798],"domain_scores_gemma":[0.9842317,0.00048628793,0.001488773,0.00069040054,0.012625975,0.0004768387],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09991371,0.00013534862,0.00027149564,0.00082435407,0.00054188527,0.00050238887,0.0010893304,0.00006250703,0.0021748364],"category_scores_gemma":[0.011344653,0.00008640947,0.00013766943,0.0020356113,0.00067234086,0.0008952027,0.000025647629,0.00021639223,0.00007371929],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014914579,0.00004224728,0.0054545803,0.0000051808256,0.000016180891,0.0000011013177,0.0013149034,0.0077252192,0.00022252322,0.0046076025,0.01266062,0.9679349],"study_design_scores_gemma":[0.0023132197,0.0013751372,0.18477406,0.00012781528,0.00035475925,0.00020611942,0.002398261,0.55174744,0.0010519045,0.07609136,0.1792323,0.00032763678],"about_ca_topic_score_codex":0.0011407328,"about_ca_topic_score_gemma":0.015753442,"teacher_disagreement_score":0.96760726,"about_ca_system_score_codex":0.0004510296,"about_ca_system_score_gemma":0.012647062,"threshold_uncertainty_score":0.99873734},"labels":[],"label_agreement":null},{"id":"W2014034431","doi":"10.3138/cjpe.29.2.21","title":"Les défis de l’évaluation d'un programme d'intervention en contexte carcéral","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Centre Jeunesse de Quebec","funders":"","keywords":"Prison; Valuation (finance); Government (linguistics); Psychology; Intervention (counseling); Public relations; Welfare economics; Political science; Business; Sociology; Applied psychology; Criminology; Economics; Finance; Psychiatry","score_opus":0.29812468333778513,"score_gpt":0.5076521920618863,"score_spread":0.20952750872410114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014034431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93198735,0.00038223452,0.058638334,0.0030131429,0.001010433,0.0013903506,0.0000053379013,0.000025903619,0.0035469453],"genre_scores_gemma":[0.9843554,0.000007485693,0.014716613,0.00015746537,0.0003802183,0.00012446543,0.000026289601,0.000016108723,0.0002159829],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914603,0.0039020374,0.0013026382,0.00026535912,0.0026047612,0.00046485887],"domain_scores_gemma":[0.99379027,0.000662523,0.0010219399,0.0003316745,0.003589748,0.0006038534],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06763887,0.00017148347,0.00030065456,0.0007434563,0.00034329822,0.0006582044,0.0005640265,0.00014783633,0.002534762],"category_scores_gemma":[0.012622556,0.00014023951,0.00028526262,0.0006534341,0.000109175504,0.00072126806,0.000016497463,0.0003028667,0.000093258735],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020143412,0.000056371187,0.03537898,0.0000054799757,0.00003018394,0.0000016651909,0.0023092725,0.0014761053,0.00006913379,0.0012333262,0.00054839754,0.95887095],"study_design_scores_gemma":[0.003488655,0.001895664,0.494542,0.00013206185,0.00026799794,0.00012138887,0.0025983602,0.33044395,0.00057877373,0.053858083,0.1117418,0.00033125895],"about_ca_topic_score_codex":0.0025259196,"about_ca_topic_score_gemma":0.023518635,"teacher_disagreement_score":0.95853966,"about_ca_system_score_codex":0.0009659827,"about_ca_system_score_gemma":0.0024539954,"threshold_uncertainty_score":0.9983771},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933179,0.000079138474,0.002806593,0.0007727885,0.0014271574,0.0011369373,9.586137e-7,0.000012903229,0.00044564836],"genre_scores_gemma":[0.99138784,0.0000067966835,0.007882078,0.00003538983,0.00058585516,0.00005212381,0.000007899006,0.000007662173,0.00003433508],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9968591,0.0011777562,0.0005003483,0.00011803857,0.0011122685,0.00023252387],"domain_scores_gemma":[0.99680334,0.000046964935,0.00074887596,0.00017406132,0.0019658322,0.00026091377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010725537,0.0000784632,0.00013302389,0.00016962943,0.0006142583,0.00037213476,0.00036593308,0.00007332381,0.000105354964],"category_scores_gemma":[0.0023285286,0.00006789251,0.00007706416,0.0004907573,0.00018786978,0.0023344262,0.000009432444,0.00014669972,0.000002771825],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005524722,0.00009550889,0.015331832,0.000006825953,0.000017316903,1.6259348e-7,0.016021939,0.00046757053,0.000051814408,0.004677142,0.00003050773,0.96329385],"study_design_scores_gemma":[0.0042645093,0.0066936775,0.36389986,0.0010441449,0.0017380886,0.000023840645,0.09124908,0.26895946,0.0006418331,0.21621865,0.04410512,0.0011617318],"about_ca_topic_score_codex":0.01384576,"about_ca_topic_score_gemma":0.17540663,"teacher_disagreement_score":0.9621321,"about_ca_system_score_codex":0.00046647404,"about_ca_system_score_gemma":0.0025733889,"threshold_uncertainty_score":0.99272114},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818291,0.0017664502,0.00705335,0.003903521,0.002136416,0.0018717007,7.2987933e-7,0.000025645655,0.001413087],"genre_scores_gemma":[0.99321127,0.000010736478,0.0013363078,0.0015540629,0.003757213,0.000067155226,0.000036487174,0.000020545318,0.000006193325],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984736,0.0001212065,0.0003548855,0.00017692681,0.00063604873,0.00023736409],"domain_scores_gemma":[0.9968494,0.000085797896,0.00044904,0.00009603573,0.0024217782,0.00009791231],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0051605976,0.00013271504,0.00016868275,0.0005265332,0.00025198757,0.0011095286,0.0001474989,0.00008121482,0.0003145],"category_scores_gemma":[0.0024384733,0.00012853398,0.00004143199,0.00064181816,0.00006115381,0.0036873303,0.000025267345,0.0001474628,0.00004504638],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012830899,0.000016344446,0.007678952,0.00001941446,0.000025488333,8.409694e-7,0.0017092214,0.0013922849,0.000021218922,0.0012426509,0.0012093883,0.9866714],"study_design_scores_gemma":[0.005076238,0.00056917337,0.39174536,0.0032035648,0.0014029295,0.000037198944,0.02525096,0.3385451,0.00022438724,0.071114324,0.16137683,0.001453924],"about_ca_topic_score_codex":0.00017742005,"about_ca_topic_score_gemma":0.0032989443,"teacher_disagreement_score":0.98521745,"about_ca_system_score_codex":0.00024136671,"about_ca_system_score_gemma":0.000310537,"threshold_uncertainty_score":0.9999274},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76431143,0.00034791086,0.0001761131,0.22826877,0.00031346176,0.0052495454,0.000017688451,0.000016464126,0.0012986104],"genre_scores_gemma":[0.9587715,0.000021565704,0.0064641535,0.03179115,0.0014282179,0.0011752925,0.000023901219,0.000036154517,0.00028801523],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9862908,0.00834821,0.0016339703,0.0003278533,0.0021407097,0.0012584487],"domain_scores_gemma":[0.98594254,0.0037415065,0.0009129293,0.00039718862,0.0078604035,0.0011454466],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.114995256,0.0001699202,0.00033436363,0.001647651,0.002326097,0.00017748887,0.0003388198,0.00014689073,0.0007630364],"category_scores_gemma":[0.060736455,0.00013146004,0.000025818312,0.0031346905,0.00038945136,0.0003690188,0.000065121494,0.00085460173,0.00016395809],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009045717,0.000015836411,0.029131811,0.00012270018,0.000027796676,1.684268e-7,0.014798172,0.00009792206,0.000104073355,0.005186394,0.05560167,0.89490443],"study_design_scores_gemma":[0.002625669,0.0032422547,0.3649143,0.0012483129,0.00009748103,0.0000073797787,0.004015087,0.049390275,0.000039254006,0.084209405,0.48982567,0.00038492915],"about_ca_topic_score_codex":0.001535462,"about_ca_topic_score_gemma":0.004626486,"teacher_disagreement_score":0.8945195,"about_ca_system_score_codex":0.0016102366,"about_ca_system_score_gemma":0.01863285,"threshold_uncertainty_score":0.9989727},"labels":[],"label_agreement":null},{"id":"W2043777716","doi":"10.3138/cjpe.29.1.36","title":"Supporting Knowledge Translation Through Evaluation: Evaluator as Knowledge Broker","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McMaster University; Queen's University","funders":"","keywords":"Knowledge translation; Context (archaeology); Knowledge management; Computer science; History","score_opus":0.4946854783565933,"score_gpt":0.5959329823406669,"score_spread":0.10124750398407362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043777716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6728983,0.010307306,0.019333895,0.0070667393,0.008343509,0.007601594,0.00001829282,0.00009115905,0.2743392],"genre_scores_gemma":[0.99219674,0.000015020231,0.0056251124,0.0002702803,0.00094635424,0.00021655628,0.000048190017,0.000033164277,0.0006486035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98792875,0.003570183,0.0024330136,0.0005339553,0.0048655192,0.0006685862],"domain_scores_gemma":[0.9837446,0.0011667992,0.0016682688,0.00064738863,0.01200564,0.0007672675],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.07480533,0.0003111415,0.00053230993,0.0009844174,0.00058571313,0.00076042814,0.0008366985,0.00022395722,0.012596377],"category_scores_gemma":[0.014309654,0.00025693356,0.00035523635,0.0016892706,0.00017572739,0.0018474521,0.00002174334,0.00042150606,0.0012681882],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002283637,0.000101648606,0.0040514097,0.00001140184,0.000045874916,0.0000011308707,0.0072878283,0.0020152899,0.000083278275,0.0012598572,0.007003614,0.97811586],"study_design_scores_gemma":[0.0030289828,0.001147647,0.013149817,0.00011747747,0.00045390197,0.000080298465,0.0021614511,0.4814937,0.00031977752,0.05012747,0.44753796,0.00038150788],"about_ca_topic_score_codex":0.00026302162,"about_ca_topic_score_gemma":0.0144968135,"teacher_disagreement_score":0.9777343,"about_ca_system_score_codex":0.00092792994,"about_ca_system_score_gemma":0.015243008,"threshold_uncertainty_score":0.9999883},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959353,0.00044506005,0.0002246399,0.0011735344,0.0010404341,0.0005143989,0.00006778324,0.00001784025,0.0005810109],"genre_scores_gemma":[0.9978414,0.000010185999,0.00029700896,0.00034440914,0.0010533881,0.000011126098,0.0004104125,0.000016704387,0.000015317568],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980599,0.00009041558,0.0007424291,0.00022042438,0.00060019747,0.00028659854],"domain_scores_gemma":[0.99749815,0.000116814255,0.0007813316,0.00043451582,0.0010530287,0.0001161332],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029078287,0.00015164277,0.00028170476,0.00031816424,0.0001989553,0.00021026989,0.00047672287,0.000076992066,0.0015896144],"category_scores_gemma":[0.00096446526,0.0001440152,0.00010027187,0.00055642106,0.000057721732,0.0011795235,0.000071712246,0.00018964232,0.000051509534],"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":[0.00005518686,0.00030382027,0.8799581,0.0001855098,0.00015194567,0.000064183674,0.0004640136,0.000267573,0.00021895091,0.0003287907,0.0076488666,0.11035307],"study_design_scores_gemma":[0.0024355978,0.00016997757,0.6898462,0.000710383,0.0014681672,0.000031341653,0.002796312,0.08567972,0.000027464584,0.0027198552,0.21350524,0.0006097208],"about_ca_topic_score_codex":0.024962317,"about_ca_topic_score_gemma":0.1261321,"teacher_disagreement_score":0.20585638,"about_ca_system_score_codex":0.0001161948,"about_ca_system_score_gemma":0.0005863765,"threshold_uncertainty_score":0.99932307},"labels":[],"label_agreement":null},{"id":"W205902208","doi":"10.3138/cjpe.17.003","title":"The Inclusion of Stakeholders in Evaluation: Benefits and Drawbacks","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stakeholder; Inclusion (mineral); Foundation (evidence); Process (computing); Empirical research; Evaluation methods; Business; Process management; Management science; Knowledge management; Psychology; Computer science; Public relations; Political science; Economics; Social psychology; Engineering","score_opus":0.5130399514960976,"score_gpt":0.5057613927462337,"score_spread":0.007278558749863939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W205902208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803259,0.00886872,0.000044557295,0.005906369,0.00052697444,0.0011872357,0.0000038738667,0.0000024912663,0.003133922],"genre_scores_gemma":[0.99912757,0.00019186761,0.00043481757,0.00008095465,0.000059917576,0.000037310023,0.0000025166855,0.0000054508273,0.00005957952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99444216,0.0008265634,0.0010833027,0.00016094056,0.0032664787,0.00022056785],"domain_scores_gemma":[0.99520004,0.0005001989,0.0007545359,0.00026126558,0.0030418106,0.00024214291],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03181007,0.00009510297,0.00019059368,0.00056602183,0.00044960904,0.00023232038,0.00039405163,0.000066685716,0.0014652563],"category_scores_gemma":[0.004038637,0.000062309475,0.000064369,0.0008690623,0.00015786412,0.0005074066,0.000040873187,0.00017527182,0.0000114971435],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075408116,0.000022595688,0.019686252,0.0000017975298,0.000007899321,7.959297e-7,0.0028092396,0.0040381323,0.0000123763875,0.00033094443,0.0008548091,0.97222763],"study_design_scores_gemma":[0.0031207262,0.000817812,0.2605093,0.0001705843,0.00011479041,0.000042324482,0.0056449273,0.6653348,0.00012428105,0.02141505,0.042499896,0.00020549064],"about_ca_topic_score_codex":0.00034148546,"about_ca_topic_score_gemma":0.041564018,"teacher_disagreement_score":0.9720221,"about_ca_system_score_codex":0.0003028049,"about_ca_system_score_gemma":0.0015919841,"threshold_uncertainty_score":0.9994475},"labels":[],"label_agreement":null},{"id":"W2071368667","doi":"10.3138/cjpe.29.2.128","title":"Pertinence de la recension réaliste des écrits pour l'analyse des évaluations de programmes complexes : l'exemple du suivi dans la communauté en santé mentale","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Relevance (law); Sociology; Humanities; Philosophy; Political science","score_opus":0.17300183107063663,"score_gpt":0.4822728331215107,"score_spread":0.3092710020508741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071368667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.977158,0.00045776306,0.017090153,0.0018479306,0.00013392296,0.00069734745,0.000014509417,0.000028090768,0.0025722487],"genre_scores_gemma":[0.9540495,0.00009759481,0.045279708,0.00018227499,0.00015074783,0.00009942266,0.00004436614,0.00002158215,0.000074768155],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98976254,0.006535487,0.0010659554,0.0002707756,0.0017602461,0.0006049715],"domain_scores_gemma":[0.9929226,0.0026798067,0.000684012,0.00041074745,0.0025553901,0.0007474227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047947854,0.00022138316,0.0003387129,0.0006150966,0.00094313355,0.0009169192,0.0007625128,0.00013637899,0.0008361263],"category_scores_gemma":[0.015348297,0.000181409,0.00020978307,0.0008988248,0.000679148,0.0007580374,0.000043557666,0.00033198783,0.000036363785],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024785413,0.00017012101,0.34319475,0.000017038758,0.00005097424,0.000008028675,0.027511027,0.00441703,0.002464872,0.0006405029,0.0020497402,0.6194511],"study_design_scores_gemma":[0.0013423505,0.00051998836,0.67978364,0.00028672552,0.00027294017,0.00049263344,0.012671437,0.23844776,0.0010580502,0.045313496,0.019538973,0.00027202856],"about_ca_topic_score_codex":0.0054344814,"about_ca_topic_score_gemma":0.08687384,"teacher_disagreement_score":0.61917907,"about_ca_system_score_codex":0.0014317207,"about_ca_system_score_gemma":0.0058849086,"threshold_uncertainty_score":0.9997508},"labels":[],"label_agreement":null},{"id":"W2081701430","doi":"10.3138/cjpe.29.1.62","title":"Assessing the Quality of Aboriginal Program Evaluations","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Treasury; Popularity; Quality (philosophy); Context (archaeology); Government (linguistics); Program evaluation; Strengths and weaknesses; Corporate governance; Replicate; Business; Political science; Public administration; Psychology; Finance; Geography; Statistics","score_opus":0.5441703005540053,"score_gpt":0.6713453947850856,"score_spread":0.1271750942310803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081701430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97209966,0.00031010687,0.008894664,0.0053995093,0.0012740468,0.001951466,0.0000056940157,0.000016952055,0.010047918],"genre_scores_gemma":[0.98893946,0.0000050339804,0.010430857,0.00015178813,0.00026907373,0.000115135685,0.000010135984,0.00000908745,0.00006944371],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9904861,0.0028566509,0.001828106,0.00021410797,0.0043084575,0.00030658382],"domain_scores_gemma":[0.9886031,0.0011304843,0.0019521005,0.0005300196,0.007432273,0.0003520031],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.071635656,0.00013753271,0.00033564895,0.00053151516,0.00040941144,0.00084167527,0.00077615504,0.00008141744,0.0014301499],"category_scores_gemma":[0.009443286,0.00008536712,0.00021772092,0.0012379902,0.00026507955,0.0010719385,0.0000105603185,0.00028323123,0.000041650314],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058553255,0.00007095182,0.045118,0.000005480016,0.000024198984,2.4565028e-7,0.0007468679,0.0025363949,0.0000763465,0.0031776682,0.00087601866,0.94736195],"study_design_scores_gemma":[0.0010424993,0.0006837851,0.71918356,0.00006230642,0.00015732835,0.00001821178,0.0021339988,0.13614297,0.00015909324,0.024139095,0.11611635,0.0001608],"about_ca_topic_score_codex":0.0008393119,"about_ca_topic_score_gemma":0.012815612,"teacher_disagreement_score":0.9472012,"about_ca_system_score_codex":0.00027066653,"about_ca_system_score_gemma":0.008181978,"threshold_uncertainty_score":0.9994827},"labels":[],"label_agreement":null},{"id":"W2081929183","doi":"10.3138/cjpe.29.2.48","title":"Think Positively! And Make a Difference Through Evaluation","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Obligation; Punishment (psychology); Theme (computing); Accountability; Reinforcement; Psychology; Social psychology; Epistemology; Computer science; Political science; Law; Philosophy","score_opus":0.37937904172344933,"score_gpt":0.5354819516833826,"score_spread":0.1561029099599333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081929183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751555,0.0007254456,0.008023181,0.0041012145,0.0008663202,0.0013767516,0.0000056929543,0.0000111674135,0.009734743],"genre_scores_gemma":[0.9938131,0.000015164867,0.0053049154,0.00047344924,0.00020133716,0.000040659423,0.000010256865,0.000008770637,0.0001323776],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99398226,0.0013833162,0.00084569765,0.00026312695,0.0032588663,0.00026673256],"domain_scores_gemma":[0.9937254,0.00042909873,0.0007310844,0.0002885477,0.004448332,0.00037753992],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026156405,0.00014264004,0.0002583504,0.00041681025,0.00029752773,0.0005839048,0.00035510003,0.00009251741,0.0011795682],"category_scores_gemma":[0.0060253507,0.00010658927,0.00008640065,0.0005356559,0.00013250991,0.00060677255,0.000016392629,0.0002102,0.00004642053],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011387634,0.000021582024,0.014522768,0.000002868024,0.000017250037,8.596913e-7,0.0029339392,0.00045319955,0.000071333,0.0019004485,0.0004294713,0.9796349],"study_design_scores_gemma":[0.0015823615,0.0007910879,0.5868156,0.000073620045,0.00018787675,0.00007166901,0.0015902997,0.29542643,0.000103734186,0.09681657,0.016343882,0.00019683535],"about_ca_topic_score_codex":0.00041622252,"about_ca_topic_score_gemma":0.0112039475,"teacher_disagreement_score":0.97943807,"about_ca_system_score_codex":0.00030348395,"about_ca_system_score_gemma":0.0030664832,"threshold_uncertainty_score":0.9997335},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40701616,0.12488848,0.27457717,0.04129592,0.018606622,0.010657351,0.000075242366,0.00014054317,0.12274251],"genre_scores_gemma":[0.99524605,0.0000026638863,0.0029883985,0.00013910593,0.00020724098,0.000014779654,3.9827694e-7,0.0000067332458,0.001394642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99597716,0.00044093034,0.0010350749,0.00016977158,0.0020932385,0.00028382562],"domain_scores_gemma":[0.99547756,0.0005671687,0.0007480641,0.00037642661,0.002402568,0.0004281917],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0093811015,0.00009739406,0.00020506396,0.00031221777,0.00054591557,0.0010123986,0.0007691639,0.000057665304,0.0011118612],"category_scores_gemma":[0.0057229665,0.000054361935,0.00017519422,0.0006003205,0.0001388561,0.00031426636,0.000016473634,0.00017841422,0.00012159143],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037857421,0.000010230766,0.0010631449,3.1473667e-7,0.000008869349,0.000011098233,0.0006729676,0.012801804,0.0000036035099,0.006142259,0.08598892,0.893293],"study_design_scores_gemma":[0.0003062218,0.00013448081,0.0014262673,0.000014507456,0.0000143416355,0.00007830094,0.0006229226,0.7298859,0.0000017807978,0.14460978,0.12283112,0.00007441043],"about_ca_topic_score_codex":0.00027053794,"about_ca_topic_score_gemma":0.0106220525,"teacher_disagreement_score":0.8932186,"about_ca_system_score_codex":0.00017694781,"about_ca_system_score_gemma":0.00076348335,"threshold_uncertainty_score":0.9998013},"labels":[],"label_agreement":null},{"id":"W2113515522","doi":"10.3138/cjpe.016.001","title":"Addressing Attribution through Contribution Analysis: Using Performance Measures Sensibly","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":342,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Canada","funders":"","keywords":"Attribution; Accountability; Authorship attribution; Public relations; Administration (probate law); Psychology; Business; Political science; Social psychology; Computer science; Law; Artificial intelligence","score_opus":0.6796845234554371,"score_gpt":0.5702891541640307,"score_spread":0.10939536929140636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113515522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8888697,0.00082637015,0.107565895,0.0007287594,0.0006935711,0.0006666715,0.000008013981,0.000013635787,0.00062737573],"genre_scores_gemma":[0.99560225,0.000048386515,0.0038184223,0.00013507526,0.0002826333,0.000016131764,0.000042168987,0.000008724095,0.00004621566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993841,0.0008973504,0.0013199361,0.00027050773,0.0032349837,0.0004362063],"domain_scores_gemma":[0.98958164,0.00015144452,0.001232262,0.00033769858,0.008321461,0.000375514],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018551076,0.0001717153,0.00041818607,0.0012312278,0.0006017481,0.00065463595,0.00035469665,0.00013210381,0.001019635],"category_scores_gemma":[0.00228243,0.00013822787,0.00027456754,0.003573975,0.00011652338,0.0018451835,0.0000119093975,0.00026303317,0.000044166944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057296238,0.0000558953,0.2139138,0.000003362315,0.00025842924,0.000012390333,0.0008444975,0.10988875,0.00038922628,0.00026829354,0.00036931163,0.67393875],"study_design_scores_gemma":[0.0013251012,0.00042452785,0.20916432,0.000098227654,0.0013315025,0.00017806873,0.00088060094,0.73570275,0.0007337685,0.0023098204,0.04758309,0.0002682058],"about_ca_topic_score_codex":0.0005635114,"about_ca_topic_score_gemma":0.010192095,"teacher_disagreement_score":0.67367053,"about_ca_system_score_codex":0.0009571845,"about_ca_system_score_gemma":0.0041317972,"threshold_uncertainty_score":0.99989355},"labels":[],"label_agreement":null},{"id":"W2115776235","doi":"10.3138/cjpe.0023.004","title":"Evaluation Capacity Building in the Schools: Administrator-Led and Teacher-Led Perspectives","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Capacity building; Sustainability; Capacity development; Process (computing); Process management; Business; Knowledge management; Computer science; Political science; Environmental resource management; Environmental science","score_opus":0.3996361563938446,"score_gpt":0.5246982158041983,"score_spread":0.1250620594103537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115776235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9854289,0.0011366346,0.0002529405,0.009171236,0.00021724038,0.0013728151,0.000002145243,0.000005769785,0.002412277],"genre_scores_gemma":[0.99716765,0.000014569034,0.0023194188,0.00022213328,0.00019456883,0.000057013527,0.0000030726114,0.0000049661026,0.000016610828],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924151,0.0024319736,0.0008886255,0.00026991926,0.0037086448,0.00028575066],"domain_scores_gemma":[0.99538875,0.00025034384,0.000607017,0.0002950518,0.0031627752,0.00029605237],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062279426,0.00014709054,0.00023754401,0.0006950101,0.0002843963,0.0008050032,0.00047215234,0.0000934149,0.0008007645],"category_scores_gemma":[0.009834752,0.00009893366,0.00009211127,0.0009541929,0.00009059022,0.00093157904,0.000005628225,0.00044257264,0.0000121499215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022594999,0.00010005707,0.024496809,0.0000016249887,0.000019823403,0.0000046227606,0.009449862,0.0006525071,0.00011272338,0.0017046955,0.00080275617,0.96263194],"study_design_scores_gemma":[0.0020577523,0.0010372606,0.7908895,0.000073413554,0.00018713968,0.00010187177,0.03170789,0.11587414,0.000047919355,0.053865302,0.0039549638,0.00020284687],"about_ca_topic_score_codex":0.0002570339,"about_ca_topic_score_gemma":0.011996215,"teacher_disagreement_score":0.9624291,"about_ca_system_score_codex":0.000737633,"about_ca_system_score_gemma":0.005078318,"threshold_uncertainty_score":0.99850583},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8383629,0.027697975,0.00032249457,0.045379467,0.023315554,0.028186068,0.00010014488,0.00026348463,0.03637197],"genre_scores_gemma":[0.972982,0.000094441704,0.018987127,0.0009886258,0.0018876676,0.0025815943,0.00016343594,0.000057753845,0.0022573858],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942981,0.002375025,0.0011990838,0.00018822003,0.0011492351,0.0007903467],"domain_scores_gemma":[0.99287915,0.0006367845,0.0010561766,0.00029411318,0.003620962,0.0015128385],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.007977033,0.00018300103,0.0002831656,0.00019139028,0.0017265915,0.00009567205,0.00047787777,0.00023688003,0.0007164588],"category_scores_gemma":[0.0025918717,0.00012236684,0.00010392793,0.00055224606,0.00018059222,0.00034951605,0.0000234679,0.00081383483,0.0001547375],"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":[0.00008816049,0.00009804734,0.03059367,0.000028298047,0.00007809574,0.000012088471,0.009205649,0.00023491275,0.00000454715,0.0013080854,0.21302475,0.7453237],"study_design_scores_gemma":[0.0013728549,0.0004742291,0.013007837,0.0005657194,0.00013830616,0.00000713331,0.014720661,0.004138851,0.000005452462,0.010197243,0.95521146,0.00016027373],"about_ca_topic_score_codex":0.009778941,"about_ca_topic_score_gemma":0.20019463,"teacher_disagreement_score":0.74516344,"about_ca_system_score_codex":0.0015809899,"about_ca_system_score_gemma":0.016635947,"threshold_uncertainty_score":0.99957305},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97429883,0.002531088,0.009240357,0.0024466454,0.0030140784,0.003047635,0.000019687364,0.000029149143,0.005372525],"genre_scores_gemma":[0.9956681,0.000020120915,0.0031364667,0.00013255818,0.0004426826,0.00020207124,0.00010335596,0.00002487559,0.0002697322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98329985,0.0070517953,0.0019123338,0.00039121677,0.00678217,0.0005626066],"domain_scores_gemma":[0.97374004,0.00080995704,0.0013132354,0.00087699085,0.022405144,0.000854659],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12187791,0.00021963265,0.00045249006,0.0020740745,0.00048989704,0.00045140172,0.0008336053,0.00020222264,0.0034348727],"category_scores_gemma":[0.015206418,0.00017862966,0.00018638776,0.0019310263,0.00054518,0.0015328806,0.000020413727,0.0005231085,0.00024274565],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007584391,0.00020909775,0.0030613132,0.000015866717,0.000021600525,4.3677656e-7,0.0029694207,0.0051443544,0.0008792125,0.0009452294,0.012389973,0.9742876],"study_design_scores_gemma":[0.003614059,0.0025831645,0.048135635,0.00030337542,0.0002968731,0.000016417747,0.0021241393,0.63264036,0.001974932,0.028588396,0.27935314,0.0003694677],"about_ca_topic_score_codex":0.0005668274,"about_ca_topic_score_gemma":0.06763281,"teacher_disagreement_score":0.9739182,"about_ca_system_score_codex":0.00086062733,"about_ca_system_score_gemma":0.014532616,"threshold_uncertainty_score":0.9974761},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98211724,0.00017297773,0.000039052444,0.007085705,0.0011678508,0.0045724995,0.000020711377,0.000020815445,0.0048031304],"genre_scores_gemma":[0.98599803,0.000007154201,0.012699672,0.00014371557,0.00042177827,0.0006732459,0.00001581263,0.00001776347,0.000022847038],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99358016,0.002493034,0.0012426302,0.0002312599,0.0019322605,0.00052066054],"domain_scores_gemma":[0.9928836,0.0010587769,0.0013685841,0.00028479815,0.004189847,0.00021438392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026505446,0.0001789538,0.00037377677,0.0004250431,0.00061861053,0.000045153916,0.0004279754,0.00019404784,0.000765029],"category_scores_gemma":[0.0064940625,0.00012758141,0.00012683433,0.00061604136,0.0002313475,0.00025219607,0.000026193786,0.0017050303,0.000005468673],"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":[0.000008424662,0.00020851055,0.833883,0.00017056245,0.00007308399,0.000008492991,0.0151824085,0.00020172312,0.000116575,0.00048249928,0.002133023,0.1475317],"study_design_scores_gemma":[0.0014448528,0.00045498216,0.9631779,0.00063269516,0.00010841824,0.000015374664,0.005289967,0.01954671,0.0000036760805,0.004863692,0.0043306164,0.00013111014],"about_ca_topic_score_codex":0.0009457337,"about_ca_topic_score_gemma":0.1818829,"teacher_disagreement_score":0.18093716,"about_ca_system_score_codex":0.00080363255,"about_ca_system_score_gemma":0.008638313,"threshold_uncertainty_score":0.9969818},"labels":[],"label_agreement":null},{"id":"W2140061750","doi":"10.3138/cjpe.29.3.134","title":"From the Outside, Looking In with a Smile: A Summary and Discussion of CES's Credentialed Evaluator Designation","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credentialing; Credential; Management; Action (physics); Political science; Context (archaeology); Humanities; Sociology; Public relations; Law; Art; Geography; Economics","score_opus":0.3069585015711737,"score_gpt":0.4904886684929546,"score_spread":0.18353016692178087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140061750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99144953,0.00095035747,0.0018591677,0.0037201822,0.00036794308,0.001120146,0.000009154853,0.0000036115919,0.00051991775],"genre_scores_gemma":[0.99705064,0.000009075789,0.0026254035,0.00008188971,0.00012422285,0.000039592305,0.000012399609,0.000007507659,0.000049275695],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99515665,0.0010767912,0.0008562973,0.00018214624,0.002554526,0.00017359694],"domain_scores_gemma":[0.9959604,0.0003691143,0.00083307904,0.00022709927,0.002304762,0.00030554715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019321483,0.00010705558,0.00023696144,0.00045075166,0.000100328056,0.00027299792,0.00032943065,0.0000616141,0.00028358307],"category_scores_gemma":[0.002799577,0.000052242896,0.000047127258,0.00072148273,0.000121780315,0.000711816,0.000016895376,0.00016750596,0.0000046752352],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013370415,0.000044525146,0.2553846,0.0000033416168,0.000029763833,0.0000061186524,0.008266307,0.0037640943,0.000109257366,0.000056246667,0.0022023504,0.72999966],"study_design_scores_gemma":[0.006483807,0.0015046025,0.7008967,0.00060247775,0.0003011081,0.000041219395,0.023526419,0.229813,0.00036873936,0.028088788,0.008090224,0.0002829263],"about_ca_topic_score_codex":0.0023860384,"about_ca_topic_score_gemma":0.060597923,"teacher_disagreement_score":0.7297168,"about_ca_system_score_codex":0.00027958886,"about_ca_system_score_gemma":0.0052931546,"threshold_uncertainty_score":0.95654374},"labels":[],"label_agreement":null},{"id":"W2142219519","doi":"","title":"System-Wide Program Assessment with Performance Indicators: Alberta's Performance Funding Mechanisms.","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Performance measurement; Business; Performance indicator; Process management; Political science; Accounting; Marketing","score_opus":0.14727823206226057,"score_gpt":0.4519045550663222,"score_spread":0.30462632300406167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142219519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9649002,0.00011576724,0.0008916878,0.00087647216,0.0006103365,0.0025440531,0.0000044402746,0.00004707519,0.030009992],"genre_scores_gemma":[0.98206955,0.00003031482,0.01618524,0.000159444,0.0001795644,0.00042658765,0.000023719538,0.000030972733,0.0008946069],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924899,0.0005770651,0.0015188581,0.00043900654,0.004249873,0.0007253268],"domain_scores_gemma":[0.9951773,0.0002815121,0.0011584765,0.00056906586,0.0018846106,0.0009289871],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014610207,0.0003147581,0.00048723977,0.0013165412,0.00070553925,0.00093795906,0.00091078854,0.00014737938,0.005684865],"category_scores_gemma":[0.00035567192,0.00022317725,0.00015133007,0.0020273048,0.00015743419,0.0017825487,0.000015840144,0.00048394522,0.0002700378],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004678719,0.00008465419,0.0908091,0.000032844197,0.000056412508,0.0000074152463,0.0005525503,0.006194991,0.0000045362267,0.0003741831,0.0004817914,0.90135473],"study_design_scores_gemma":[0.003021059,0.0058676153,0.443175,0.00074413774,0.00033743845,0.0003880192,0.0024658793,0.41123438,0.00023361966,0.00036605637,0.13149238,0.0006744256],"about_ca_topic_score_codex":0.00049013254,"about_ca_topic_score_gemma":0.006258432,"teacher_disagreement_score":0.9006803,"about_ca_system_score_codex":0.0013159168,"about_ca_system_score_gemma":0.0074588903,"threshold_uncertainty_score":0.9981679},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":true,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2150927259","doi":"10.3138/cjpe.27.003","title":"The Art of the Nudge: Five Practices for Developmental Evaluators","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Servant; Psychology; Adaptation (eye); Servant leadership; Energy (signal processing); Pedagogy; Applied psychology; Public relations; Social psychology; Political science; Computer science","score_opus":0.5020626007095538,"score_gpt":0.5787691116820812,"score_spread":0.07670651097252745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150927259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9608999,0.0018735748,0.0006508701,0.0192021,0.0049543967,0.003883451,0.000018555074,0.00000582638,0.008511353],"genre_scores_gemma":[0.99470854,0.000011069606,0.0036954382,0.00026207822,0.00021421861,0.00012675842,0.0000034962923,0.0000074375766,0.0009709466],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955459,0.00073329115,0.0008957553,0.00010337824,0.0024201907,0.00030143108],"domain_scores_gemma":[0.9926672,0.0012130376,0.0022974194,0.00023987725,0.0033106382,0.00027182678],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036570325,0.00009411802,0.0001539886,0.00017599436,0.0005625016,0.00025182776,0.0006672526,0.000054056363,0.0005739893],"category_scores_gemma":[0.017172627,0.000047000995,0.00016052752,0.0005574756,0.00015483206,0.000815033,0.000018982513,0.0001526935,0.000044043634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036845264,0.00005077911,0.0847872,0.0000044167255,0.000065259694,1.10843146e-7,0.0031514221,0.00029070047,0.000060770682,0.0011040999,0.052906036,0.85754234],"study_design_scores_gemma":[0.00086578936,0.00026820062,0.18730994,0.00002742228,0.00016959535,0.00003942937,0.007618861,0.011328597,0.0006366092,0.004598858,0.7870238,0.00011294409],"about_ca_topic_score_codex":0.00012267273,"about_ca_topic_score_gemma":0.008814751,"teacher_disagreement_score":0.85742944,"about_ca_system_score_codex":0.0003638521,"about_ca_system_score_gemma":0.0072142,"threshold_uncertainty_score":0.998414},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93880355,0.000543826,0.000048163507,0.0032770413,0.0013580158,0.0026459259,0.0000037351465,0.000029040031,0.053290684],"genre_scores_gemma":[0.9953082,0.000054371976,0.0016554464,0.0012670843,0.00040185096,0.00064508413,0.00006461119,0.000015117519,0.00058822904],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99570763,0.0020405997,0.00076486176,0.00015027932,0.0008927284,0.0004438771],"domain_scores_gemma":[0.9971348,0.0002675499,0.00035526964,0.0002358203,0.0012737958,0.0007327639],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004543655,0.00012248158,0.00018441664,0.0002858137,0.001722068,0.00003764742,0.00019389519,0.00012964693,0.028155435],"category_scores_gemma":[0.0010677084,0.00011581375,0.0000611225,0.00036555188,0.000046127825,0.00017754642,0.000007436879,0.0009782151,0.000378594],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007382353,0.000060961855,0.009244958,0.000009916868,0.000024767887,0.0000046582522,0.03735889,0.0016468739,0.000011501023,0.000082428465,0.0033417584,0.9481394],"study_design_scores_gemma":[0.0026889804,0.0010611597,0.19141112,0.00060888345,0.00011663695,0.000010860538,0.01931093,0.0067730243,0.000016043447,0.003219294,0.77452517,0.00025788753],"about_ca_topic_score_codex":0.007957079,"about_ca_topic_score_gemma":0.053110138,"teacher_disagreement_score":0.9478816,"about_ca_system_score_codex":0.0020828685,"about_ca_system_score_gemma":0.010547245,"threshold_uncertainty_score":0.9995776},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008109172,0.0032127188,0.97589684,0.0060497737,0.0033433537,0.0016963481,0.000022895976,0.000037370744,0.0016315363],"genre_scores_gemma":[0.9619273,0.00002094071,0.032609306,0.00041770007,0.002782732,0.00016255873,0.000019854728,0.000023423589,0.0020361722],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799633,0.0002566762,0.00056720804,0.00018254455,0.00048502666,0.00051219127],"domain_scores_gemma":[0.9976229,0.000122976,0.0004887536,0.000286125,0.0011608351,0.00031843255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045836414,0.00016621925,0.00018806108,0.00018240261,0.00046690885,0.000536442,0.0005166723,0.00008937458,0.000033930068],"category_scores_gemma":[0.00028781896,0.00011423791,0.00013661078,0.00016027525,0.00006506876,0.0011384982,0.00001821636,0.0002444228,0.000017174138],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005069364,0.00008788355,0.0007724313,0.00006178429,0.00023550441,0.00001602523,0.010819533,0.10162659,0.00014731969,0.17371073,0.11534796,0.59712356],"study_design_scores_gemma":[0.00085457094,0.0003807559,0.0014203376,0.00020253533,0.00012571103,0.00012729039,0.00054019864,0.30219227,0.00011426942,0.023389827,0.6703419,0.0003103362],"about_ca_topic_score_codex":0.00074496615,"about_ca_topic_score_gemma":0.003227555,"teacher_disagreement_score":0.95381814,"about_ca_system_score_codex":0.00028887592,"about_ca_system_score_gemma":0.0013967883,"threshold_uncertainty_score":0.51729226},"labels":[],"label_agreement":null},{"id":"W2163998785","doi":"10.3138/cjpe.0023.002","title":"Organizational Capacity To Do and Use Evaluation: Results of a Pan-Canadian Survey of Evaluators","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada; Atlantic Canada Opportunities Agency; University of Ottawa","funders":"","keywords":"Respondent; Psychology; Stakeholder; Knowledge management; Organizational learning; Context (archaeology); Descriptive statistics; Exploratory research; Social psychology; Applied psychology; Public relations; Sociology; Political science; Computer science; Social science; Geography","score_opus":0.44394440400345575,"score_gpt":0.5021568546325215,"score_spread":0.058212450629065715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163998785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99422735,0.00026081371,0.0002009356,0.0019620545,0.0004326339,0.0016345764,0.00022293083,0.0000035435696,0.0010551838],"genre_scores_gemma":[0.9956908,0.000009099865,0.0038756004,0.00022913197,0.00006957332,0.000015649593,0.00006818087,0.000009861198,0.000032094275],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99121886,0.0018470892,0.0019122459,0.00033029428,0.0043599303,0.000331548],"domain_scores_gemma":[0.97623914,0.0006689486,0.0015821394,0.00044647063,0.020055244,0.0010080272],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04944271,0.00017886134,0.00043879458,0.0017237766,0.000191066,0.00030952296,0.00047850894,0.00013393667,0.0011856246],"category_scores_gemma":[0.043004718,0.00015280329,0.00008777263,0.00252158,0.00013753299,0.0007612117,0.000012404374,0.00018023246,0.000019497973],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013065216,0.00009618478,0.35095757,0.0000063049483,0.0000622109,0.0000019552324,0.0039940155,0.0054195817,0.00018056046,0.0009057941,0.0039238227,0.63432133],"study_design_scores_gemma":[0.0015145114,0.00093271345,0.96733075,0.000071717564,0.00011326695,0.00001919332,0.00033704267,0.020850612,0.00019237297,0.006691575,0.0017896463,0.00015660589],"about_ca_topic_score_codex":0.05135973,"about_ca_topic_score_gemma":0.57705003,"teacher_disagreement_score":0.63416475,"about_ca_system_score_codex":0.0006370758,"about_ca_system_score_gemma":0.01531216,"threshold_uncertainty_score":0.9997274},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99469763,0.0004879681,0.00019599039,0.0011561739,0.000858276,0.00037607172,0.0000016977356,0.000006740129,0.002219459],"genre_scores_gemma":[0.99617934,0.0000026311334,0.0034904408,0.000055260793,0.00016690484,0.000012465213,0.0000032117687,0.0000052521327,0.00008452023],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9668898,0.031943657,0.00039614784,0.00008083699,0.0004083839,0.00028119344],"domain_scores_gemma":[0.996815,0.0015761335,0.00020957585,0.00006556136,0.0008365053,0.000497227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22139865,0.00005786244,0.00015341854,0.00033430447,0.00014494716,0.00006410624,0.00015190849,0.000111774665,0.00016095386],"category_scores_gemma":[0.06507009,0.00005588219,0.00004706316,0.00048731177,0.00014600046,0.00022971503,0.0000034573325,0.00019518615,0.000012205509],"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":[0.000050657945,0.000013359995,0.8497911,0.0000011310165,0.000008289,0.00002712109,0.0066415165,0.00024163608,0.000009057218,0.00016272145,0.00017876229,0.14287461],"study_design_scores_gemma":[0.0009487508,0.00015069645,0.97849625,0.000024812247,0.000025806747,0.000010835552,0.0059301495,0.0015053957,0.000015714066,0.0022086876,0.010569126,0.000113786475],"about_ca_topic_score_codex":0.025296606,"about_ca_topic_score_gemma":0.70702916,"teacher_disagreement_score":0.6817326,"about_ca_system_score_codex":0.0005044048,"about_ca_system_score_gemma":0.007934605,"threshold_uncertainty_score":0.9976895},"labels":[],"label_agreement":null},{"id":"W2177445649","doi":"10.3138/cjpe.0028.009","title":"The Emerging Field of Evaluation and the Growth of the Evaluation Profession: The Russian Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Institutionalisation; Field (mathematics); Political science; Capacity development; Private sector; Evaluation methods; Foundation (evidence); Engineering ethics; Environmental resource management; Engineering; Economics; Law","score_opus":0.20594391447379515,"score_gpt":0.5328023639531525,"score_spread":0.3268584494793574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177445649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9142254,0.0018031457,0.00089890277,0.072722115,0.0021428338,0.0043048915,0.0000021695707,0.0000040427485,0.0038965112],"genre_scores_gemma":[0.9990184,0.000036042333,0.00016380897,0.00030149898,0.00015990163,0.00025120974,0.0000016480955,0.000006692171,0.000060823208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9879033,0.0051233335,0.0013222524,0.0001939201,0.005219756,0.0002374621],"domain_scores_gemma":[0.99087065,0.0022160204,0.0019306778,0.0006513149,0.0042066197,0.00012470338],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08238429,0.00013145445,0.00023639112,0.00017949282,0.001052972,0.0002658433,0.00091824005,0.000074649295,0.00045930088],"category_scores_gemma":[0.018550863,0.000049844497,0.00016319756,0.00092761306,0.0005963411,0.00042746533,0.000049602913,0.00029211852,0.0000030272906],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007038811,0.000019295943,0.018175252,0.000007105399,0.0000342258,6.380719e-8,0.011377116,0.001097351,0.000052712392,0.014570975,0.0008896599,0.95370585],"study_design_scores_gemma":[0.0027623142,0.00036947036,0.23607671,0.0001854899,0.00040825497,0.000022696595,0.012890796,0.65077627,0.0011200982,0.0883175,0.0069366177,0.0001338166],"about_ca_topic_score_codex":0.0004379454,"about_ca_topic_score_gemma":0.008022066,"teacher_disagreement_score":0.95357203,"about_ca_system_score_codex":0.0001560525,"about_ca_system_score_gemma":0.003187804,"threshold_uncertainty_score":0.9897163},"labels":[],"label_agreement":null},{"id":"W2179175560","doi":"10.3138/cjpe.0026.004","title":"L’évaluation des interventions complexes : quelle peut être la contribution des approches configurationnelles?","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Operationalization; Epistemology; Psychological intervention; Sociology; Valuation (finance); Psychology; Philosophy; Economics","score_opus":0.42523218998141776,"score_gpt":0.5299160107559208,"score_spread":0.104683820774503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179175560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9313954,0.0038863423,0.0551345,0.0009117895,0.00086044194,0.0014915382,0.000021274338,0.000026865027,0.0062718177],"genre_scores_gemma":[0.990214,0.000036119436,0.00892231,0.000054715423,0.00028604385,0.00012015191,0.000083231265,0.00001277482,0.00027067837],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945048,0.0016911448,0.0013180802,0.00018912589,0.0018595874,0.00043727382],"domain_scores_gemma":[0.99129564,0.0005842677,0.000957866,0.0002519337,0.006321395,0.00058888673],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026494825,0.00017454717,0.0002953831,0.0007617609,0.0008064476,0.0006400399,0.00036746653,0.00012314787,0.0033961497],"category_scores_gemma":[0.007715263,0.0001420783,0.00028804032,0.0008602303,0.0004335187,0.0018963172,0.000015647889,0.00022683936,0.0001450946],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026700438,0.00021125608,0.108408295,0.000028439867,0.00007427628,0.0000013953077,0.0069645336,0.0023602068,0.00036805385,0.006931157,0.0020676383,0.87255806],"study_design_scores_gemma":[0.002437833,0.0007255099,0.7935768,0.00040633173,0.00044719715,0.00021735535,0.010407368,0.051549643,0.001188708,0.09989465,0.03874882,0.00039981984],"about_ca_topic_score_codex":0.0004021985,"about_ca_topic_score_gemma":0.013302973,"teacher_disagreement_score":0.8721582,"about_ca_system_score_codex":0.000575293,"about_ca_system_score_gemma":0.0024933387,"threshold_uncertainty_score":0.9975149},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2182857497","doi":"10.3138/cjpe.29.3.154","title":"A Point of No Return Finally Reached: The Journey Ahead","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Point (geometry); Mathematics; Economics; Econometrics; History; Geometry","score_opus":0.5769749004666175,"score_gpt":0.5455323490261877,"score_spread":0.031442551440429733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182857497","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93933815,0.0015094898,0.0013887278,0.02266029,0.0027846538,0.0017873495,0.000012779575,0.000011192433,0.030507347],"genre_scores_gemma":[0.99543166,0.000009792527,0.0033675926,0.0003260754,0.0002915363,0.000023950277,0.000005098549,0.000008458412,0.000535809],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941154,0.0009528297,0.0012291349,0.0001489448,0.003302815,0.00025087103],"domain_scores_gemma":[0.98849094,0.00028388415,0.0012585428,0.00041358493,0.00895736,0.000595687],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039952103,0.00011312529,0.00026032559,0.0004698727,0.00014210962,0.00029842142,0.0007345899,0.00007586592,0.0014183185],"category_scores_gemma":[0.010862658,0.00006629348,0.0001597994,0.00076247193,0.00014695598,0.00059144205,0.000017121252,0.00029511235,0.00013062023],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099723,0.00008989103,0.026711786,0.000006842538,0.000067968256,0.000011588533,0.007821334,0.0028033603,0.00010088372,0.0010878514,0.08723984,0.87395895],"study_design_scores_gemma":[0.0047634756,0.0045646653,0.16348813,0.00028258518,0.0003889684,0.0004888606,0.0147936875,0.19366665,0.00042496674,0.07994007,0.53673476,0.00046318167],"about_ca_topic_score_codex":0.00061778206,"about_ca_topic_score_gemma":0.012360817,"teacher_disagreement_score":0.87349576,"about_ca_system_score_codex":0.00037292606,"about_ca_system_score_gemma":0.010889496,"threshold_uncertainty_score":0.9994945},"labels":[],"label_agreement":null},{"id":"W2183451661","doi":"10.3138/cjpe.0021.007","title":"The Role of Culture and the Future of the Evaluation Function: Considerations and Key Questions","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Treasury Board of Canada Secretariat","funders":"","keywords":"Function (biology); Extension (predicate logic); Key (lock); Work (physics); Political science; Public relations; Administration (probate law); Sociology; Public administration; Computer science; Engineering; Law","score_opus":0.13572695358587547,"score_gpt":0.46709632153462205,"score_spread":0.3313693679487466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183451661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8872782,0.054375917,0.0014178305,0.037510473,0.0032988272,0.005543644,0.000026160264,0.000009427067,0.010539499],"genre_scores_gemma":[0.9989298,0.00011652523,0.0005060536,0.00013635059,0.00020096118,0.00003169051,0.000002244204,0.000003762897,0.00007258417],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99598765,0.0010189929,0.0008549409,0.00011502732,0.0018835099,0.00013989197],"domain_scores_gemma":[0.99310654,0.00081871863,0.00093845266,0.00028475354,0.0047146343,0.00013688048],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.031008836,0.00008600448,0.00016008918,0.00015852082,0.00079051754,0.00023405955,0.00021163434,0.00007236754,0.00021878417],"category_scores_gemma":[0.0035298911,0.00003789291,0.00008904807,0.000518556,0.00053590507,0.0003046755,0.000016077776,0.00021079644,0.0000013367854],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057011148,0.000019050767,0.018867414,0.0000030219462,0.00005398057,1.449551e-7,0.004799527,0.0008115549,0.0001003969,0.06725311,0.001352075,0.9066827],"study_design_scores_gemma":[0.002437026,0.00036925395,0.48464984,0.000067154375,0.0005460708,0.0000971729,0.023640975,0.045013998,0.00026008,0.32621896,0.11658648,0.00011300825],"about_ca_topic_score_codex":0.00020347278,"about_ca_topic_score_gemma":0.039375164,"teacher_disagreement_score":0.9065697,"about_ca_system_score_codex":0.00009249206,"about_ca_system_score_gemma":0.0024104102,"threshold_uncertainty_score":0.9977803},"labels":[],"label_agreement":null},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98340523,0.0016748252,0.00054448424,0.010876206,0.00018154195,0.0006005813,0.0000022978406,0.00000307473,0.0027117436],"genre_scores_gemma":[0.9968807,0.00002447903,0.0029546341,0.0000100150955,0.00007656041,0.0000275536,0.0000011849113,0.0000037801353,0.000021102416],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948072,0.0032099735,0.00047579856,0.00009172693,0.0010582822,0.00035700848],"domain_scores_gemma":[0.9966793,0.0006464465,0.00023927362,0.00012346804,0.002035583,0.0002759416],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052810956,0.000047136597,0.00017117924,0.0010217971,0.00044715105,0.00023841031,0.00030248106,0.000058347952,0.000111808804],"category_scores_gemma":[0.009379963,0.000034169785,0.00011786731,0.0041216207,0.00060430286,0.0003212023,0.000006195813,0.00024827608,0.0000014468899],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001779868,0.00005748451,0.01387128,0.0000025163745,0.00015537809,0.0000055521587,0.047796287,0.0008837333,0.000039582843,0.101061136,0.00011029131,0.83599895],"study_design_scores_gemma":[0.0012823356,0.0006269204,0.35922277,0.000075344964,0.00044374875,0.0000014161703,0.08757886,0.0016369425,0.00026206125,0.5331162,0.015593033,0.0001603496],"about_ca_topic_score_codex":0.08972934,"about_ca_topic_score_gemma":0.8353028,"teacher_disagreement_score":0.8358386,"about_ca_system_score_codex":0.00073416624,"about_ca_system_score_gemma":0.0034538012,"threshold_uncertainty_score":0.9989644},"labels":[],"label_agreement":null},{"id":"W2185313922","doi":"10.3138/cjpe.29.3.1","title":"Building the Foundation for the CES Professional Designation Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Psychology; Archaeology; History","score_opus":0.6387757866045108,"score_gpt":0.6092163742699974,"score_spread":0.029559412334513424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185313922","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50269675,0.003844945,0.29660168,0.13939947,0.020927109,0.03235478,0.000022802507,0.000104282466,0.004048173],"genre_scores_gemma":[0.9787304,0.00000451997,0.019257376,0.00029623637,0.0005823387,0.0008605972,0.000017488954,0.000010275376,0.00024078053],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99535763,0.0007087234,0.00081089826,0.00016530373,0.0026996417,0.00025782196],"domain_scores_gemma":[0.99091554,0.0011476709,0.00089800684,0.00026488389,0.0064885328,0.00028537473],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03797134,0.00011096298,0.00014341279,0.0003097591,0.0007091533,0.00090976054,0.000702409,0.00006644703,0.00028777734],"category_scores_gemma":[0.007833311,0.00005383614,0.00012482317,0.0007547781,0.00013807394,0.0008442778,0.000013908367,0.00019393474,0.000024328863],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028116678,0.000034956396,0.0023018185,0.000001942969,0.000023371895,2.6394918e-7,0.0011261838,0.0057526636,0.000016785149,0.0027652772,0.009516237,0.97843236],"study_design_scores_gemma":[0.0011926627,0.0007770341,0.02715463,0.000038262526,0.00014226013,0.000024926112,0.0037868782,0.42831945,0.00010594409,0.05911112,0.4792265,0.00012034813],"about_ca_topic_score_codex":0.0001508719,"about_ca_topic_score_gemma":0.005389328,"teacher_disagreement_score":0.978312,"about_ca_system_score_codex":0.00042423984,"about_ca_system_score_gemma":0.007701662,"threshold_uncertainty_score":0.99792373},"labels":[],"label_agreement":null},{"id":"W2185731738","doi":"10.3138/cjpe.19.001","title":"The Role of the Evaluator in a Political World","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Politics; Power (physics); Simplicity; Argument (complex analysis); Elite; Ambiguity; Servant; Sociology; Independence (probability theory); Fundamentalism; Environmental ethics; Law; Political science; Political economy; Epistemology; Philosophy","score_opus":0.22938257899034617,"score_gpt":0.5204448598505118,"score_spread":0.2910622808601656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185731738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96268165,0.0012328262,0.00007808899,0.021587493,0.0010176109,0.0013863068,0.000004697785,0.0000032814817,0.012008054],"genre_scores_gemma":[0.9991939,0.000002950341,0.00039119725,0.00018071769,0.00009499727,0.000036285157,5.7847336e-7,0.000004892448,0.00009449571],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99540824,0.0006664001,0.00095686,0.000112963084,0.0025415523,0.00031400664],"domain_scores_gemma":[0.9966816,0.00036500185,0.0005285559,0.00033604458,0.0018122591,0.00027658942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018371304,0.00007869399,0.00015623578,0.00040477485,0.00021611982,0.0002021653,0.0007169961,0.000040932864,0.0004017472],"category_scores_gemma":[0.004548977,0.000039879993,0.00013567084,0.0012574816,0.00020382133,0.0002547996,0.000017038954,0.00023759346,0.000027364584],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022951117,0.00006305381,0.11483586,0.0000017491217,0.000018536803,0.0000015069131,0.0011808595,0.0054785525,0.00007306213,0.084596515,0.00040132875,0.793326],"study_design_scores_gemma":[0.0016475286,0.00026484963,0.448495,0.00010678878,0.00006424385,0.00003033235,0.0041524554,0.021979114,0.00094538793,0.44784227,0.07435546,0.00011657752],"about_ca_topic_score_codex":0.0011857838,"about_ca_topic_score_gemma":0.15661411,"teacher_disagreement_score":0.79320943,"about_ca_system_score_codex":0.00066271605,"about_ca_system_score_gemma":0.009871162,"threshold_uncertainty_score":0.99574196},"labels":[],"label_agreement":null},{"id":"W2188387579","doi":"10.3138/cjpe.019.002","title":"Reporting on Outcomes: Setting Performance Expectations and Telling Performance Stories","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Canada","funders":"","keywords":"Outcome (game theory); Chart; Public relations; Actuarial science; Business; Psychology; Political science; Economics; Microeconomics; Statistics","score_opus":0.4090562215533984,"score_gpt":0.5347074822731473,"score_spread":0.12565126071974897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188387579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946532,0.00020183981,0.0005174054,0.0016683356,0.0006848122,0.0005423995,0.0000016648283,0.0000137693105,0.0017165403],"genre_scores_gemma":[0.991978,0.000016008666,0.0075618383,0.00015350117,0.00014390783,0.000043588545,0.000005142505,0.0000113683745,0.00008667346],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9953899,0.00015964889,0.0019269014,0.00023779419,0.0019787769,0.00030697644],"domain_scores_gemma":[0.99464965,0.00025197462,0.0024813951,0.00025791704,0.0020090959,0.00034994798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014154803,0.00015267487,0.00028690894,0.0006951425,0.00065470283,0.00045525967,0.0002574006,0.000066306144,0.0001733925],"category_scores_gemma":[0.006707187,0.00011536335,0.00008894204,0.0006148996,0.000096602984,0.001083278,0.000010932609,0.00028389398,0.000039063198],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010768681,0.000026098262,0.2800477,0.000009756869,0.000019910842,0.000004961333,0.006424821,0.03151759,0.000019854457,0.00022050705,0.00006768226,0.6816303],"study_design_scores_gemma":[0.0018400806,0.0014915611,0.8909363,0.00036846226,0.00010267994,0.00017955535,0.016012026,0.08072186,0.000848031,0.0027070027,0.004422542,0.0003698901],"about_ca_topic_score_codex":0.000120906894,"about_ca_topic_score_gemma":0.0019793878,"teacher_disagreement_score":0.68126047,"about_ca_system_score_codex":0.0004796234,"about_ca_system_score_gemma":0.0034215883,"threshold_uncertainty_score":0.80296135},"labels":[],"label_agreement":null},{"id":"W2188606052","doi":"10.3138/cjpe.0028.011","title":"A Good Start, but We Can Do Better","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Globe; Engineering ethics; Computer science; Psychology; Engineering management; Process management; Knowledge management; Risk analysis (engineering); Business; Management science; Engineering","score_opus":0.31888172658606007,"score_gpt":0.4975859348037114,"score_spread":0.17870420821765132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188606052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9479666,0.0005312665,0.0030803462,0.030605787,0.0020304853,0.001178524,0.000017307702,0.000017194432,0.014572536],"genre_scores_gemma":[0.99455214,0.000007869703,0.0037510942,0.00081776746,0.00042164823,0.000037069956,0.0000072286816,0.000010594516,0.00039460813],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952235,0.00075889775,0.000900536,0.00020900683,0.0025813282,0.00032671215],"domain_scores_gemma":[0.9955965,0.00025574482,0.0006609061,0.00036248058,0.0024827947,0.00064157514],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017098479,0.00012731942,0.00024090717,0.00067505403,0.00021942254,0.0006355171,0.0005163736,0.00007876074,0.0043619196],"category_scores_gemma":[0.0022444546,0.000095100244,0.00013555007,0.00057221047,0.00008211859,0.00047535173,0.00001149639,0.00023020482,0.00018901097],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062151785,0.00002006219,0.025739275,0.0000024339247,0.00001774335,0.0000026536513,0.0009756158,0.0006209504,0.000034546676,0.0006280677,0.0073298425,0.9646226],"study_design_scores_gemma":[0.0017565512,0.0011049367,0.100794025,0.000084684485,0.00012821492,0.000071851806,0.0018872323,0.061667014,0.00019794454,0.048575453,0.7834445,0.00028757766],"about_ca_topic_score_codex":0.00039684647,"about_ca_topic_score_gemma":0.022685625,"teacher_disagreement_score":0.964335,"about_ca_system_score_codex":0.00032611476,"about_ca_system_score_gemma":0.0037751277,"threshold_uncertainty_score":0.99654824},"labels":[],"label_agreement":null},{"id":"W2188824898","doi":"10.3138/cjpe.0020.004","title":"Two Decades of the <i>Canadian Journal of Program Evaluation</i> : A Content Analysis","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Milestone; Editorial board; Content analysis; Library science; Descriptive statistics; History; Sociology; Social science; Computer science; Statistics; Mathematics","score_opus":0.43548977213527457,"score_gpt":0.5284019432527968,"score_spread":0.0929121711175222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188824898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9833433,0.002284182,0.00078764604,0.0041623907,0.0015726063,0.0032868916,0.000032534736,0.0000062833356,0.0045241443],"genre_scores_gemma":[0.99448824,0.00000600943,0.004802921,0.00014196393,0.00029379004,0.000092975235,0.0000157676,0.000013261327,0.0001450668],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9889911,0.0017216859,0.0027613952,0.00024531013,0.0058067595,0.00047374723],"domain_scores_gemma":[0.9775122,0.0003230216,0.003657634,0.0005491957,0.017214991,0.0007429751],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037571117,0.00021776067,0.0006174396,0.0024439644,0.00052181684,0.0007768497,0.0012290018,0.00013624405,0.0022142287],"category_scores_gemma":[0.0045722057,0.0001412889,0.0007702761,0.0040913513,0.0004011367,0.00077413674,0.000016711221,0.00041999528,0.000013717866],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002185915,0.00012306335,0.4070786,0.000005793582,0.0003584933,0.000005141841,0.0009214479,0.04127736,0.000075475575,0.00078582985,0.0028393173,0.5465076],"study_design_scores_gemma":[0.003081575,0.00089194503,0.8315656,0.00013437448,0.003235838,0.00010919985,0.002096076,0.1065454,0.00059734297,0.013604321,0.037865132,0.00027316902],"about_ca_topic_score_codex":0.030768434,"about_ca_topic_score_gemma":0.8137094,"teacher_disagreement_score":0.782941,"about_ca_system_score_codex":0.0011109059,"about_ca_system_score_gemma":0.028828973,"threshold_uncertainty_score":0.9986979},"labels":[],"label_agreement":null},{"id":"W219521914","doi":"10.3138/cjpe.0025.010","title":"Successful or Not: It Depends on Your Frame of Reference","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Frame (networking); Point (geometry); Frame of reference; Key (lock); Psychology; Knowledge management; Computer science; Engineering ethics; Process management; Business; Computer security; Engineering","score_opus":0.7666920347927102,"score_gpt":0.5786637113913813,"score_spread":0.1880283234013289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W219521914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9679827,0.00009061893,0.0008627351,0.0016229618,0.0009826178,0.00081152655,0.000024933517,0.000008749527,0.02761316],"genre_scores_gemma":[0.9956588,0.000012741411,0.0034369228,0.0003923115,0.00008771529,0.000026746397,0.00000629791,0.000008763146,0.0003697098],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951945,0.0005398358,0.0011570122,0.00020437618,0.0026431046,0.00026117213],"domain_scores_gemma":[0.994279,0.00028373284,0.0011088871,0.0003825401,0.0034934275,0.00045240266],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014023587,0.00012926906,0.00028439736,0.00080235116,0.00012877819,0.00015059164,0.0007222843,0.00011187669,0.016205456],"category_scores_gemma":[0.0040231114,0.00008592452,0.000109742316,0.00075584586,0.0001001028,0.0005957747,0.00001304332,0.00026783854,0.00014763878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022570105,0.00009965375,0.034038868,0.0000063628313,0.000032932043,0.000012480396,0.0029505377,0.00023257268,0.00005063462,0.0010970366,0.0025026218,0.9587506],"study_design_scores_gemma":[0.0034431275,0.0072886893,0.83037895,0.00036566614,0.00029549457,0.00013141305,0.008917135,0.02886638,0.005588109,0.016929744,0.09721553,0.00057976006],"about_ca_topic_score_codex":0.0012902553,"about_ca_topic_score_gemma":0.032950368,"teacher_disagreement_score":0.95817083,"about_ca_system_score_codex":0.00020890833,"about_ca_system_score_gemma":0.005270085,"threshold_uncertainty_score":0.9846958},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9449147,0.0004141857,0.00018798227,0.03472681,0.0012140704,0.0060914597,0.00072508364,0.000028301723,0.011697415],"genre_scores_gemma":[0.9973662,0.0000024787728,0.00070057425,0.0002744043,0.0013371276,0.00005839735,0.00006423878,0.000012254279,0.00018431112],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973169,0.00020675457,0.0005262992,0.0001459312,0.001235978,0.0005681617],"domain_scores_gemma":[0.99710244,0.00006206671,0.0006019753,0.000069878115,0.0015158836,0.0006477645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036212574,0.000099340294,0.00026217458,0.00040830567,0.0012170902,0.00023635366,0.0005418988,0.0001208388,0.00023659412],"category_scores_gemma":[0.0011146896,0.000095219955,0.00006787686,0.00035511944,0.00029987117,0.00058124406,0.000010615747,0.00015616481,0.0000015576898],"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":[0.000028876906,0.00014911151,0.50370663,0.00015153037,0.0001417347,0.0000051900547,0.04806323,0.000035666533,8.054426e-7,0.0074705463,0.028308649,0.41193804],"study_design_scores_gemma":[0.002488593,0.00070187537,0.74814624,0.0000875193,0.00027846082,0.000004871862,0.026708813,0.0066610635,0.000004313547,0.00063053245,0.21390408,0.00038362487],"about_ca_topic_score_codex":0.71499634,"about_ca_topic_score_gemma":0.9895452,"teacher_disagreement_score":0.41155443,"about_ca_system_score_codex":0.0018468838,"about_ca_system_score_gemma":0.023866914,"threshold_uncertainty_score":0.98166686},"labels":[],"label_agreement":null},{"id":"W2228177330","doi":"10.3138/cjpe.026.003","title":"Addressing the Challenges Encountered During a Developmental Evaluation: Implications for Evaluation Practice","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Perspective (graphical); Evaluation methods; Program evaluation; Psychology; Government (linguistics); Engineering ethics; Knowledge management; Process management; Medical education; Management science; Political science; Computer science; Business; Medicine; Engineering; Public administration","score_opus":0.8348360624185777,"score_gpt":0.6002670065070299,"score_spread":0.23456905591154775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228177330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8328425,0.015467816,0.005574405,0.046295,0.004659841,0.023487747,0.000066616216,0.000063225256,0.07154284],"genre_scores_gemma":[0.98532134,0.00005337842,0.012378754,0.0002323169,0.0003143947,0.0016196299,0.000023535958,0.000018755507,0.000037895737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99243385,0.0017875788,0.0013927822,0.00037010774,0.0036244453,0.00039125432],"domain_scores_gemma":[0.98062533,0.00083184626,0.0015864918,0.00045611136,0.016162869,0.00033735702],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.061053388,0.00019341332,0.0002478096,0.0006278952,0.0010461098,0.00050167553,0.0007829093,0.000110286455,0.0021435986],"category_scores_gemma":[0.017702868,0.00013675487,0.00017337895,0.0007156166,0.00013359869,0.0018067055,0.000024101611,0.0002284314,0.00004619433],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007216813,0.00008925286,0.002636459,0.000008188193,0.00009501636,6.3052306e-7,0.011882577,0.0006519701,0.00008240125,0.0012469675,0.0010259817,0.9822084],"study_design_scores_gemma":[0.0069380994,0.00085799024,0.7095754,0.00023140627,0.0016113883,0.000524817,0.047645543,0.11636415,0.00054125645,0.07073297,0.04440452,0.0005724671],"about_ca_topic_score_codex":0.0001932257,"about_ca_topic_score_gemma":0.011398829,"teacher_disagreement_score":0.9816359,"about_ca_system_score_codex":0.0015351374,"about_ca_system_score_gemma":0.013701034,"threshold_uncertainty_score":0.99876857},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98552674,0.00015057418,0.000001221671,0.008259045,0.00026577883,0.00094920397,0.000007626881,0.000006372778,0.004833413],"genre_scores_gemma":[0.99704105,0.000012687394,0.00079892704,0.0006868497,0.0003737885,0.0000672367,0.000010724885,0.000012657999,0.0009961084],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975876,0.0003251897,0.000603544,0.00015600472,0.0006646864,0.00066297187],"domain_scores_gemma":[0.99859005,0.00005493747,0.00027563595,0.00010952337,0.00020104123,0.0007687903],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028421197,0.0001314063,0.00022796409,0.0002663307,0.00043894927,0.00022442274,0.00029772797,0.00008166279,0.0009241618],"category_scores_gemma":[0.00057691213,0.00013900314,0.00006462001,0.00034766237,0.00010480802,0.0002771345,0.0000034480177,0.0001954486,0.00002095967],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000007693959,0.00001884301,0.09231523,0.000005716359,0.000024601428,0.000026461137,0.006013657,0.0008350155,3.4157665e-7,0.0008039002,0.0020472275,0.8979013],"study_design_scores_gemma":[0.0011679886,0.00013087552,0.34293267,0.00013718562,0.000026393514,0.000021482287,0.000978517,0.0009493938,0.0000026875423,0.0009605558,0.6523821,0.00031017762],"about_ca_topic_score_codex":0.9979916,"about_ca_topic_score_gemma":0.99996716,"teacher_disagreement_score":0.8975911,"about_ca_system_score_codex":0.008456948,"about_ca_system_score_gemma":0.09902504,"threshold_uncertainty_score":0.99998915},"labels":[],"label_agreement":null},{"id":"W2274124070","doi":"10.3138/cjpe.21.003","title":"Understanding Cultural Competence Through the Evaluation of “Breaking the Silence: A Project to Generate Critical Knowledge About Family Violence within Immigrant Communities”","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Salient; Silence; Cultural competence; Competence (human resources); Immigration; Psychology; Cultural knowledge; Social psychology; Sociology; Pedagogy; Political science","score_opus":0.6873320058970728,"score_gpt":0.5646945822728154,"score_spread":0.12263742362425734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274124070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97425044,0.002689261,0.012129166,0.0031728584,0.0013062416,0.002694868,0.000021971904,0.000011423109,0.0037237583],"genre_scores_gemma":[0.99687237,0.000024472045,0.0023620038,0.0002951481,0.00022773759,0.000177462,0.000011371859,0.0000108379,0.000018575989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990696,0.0031904764,0.0014655002,0.00021421465,0.004047886,0.00038591516],"domain_scores_gemma":[0.98953354,0.0011267716,0.0008838613,0.00049947505,0.0078116604,0.00014466306],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03511281,0.00019718299,0.00030374635,0.00034975595,0.0010550993,0.00074980396,0.0010913585,0.00007756988,0.00020160618],"category_scores_gemma":[0.0027328883,0.00010554592,0.00015936822,0.0015295506,0.0005716413,0.0008455647,0.00004120522,0.00039503985,0.000017598666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014345978,0.00029905257,0.015166722,0.000051978397,0.00014045637,0.0000059453905,0.16943906,0.2995904,0.0013239813,0.06541594,0.009112211,0.43931076],"study_design_scores_gemma":[0.0010832933,0.00061197917,0.05080122,0.0007912175,0.0003818456,0.000077305565,0.17691961,0.7140249,0.0002964678,0.052012462,0.0027120225,0.0002876961],"about_ca_topic_score_codex":0.011879437,"about_ca_topic_score_gemma":0.0745038,"teacher_disagreement_score":0.43902308,"about_ca_system_score_codex":0.0009381069,"about_ca_system_score_gemma":0.0067610345,"threshold_uncertainty_score":0.9988697},"labels":[],"label_agreement":null},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9091344,0.00026665063,0.029502772,0.041936293,0.0039879526,0.007415172,0.000021394808,0.00004946939,0.0076858904],"genre_scores_gemma":[0.95368254,0.0000027924998,0.031598534,0.013335231,0.0006807729,0.00029444593,0.0000045029956,0.000024123668,0.00037706172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961933,0.0008144001,0.0012138532,0.00015106374,0.0007309387,0.00089642836],"domain_scores_gemma":[0.99454474,0.00059047877,0.00052890985,0.00017167511,0.0029760587,0.0011881269],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026557537,0.00011968985,0.00023427719,0.00086039095,0.00071490946,0.000034708486,0.0002763862,0.000112064015,0.0007703861],"category_scores_gemma":[0.008443861,0.00010577653,0.000057102607,0.0009722848,0.00003716687,0.00028065534,0.000019049507,0.00036374383,0.00032440393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013682273,0.000010018501,0.093100905,0.000081215745,0.000017949402,0.0000075793405,0.03153177,0.0000047866656,0.000030096004,0.0010784983,0.01330706,0.8608164],"study_design_scores_gemma":[0.0010619147,0.00017574344,0.45494154,0.000217912,0.000028368911,0.000009077087,0.0033596773,0.000058748094,0.000025890346,0.00045556674,0.5395155,0.00015004502],"about_ca_topic_score_codex":0.001916389,"about_ca_topic_score_gemma":0.20936291,"teacher_disagreement_score":0.8606664,"about_ca_system_score_codex":0.0026943018,"about_ca_system_score_gemma":0.01927166,"threshold_uncertainty_score":0.99990845},"labels":[],"label_agreement":null},{"id":"W2283637488","doi":"10.3138/cjpe.29.3.vii","title":"Introduction to Professionalization of Evaluation in Canada","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Engineering ethics; Political science; Professional development; Public relations; Professional association; Library science; Sociology; Medical education; Pedagogy; Engineering; Computer science; Law; Medicine","score_opus":0.40279152132935725,"score_gpt":0.5399497411847914,"score_spread":0.1371582198554342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2283637488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98244333,0.00024736294,0.00090084586,0.010712517,0.0026184733,0.0018652815,0.00000581496,0.000002580712,0.0012037967],"genre_scores_gemma":[0.9974992,0.0000015236837,0.0017957446,0.00015266775,0.00035203545,0.0000856035,0.00002685777,0.0000068569434,0.000079458616],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99239135,0.001092264,0.0013141693,0.00020269754,0.00478763,0.00021190039],"domain_scores_gemma":[0.98840827,0.000119249424,0.00081513554,0.0002637108,0.009879127,0.00051450613],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030539516,0.00009843724,0.00024443885,0.0010341726,0.000055955697,0.00007493418,0.00027298005,0.00005159315,0.0015290171],"category_scores_gemma":[0.010855281,0.000080692174,0.000042778105,0.0017445898,0.000027090433,0.0006002834,0.000011676994,0.00013685625,0.000022769162],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051807743,0.000044676926,0.11237778,0.000005586194,0.000011913415,0.0000021541368,0.0022995763,0.15689968,0.00006594007,0.00026532696,0.037155244,0.69082034],"study_design_scores_gemma":[0.0031548503,0.000859547,0.5134004,0.00014547577,0.000115153925,0.00004181206,0.011025488,0.34713438,0.00076828926,0.013068842,0.10998768,0.00029809226],"about_ca_topic_score_codex":0.4097814,"about_ca_topic_score_gemma":0.9868402,"teacher_disagreement_score":0.69052225,"about_ca_system_score_codex":0.003521246,"about_ca_system_score_gemma":0.06466466,"threshold_uncertainty_score":0.99938375},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9688594,0.0012450686,0.00019405155,0.017102186,0.0008496771,0.004106349,0.000044894623,0.00003414515,0.007564251],"genre_scores_gemma":[0.9838941,0.00004478628,0.015290229,0.0001052308,0.00018446086,0.00035518486,0.00003069184,0.00001800318,0.000077291654],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9940667,0.0030980713,0.0015425954,0.00015613955,0.00074494747,0.00039152036],"domain_scores_gemma":[0.99202704,0.00044552132,0.001659676,0.0005436489,0.004927088,0.00039701606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010666436,0.00013202337,0.0003991422,0.00029310127,0.000348081,0.0000128874535,0.00042345855,0.00024094674,0.00080356555],"category_scores_gemma":[0.0017393528,0.00011876899,0.00016920776,0.00038212887,0.00016158876,0.00014591358,0.000025843694,0.00090913055,0.0000048103534],"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":[0.000043914355,0.00023970938,0.15732317,0.00036770396,0.00007332508,6.187921e-7,0.007449365,0.00073692837,0.00006412651,0.0018776392,0.0008663143,0.8309572],"study_design_scores_gemma":[0.0038133946,0.0043136124,0.74268454,0.0039087483,0.0006604582,0.000020182053,0.024096442,0.06933713,0.00019811539,0.006193337,0.14421977,0.00055427215],"about_ca_topic_score_codex":0.008565924,"about_ca_topic_score_gemma":0.09196035,"teacher_disagreement_score":0.8304029,"about_ca_system_score_codex":0.0010085171,"about_ca_system_score_gemma":0.011493264,"threshold_uncertainty_score":0.99803615},"labels":[],"label_agreement":null},{"id":"W2292486103","doi":"10.3138/cjpe.024.002","title":"Learning Through Evaluation? Reflections on Two Federal Community-Building Initiatives","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Western University","funders":"","keywords":"Stakeholder; Government (linguistics); Corporate governance; Policy learning; Political science; Public relations; Community engagement; Public administration; Stakeholder engagement; Collaborative governance; Action (physics); Business; Computer science","score_opus":0.6156032355612,"score_gpt":0.6355201743114897,"score_spread":0.01991693875028966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292486103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88941413,0.00024473816,0.0034088786,0.00643099,0.0011534574,0.0015553606,0.00000409089,0.00003481757,0.09775352],"genre_scores_gemma":[0.9917457,0.000009816325,0.006762714,0.000984135,0.00030049056,0.00005351607,0.000021829144,0.000010875916,0.00011092715],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9901664,0.004688903,0.0010968064,0.0002157717,0.0034744996,0.00035760342],"domain_scores_gemma":[0.9925183,0.0007424623,0.0009813801,0.00035590678,0.0050545586,0.0003473675],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03350315,0.00018207986,0.00029082195,0.0008745705,0.0017668479,0.00086498656,0.00053193525,0.00008512487,0.001848807],"category_scores_gemma":[0.009039882,0.00015104417,0.00017252786,0.0012663756,0.000096395954,0.0016506084,0.000011282849,0.0010039596,0.00008436422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034480567,0.00014171074,0.005119699,0.0000017072687,0.000040731335,0.0000029090975,0.011347205,0.077498354,0.00018013967,0.004663851,0.0010385702,0.89993066],"study_design_scores_gemma":[0.006374349,0.009852879,0.34873462,0.00034405346,0.00036214557,0.0001537943,0.035991095,0.2041474,0.0006519422,0.3403771,0.052272025,0.00073861604],"about_ca_topic_score_codex":0.00061862636,"about_ca_topic_score_gemma":0.010599865,"teacher_disagreement_score":0.89919204,"about_ca_system_score_codex":0.00092832535,"about_ca_system_score_gemma":0.004767659,"threshold_uncertainty_score":0.9995327},"labels":[],"label_agreement":null},{"id":"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053073123,0.7551633,0.000109520355,0.01933532,0.06603636,0.0023304736,0.000060299262,0.000030244493,0.10386137],"genre_scores_gemma":[0.8660124,0.004066839,0.0019960403,0.0019083761,0.07169985,0.00016250621,0.0001390245,0.0001240138,0.053890966],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99705684,0.0005630263,0.0008135072,0.00012472141,0.0006881956,0.00075368024],"domain_scores_gemma":[0.9923919,0.000053802836,0.0006206144,0.00015073424,0.005827244,0.0009556946],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008759898,0.00019400156,0.00027164776,0.00032069063,0.00063395506,0.0006479894,0.0002918357,0.00015521442,0.00973419],"category_scores_gemma":[0.0039435946,0.0001886074,0.00018310161,0.00015394125,0.00024150578,0.001687586,0.000014456323,0.00062465423,0.00024568333],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002046061,0.00006816355,0.0032881887,0.00011026773,0.00007476553,0.0000021050575,0.007987688,0.000007971767,9.667036e-7,0.009120779,0.37215415,0.6071829],"study_design_scores_gemma":[0.000388059,0.00020241026,0.0021597696,0.0010154527,0.00056551915,0.000021215883,0.0021878518,0.00024117902,0.0000058798078,0.0006648626,0.992352,0.00019579886],"about_ca_topic_score_codex":0.0035414305,"about_ca_topic_score_gemma":0.012562528,"teacher_disagreement_score":0.8129393,"about_ca_system_score_codex":0.0008528672,"about_ca_system_score_gemma":0.0026490157,"threshold_uncertainty_score":0.99117106},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81502575,0.006646969,0.0009874837,0.0066860626,0.004444401,0.0044322945,0.000006011489,0.000057841262,0.16171317],"genre_scores_gemma":[0.9885642,0.00009701312,0.008187435,0.00023436431,0.0017642458,0.00007995813,0.000013673817,0.000015090702,0.0010440017],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99446666,0.0033663057,0.00032531063,0.00013715363,0.0010628426,0.0006416952],"domain_scores_gemma":[0.99582976,0.00024535364,0.00023799758,0.00016486245,0.002933038,0.00058896065],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.029595364,0.00008374973,0.00016253669,0.0003450818,0.0020994048,0.00030926568,0.00042101287,0.00019107503,0.0004113671],"category_scores_gemma":[0.0039888266,0.000076245284,0.00009994919,0.00050587585,0.00037280057,0.00035623694,0.0000065549048,0.0004237635,0.00004171043],"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":[0.00000463022,0.00004140429,0.0012029494,0.0000060954044,0.000018818999,0.0000014540799,0.108509645,0.00003723943,0.00001644699,0.011353488,0.0045029926,0.87430483],"study_design_scores_gemma":[0.0002651792,0.0004315736,0.0054450566,0.000041202456,0.00006113697,0.0000136283015,0.040470593,0.000037149446,0.000037542497,0.05951172,0.8935299,0.00015534947],"about_ca_topic_score_codex":0.045087766,"about_ca_topic_score_gemma":0.28997633,"teacher_disagreement_score":0.8890269,"about_ca_system_score_codex":0.001149722,"about_ca_system_score_gemma":0.017267795,"threshold_uncertainty_score":0.9992358},"labels":[],"label_agreement":null},{"id":"W2298222049","doi":"10.3138/cjpe.28.006","title":"Exemple d’application de l’évaluation formative centrée sur l’utilisation des résultats","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Intégré de Santé et de Services Sociaux des Laurentides","funders":"","keywords":"Formative assessment; Valuation (finance); Process (computing); Evaluation methods; Computer science; Process management; Risk analysis (engineering); Business; Psychology; Engineering; Reliability engineering; Pedagogy; Accounting","score_opus":0.29907530459644416,"score_gpt":0.4846502697928911,"score_spread":0.18557496519644695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298222049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95948845,0.00023068205,0.03235165,0.0021532073,0.00041738412,0.0022040342,0.0000070798433,0.000020037498,0.0031274597],"genre_scores_gemma":[0.9900087,0.000019649693,0.009064431,0.0002113566,0.00016862988,0.000325958,0.000051597966,0.000013338745,0.00013633227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99485654,0.00088877266,0.0012490934,0.00022841754,0.002351743,0.00042545705],"domain_scores_gemma":[0.9895742,0.00040352353,0.0011127149,0.00031994804,0.008025879,0.0005637554],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016493807,0.00016260266,0.00024090744,0.0007349076,0.0004162309,0.0006920782,0.00045851257,0.00011523136,0.0034761059],"category_scores_gemma":[0.005024514,0.000132738,0.00013349263,0.001015485,0.00014815888,0.0027009714,0.000012999223,0.00020703717,0.0004056254],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009101356,0.00004682866,0.041722894,0.0000055583632,0.000018735576,4.5749147e-7,0.0072376025,0.0056923586,0.00035902375,0.00035788422,0.0034938036,0.9410558],"study_design_scores_gemma":[0.0009525438,0.00030296494,0.45057508,0.00003484121,0.00006567666,0.00002796874,0.0037754546,0.459669,0.00049966725,0.07080019,0.01313997,0.00015664865],"about_ca_topic_score_codex":0.003416151,"about_ca_topic_score_gemma":0.018093396,"teacher_disagreement_score":0.94089913,"about_ca_system_score_codex":0.00087204564,"about_ca_system_score_gemma":0.005250928,"threshold_uncertainty_score":0.99982387},"labels":[],"label_agreement":null},{"id":"W2299937421","doi":"10.3138/cjpe.28.003","title":"Outsource Versus In-House? An Identification of Organizational Conditions Influencing the Choice for Internal or External Evaluators","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outsourcing; Flemish; Pairwise comparison; Discretion; Identification (biology); Business; Public sector; Locus of control; Marketing; Computer science; Psychology; Social psychology; Political science; Law","score_opus":0.31042600741340926,"score_gpt":0.5320363808943255,"score_spread":0.22161037348091622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2299937421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99110186,0.000090818256,0.004990685,0.0010127496,0.0009577545,0.0017189381,0.000014949314,0.000009373686,0.0001028624],"genre_scores_gemma":[0.99786884,0.000003384589,0.0014422839,0.00012212583,0.00022705966,0.0002048165,0.000014835935,0.000017514136,0.00009915906],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955355,0.00056225,0.001542414,0.0002029536,0.0019227989,0.00023409016],"domain_scores_gemma":[0.9910207,0.0009889709,0.001355603,0.00031614874,0.006047868,0.00027073539],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011502423,0.00012085469,0.0002104974,0.0007044006,0.0002451655,0.00047889721,0.00072343554,0.0000732066,0.0027813313],"category_scores_gemma":[0.008697866,0.00007948179,0.00009632278,0.0009214937,0.0001365331,0.0013458112,0.000014010151,0.00017999683,0.000049920014],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023564145,0.00024264364,0.35247943,0.000022350003,0.000114475166,0.0000016508028,0.010540625,0.050902758,0.0033951406,0.002173691,0.002465645,0.57742596],"study_design_scores_gemma":[0.0028554704,0.0008346718,0.7717471,0.000079617836,0.000121827594,0.000022722845,0.0057751536,0.204349,0.00085168966,0.010860137,0.0023425748,0.00016003879],"about_ca_topic_score_codex":0.0011558793,"about_ca_topic_score_gemma":0.022555443,"teacher_disagreement_score":0.5772659,"about_ca_system_score_codex":0.00045124764,"about_ca_system_score_gemma":0.004315408,"threshold_uncertainty_score":0.99965227},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8457696,0.051719777,0.0007294725,0.0903244,0.0011153545,0.007252891,0.00026483202,0.000012767701,0.0028109076],"genre_scores_gemma":[0.99695915,0.00009086525,0.0014573766,0.001061219,0.00018101856,0.00014887545,0.00006196937,0.000025076157,0.000014438062],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9928581,0.002186367,0.0036883554,0.00018490195,0.00058221683,0.00050006533],"domain_scores_gemma":[0.9877995,0.00071139465,0.004661112,0.0003348589,0.0059129465,0.0005801402],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.111447215,0.00013509124,0.000492045,0.0011131483,0.0001658348,0.000056433175,0.00030413782,0.00011222029,0.00019840717],"category_scores_gemma":[0.06381288,0.00014421355,0.000053295982,0.0013988462,0.00010057633,0.0011645446,0.000007504282,0.00022405274,0.000032163112],"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":[0.00006204132,0.000667164,0.57327926,0.0016114227,0.00056039187,0.0000018248699,0.1447376,0.060193177,0.000012955467,0.029147856,0.008547289,0.181179],"study_design_scores_gemma":[0.005616256,0.001196764,0.594446,0.0016564552,0.0008513401,0.00018073624,0.034984984,0.08803036,0.00021039102,0.038487513,0.23319927,0.001139953],"about_ca_topic_score_codex":0.39709237,"about_ca_topic_score_gemma":0.78643894,"teacher_disagreement_score":0.3893466,"about_ca_system_score_codex":0.0033620459,"about_ca_system_score_gemma":0.020115584,"threshold_uncertainty_score":0.9854395},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08364305,0.026827578,0.0006819654,0.001736192,0.18255603,0.0013778037,0.00018450775,0.000027047015,0.70296586],"genre_scores_gemma":[0.9831925,0.000045125726,0.002149319,0.00011808377,0.0060226843,0.000020226109,0.000009251001,0.000013458068,0.008429326],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990796,0.000019006464,0.00044344328,0.000098700686,0.000054230375,0.0003050393],"domain_scores_gemma":[0.9989384,0.000016195532,0.00040730482,0.00011606222,0.00016388658,0.00035818605],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0033968757,0.00007002766,0.00018691996,0.00029748416,0.00010609317,0.00009355599,0.00013926232,0.00005439805,0.006379824],"category_scores_gemma":[0.00037598208,0.000076254146,0.00009504883,0.00013881602,0.000066041386,0.000489175,0.000007749929,0.00009495402,0.0024388388],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036916742,0.000039833503,0.07514855,0.0000065517474,0.00008411426,0.0000012074563,0.0013756097,0.000054120857,7.9729205e-7,0.012020999,0.8802511,0.031013405],"study_design_scores_gemma":[0.00030562392,0.000047859638,0.0151296435,0.000009927603,0.00002058404,0.0000083790765,0.0004201269,0.00045951988,0.0000041249705,0.0024651075,0.9810295,0.00009960901],"about_ca_topic_score_codex":0.00054509763,"about_ca_topic_score_gemma":0.00055614696,"teacher_disagreement_score":0.8995495,"about_ca_system_score_codex":0.00034024002,"about_ca_system_score_gemma":0.00021214332,"threshold_uncertainty_score":0.99833786},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64483404,0.012479012,0.01605754,0.04861773,0.066321395,0.01718988,0.000035169676,0.00034879986,0.1941164],"genre_scores_gemma":[0.9751351,0.000018016415,0.010667101,0.0005556306,0.011603687,0.0010466073,0.00001863811,0.000035168454,0.00092006807],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990029,0.00012814031,0.0003169831,0.00012023625,0.00021119867,0.00022056692],"domain_scores_gemma":[0.9984359,0.000022551898,0.00023152868,0.00025260294,0.00073710317,0.00032032764],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00095178484,0.000079551544,0.00010688716,0.00022187454,0.00007905808,0.00007306968,0.00020814416,0.00009638097,0.0097691],"category_scores_gemma":[0.000056580986,0.00007267366,0.00006935839,0.00019752067,0.00006725711,0.00014497683,0.0000017572956,0.0001982592,0.00017726501],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025764227,0.000033262448,0.0006604797,0.0000011108075,0.000025967165,8.847388e-7,0.00030336416,0.0000018911044,0.00018016448,0.00093847845,0.48929322,0.5085586],"study_design_scores_gemma":[0.00045020878,0.0003226371,0.04904282,0.000020338566,0.000042590593,0.00005275107,0.00026405646,0.00016912434,0.000045225996,0.010072614,0.9393961,0.000121571065],"about_ca_topic_score_codex":0.0018279249,"about_ca_topic_score_gemma":0.0013943891,"teacher_disagreement_score":0.50843704,"about_ca_system_score_codex":0.00016468631,"about_ca_system_score_gemma":0.00049883046,"threshold_uncertainty_score":0.99113613},"labels":[],"label_agreement":null},{"id":"W2309457767","doi":"10.3138/cjpe.028.001","title":"Les défis de l’évaluation développementale en recherche : une analyse d’implantation d’un projet «hôpital promoteur de santé»","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Valuation (finance); Context (archaeology); Sociology; Library science; Psychology; Computer science; Business; Geography","score_opus":0.4962628710410104,"score_gpt":0.5603129622147885,"score_spread":0.06405009117377813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2309457767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9806677,0.00015303359,0.009298029,0.005174303,0.00026093502,0.0018830778,0.000008738362,0.000019372748,0.0025348156],"genre_scores_gemma":[0.9436803,0.00003272679,0.05540807,0.00019416932,0.00022371333,0.00025983882,0.00005569751,0.00001770585,0.00012777565],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99132836,0.0044999425,0.0012160138,0.0002864493,0.0021954896,0.00047375564],"domain_scores_gemma":[0.9944783,0.00074241543,0.0009437529,0.000295631,0.003010384,0.0005295089],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.046370625,0.00019421625,0.00027824653,0.00089523994,0.00033132712,0.0007070454,0.00053672306,0.00022138766,0.004675667],"category_scores_gemma":[0.0069134627,0.00015852405,0.00015609355,0.0014118239,0.00008032482,0.0012196079,0.000017587707,0.00043292588,0.00017047995],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013464266,0.00006641555,0.112634405,0.00000661396,0.000049850532,0.0000048651027,0.010467548,0.0010882404,0.0013675771,0.000053681993,0.0015126717,0.87273467],"study_design_scores_gemma":[0.001118983,0.00052384613,0.8167486,0.000055151544,0.00019077765,0.00015862632,0.0093566375,0.13682427,0.0015009056,0.03136312,0.0019315212,0.00022752782],"about_ca_topic_score_codex":0.006120562,"about_ca_topic_score_gemma":0.019826781,"teacher_disagreement_score":0.87250715,"about_ca_system_score_codex":0.0026280512,"about_ca_system_score_gemma":0.0072604986,"threshold_uncertainty_score":0.9983674},"labels":[],"label_agreement":null},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9790648,0.0014201325,0.000019283636,0.012404648,0.00036454265,0.0037903863,0.000003990423,0.000006816524,0.0029253596],"genre_scores_gemma":[0.99589854,0.000090270194,0.0022945867,0.0009254516,0.00026720564,0.00037446525,0.000022035101,0.000012424812,0.00011499226],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975623,0.00030864283,0.00067517353,0.00014584379,0.0009375896,0.00037045687],"domain_scores_gemma":[0.9953306,0.00028903168,0.00019291486,0.00017737666,0.0028738172,0.0011362984],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005060861,0.00011152466,0.00024202654,0.00055187405,0.00009164805,0.000098011624,0.000075055235,0.00013166547,0.0019110269],"category_scores_gemma":[0.010272265,0.00009796839,0.000046893994,0.00046482251,0.000072986295,0.00021445582,0.000008995211,0.00034087276,0.00006190281],"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":[0.000047983653,0.00010845553,0.28331998,0.00022633302,0.000073705516,0.000019757299,0.0092932675,0.00041429367,0.000036005116,0.0005885475,0.013755362,0.6921163],"study_design_scores_gemma":[0.005689017,0.0021586863,0.9433504,0.0011378636,0.0006908068,0.00010767162,0.004701834,0.01738895,0.00005404023,0.006197801,0.018210005,0.00031297468],"about_ca_topic_score_codex":0.010152232,"about_ca_topic_score_gemma":0.13257506,"teacher_disagreement_score":0.69180334,"about_ca_system_score_codex":0.0010523623,"about_ca_system_score_gemma":0.015962249,"threshold_uncertainty_score":0.9990014},"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":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993809,0.000073724565,0.00023208505,0.002675779,0.0002596992,0.0027185243,0.000009204335,0.0000026587431,0.00021936967],"genre_scores_gemma":[0.99717915,0.000005243279,0.0025714666,0.000059622274,0.000044452754,0.00008335992,0.000008107255,0.0000075011862,0.00004112171],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99060434,0.006815301,0.0013645364,0.00010140653,0.00080126635,0.0003131496],"domain_scores_gemma":[0.9929044,0.0014516118,0.0008219472,0.00014587338,0.0044045537,0.00027156534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021643603,0.00005893197,0.0001883153,0.0005118892,0.00028997014,0.000024315981,0.0001610649,0.000083367035,0.00049054634],"category_scores_gemma":[0.0054263836,0.000046244484,0.000021423379,0.0012068261,0.0001389279,0.00045376425,0.000015463875,0.00036039652,0.0000081988355],"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":[0.0000015883809,0.000035655055,0.9390181,0.00007278049,0.000008034319,2.778985e-7,0.018519875,0.000062487736,0.00013133352,0.00008822268,0.0016070402,0.040454652],"study_design_scores_gemma":[0.00070247706,0.00010499829,0.9864634,0.000145149,0.000014100579,0.0000041734206,0.0016086539,0.005059537,0.00007355426,0.0005082322,0.0052768136,0.00003885611],"about_ca_topic_score_codex":0.014806069,"about_ca_topic_score_gemma":0.10284103,"teacher_disagreement_score":0.08803496,"about_ca_system_score_codex":0.00047939084,"about_ca_system_score_gemma":0.009351022,"threshold_uncertainty_score":0.99626505},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78329176,0.040886633,0.003608288,0.12778202,0.007434759,0.008144337,0.00013584299,0.00007059203,0.028645772],"genre_scores_gemma":[0.99432105,0.000058674887,0.0027867912,0.0012894424,0.0011751113,0.000060021306,0.000040460334,0.000018541405,0.00024992914],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941681,0.0009572637,0.0010139862,0.0003999517,0.0025201759,0.0009405349],"domain_scores_gemma":[0.9947832,0.000096882606,0.0010535774,0.00040935457,0.002098518,0.0015584438],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02030199,0.00023292995,0.00041980846,0.0006574037,0.0010078365,0.0017873374,0.0005189229,0.000115158735,0.00059778907],"category_scores_gemma":[0.0009549903,0.00018879739,0.00012989187,0.0013903403,0.0001695992,0.00089570205,0.000017930348,0.0003362503,0.000018520395],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020679221,0.000025421848,0.09494039,0.0000056155855,0.000032242904,0.000008791056,0.005623577,0.033628788,7.3306467e-7,0.0021754345,0.027977206,0.8355611],"study_design_scores_gemma":[0.0027311877,0.0014070094,0.33627304,0.0004053582,0.00018280352,0.0002992463,0.012601619,0.103174075,0.000004455383,0.024606658,0.5176031,0.0007114657],"about_ca_topic_score_codex":0.07389688,"about_ca_topic_score_gemma":0.8208237,"teacher_disagreement_score":0.83484966,"about_ca_system_score_codex":0.0008943471,"about_ca_system_score_gemma":0.011043857,"threshold_uncertainty_score":0.9992489},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2313199284","doi":"10.3138/cjpe.30.2.231","title":"Donaldson, S. L. (Ed.). <i>The future of evaluation in society: A tribute to Michael Scriven.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tribute; Theology; Art; Political science; Philosophy; Art history","score_opus":0.25324641466730924,"score_gpt":0.4940376517860622,"score_spread":0.24079123711875294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313199284","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9095636,0.00687285,0.0021938097,0.072418146,0.0032362514,0.004419117,0.00003355996,0.000009397805,0.001253258],"genre_scores_gemma":[0.99352926,0.00002941749,0.0045761582,0.0010732039,0.00048784254,0.00015271708,0.000020703746,0.000011432044,0.00011924938],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99204725,0.0012419184,0.0013379847,0.00023424772,0.0048185233,0.00032006606],"domain_scores_gemma":[0.98926383,0.00022249717,0.00088278466,0.00037973322,0.008667211,0.00058391906],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.057842333,0.00014446763,0.00031824142,0.00057707087,0.00012435463,0.00022277268,0.0005986534,0.000108059416,0.0005971373],"category_scores_gemma":[0.003229001,0.00009822789,0.00019712924,0.0018057869,0.00009533592,0.00057934877,0.00002349228,0.00027244468,0.000059367834],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050918206,0.000061716055,0.018313395,0.000004330235,0.00002949601,0.0000021487187,0.006794015,0.015635667,0.00006789605,0.00016292075,0.11891209,0.8399654],"study_design_scores_gemma":[0.0049886927,0.001407957,0.10350493,0.00015406388,0.0002538432,0.00006910083,0.018107587,0.20504865,0.00027934735,0.027845385,0.6380162,0.0003241897],"about_ca_topic_score_codex":0.00070413965,"about_ca_topic_score_gemma":0.044976536,"teacher_disagreement_score":0.8396412,"about_ca_system_score_codex":0.0008590298,"about_ca_system_score_gemma":0.012091754,"threshold_uncertainty_score":0.99350876},"labels":[],"label_agreement":null},{"id":"W231595241","doi":"10.3138/cjpe.0015.006","title":"Incorporating Stakeholders in Standard Setting: What’s at Stake?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Representativeness heuristic; Stakeholder; Insider; Psychology; Scale (ratio); Decision maker; Applied psychology; Rating scale; Public relations; Social psychology; Political science; Management science; Economics","score_opus":0.5441481476401734,"score_gpt":0.5151732825914709,"score_spread":0.028974865048702503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W231595241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862941,0.0007581755,0.00057569164,0.0066544735,0.0011349017,0.00097272824,0.000005660514,0.000009094681,0.0035951836],"genre_scores_gemma":[0.99620086,0.000036664685,0.0030103237,0.0002986982,0.00013324695,0.0000345645,0.000013876926,0.000011709628,0.0002600263],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943571,0.000723056,0.0013392075,0.00023894428,0.0029720352,0.00036965788],"domain_scores_gemma":[0.9954486,0.00026636157,0.0010495537,0.0002826304,0.002449964,0.00050287956],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026334228,0.00013877972,0.00027417153,0.0010491449,0.0002453227,0.00092304783,0.00042210665,0.00008482926,0.0029944142],"category_scores_gemma":[0.0029605064,0.00011428598,0.00010202342,0.0012825395,0.00008887743,0.002007905,0.000017497112,0.00026481252,0.00006620224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039750666,0.000018878067,0.16204154,0.000002172063,0.000009366272,0.00003314413,0.001593114,0.006900007,0.000027490525,0.00014298028,0.0022474977,0.82694405],"study_design_scores_gemma":[0.0068170764,0.0021628293,0.33944008,0.00054217654,0.00011735103,0.00035404923,0.045835357,0.15797001,0.00030144595,0.039977152,0.40574792,0.0007345328],"about_ca_topic_score_codex":0.00035681768,"about_ca_topic_score_gemma":0.13074769,"teacher_disagreement_score":0.82620955,"about_ca_system_score_codex":0.0014845455,"about_ca_system_score_gemma":0.0060980422,"threshold_uncertainty_score":0.99953645},"labels":[],"label_agreement":null},{"id":"W2316547733","doi":"10.3138/cjpe.016.002","title":"The Strong Focus on Output Information: A Threat to Evaluation in the Swedish State Sector?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Public sector; Public interest; State (computer science); Quality (philosophy); Focus (optics); Business; Information management; Private sector; Management information systems; Information system; Public relations; Economics; Public economics; Political science; Economic growth; Computer science; Management","score_opus":0.39228625282051927,"score_gpt":0.5057903060285184,"score_spread":0.11350405320799911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316547733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9296169,0.000359029,0.0020306783,0.03907496,0.0017417582,0.0048316983,0.00001234405,0.00001125497,0.022321353],"genre_scores_gemma":[0.9983776,0.000018702096,0.0002030232,0.0008177924,0.00019254774,0.0002749097,0.000009961344,0.0000062464696,0.000099175326],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9918308,0.0013920533,0.0011916717,0.00016154847,0.0050390232,0.00038485235],"domain_scores_gemma":[0.9945304,0.00070772396,0.0006494728,0.00046421489,0.003343447,0.0003047404],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.044585217,0.00014719686,0.00017811467,0.0007410806,0.0005064581,0.00136355,0.0008506008,0.00004887099,0.00065325544],"category_scores_gemma":[0.0045954734,0.0000795599,0.00010648688,0.0015213533,0.00006519064,0.001258406,0.000013384366,0.00030806946,0.00022845413],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048883117,0.000019308527,0.01053879,7.5301875e-7,0.000011268032,0.000002785667,0.00541638,0.02393267,6.030629e-7,0.0006096287,0.005417606,0.9540013],"study_design_scores_gemma":[0.0023976266,0.0016213286,0.524615,0.00008830272,0.000091105474,0.00008753352,0.01140397,0.17966206,0.00002099453,0.0547522,0.22499867,0.00026118488],"about_ca_topic_score_codex":0.00074987265,"about_ca_topic_score_gemma":0.08875212,"teacher_disagreement_score":0.9537401,"about_ca_system_score_codex":0.000839934,"about_ca_system_score_gemma":0.00406931,"threshold_uncertainty_score":0.9996731},"labels":[],"label_agreement":null},{"id":"W2320230425","doi":"10.3138/cjpe.29.1.104","title":"Contributing Factors to the Continued Blurring of Evaluation and Research: Strategies for Moving Forward","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Terminology; Confusion; Management science; Psychology; Control (management); Political science; Engineering ethics; Computer science; Economics; Engineering; Artificial intelligence","score_opus":0.5421588467804487,"score_gpt":0.5906286609896096,"score_spread":0.048469814209160966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320230425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97953,0.00024239607,0.014003947,0.0026591842,0.00042579215,0.0024519893,0.000009547482,0.000003598538,0.0006735432],"genre_scores_gemma":[0.99788874,0.0000019769625,0.0017386301,0.000055917426,0.00016429002,0.00011448382,0.00000697566,0.0000073973642,0.00002160553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942142,0.0014146653,0.00090703834,0.00018922237,0.0029119805,0.00036294176],"domain_scores_gemma":[0.98663133,0.002037655,0.00065569725,0.0002381924,0.010137632,0.00029946503],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10056718,0.000095159376,0.00024404033,0.0006575753,0.00050510105,0.00063874084,0.000334495,0.000059131336,0.00015092616],"category_scores_gemma":[0.029459981,0.00006113902,0.000087481356,0.000655,0.00010783433,0.0005497179,0.000023113083,0.00017927468,0.0000036831075],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033288747,0.000014849981,0.02605238,0.000011960439,0.000033120974,1.4831193e-7,0.007084948,0.013018862,0.00032541776,0.0036190965,0.0011431357,0.9486628],"study_design_scores_gemma":[0.0021678535,0.001574917,0.21031125,0.00018560466,0.00017803791,0.000008496697,0.033196025,0.6550601,0.0009971518,0.062370792,0.033762775,0.00018695624],"about_ca_topic_score_codex":0.0004938818,"about_ca_topic_score_gemma":0.015873937,"teacher_disagreement_score":0.94847584,"about_ca_system_score_codex":0.00024310997,"about_ca_system_score_gemma":0.003372903,"threshold_uncertainty_score":0.9787153},"labels":[],"label_agreement":null},{"id":"W232181897","doi":"10.3138/cjpe.025.005","title":"Using Web-Based Technologies to Increase Evaluation Capacity in Organizations Providing Child and Youth Mental Health Services","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; Natural Sciences and Engineering Research Council of Canada; Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Mental health; Excellence; Context (archaeology); Service provider; Process (computing); Capacity building; Face (sociological concept); Public relations; Medical education; Service (business); Business; Knowledge management; Psychology; Marketing; Computer science; Medicine; Sociology; Psychiatry; Political science","score_opus":0.31751165643650486,"score_gpt":0.4729386949800939,"score_spread":0.15542703854358902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W232181897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98975414,0.00021621081,0.0003920675,0.006847814,0.000510157,0.0020271295,0.000037898215,0.00002119307,0.00019336447],"genre_scores_gemma":[0.9877934,0.000004120703,0.011704755,0.00035968862,0.000053238917,0.000036361333,0.000035243287,0.000010718032,0.000002496978],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962397,0.0005338735,0.00085228443,0.00026351368,0.0018258666,0.00028474754],"domain_scores_gemma":[0.995654,0.00006487312,0.0006482839,0.00025977605,0.0029929006,0.00038015566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018444592,0.00013693956,0.00023027345,0.0015421131,0.00046924868,0.00045987085,0.00034119186,0.000098770535,0.0002831296],"category_scores_gemma":[0.0028080428,0.00011614437,0.000035841895,0.0019116518,0.00008347077,0.00072113535,0.0000229571,0.00031723286,0.0000073439323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000342751,0.00014291248,0.24977429,0.000033670818,0.000025348192,8.5186775e-7,0.013921872,0.019909954,0.0014371771,0.00046540928,0.0001264901,0.7141277],"study_design_scores_gemma":[0.0019830954,0.0003556137,0.07069842,0.00025408342,0.00008238053,0.000037765705,0.013714124,0.9077855,0.00038206147,0.0016837294,0.0028091834,0.00021407218],"about_ca_topic_score_codex":0.0040031737,"about_ca_topic_score_gemma":0.18764102,"teacher_disagreement_score":0.8878755,"about_ca_system_score_codex":0.00051885087,"about_ca_system_score_gemma":0.0072637806,"threshold_uncertainty_score":0.9983641},"labels":[],"label_agreement":null},{"id":"W2322332679","doi":"10.3138/cjpe.30.3.07","title":"Considering the Social Determinants of Equity in International Development Evaluation Guidance Documents","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Equity (law); Business; Social equality; Public economics; Public relations; Political science; Accounting; Economics","score_opus":0.5190978300383406,"score_gpt":0.6044219470048832,"score_spread":0.08532411696654252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2322332679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99300736,0.0001533114,0.0005262038,0.0024774119,0.0010273333,0.00082037353,0.0000042209485,0.0000024931103,0.0019812654],"genre_scores_gemma":[0.998104,0.00000537997,0.001549777,0.00007174001,0.000105189836,0.00008388499,0.0000020562372,0.0000052553446,0.00007276611],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9939568,0.0006674063,0.0014199185,0.00017140535,0.0035514317,0.00023300966],"domain_scores_gemma":[0.9947978,0.0003092979,0.0011695749,0.0001756983,0.0034193825,0.00012821198],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032936636,0.00009955501,0.000202913,0.0005178377,0.00017737434,0.00016476003,0.0006462141,0.000058203328,0.0019229718],"category_scores_gemma":[0.00478544,0.000056853067,0.00007592118,0.0004220617,0.00012709347,0.0007102801,0.000043820983,0.00009761336,0.00002754794],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014089771,0.000020998961,0.17414777,0.0000018578884,0.000013483015,0.0000012338978,0.0016906029,0.00018896173,0.00012951391,0.000077065175,0.00029544087,0.823419],"study_design_scores_gemma":[0.0021556842,0.0001159695,0.9532177,0.00020334468,0.00004060859,0.000017984077,0.0012823567,0.017832175,0.0015225625,0.009918388,0.0135628525,0.00013039229],"about_ca_topic_score_codex":0.00020459357,"about_ca_topic_score_gemma":0.030377697,"teacher_disagreement_score":0.82328856,"about_ca_system_score_codex":0.0010947026,"about_ca_system_score_gemma":0.007104039,"threshold_uncertainty_score":0.9989894},"labels":[],"label_agreement":null},{"id":"W2324237053","doi":"10.3138/cjpe.30.3.390","title":"A Transcultural Global Systems Perspective: In Search of Blue Marble Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Framing (construction); Reflexivity; Indigenous; Sociology; Praxis; Perspective (graphical); Epistemology; Political science; Management science; Public relations; Engineering ethics; Social science; Computer science; Geography; Engineering","score_opus":0.33164886305323843,"score_gpt":0.5492553374225089,"score_spread":0.21760647436927044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324237053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99112713,0.0009082091,0.00091585354,0.0024103057,0.0007942328,0.0011241458,0.000024749854,0.0000045002635,0.0026908845],"genre_scores_gemma":[0.9992231,0.000014564175,0.00045539925,0.000018007224,0.00009625235,0.00004054378,0.0000015123662,0.0000056139106,0.00014498078],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9939693,0.0012066663,0.0011310107,0.0002216023,0.0031493166,0.00032205897],"domain_scores_gemma":[0.9932659,0.00020554784,0.00049091806,0.00024751897,0.005405118,0.00038498966],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020650186,0.00012084922,0.00031787474,0.00059450057,0.0000790579,0.00016751747,0.0004942995,0.0000973594,0.0013848356],"category_scores_gemma":[0.0023115037,0.000071008006,0.00015370618,0.0012201356,0.00014656576,0.0006938084,0.000008309102,0.00013741672,0.000040718878],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098279015,0.00011047567,0.3165316,0.000014195636,0.00006840246,0.0000117154905,0.005554768,0.0072711003,0.00042594864,0.006080656,0.0011538665,0.662679],"study_design_scores_gemma":[0.006133266,0.0017109481,0.88598365,0.00049701985,0.0001473551,0.00018362366,0.030159296,0.05671376,0.00038649284,0.010838681,0.0068826936,0.00036319284],"about_ca_topic_score_codex":0.0038866482,"about_ca_topic_score_gemma":0.04323935,"teacher_disagreement_score":0.6623158,"about_ca_system_score_codex":0.0017430431,"about_ca_system_score_gemma":0.0070953383,"threshold_uncertainty_score":0.99952805},"labels":[],"label_agreement":null},{"id":"W2324490698","doi":"10.3138/cjpe.30.3.394","title":"Hood, S., Hopson, R., &amp; Frierson, H., (2015). <i>Continuing the journey to reposition culture and cultural context in evaluation theory and practice.</i>","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Sociology; Psychology; History; Archaeology","score_opus":0.22758183789853317,"score_gpt":0.5146177563723437,"score_spread":0.2870359184738106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324490698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9406097,0.0066019576,0.0031450544,0.04423142,0.00077077,0.0026982608,0.000011157706,0.000010074553,0.0019216392],"genre_scores_gemma":[0.9962666,0.00013445922,0.0019736106,0.0010101919,0.00019250202,0.00010445711,0.0000054179177,0.0000096507865,0.00030311104],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925786,0.0036341632,0.0009932129,0.0003104241,0.0021794064,0.00030418474],"domain_scores_gemma":[0.9921193,0.0012456737,0.0009233295,0.00028753042,0.004950666,0.00047348344],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06348135,0.0001646732,0.00024615918,0.0004508399,0.00029456412,0.00083337835,0.0002766345,0.00010631492,0.0004119133],"category_scores_gemma":[0.032228265,0.000084714266,0.00006494987,0.0006099097,0.00015853927,0.0019151609,0.000023579687,0.00023875448,0.000030286443],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012749869,0.000018776878,0.006868336,0.0000021860174,0.000023752997,0.000002968759,0.017330674,0.00008167033,0.00057823875,0.0010642743,0.0060799206,0.9678217],"study_design_scores_gemma":[0.008430098,0.0017614338,0.29651257,0.0010827256,0.00077611115,0.0016493578,0.08648451,0.007212007,0.00032150926,0.060375374,0.53460306,0.00079124345],"about_ca_topic_score_codex":0.00026279452,"about_ca_topic_score_gemma":0.018726386,"teacher_disagreement_score":0.96703047,"about_ca_system_score_codex":0.0004718284,"about_ca_system_score_gemma":0.0012750459,"threshold_uncertainty_score":0.9991793},"labels":[],"label_agreement":null},{"id":"W2324880020","doi":"10.3138/cjpe.30.3.391","title":"Goodyear, L., Jewiss, J., Usinger, J., &amp; Barela, E. (Eds.). (2014). <i>Qualitative inquiry in evaluation: From theory to practice.</i>","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Epistemology; Philosophy","score_opus":0.4800931468809325,"score_gpt":0.5926954103586337,"score_spread":0.11260226347770119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324880020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8013842,0.018110374,0.07738004,0.07047283,0.012384353,0.00917961,0.00017229463,0.000058792924,0.010857473],"genre_scores_gemma":[0.95303106,0.00014292051,0.04248462,0.0023419894,0.00087911537,0.0003538522,0.000047453508,0.000040983155,0.0006780311],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.984703,0.0071596275,0.0018817144,0.0005356224,0.0051984466,0.0005215832],"domain_scores_gemma":[0.9853945,0.0040234914,0.0012782215,0.0006985114,0.007753608,0.0008517164],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.08635211,0.00025037728,0.0004468105,0.0013345778,0.00021269775,0.0004904669,0.000757431,0.000169272,0.013253012],"category_scores_gemma":[0.040946595,0.00017084052,0.0001623066,0.0013662134,0.0001869917,0.0021416221,0.000038926013,0.00030770226,0.0014947032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012363946,0.00008546004,0.0029605746,0.0000021716749,0.0000531599,0.0000062577906,0.017413154,0.0009336385,0.00015510937,0.0005560148,0.020463094,0.95724773],"study_design_scores_gemma":[0.004300674,0.00079508533,0.033887308,0.0004707469,0.0003311462,0.000039474617,0.01598847,0.0027741448,0.00014464353,0.13410844,0.80662084,0.000539021],"about_ca_topic_score_codex":0.0009882561,"about_ca_topic_score_gemma":0.031014338,"teacher_disagreement_score":0.9567087,"about_ca_system_score_codex":0.001332277,"about_ca_system_score_gemma":0.009321745,"threshold_uncertainty_score":0.9992828},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5647288,0.0015330572,0.0043378114,0.01626342,0.0048715333,0.0038497113,0.000011441057,0.00010554076,0.4042987],"genre_scores_gemma":[0.99563104,0.000011494719,0.0020833015,0.0002766773,0.0012436529,0.000036203604,0.000012333078,0.00000826425,0.00069703115],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816245,0.00047719953,0.0003898727,0.00010547732,0.00056460535,0.00030039405],"domain_scores_gemma":[0.997862,0.00011299568,0.0003805955,0.00016116306,0.00078692514,0.0006963285],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052955686,0.000085851636,0.00020418015,0.00060515985,0.00034695867,0.00019064921,0.00025312422,0.00008587439,0.002183086],"category_scores_gemma":[0.0013842749,0.00008012593,0.00014012007,0.0009029445,0.00014196632,0.00016330565,0.0000030248227,0.0001376092,0.000060806913],"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":[0.0000050378076,0.00005596458,0.0031644811,0.000011869287,0.0002071596,8.023061e-7,0.032096755,0.00032182966,0.0000101970645,0.018190367,0.0051725553,0.940763],"study_design_scores_gemma":[0.0007093175,0.00013344512,0.021473387,0.000042951302,0.0015064371,0.0000046190285,0.007839294,0.0064388216,0.000036968184,0.009819784,0.9516831,0.0003118555],"about_ca_topic_score_codex":0.013493108,"about_ca_topic_score_gemma":0.1751085,"teacher_disagreement_score":0.94651055,"about_ca_system_score_codex":0.0003350503,"about_ca_system_score_gemma":0.0032454329,"threshold_uncertainty_score":0.99872905},"labels":[],"label_agreement":null},{"id":"W233084541","doi":"10.3138/cjpe.017.006","title":"Public Training Programs in Canada: A Meta-evaluation","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Summative assessment; Formative assessment; Training (meteorology); Program evaluation; Medical education; Political science; Public relations; Psychology; Pedagogy; Public administration; Medicine; Geography","score_opus":0.9006990989952361,"score_gpt":0.5282974646477141,"score_spread":0.37240163434752205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W233084541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95176154,0.0044805794,0.00038953143,0.021945722,0.0020647643,0.004387647,0.0000110163755,0.000016725782,0.014942487],"genre_scores_gemma":[0.9975076,0.0000129305845,0.001590763,0.00028367026,0.00012555979,0.00034971564,0.000015469677,0.000012669992,0.0001016728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9902838,0.0014958618,0.0016387617,0.00030869636,0.0057129962,0.0005598889],"domain_scores_gemma":[0.9930124,0.00026770963,0.0009877279,0.00035695813,0.004672662,0.00070249895],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.033242255,0.00018879346,0.00049217435,0.001144385,0.00018774414,0.00057723647,0.00063075434,0.00007882191,0.015695544],"category_scores_gemma":[0.00586014,0.00014375198,0.00020112119,0.0019555113,0.00006684631,0.001150254,0.000011219119,0.0003306842,0.00005078962],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026508728,0.000039424176,0.02816503,0.0000019171475,0.00009709614,0.000009592594,0.0020124305,0.0025774606,0.0000022635004,0.00016523058,0.0022207813,0.9647061],"study_design_scores_gemma":[0.0024604027,0.00047759543,0.10485934,0.000047863487,0.0008388146,0.00011277623,0.009278659,0.7696825,0.000009431111,0.008765075,0.10308641,0.00038110942],"about_ca_topic_score_codex":0.34388363,"about_ca_topic_score_gemma":0.99592984,"teacher_disagreement_score":0.964325,"about_ca_system_score_codex":0.003129474,"about_ca_system_score_gemma":0.03065914,"threshold_uncertainty_score":0.99548054},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":["metaepi_broad"],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2331580938","doi":"10.3138/cjpe.30.3.02","title":"A Critical Exploration of Culture in International Development Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Context (archaeology); Engineering ethics; Epistemology","score_opus":0.5144255173283512,"score_gpt":0.58370906981695,"score_spread":0.06928355248859885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331580938","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9414468,0.00072937144,0.026706744,0.016119037,0.0036414035,0.0023938778,0.000015671487,0.000011827402,0.008935281],"genre_scores_gemma":[0.9922971,0.000011494132,0.0072883717,0.000059332186,0.0001225604,0.000107587424,0.000010887922,0.00000577642,0.000096896394],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99403024,0.0006491894,0.0013622788,0.00019152004,0.0035720891,0.00019467552],"domain_scores_gemma":[0.99089956,0.00029175053,0.0006338282,0.00018391843,0.0077624577,0.000228486],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021487162,0.00010157171,0.00020021356,0.0009950374,0.00007270749,0.00014690246,0.00040700566,0.000086676235,0.0033710047],"category_scores_gemma":[0.01297649,0.000064457214,0.0000760071,0.00059806724,0.00009257394,0.0020562415,0.000012779809,0.00010647767,0.000053974618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024764893,0.00006109762,0.023804948,0.0000026262137,0.000014421086,0.0000016466371,0.0031305512,0.0005945097,0.00036332203,0.00081298046,0.0006811216,0.97050804],"study_design_scores_gemma":[0.00889797,0.0013745489,0.58433175,0.0009779257,0.00019228934,0.00006606055,0.009168787,0.102784276,0.0062930565,0.13932641,0.14596222,0.0006247045],"about_ca_topic_score_codex":0.000070931026,"about_ca_topic_score_gemma":0.010202997,"teacher_disagreement_score":0.9698833,"about_ca_system_score_codex":0.000868365,"about_ca_system_score_gemma":0.0064564664,"threshold_uncertainty_score":0.999176},"labels":[],"label_agreement":null},{"id":"W2332681108","doi":"10.3138/cjpe.30.2.228","title":"Trevisan, M. S., &amp; Walser, T. M. (2015) <i>Evaluability assessment: Improving evaluation quality and use.</i>","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Philosophy; Epistemology","score_opus":0.6893862509287247,"score_gpt":0.6140360373202267,"score_spread":0.07535021360849803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2332681108","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9811114,0.001815964,0.0037381942,0.0055870013,0.0017873165,0.003032283,0.000026616293,0.000025754174,0.0028754505],"genre_scores_gemma":[0.9850796,0.000018102492,0.013820823,0.0003948555,0.0002762434,0.00014152467,0.000058716698,0.000019472845,0.00019067478],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98495704,0.004638206,0.0022966436,0.0005485074,0.007064892,0.00049472245],"domain_scores_gemma":[0.9807506,0.00085298903,0.001878694,0.00077348016,0.014340102,0.001404121],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13153072,0.0002711448,0.00055679027,0.0007850798,0.0003508092,0.0014996793,0.0005510934,0.0001725865,0.0020038884],"category_scores_gemma":[0.028855763,0.00021619268,0.0001863378,0.0010244142,0.00023042252,0.002728225,0.0000464808,0.00042380608,0.00006949462],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034091274,0.00007699148,0.15844215,0.000011469184,0.000033417095,0.0000011665289,0.000994954,0.0016701261,0.00007902474,0.0003451781,0.0055084964,0.83280295],"study_design_scores_gemma":[0.004146789,0.00073458225,0.7006008,0.00006562821,0.0004392274,0.000069240916,0.001810032,0.15452753,0.00004128695,0.031854503,0.10525603,0.00045438175],"about_ca_topic_score_codex":0.002535575,"about_ca_topic_score_gemma":0.036347516,"teacher_disagreement_score":0.8323485,"about_ca_system_score_codex":0.0016678949,"about_ca_system_score_gemma":0.017653648,"threshold_uncertainty_score":0.9995369},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4815011,0.28289956,0.0015530208,0.04168089,0.031904105,0.0036326956,0.00007211397,0.000025750705,0.15673074],"genre_scores_gemma":[0.9773294,0.00019398061,0.0031947615,0.00046266132,0.004682711,0.000141179,0.000023666387,0.00005161049,0.013920045],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938838,0.0030146053,0.00079365645,0.00021287701,0.0006437254,0.001451326],"domain_scores_gemma":[0.99546665,0.00011721853,0.000564389,0.00040470608,0.0012397784,0.002207241],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015625704,0.00022679627,0.0003788432,0.0008501417,0.00022254726,0.00014663604,0.00044002646,0.0004574294,0.015934283],"category_scores_gemma":[0.00052969175,0.00022578992,0.00033128852,0.0007910006,0.0003850477,0.0004269416,0.000008135058,0.00094393926,0.00095910305],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004938729,0.00045346297,0.123630784,0.000030240859,0.00034860783,0.00008575461,0.004088355,0.000025478403,0.000052454136,0.0011420782,0.0969345,0.7731589],"study_design_scores_gemma":[0.0015363496,0.0008653743,0.14208938,0.00013615907,0.0008381657,0.0020666241,0.0008754889,0.0006585747,0.000019869904,0.0018293634,0.8488472,0.00023743608],"about_ca_topic_score_codex":0.0023004194,"about_ca_topic_score_gemma":0.004760385,"teacher_disagreement_score":0.77292144,"about_ca_system_score_codex":0.0007770732,"about_ca_system_score_gemma":0.0035582203,"threshold_uncertainty_score":0.99981874},"labels":[],"label_agreement":null},{"id":"W2337090609","doi":"10.3138/cjpe.022.005","title":"A Participatory Approach to the Development of an Evaluation Framework: Process, Pitfalls, and Payoffs","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Alberta Health; Alberta Community Council on HIV; Public Health Agency of Canada","funders":"","keywords":"Citizen journalism; Participatory evaluation; Participatory GIS; Process (computing); Participatory development; Process management; Knowledge management; Business; Sociology; Management science; Computer science; Economics; Social science; World Wide Web","score_opus":0.5222899769278269,"score_gpt":0.5645426097571967,"score_spread":0.04225263282936986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337090609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97285044,0.00040723814,0.022461955,0.00065262493,0.00033616822,0.0017610419,0.0000020599987,0.0000052582204,0.00152322],"genre_scores_gemma":[0.96025497,0.0000015018416,0.03926586,0.00018929066,0.000137677,0.00012146643,0.000008410546,0.000008871774,0.000011927745],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99359846,0.0006548917,0.0013601047,0.00024941718,0.003802967,0.00033415295],"domain_scores_gemma":[0.9936635,0.00025290463,0.00077934033,0.00032926354,0.0043542664,0.0006207063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07402125,0.00012914308,0.00022406182,0.0005709598,0.0003186923,0.00023861523,0.00048750802,0.00009441131,0.00028694895],"category_scores_gemma":[0.0043747555,0.00008326373,0.000051650855,0.0009651523,0.00009920448,0.0005361862,0.0000156395,0.00021649513,0.000013908587],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028651002,0.00009522614,0.014345506,0.000007770929,0.000023558094,3.8946752e-7,0.020334326,0.0040927506,0.000020993124,0.00041862344,0.00012777818,0.9605044],"study_design_scores_gemma":[0.001115249,0.00076306507,0.74541694,0.000118940894,0.00022056498,0.00003131912,0.019436192,0.19715771,0.00080608536,0.015920846,0.018714672,0.00029838597],"about_ca_topic_score_codex":0.00008177498,"about_ca_topic_score_gemma":0.015754929,"teacher_disagreement_score":0.96020603,"about_ca_system_score_codex":0.00030625545,"about_ca_system_score_gemma":0.007438188,"threshold_uncertainty_score":0.99818873},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83341664,0.0027201576,0.061532196,0.009070581,0.0009912543,0.0071768244,0.0000498348,0.00020045516,0.08484206],"genre_scores_gemma":[0.9689533,0.00010929863,0.028211616,0.00029871342,0.0006408969,0.00026555095,0.00003675845,0.000020894422,0.0014629602],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99542505,0.0012383382,0.0006694036,0.0002284523,0.0012140315,0.0012247079],"domain_scores_gemma":[0.99595046,0.00013068838,0.00045928045,0.00014334077,0.0022208001,0.0010954125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014560557,0.00021333001,0.00024543374,0.00030571103,0.0012178717,0.00059654587,0.00032556712,0.00019648731,0.0001363259],"category_scores_gemma":[0.0027602452,0.00022621654,0.00015626814,0.00060517865,0.00034883845,0.00035251482,0.000007731234,0.0002567679,0.0000046853806],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000049506463,0.0003378355,0.012757228,0.000022214635,0.00010263924,0.000033989258,0.07302127,0.001090346,0.00019569328,0.14005679,0.000057661426,0.77227485],"study_design_scores_gemma":[0.0031469455,0.0024956628,0.29418832,0.00038743034,0.00084586715,0.00012897568,0.020505797,0.032277506,0.0009968752,0.41579482,0.22836207,0.000869739],"about_ca_topic_score_codex":0.009332848,"about_ca_topic_score_gemma":0.15770869,"teacher_disagreement_score":0.7714051,"about_ca_system_score_codex":0.0045571094,"about_ca_system_score_gemma":0.0170102,"threshold_uncertainty_score":0.99926424},"labels":[],"label_agreement":null},{"id":"W2338777541","doi":"10.3138/cjpe.0023.011","title":"Understanding Organization Capacity for Evaluation: Synthesis and Integration","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Context (archaeology); Empirical examination; Capacity building; Capacity development; Political science; Regional science; Process management; Knowledge management; Sociology; Business; Environmental resource management; Computer science; Geography; Economics; Archaeology","score_opus":0.6461461480260806,"score_gpt":0.5144417351249825,"score_spread":0.13170441290109813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338777541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6423295,0.00043947255,0.33081377,0.015983721,0.0015119814,0.004953599,0.000020832065,0.000029234818,0.0039178627],"genre_scores_gemma":[0.9897749,0.000008999988,0.009760496,0.00018659688,0.0001715482,0.00005275838,0.000017307115,0.0000074130044,0.000019994792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964657,0.0005089066,0.0007722218,0.00020335351,0.0018556863,0.000194145],"domain_scores_gemma":[0.99256045,0.00047460434,0.00065706036,0.00017997288,0.00583559,0.00029230895],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021255374,0.00011606143,0.00020583815,0.00066721183,0.00038403278,0.00059925043,0.00021131645,0.000075826916,0.0008957825],"category_scores_gemma":[0.014939678,0.00009311519,0.0000587075,0.00084473146,0.000062778105,0.0009497191,0.000003568893,0.000110922745,0.000007692732],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001906658,0.00003322135,0.0035787437,0.0000028859233,0.000016609618,3.0720742e-7,0.0009361584,0.0012196548,0.00018429346,0.0074181086,0.0019372235,0.9846537],"study_design_scores_gemma":[0.0034036036,0.0022968107,0.15119055,0.00017603331,0.0006380883,0.000091382855,0.004431694,0.52747685,0.0017980216,0.29901153,0.009065995,0.0004194475],"about_ca_topic_score_codex":0.000060889404,"about_ca_topic_score_gemma":0.004146175,"teacher_disagreement_score":0.9842343,"about_ca_system_score_codex":0.000996008,"about_ca_system_score_gemma":0.0027818903,"threshold_uncertainty_score":0.9933579},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921093,0.00071714405,0.000043932865,0.0012056933,0.0012269221,0.0043151383,0.00004535611,0.0000106260695,0.00032588272],"genre_scores_gemma":[0.9987643,0.00007019499,0.00078434823,0.000083434206,0.00007683773,0.00014957284,0.000043479944,0.000016872062,0.000010968042],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98652774,0.009320685,0.0019475311,0.00013495744,0.0016398291,0.00042928234],"domain_scores_gemma":[0.99280876,0.00021254529,0.002357905,0.00021640136,0.004089356,0.0003150353],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017607776,0.00014024018,0.00039254653,0.00087737193,0.0005431374,0.00000753372,0.000115804396,0.00018338484,0.0018691162],"category_scores_gemma":[0.002016107,0.00014769477,0.000092272756,0.00080779457,0.000071932394,0.00035439152,0.000010552226,0.0009412741,0.000011247533],"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":[0.00002615919,0.00006387686,0.6306976,0.00016156172,0.00002819428,1.3246728e-7,0.015074143,0.0008306424,0.000048662725,0.000043437787,0.001032443,0.35199314],"study_design_scores_gemma":[0.0030527518,0.0009786909,0.9479105,0.0009685116,0.00010759575,0.000008700976,0.007810691,0.03771563,0.000051486444,0.0006924687,0.0005895052,0.0001135078],"about_ca_topic_score_codex":0.06421483,"about_ca_topic_score_gemma":0.44440916,"teacher_disagreement_score":0.38019434,"about_ca_system_score_codex":0.0058782957,"about_ca_system_score_gemma":0.0054365173,"threshold_uncertainty_score":0.9990433},"labels":[],"label_agreement":null},{"id":"W2340392036","doi":"10.3138/cjpe.0026.007","title":"Trois conceptions de la nature des programmes : implications pour l’évaluation de programmes complexes en santé publique","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Dysfunctional family; Epistemology; Program evaluation; Valuation (finance); Psychology; Sociology; Business; Political science; Philosophy; Psychotherapist","score_opus":0.22282856566803982,"score_gpt":0.5388556115237819,"score_spread":0.3160270458557421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340392036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9710492,0.0024206177,0.015813714,0.0057942015,0.0003673683,0.001980186,0.00003052377,0.000052904146,0.0024912946],"genre_scores_gemma":[0.93746966,0.000052524458,0.06087284,0.00033873043,0.0005655908,0.00052601297,0.00006552429,0.00002264754,0.00008643794],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9931326,0.0031180878,0.0010668808,0.00025190163,0.0016219642,0.0008085561],"domain_scores_gemma":[0.9927992,0.0012504421,0.0008371411,0.00038816774,0.0037021928,0.0010228426],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035775106,0.00022511606,0.0003117498,0.00087387214,0.00060496345,0.0010534236,0.0006815988,0.0003321453,0.0012027835],"category_scores_gemma":[0.009422355,0.00018440507,0.00024411769,0.0012831573,0.0003905484,0.0016416095,0.00002351294,0.0006569043,0.000039668663],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009124345,0.00015999371,0.3625515,0.0000063408893,0.000041232397,8.184947e-7,0.005786663,0.0005155909,0.0002469946,0.004594444,0.0033195126,0.62276775],"study_design_scores_gemma":[0.0008122669,0.00027616016,0.8737729,0.000050626466,0.00017808328,0.0002589808,0.0049905283,0.010287418,0.00025150008,0.05259086,0.056314256,0.00021641413],"about_ca_topic_score_codex":0.00087782764,"about_ca_topic_score_gemma":0.009699292,"teacher_disagreement_score":0.6225513,"about_ca_system_score_codex":0.0013731685,"about_ca_system_score_gemma":0.011233715,"threshold_uncertainty_score":0.99998355},"labels":[],"label_agreement":null},{"id":"W237532803","doi":"10.3138/cjpe.26.006","title":"The Essential Skills Series in Evaluation: Assessing the Validity of the ESS Participant Workshop Evaluation Questionnaire","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre de Liaison Sur l'Intervention et la Prévention Psychosociales; Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Psychology; Medical education; Applied psychology; Medicine","score_opus":0.518137140465873,"score_gpt":0.548237636298514,"score_spread":0.03010049583264096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W237532803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836564,0.0011011629,0.0005890633,0.0067049586,0.0032204285,0.0031163853,0.0000037491461,0.0000067905776,0.0016010748],"genre_scores_gemma":[0.9988406,0.000026446105,0.00039092547,0.00008924334,0.00022861757,0.00033015394,0.0000049497603,0.000011973766,0.000077099496],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9838411,0.007246238,0.0019373316,0.0002855865,0.006257947,0.00043176225],"domain_scores_gemma":[0.9881095,0.00087532384,0.001996249,0.0008092596,0.0079968935,0.0002127336],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10130053,0.00019084217,0.00029769258,0.00032198027,0.0009840672,0.00070253067,0.0011894483,0.00012126301,0.0010210243],"category_scores_gemma":[0.01912317,0.000094300085,0.00022397765,0.0016418836,0.00054190605,0.001379401,0.000048823484,0.00043021239,0.0000126447785],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030712203,0.00014719395,0.15487787,0.000007096411,0.00006272527,0.0000015063703,0.011612259,0.014197379,0.000040564963,0.0013280927,0.000990496,0.8167041],"study_design_scores_gemma":[0.0009522966,0.00015919376,0.80145407,0.00022980102,0.00046351412,0.000030659037,0.007948485,0.14694789,0.00048052892,0.039612103,0.0015764547,0.00014497757],"about_ca_topic_score_codex":0.0006206697,"about_ca_topic_score_gemma":0.07303869,"teacher_disagreement_score":0.81655914,"about_ca_system_score_codex":0.000639029,"about_ca_system_score_gemma":0.011873252,"threshold_uncertainty_score":0.9998922},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W242703065","doi":"10.3138/cjpe.0014.005","title":"Organizational Development and Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Organization development; Organizational learning; Organizational effectiveness; Organizational culture; Organizational behavior and human resources; Knowledge management; Facilitation; Organizational commitment; Organizational performance; Organizational studies; Organizational engineering; Process (computing); Psychology; Process management; Business; Computer science; Public relations; Political science; Social psychology","score_opus":0.3470470019193243,"score_gpt":0.5167326550286309,"score_spread":0.16968565310930656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W242703065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9848315,0.00059873913,0.00020943723,0.0015919893,0.0003473457,0.000852512,0.0000021949875,0.000006861273,0.011559385],"genre_scores_gemma":[0.99203706,0.0000105148965,0.007120703,0.00019346764,0.00013930512,0.000044271692,0.000025046242,0.000008064774,0.00042155443],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99511397,0.000479311,0.00086574914,0.00018701941,0.0031608173,0.00019313527],"domain_scores_gemma":[0.994701,0.00013147466,0.0003607743,0.00016478283,0.004245061,0.00039685983],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018886132,0.00010251714,0.00015921968,0.00049297005,0.00029217592,0.00039247482,0.0002472586,0.000064020045,0.030043043],"category_scores_gemma":[0.0016846117,0.00008153411,0.000039175357,0.0007273301,0.0000671318,0.0005667342,0.0000058724786,0.0001169412,0.00022470689],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066792977,0.000019406772,0.016743524,0.0000012194348,0.00001476917,0.0000010737588,0.0012953348,0.0015426663,0.000008297396,0.00028805315,0.000943133,0.9791359],"study_design_scores_gemma":[0.002336901,0.0003609886,0.45420936,0.00005719761,0.00015846833,0.00014092268,0.00118837,0.18080038,0.000297725,0.02987434,0.33027124,0.0003040879],"about_ca_topic_score_codex":0.00006852469,"about_ca_topic_score_gemma":0.0047591617,"teacher_disagreement_score":0.97883177,"about_ca_system_score_codex":0.0003954455,"about_ca_system_score_gemma":0.008964811,"threshold_uncertainty_score":0.99665344},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4531066,0.0002451048,0.52459717,0.0016052839,0.00044685317,0.019465573,0.00047448135,0.000019472018,0.000039439932],"genre_scores_gemma":[0.537496,4.921918e-7,0.45770988,0.000090319576,0.000053539694,0.004517762,0.00011387095,0.000015100263,0.0000030958925],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99515814,0.0002982061,0.0037360564,0.00034323893,0.00014008107,0.00032425232],"domain_scores_gemma":[0.9935211,0.0008786773,0.003282917,0.0001759084,0.0017285988,0.00041281703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02716996,0.0001532451,0.00084168086,0.0012632242,0.00020221177,0.000059949543,0.00014181518,0.00012505366,0.000012280547],"category_scores_gemma":[0.006021066,0.00017845538,0.00025504213,0.00038359358,0.000032675674,0.00029603878,0.000004587739,0.000050794468,0.0000026134146],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015802896,0.0017583185,0.24465676,0.0046484782,0.0037200733,1.4553676e-7,0.04559271,0.00046871178,0.000032711447,0.019379487,0.0020086605,0.67615366],"study_design_scores_gemma":[0.009473908,0.008681988,0.5819028,0.00028394072,0.0012068081,0.0000022460201,0.007084097,0.37304744,0.000038419545,0.0039218226,0.013856821,0.000499727],"about_ca_topic_score_codex":0.0006209648,"about_ca_topic_score_gemma":0.00514309,"teacher_disagreement_score":0.67565393,"about_ca_system_score_codex":0.0013148105,"about_ca_system_score_gemma":0.0011944931,"threshold_uncertainty_score":0.941662},"labels":[],"label_agreement":null},{"id":"W2482243048","doi":"","title":"L’étude d’évaluabilité : Une approche d’évaluation de programmes encore mal connue et peu utilisée","year":2016,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.2956668829198084,"score_gpt":0.49993669500760696,"score_spread":0.20426981208779854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482243048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84755886,0.008271438,0.019218737,0.107952565,0.005464288,0.0056339735,0.00009491484,0.000057193713,0.005748027],"genre_scores_gemma":[0.9667224,0.00035978152,0.028513476,0.0008119783,0.00069095497,0.0004063413,0.000039539405,0.000054755506,0.002400723],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9863536,0.004523845,0.0024510573,0.00069219567,0.004750431,0.0012288808],"domain_scores_gemma":[0.98660856,0.0013625527,0.0018346827,0.0007539352,0.007857041,0.0015832015],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06195263,0.0004960501,0.0007093857,0.0010970439,0.00048491723,0.0010352039,0.001097182,0.0004918058,0.0073642298],"category_scores_gemma":[0.012353503,0.00036082193,0.00049284636,0.0018550681,0.00083830545,0.0022893583,0.000051299987,0.00064052735,0.00035821303],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008038972,0.00026965357,0.032408644,0.00004108818,0.00012737114,0.000021879972,0.010388147,0.0012549561,0.00026927848,0.003314676,0.005019215,0.9468047],"study_design_scores_gemma":[0.0075732116,0.004314231,0.21177459,0.0014785578,0.0013026352,0.0007320699,0.012364976,0.121984825,0.0008162179,0.09693653,0.53962046,0.0011017121],"about_ca_topic_score_codex":0.0037618002,"about_ca_topic_score_gemma":0.07189041,"teacher_disagreement_score":0.94570297,"about_ca_system_score_codex":0.002115037,"about_ca_system_score_gemma":0.035790008,"threshold_uncertainty_score":0.99988437},"labels":[],"label_agreement":null},{"id":"W2483463161","doi":"10.3138/cjpe.31.1.122","title":"Hallie Preskill et Darlene Russ-Eft. (2016). <i>Building evaluation capacity: Activities for teaching and training</i> (2nd ed.).","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Sociology; Physics","score_opus":0.4310966052308271,"score_gpt":0.5106947102029149,"score_spread":0.0795981049720878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2483463161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9487782,0.0010010388,0.033041246,0.009747823,0.0014442954,0.0028359815,0.000062532505,0.000022941254,0.0030659314],"genre_scores_gemma":[0.9755666,0.000044128108,0.023150036,0.00035013625,0.00036865735,0.00025075473,0.000010927974,0.00002260661,0.00023613824],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99377304,0.0015919245,0.0010787868,0.00038068314,0.0027248398,0.00045071877],"domain_scores_gemma":[0.9939671,0.0017234499,0.0010808184,0.00031896244,0.0023933935,0.0005162567],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05778622,0.00021299481,0.00036596265,0.000732569,0.00055735995,0.0006699086,0.00038787458,0.00012912623,0.00080816867],"category_scores_gemma":[0.01237312,0.00014287452,0.00014909786,0.00022190389,0.0002011748,0.0021509628,0.000019845202,0.0002774537,0.000008418449],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030954365,0.000027679951,0.0016858528,0.000007374379,0.000045966943,6.720422e-7,0.0038653598,0.00043278598,0.00097090943,0.0018964856,0.003866011,0.9871699],"study_design_scores_gemma":[0.012782238,0.003457099,0.050992634,0.0013072153,0.0010532798,0.00027938592,0.013058447,0.16627775,0.0019340436,0.1936308,0.5539788,0.0012482888],"about_ca_topic_score_codex":0.00030980588,"about_ca_topic_score_gemma":0.0075110765,"teacher_disagreement_score":0.9859217,"about_ca_system_score_codex":0.0005972922,"about_ca_system_score_gemma":0.0058150305,"threshold_uncertainty_score":0.99982107},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96581143,0.0017247302,0.00507942,0.010969718,0.0050193877,0.0077035525,0.000020002359,0.000113048656,0.0035587081],"genre_scores_gemma":[0.9439402,0.0000015938883,0.05200109,0.0016279017,0.001268245,0.00092732365,0.00009043375,0.000023470373,0.000119712466],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946679,0.0025057027,0.0011388536,0.00017374368,0.00056446873,0.000949319],"domain_scores_gemma":[0.9943152,0.00040464592,0.0007999697,0.0002765278,0.0024922125,0.0017114305],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0150115825,0.00016334749,0.0003386909,0.0012364432,0.00086870475,0.000058559253,0.0002393092,0.00015133119,0.0018996797],"category_scores_gemma":[0.00418575,0.00014360806,0.00024384134,0.0018702118,0.000058306952,0.00034569105,0.000012988395,0.0006216301,0.00023850835],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003130009,0.00018930834,0.29181665,0.00009955731,0.00017247556,8.662133e-7,0.0032393022,0.00011648549,0.000015398748,0.00023372848,0.008701886,0.695383],"study_design_scores_gemma":[0.00061644544,0.00073972635,0.9686468,0.0005156004,0.0018862227,0.000011036102,0.0027312327,0.0020620462,0.0000023957173,0.0032164615,0.019394305,0.0001776806],"about_ca_topic_score_codex":0.0012215994,"about_ca_topic_score_gemma":0.01098647,"teacher_disagreement_score":0.69520533,"about_ca_system_score_codex":0.0012605675,"about_ca_system_score_gemma":0.003323157,"threshold_uncertainty_score":0.9990127},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82219225,0.00033659238,0.0020082525,0.15809229,0.0114581315,0.003975544,0.000032304986,0.000016605361,0.0018880237],"genre_scores_gemma":[0.96717614,0.000002458034,0.0019426612,0.00032175882,0.030109828,0.00009610709,0.000037409725,0.0000116824085,0.00030196432],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99217016,0.0020760472,0.00075970945,0.00024704653,0.0042784535,0.00046858838],"domain_scores_gemma":[0.99186444,0.00014654883,0.0006965695,0.0005905262,0.0056878277,0.0010140728],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.045736507,0.00017082704,0.0002506859,0.0006743331,0.0005274036,0.0013160515,0.000675114,0.00007454296,0.016031774],"category_scores_gemma":[0.0060512535,0.000090018795,0.00016215185,0.0011241763,0.0001240743,0.0027227579,0.00001800521,0.00025936187,0.00021428558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028411596,0.000071321956,0.0149643505,0.0000013064491,0.000026109548,3.7704845e-7,0.003253714,0.0037188022,0.000042882526,0.00043637012,0.09615621,0.88130015],"study_design_scores_gemma":[0.0005868735,0.00066062645,0.25603443,0.000008250027,0.00015604153,0.000058572325,0.0048321295,0.03136617,0.00014691734,0.0059028277,0.70007163,0.00017551913],"about_ca_topic_score_codex":0.0004171657,"about_ca_topic_score_gemma":0.048126027,"teacher_disagreement_score":0.8811246,"about_ca_system_score_codex":0.0011238743,"about_ca_system_score_gemma":0.0031818,"threshold_uncertainty_score":0.9997207},"labels":[],"label_agreement":null},{"id":"W249659815","doi":"10.3138/cjpe.17.005","title":"New Partnerships Require New Approaches to Participatory Program Evaluations: Planning for the Future","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Participatory evaluation; Independence (probability theory); Citizen journalism; Work (physics); Government (linguistics); Affect (linguistics); Power (physics); Civil society; Public relations; Program evaluation; Process management; Business; Political science; Psychology; Public administration; Engineering; Politics","score_opus":0.8918311256608674,"score_gpt":0.5795271091974086,"score_spread":0.31230401646345884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W249659815","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11190089,0.049305055,0.2114975,0.56085294,0.014240603,0.043164,0.000052168383,0.00025145515,0.008735387],"genre_scores_gemma":[0.93700635,0.000020840991,0.05421546,0.001051659,0.0035694982,0.0011782877,0.000016830969,0.000034850087,0.0029062137],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945733,0.0006070521,0.0011873926,0.00033466867,0.0027555819,0.0005420107],"domain_scores_gemma":[0.9954454,0.00069252757,0.000733914,0.00052714784,0.001328437,0.0012725935],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017652106,0.00020627584,0.00029551436,0.00054344797,0.000611891,0.000954235,0.00084432674,0.00012558498,0.0031221781],"category_scores_gemma":[0.003632237,0.00013519984,0.00023102587,0.0012385987,0.00006771985,0.0009552875,0.000017281189,0.00027970597,0.00013678687],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022005259,0.00003484679,0.0027474377,0.0000038172893,0.000043944943,0.0000010326477,0.0045527597,0.010978329,0.0000018308783,0.0014988804,0.099831484,0.88028365],"study_design_scores_gemma":[0.0011533241,0.0010026951,0.011826763,0.000058768135,0.00022625532,0.00001997032,0.0045896317,0.23951,0.000022561697,0.011694651,0.729694,0.00020137931],"about_ca_topic_score_codex":0.000096111595,"about_ca_topic_score_gemma":0.008737331,"teacher_disagreement_score":0.88008225,"about_ca_system_score_codex":0.00038570593,"about_ca_system_score_gemma":0.0053229057,"threshold_uncertainty_score":0.9977891},"labels":[],"label_agreement":null},{"id":"W2498848778","doi":"10.3138/cjpe.307","title":"Evaluating a Prison-Based Intervention Program: Approaches and Challenges","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université Laval","funders":"","keywords":"Prison; Government (linguistics); Intervention (counseling); Process (computing); Face (sociological concept); Public relations; Psychology; Business; Process management; Political science; Sociology; Computer science; Criminology; Psychiatry","score_opus":0.7617709376605948,"score_gpt":0.5696057253886638,"score_spread":0.19216521227193095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2498848778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9572402,0.007538209,0.0050552716,0.023732292,0.0008836167,0.0035161672,0.000007865205,0.000043925345,0.0019824253],"genre_scores_gemma":[0.98300123,0.00006455795,0.01635922,0.000048402857,0.00015053808,0.00027207876,0.0000039419733,0.000012871901,0.000087183675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949832,0.0010781356,0.0010600215,0.00031486602,0.0022497256,0.00031404753],"domain_scores_gemma":[0.99555457,0.00051336864,0.0009673466,0.00030107857,0.0022032107,0.00046041864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027472114,0.00015561651,0.00026559032,0.0007244074,0.00019259717,0.0003893023,0.00036445816,0.00009752443,0.0008613683],"category_scores_gemma":[0.0053286045,0.00009457686,0.00015381904,0.0004072026,0.00015906067,0.0007400686,0.000016349783,0.00013429607,0.000035131237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024511099,0.000080587575,0.007431304,0.000015203084,0.000022464248,0.000001334068,0.00046043593,0.00018385056,0.000036127887,0.00035381835,0.00012774332,0.9912626],"study_design_scores_gemma":[0.009573988,0.008346784,0.38325873,0.0010014374,0.00037732054,0.0001047928,0.00472745,0.4740058,0.0006142023,0.031431355,0.08589619,0.0006619702],"about_ca_topic_score_codex":0.00010932353,"about_ca_topic_score_gemma":0.007145909,"teacher_disagreement_score":0.99060065,"about_ca_system_score_codex":0.0003221289,"about_ca_system_score_gemma":0.002514481,"threshold_uncertainty_score":0.95213413},"labels":[],"label_agreement":null},{"id":"W2505652211","doi":"10.3138/cjpe.225","title":"Improving Interprofessional Education and Collaborative Practice Through Evaluation: An Exploration of Current Trends","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Interdisciplinary Research in Rehabilitation; University of British Columbia","funders":"","keywords":"Political science; Humanities; Psychology; Sociology; Philosophy","score_opus":0.4583917648546845,"score_gpt":0.6133023389854954,"score_spread":0.15491057413081083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2505652211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88807213,0.011767515,0.053219575,0.024606602,0.009396067,0.004382689,0.00007388969,0.000028182294,0.00845336],"genre_scores_gemma":[0.98749137,0.00006916527,0.01174718,0.00010415066,0.0002991462,0.00017032007,0.000028021928,0.000009606104,0.000081038655],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99365866,0.0018668069,0.0011803437,0.00027954247,0.0028295654,0.000185086],"domain_scores_gemma":[0.9839836,0.00050261494,0.0019006621,0.0002911148,0.013005108,0.00031689837],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018372267,0.00014122047,0.00023911834,0.00074622984,0.00020715677,0.00023994886,0.00028396194,0.00007848933,0.0013522033],"category_scores_gemma":[0.0074808123,0.00009069195,0.00006257361,0.0010184187,0.00014480014,0.008666548,0.000017493892,0.00014388311,0.0000114423],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007057975,0.00014437886,0.002405762,0.0000045581164,0.000016446824,2.408491e-7,0.0041187876,0.0000990781,0.00026830778,0.0017363355,0.00071999716,0.9904155],"study_design_scores_gemma":[0.01427121,0.010620908,0.11866328,0.002495168,0.001986494,0.00022407403,0.120829985,0.1528864,0.0037643632,0.24163616,0.33104157,0.0015803997],"about_ca_topic_score_codex":0.00024391602,"about_ca_topic_score_gemma":0.00533397,"teacher_disagreement_score":0.98883516,"about_ca_system_score_codex":0.0004815928,"about_ca_system_score_gemma":0.020579588,"threshold_uncertainty_score":0.9995607},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8574344,0.0053956686,0.00042832913,0.11811313,0.0061325585,0.0032326279,0.00005823182,0.000021999913,0.009183081],"genre_scores_gemma":[0.9958151,0.0017590213,0.00067554973,0.000019092839,0.0014001611,0.0001818805,0.000003830042,0.000008291764,0.00013707508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99775636,0.0003202961,0.000504834,0.00010081557,0.0010823912,0.00023530044],"domain_scores_gemma":[0.9954095,0.00051779376,0.0004989154,0.000103156126,0.0032997879,0.00017087764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044324826,0.000089793895,0.00013396241,0.0002627496,0.0008143055,0.00016891667,0.00032662522,0.00007152256,0.00024163797],"category_scores_gemma":[0.0011673019,0.000058809015,0.00014519769,0.00010283639,0.00017735777,0.00032775642,0.000011227785,0.000078511104,0.0000017385463],"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":[0.00007867314,0.00029376015,0.015092893,0.000024138262,0.0010716098,0.000005452771,0.19725825,0.00024498266,0.00045374595,0.43015683,0.0019645346,0.3533551],"study_design_scores_gemma":[0.0070331506,0.0010044597,0.21831755,0.00045282222,0.00051189144,0.000022059055,0.5282823,0.0006303157,0.00025433014,0.058259528,0.18476218,0.00046942555],"about_ca_topic_score_codex":0.0004570659,"about_ca_topic_score_gemma":0.1112653,"teacher_disagreement_score":0.3718973,"about_ca_system_score_codex":0.000814317,"about_ca_system_score_gemma":0.002543533,"threshold_uncertainty_score":0.9049518},"labels":[],"label_agreement":null},{"id":"W2508682278","doi":"10.3138/cjpe.258","title":"Capturing the Imagination: Arts-Informed Inquiry as a Method in Program Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"The arts; Context (archaeology); Representation (politics); Field (mathematics); Qualitative research; Arts in education; Sociology; Psychology; Pedagogy; Engineering ethics; Social science; Visual arts; Political science; Engineering; Art","score_opus":0.5462734858006425,"score_gpt":0.6255805119329582,"score_spread":0.07930702613231566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508682278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.867189,0.0019301404,0.012254197,0.07502822,0.0051064272,0.015573493,0.000010993402,0.00006756597,0.022839954],"genre_scores_gemma":[0.98820513,0.00002061981,0.0098293135,0.00037052165,0.00037125868,0.0009824877,0.000008908917,0.000014567161,0.00019720578],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99151146,0.0015716273,0.0015180697,0.00031390568,0.0046264245,0.0004585065],"domain_scores_gemma":[0.9916491,0.0009755034,0.001097801,0.0004844608,0.005399245,0.00039392477],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052481346,0.00019032322,0.0002876194,0.0011435916,0.00026893767,0.0006548511,0.0007318885,0.00010959618,0.0030947712],"category_scores_gemma":[0.0126695195,0.00010234848,0.00016438804,0.0013904249,0.00018458533,0.0017687884,0.000024602417,0.00026665552,0.00018586763],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021075834,0.000043489166,0.007238515,0.0000029726957,0.000019326302,0.0000037565355,0.0039458894,0.00095571333,0.000035127556,0.0007084125,0.0015761501,0.98544955],"study_design_scores_gemma":[0.0069494937,0.0014366265,0.37518585,0.00042020658,0.0003104818,0.0002883561,0.012816513,0.20319165,0.00062534417,0.09800104,0.30020377,0.0005706648],"about_ca_topic_score_codex":0.00063890463,"about_ca_topic_score_gemma":0.03447505,"teacher_disagreement_score":0.9848789,"about_ca_system_score_codex":0.0015684015,"about_ca_system_score_gemma":0.012386379,"threshold_uncertainty_score":0.99781656},"labels":[],"label_agreement":null},{"id":"W2509640135","doi":"10.3138/cjpe.31.1.125","title":"Huey T. Chen. (2015). <i>Practical program evaluation: Theory-driven evaluation and the integrated evaluation perspective</i> (2nd ed.).","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Chen; Perspective (graphical); Evaluation methods; Sociology; Program evaluation; Epistemology; Management science; Psychology; Computer science; Mathematics; Philosophy; Statistics; Artificial intelligence; Economics; Engineering; Reliability engineering","score_opus":0.27595033564129184,"score_gpt":0.5513600661607184,"score_spread":0.2754097305194266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509640135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65918225,0.021510176,0.019441085,0.18542649,0.009565019,0.07203196,0.00012837427,0.00023332158,0.03248132],"genre_scores_gemma":[0.9910821,0.00014351899,0.0045386725,0.0004073518,0.0006501154,0.0028707988,0.00005607779,0.000040887622,0.000210505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9688457,0.014479715,0.0023460402,0.0009061513,0.012649585,0.00077277207],"domain_scores_gemma":[0.95830166,0.002838117,0.0021412184,0.0009535472,0.034954075,0.0008113919],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17340463,0.00046183052,0.0006789795,0.0010393655,0.0008388877,0.0013898443,0.0008613431,0.0003016062,0.014546612],"category_scores_gemma":[0.05666442,0.000251587,0.00034172204,0.001612539,0.0010695326,0.0023935928,0.00006079161,0.00060951174,0.00021376446],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031300946,0.00018413222,0.0030873283,0.000004336839,0.00019029071,0.0000025093202,0.0022469421,0.0008656066,0.000079921185,0.008036325,0.007862286,0.9771273],"study_design_scores_gemma":[0.020416437,0.0016949156,0.047296062,0.00029086057,0.0032756026,0.00029956692,0.011533669,0.64388853,0.00015000057,0.20111299,0.06935454,0.000686817],"about_ca_topic_score_codex":0.00051356567,"about_ca_topic_score_gemma":0.010346884,"teacher_disagreement_score":0.9764405,"about_ca_system_score_codex":0.0032465705,"about_ca_system_score_gemma":0.022618946,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W2512095165","doi":"10.3138/cjpe.274","title":"Evaluate This! A Case for Developing Evaluation Competencies","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Competition (biology); Psychology; Business; Medical education; Public relations; Political science; Medicine; Ecology","score_opus":0.5723191234277859,"score_gpt":0.562928248525481,"score_spread":0.009390874902304946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512095165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9254388,0.0012358942,0.037165463,0.022738542,0.003605374,0.006586937,0.000050531555,0.000032152308,0.0031463031],"genre_scores_gemma":[0.9771815,0.000012671166,0.021445166,0.0002544582,0.0003356656,0.00043724466,0.000010650665,0.000017352106,0.00030527433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99282396,0.0011560787,0.0014971939,0.00033371523,0.003743916,0.00044515383],"domain_scores_gemma":[0.98371226,0.0010746154,0.001204151,0.00039257243,0.013183756,0.0004326463],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054492533,0.0001920546,0.0003415507,0.00070901704,0.0004894453,0.00045208808,0.0005054364,0.00011085585,0.0039134813],"category_scores_gemma":[0.012808461,0.0001180008,0.00022255366,0.00074934796,0.00017750065,0.0011784332,0.000017006436,0.000115057504,0.00012724644],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026716452,0.000019944773,0.0037242358,0.00000539601,0.000041424537,0.000016237831,0.00066140364,0.00034356074,0.00018481929,0.0010835944,0.0042374963,0.9896552],"study_design_scores_gemma":[0.013358807,0.0026190882,0.043988932,0.00060781755,0.0011579697,0.003604011,0.0045608715,0.41630852,0.0018791155,0.14576338,0.365082,0.0010694948],"about_ca_topic_score_codex":0.00030665618,"about_ca_topic_score_gemma":0.026465822,"teacher_disagreement_score":0.98858565,"about_ca_system_score_codex":0.0015667378,"about_ca_system_score_gemma":0.0128331585,"threshold_uncertainty_score":0.99699706},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9158357,0.0034743575,0.06838212,0.0027447636,0.0007318476,0.003404357,0.0000076476645,0.000019673782,0.0053995396],"genre_scores_gemma":[0.9393056,0.0000039719403,0.06034914,0.00005644121,0.000110379864,0.00007380896,0.0000017558458,0.000014922942,0.00008399658],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935646,0.00094631215,0.0014949503,0.00044824768,0.0031449597,0.00040089551],"domain_scores_gemma":[0.99393284,0.0010558531,0.00096560386,0.00035459557,0.0030590268,0.00063208066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024577718,0.00019927509,0.0004483048,0.0008219038,0.00027353415,0.0004597166,0.00031046386,0.00009586554,0.00057509984],"category_scores_gemma":[0.004653638,0.00011748501,0.000073653464,0.0007073819,0.00019010459,0.00067744334,0.000037974656,0.00019780989,0.000029302973],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101487836,0.000078160636,0.028875714,0.0000072392972,0.000040558294,0.000038500093,0.0013108241,0.00046467775,0.000075273965,0.0023011693,0.0020601489,0.9646462],"study_design_scores_gemma":[0.018884547,0.0015848604,0.3816888,0.0019275042,0.00039530935,0.004066492,0.009928877,0.21412686,0.00020864302,0.10981593,0.25564107,0.0017311056],"about_ca_topic_score_codex":0.00045069028,"about_ca_topic_score_gemma":0.024003044,"teacher_disagreement_score":0.9629151,"about_ca_system_score_codex":0.000484637,"about_ca_system_score_gemma":0.0053887293,"threshold_uncertainty_score":0.99380636},"labels":[],"label_agreement":null},{"id":"W2517356492","doi":"10.3138/cjpe.267","title":"Process Flow Mapping for Systems Improvement: Lessons Learned","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Process (computing); Computer science; Context (archaeology); Process management; Flow (mathematics); Risk analysis (engineering); Management science; Engineering; Business; Mathematics; Geography","score_opus":0.5733614912876671,"score_gpt":0.5667968770536289,"score_spread":0.006564614234038202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517356492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67975587,0.0021538548,0.2191912,0.074308544,0.00861209,0.010969184,0.00017213993,0.0000636096,0.0047735195],"genre_scores_gemma":[0.99661094,0.000012199016,0.0019579178,0.00010368187,0.00034072113,0.00032527748,0.000006668448,0.000012601399,0.0006299932],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99631023,0.00024981456,0.0010032711,0.00023727628,0.0018523172,0.00034709246],"domain_scores_gemma":[0.9930999,0.0003451296,0.0008954168,0.00026018196,0.0049664862,0.0004328437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017333744,0.00012055005,0.00024416434,0.00063582166,0.0002692112,0.00043906938,0.0004762207,0.00007775728,0.0005370318],"category_scores_gemma":[0.0040663723,0.00007250821,0.00013400699,0.0005095955,0.00006262938,0.0007833258,0.0000072500484,0.00008944472,0.000055099328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000149941225,0.000018784753,0.0020936423,0.000009823179,0.000027202716,9.1096405e-7,0.0005844937,0.0017683861,0.00039896287,0.00047702703,0.0026165184,0.99198925],"study_design_scores_gemma":[0.00726273,0.0023868098,0.015621893,0.00052603014,0.0002156044,0.00006003752,0.008122462,0.4517606,0.0011317829,0.06464644,0.4476783,0.0005873206],"about_ca_topic_score_codex":0.000096418364,"about_ca_topic_score_gemma":0.002513491,"teacher_disagreement_score":0.9914019,"about_ca_system_score_codex":0.00044686408,"about_ca_system_score_gemma":0.005278585,"threshold_uncertainty_score":0.93639827},"labels":[],"label_agreement":null},{"id":"W2520223558","doi":"10.3138/cjpe.261","title":"Data Quality Evaluation for Program Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Computer science; Philosophy; Epistemology","score_opus":0.8261497658997451,"score_gpt":0.6791874459859031,"score_spread":0.146962319913842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520223558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.898655,0.00245797,0.030731468,0.029141763,0.007745378,0.024527026,0.0007696941,0.000111835434,0.0058598644],"genre_scores_gemma":[0.9789172,0.000015721245,0.018944863,0.00019119329,0.00061030226,0.0008631262,0.0001633669,0.000024939394,0.000269304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9880323,0.0021830683,0.0021908917,0.0006101159,0.0064362846,0.000547372],"domain_scores_gemma":[0.9813163,0.0013152628,0.00180972,0.0013874767,0.013430304,0.00074093597],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1198193,0.00022411389,0.00042955423,0.0008411665,0.00035928361,0.0005976603,0.0017351159,0.00015514827,0.0041519892],"category_scores_gemma":[0.036143035,0.00013812805,0.00022075255,0.0009224303,0.00018800801,0.0020836121,0.000050461542,0.0001535728,0.00013343655],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046323297,0.00008894667,0.014200328,0.0000059348513,0.000046061665,5.2487866e-7,0.00019809695,0.0001756776,0.00008467055,0.0004989415,0.013851008,0.9708035],"study_design_scores_gemma":[0.0064687054,0.001899504,0.15116438,0.00015611218,0.0005924234,0.000031470674,0.00096984016,0.21215537,0.00020082238,0.057284456,0.5685998,0.00047711233],"about_ca_topic_score_codex":0.00020050054,"about_ca_topic_score_gemma":0.020488763,"teacher_disagreement_score":0.97032636,"about_ca_system_score_codex":0.0009769184,"about_ca_system_score_gemma":0.0158549,"threshold_uncertainty_score":0.9973848},"labels":[],"label_agreement":null},{"id":"W2523734706","doi":"10.3138/cjpe.207","title":"L’étude d’évaluabilité : utilité et pertinence pour l’évaluation de programme","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science","score_opus":0.42773972430882595,"score_gpt":0.52477615985024,"score_spread":0.097036435541414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523734706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9543561,0.00036969795,0.016759222,0.023960596,0.000696046,0.0016074997,0.000009676367,0.000031506006,0.0022096948],"genre_scores_gemma":[0.9812846,0.000026225673,0.017405497,0.00050917995,0.00023529131,0.00018452173,0.000006085873,0.000019649522,0.00032891],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9916922,0.0020542957,0.0015267972,0.00039070993,0.0036763682,0.0006596354],"domain_scores_gemma":[0.99085265,0.0010185918,0.0010178129,0.00054059096,0.005703886,0.00086646376],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05709461,0.00021634795,0.00032161074,0.0007730405,0.00023786451,0.00048190178,0.0007778425,0.00014165422,0.0043397294],"category_scores_gemma":[0.021103842,0.00013405112,0.00024699076,0.00090395275,0.0001762252,0.0011829665,0.000024583374,0.00023805181,0.00023523692],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026427773,0.000062616935,0.09455938,0.0000035949565,0.00002257299,0.000004378011,0.0018902178,0.00043608787,0.0008905025,0.00074349064,0.0012601895,0.9001005],"study_design_scores_gemma":[0.0031872771,0.0012137297,0.7899452,0.00021220124,0.00017407497,0.00018216955,0.0018697662,0.054465503,0.0011177043,0.08929368,0.057940476,0.00039825405],"about_ca_topic_score_codex":0.0005371649,"about_ca_topic_score_gemma":0.014728337,"teacher_disagreement_score":0.8997023,"about_ca_system_score_codex":0.0009470432,"about_ca_system_score_gemma":0.015905267,"threshold_uncertainty_score":0.99657047},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932518,0.00022535196,0.000033848046,0.002747086,0.00012711933,0.0014815552,0.000005803231,0.0000056719746,0.002121789],"genre_scores_gemma":[0.99329394,0.000039974784,0.0061108377,0.00005646311,0.0001776551,0.00022831402,0.0000074895715,0.000005869362,0.000079461715],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984921,0.00020231915,0.00060702424,0.0001227562,0.0002796032,0.0002961916],"domain_scores_gemma":[0.9985678,0.000078783705,0.0003594962,0.00009738488,0.0006051626,0.0002913348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045638056,0.00006710348,0.0001500041,0.00049218914,0.0002889597,0.00004644882,0.00018445929,0.00006494605,0.000031363288],"category_scores_gemma":[0.0014164757,0.00007816256,0.00005714983,0.00042574565,0.00009319753,0.00020823296,0.000004901853,0.00012920133,0.0000016473732],"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":[0.000008511311,0.0001299206,0.8265928,0.00004604914,0.000008322943,0.0000029036487,0.002654906,0.000038107908,0.00002168277,0.0008395016,0.00069786824,0.16895944],"study_design_scores_gemma":[0.0008873886,0.00010547759,0.98657364,0.00023310627,0.00003411738,0.0000063921702,0.006055354,0.00020948656,0.000032673077,0.002272844,0.0034969582,0.00009254535],"about_ca_topic_score_codex":0.007494675,"about_ca_topic_score_gemma":0.11103616,"teacher_disagreement_score":0.1688669,"about_ca_system_score_codex":0.000796774,"about_ca_system_score_gemma":0.0027547039,"threshold_uncertainty_score":0.9991145},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9689466,0.00044122085,0.013550123,0.015560929,0.000156344,0.0007053366,0.000012900585,0.00003701315,0.0005895566],"genre_scores_gemma":[0.99227035,0.00046152496,0.006477831,0.00014482695,0.000441736,0.00008137224,0.00001049716,0.00001771016,0.00009415189],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99306506,0.0049042613,0.000451588,0.00019639362,0.0007393428,0.000643326],"domain_scores_gemma":[0.99742967,0.00045349056,0.0007313105,0.00008470865,0.0008687379,0.0004320728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01909805,0.00015255657,0.00017123169,0.00014937493,0.00087096053,0.000399624,0.00032611535,0.0002498028,0.00028236426],"category_scores_gemma":[0.0027830391,0.00013210464,0.00010070556,0.0006878033,0.0003979392,0.0008595478,0.000014490846,0.00018297347,0.000003946273],"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":[0.000025024186,0.00012563959,0.3686093,0.000051007435,0.00003871018,0.000007726151,0.22703575,0.00023679312,0.0032015,0.0030640666,0.0006681398,0.39693633],"study_design_scores_gemma":[0.00088384247,0.00014211125,0.8313291,0.00075713504,0.00011701751,0.0000133118165,0.081647806,0.0023489671,0.0012783543,0.07999197,0.0013060188,0.00018436415],"about_ca_topic_score_codex":0.051721133,"about_ca_topic_score_gemma":0.42976186,"teacher_disagreement_score":0.4627198,"about_ca_system_score_codex":0.0050745136,"about_ca_system_score_gemma":0.011754938,"threshold_uncertainty_score":0.99874485},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9736783,0.0005173434,0.01900536,0.0038126907,0.0004773959,0.000788537,0.000013302783,0.000018134613,0.0016889614],"genre_scores_gemma":[0.9966599,0.000053155287,0.002756067,0.00014150969,0.00018122961,0.000106937216,0.000006229996,0.000016262627,0.0000787367],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99433494,0.0021139719,0.0011118692,0.000295911,0.0017343643,0.0004089709],"domain_scores_gemma":[0.99621356,0.0006419744,0.00083941926,0.00029237705,0.0015019217,0.00051073683],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027809678,0.0001762921,0.00028408822,0.0006277158,0.00023183807,0.00037152084,0.00045488216,0.00014441044,0.0026111617],"category_scores_gemma":[0.0020191725,0.00011954152,0.00029207382,0.00068020116,0.0002898999,0.0013005509,0.000006777476,0.00022750086,0.000037552036],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008729866,0.00013256026,0.030518308,0.000011915529,0.000048782338,0.00000868099,0.007310072,0.00059639616,0.0013457905,0.00024964882,0.0006054279,0.9590851],"study_design_scores_gemma":[0.0035573274,0.0012258978,0.9081154,0.00047283087,0.00018097428,0.0001835168,0.0061498526,0.013718489,0.0025217028,0.051669747,0.01188294,0.00032133353],"about_ca_topic_score_codex":0.00042078967,"about_ca_topic_score_gemma":0.01833103,"teacher_disagreement_score":0.9587638,"about_ca_system_score_codex":0.001126812,"about_ca_system_score_gemma":0.0036858476,"threshold_uncertainty_score":0.9995819},"labels":[],"label_agreement":null},{"id":"W2559871496","doi":"10.3138/cjpe.263","title":"Evaluating System Change Initiatives: Advancing the Need for Adapting Evaluation Practices","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"PolicyWise for Children & Families; University of Alberta","funders":"","keywords":"Process management; Plan (archaeology); Context (archaeology); Strategic planning; Government (linguistics); Key (lock); Business; Outcome (game theory); Program evaluation; Monitoring and evaluation; Knowledge management; Political science; Management science; Computer science; Public administration; Engineering; Marketing; Economics; Computer security","score_opus":0.771827991309673,"score_gpt":0.6310206511420624,"score_spread":0.14080734016761054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559871496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89291674,0.0034419452,0.035508383,0.036229856,0.006170598,0.01954091,0.000058825706,0.00007173341,0.0060609863],"genre_scores_gemma":[0.98673975,0.000012826906,0.010465026,0.00026563153,0.0010327884,0.0013997878,0.000009128088,0.000021601392,0.00005343167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896707,0.0031312462,0.0016314887,0.00036126177,0.004688583,0.0005167065],"domain_scores_gemma":[0.9782064,0.0041848132,0.0048265983,0.00045317604,0.011952314,0.0003766958],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11777359,0.00020017252,0.00033205858,0.0006886445,0.00079448434,0.0005933375,0.00070499,0.00010020795,0.0007003974],"category_scores_gemma":[0.058747627,0.00010583737,0.00020604482,0.0008723181,0.00010815818,0.0031155285,0.000022248769,0.00018671843,0.000048773807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046182624,0.000017396707,0.005813794,0.00001403642,0.000045780136,8.1560336e-7,0.002586119,0.00082785706,0.00028277075,0.0007842796,0.00044717462,0.9891338],"study_design_scores_gemma":[0.004080933,0.0016724253,0.042394914,0.000756664,0.0006563582,0.00008014601,0.027310919,0.89414895,0.00029774092,0.006125252,0.022146452,0.00032925082],"about_ca_topic_score_codex":0.00032122337,"about_ca_topic_score_gemma":0.009110141,"teacher_disagreement_score":0.9888045,"about_ca_system_score_codex":0.0014824657,"about_ca_system_score_gemma":0.0074361037,"threshold_uncertainty_score":0.9981908},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6997656,0.0030396988,0.27100977,0.013617407,0.0004285794,0.0060538407,0.00019000021,0.000029806093,0.0058652824],"genre_scores_gemma":[0.99768335,0.000027964732,0.001669388,0.00010851224,0.00012762667,0.00019823201,0.000017560173,0.000005851378,0.00016151246],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9919843,0.0058515267,0.0007055942,0.00016310875,0.00086900935,0.00042644373],"domain_scores_gemma":[0.9906227,0.0035263968,0.00075047347,0.0001776869,0.0044638678,0.00045887934],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028881242,0.00014733874,0.0003844626,0.0008029547,0.0012886316,0.00042736062,0.0002988754,0.00007726486,0.00044595235],"category_scores_gemma":[0.0051287785,0.00008870089,0.0002373043,0.0013126993,0.0010410916,0.0014665317,0.000013228667,0.00017122377,0.000024465286],"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":[0.00020644716,0.000048490474,0.0019071015,0.00002531487,0.002017868,0.00001686188,0.56197023,0.00015946796,0.00009804887,0.11290704,0.005403287,0.31523982],"study_design_scores_gemma":[0.0028560383,0.0010937505,0.005664362,0.00012208283,0.0030847604,0.0000767066,0.7410065,0.0121620605,0.00021731207,0.0627492,0.17038557,0.0005816825],"about_ca_topic_score_codex":0.0036018824,"about_ca_topic_score_gemma":0.13704029,"teacher_disagreement_score":0.31465814,"about_ca_system_score_codex":0.00050277996,"about_ca_system_score_gemma":0.0018342724,"threshold_uncertainty_score":0.9999711},"labels":[],"label_agreement":null},{"id":"W2560013324","doi":"10.3138/cjpe.339","title":"La production de la théorie du programme dans le cadre d’une évaluation participative : une étude de cas","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Process management; Business","score_opus":0.2661443501415783,"score_gpt":0.4849594687576983,"score_spread":0.21881511861612002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560013324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95953166,0.00009904118,0.016410893,0.019077558,0.00046525925,0.0011531352,0.000005994387,0.000025717862,0.0032307405],"genre_scores_gemma":[0.995279,0.00002699596,0.0037281765,0.000079766156,0.0003691497,0.00028439763,0.000008018103,0.000019911078,0.00020457755],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9928341,0.003313486,0.0009616999,0.00031733868,0.0020514121,0.0005219711],"domain_scores_gemma":[0.99469936,0.00072386063,0.0008521174,0.00032733093,0.0027839208,0.00061342464],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042368006,0.0001807821,0.00026071112,0.00048898713,0.0004045258,0.00041617698,0.00039976748,0.00016537598,0.00040889223],"category_scores_gemma":[0.010366895,0.00012357,0.00014219143,0.001208333,0.00035987466,0.0009754188,0.000015212237,0.00025468346,0.000040905972],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003905803,0.00012767258,0.137877,0.000004960563,0.000046801986,0.000017406142,0.013235081,0.003056702,0.001398433,0.00157955,0.0012727886,0.84134454],"study_design_scores_gemma":[0.0024948695,0.00088657177,0.8424893,0.00017335518,0.0002590237,0.0004205042,0.012264493,0.02425306,0.004261663,0.096190445,0.01597106,0.00033565192],"about_ca_topic_score_codex":0.003278734,"about_ca_topic_score_gemma":0.05796284,"teacher_disagreement_score":0.8410089,"about_ca_system_score_codex":0.0013806053,"about_ca_system_score_gemma":0.01202589,"threshold_uncertainty_score":0.9979692},"labels":[],"label_agreement":null},{"id":"W2560249367","doi":"10.3138/cjpe.31.2.262","title":"Kenneth Bush and Colleen Duggan (eds.). (2015). <i>Evaluation in the Extreme: Research, Impact and Politics in Violently Divided Societies</i> .","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Politics; Political science; Environmental ethics; Psychology; Criminology; Sociology; Law; Philosophy","score_opus":0.48133458098590837,"score_gpt":0.5657556512806122,"score_spread":0.08442107029470386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560249367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9800959,0.0036701285,0.00005146585,0.013566724,0.00018649615,0.0017012823,0.000015114736,0.0000028928348,0.000709996],"genre_scores_gemma":[0.9987014,0.0004472969,0.00028351677,0.00021410109,0.00013608928,0.00010518462,0.0000059176036,0.000009064906,0.00009743636],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910818,0.0033295813,0.0009676086,0.00027533234,0.0038345759,0.0005111413],"domain_scores_gemma":[0.9946375,0.0014593217,0.0004018201,0.00030135902,0.00281748,0.0003825237],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0757867,0.00014056965,0.00024994093,0.0010801313,0.00027631974,0.0005299657,0.00042219413,0.000112720874,0.00065226527],"category_scores_gemma":[0.0069184885,0.000077122866,0.00006490805,0.0011695974,0.00032498685,0.0007828825,0.000028330769,0.00032792374,0.000013560209],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002339624,0.00005345539,0.11350302,0.000004597925,0.00001332319,0.0000051769393,0.003345285,0.00013093643,0.00009469483,0.00018040142,0.013912382,0.86873335],"study_design_scores_gemma":[0.0036586057,0.0009442669,0.8634307,0.0002318935,0.000053860134,0.000058911257,0.00447557,0.023700928,0.000040195926,0.07755379,0.02566306,0.00018822149],"about_ca_topic_score_codex":0.001294187,"about_ca_topic_score_gemma":0.041365746,"teacher_disagreement_score":0.8685451,"about_ca_system_score_codex":0.0008570418,"about_ca_system_score_gemma":0.00583716,"threshold_uncertainty_score":0.99979883},"labels":[],"label_agreement":null},{"id":"W2560370233","doi":"10.3138/cjpe.306","title":"Measuring Evaluation Capacity in Ontario Public Health Units","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Business; Capacity building; Process (computing); Evaluation methods; Knowledge management; Process management; Public health; Program evaluation; Public relations; Nursing; Medicine; Political science; Computer science; Public administration; Engineering","score_opus":0.9060914930214881,"score_gpt":0.5182209136786268,"score_spread":0.3878705793428613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560370233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9806124,0.00023792054,0.0013748645,0.012621835,0.00103512,0.0014308174,0.000004369182,0.000007589852,0.002675085],"genre_scores_gemma":[0.9982151,0.0000064168657,0.0011822461,0.00023464802,0.00009159034,0.00008308589,0.0000067043343,0.000008786118,0.00017142587],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99085605,0.002211713,0.0014925163,0.00027815666,0.004652212,0.00050935464],"domain_scores_gemma":[0.9899289,0.0002872569,0.0010617184,0.00034354388,0.00760336,0.00077524455],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.077727795,0.0001388744,0.000297573,0.0014863774,0.00021464693,0.00036799957,0.00048811946,0.000084007916,0.004825947],"category_scores_gemma":[0.010347604,0.00009199527,0.00008091174,0.0013751683,0.00008610649,0.00149792,0.000012362616,0.00026512716,0.00009180222],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000053747385,0.000028484468,0.20235527,0.0000013765864,0.000010463935,0.000001053058,0.0024405052,0.0003909313,0.000022614267,0.00026843854,0.0006094369,0.79386604],"study_design_scores_gemma":[0.0023968369,0.00046165957,0.90920156,0.00015611225,0.000025575511,0.000033163353,0.0009303371,0.011100992,0.000043314416,0.01139984,0.06407487,0.00017573532],"about_ca_topic_score_codex":0.045580003,"about_ca_topic_score_gemma":0.96183324,"teacher_disagreement_score":0.9162532,"about_ca_system_score_codex":0.0063032643,"about_ca_system_score_gemma":0.051754877,"threshold_uncertainty_score":0.99798864},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2560370905","doi":"10.3138/cjpe.31.2.265","title":"Katherine Eve Hay and Shubh Kumar-Range (eds.). (2014). <i>Making Evaluation Matter: Writings from South Asia</i> .","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hay; Range (aeronautics); South asia; History; Ancient history; Animal science; Engineering; Biology","score_opus":0.20613094438966154,"score_gpt":0.46084156104524177,"score_spread":0.25471061665558026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560370905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725852,0.00311442,0.0029961274,0.013137939,0.0010504998,0.0019025642,0.00005937711,0.000023571081,0.0051302942],"genre_scores_gemma":[0.996488,0.00003863603,0.0021406405,0.00053242594,0.0003948792,0.00010684695,0.000013968732,0.000024013483,0.00026060242],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933762,0.001013759,0.0012697254,0.0004331162,0.0034862459,0.00042094965],"domain_scores_gemma":[0.99376434,0.00048686904,0.0012426764,0.00043552349,0.0035576313,0.00051293283],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02152673,0.00022742181,0.00036464934,0.0006554706,0.00030103567,0.00064943486,0.0004810976,0.0001324924,0.013173599],"category_scores_gemma":[0.002750609,0.00015234674,0.00013949734,0.0004503465,0.00015826705,0.00121136,0.00003150729,0.00019889454,0.0004590436],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027398817,0.000020120355,0.14430743,0.000003368855,0.000035691268,0.000003353031,0.0012149574,0.000062245075,0.00025300914,0.00005604223,0.005486047,0.84853035],"study_design_scores_gemma":[0.006357458,0.0007057474,0.8020369,0.0006239148,0.0005918453,0.00010966459,0.0027383065,0.050395988,0.0002940298,0.02937071,0.10607703,0.0006984224],"about_ca_topic_score_codex":0.0004010148,"about_ca_topic_score_gemma":0.0044858954,"teacher_disagreement_score":0.8478319,"about_ca_system_score_codex":0.00049411407,"about_ca_system_score_gemma":0.002883094,"threshold_uncertainty_score":0.9877285},"labels":[],"label_agreement":null},{"id":"W2560535401","doi":"10.3138/cjpe.276","title":"Canada’s National Alcohol Strategy: It’s Time to Assess Progress","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Centre on Substance Use and Addiction","funders":"","keywords":"Moderation; Harm; Alcohol; Political science; Risk analysis (engineering); Psychology; Business; Public relations; Social psychology","score_opus":0.5170074637952967,"score_gpt":0.5469577318808765,"score_spread":0.029950268085579768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560535401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5049042,0.0004942961,0.0026779324,0.39561102,0.004215536,0.0073386836,0.0003831287,0.00005511354,0.08432007],"genre_scores_gemma":[0.9935736,0.0000015198505,0.0014799314,0.0015321162,0.00030477185,0.000095913834,0.000009563011,0.000012768825,0.0029897878],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923806,0.00051331124,0.0010980604,0.000266021,0.00535149,0.00039050748],"domain_scores_gemma":[0.9898163,0.0003785065,0.00063906185,0.0002522869,0.00795514,0.0009586854],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01528773,0.0001539403,0.0002504027,0.0006628329,0.0002126381,0.0004706822,0.0007078612,0.000072955256,0.0154230315],"category_scores_gemma":[0.0041657398,0.00009709021,0.000091746566,0.0007434394,0.000079490106,0.00078396226,0.000016953913,0.00012591227,0.00061818433],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014049906,0.000024311228,0.0063014547,0.0000014032901,0.000028613686,0.000007985156,0.0000954657,0.0009915716,0.000068682995,0.00034863202,0.28824207,0.7038758],"study_design_scores_gemma":[0.0012867539,0.0005423818,0.13660274,0.000110223955,0.000049875314,0.000065500106,0.00031611885,0.010991308,0.00022109796,0.004319595,0.84521276,0.00028167252],"about_ca_topic_score_codex":0.02584108,"about_ca_topic_score_gemma":0.7997829,"teacher_disagreement_score":0.7739418,"about_ca_system_score_codex":0.001788921,"about_ca_system_score_gemma":0.06714829,"threshold_uncertainty_score":0.98547703},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9673468,0.00029105434,0.015060749,0.010789829,0.00022006598,0.00067596254,0.000017234039,0.000028443905,0.0055699022],"genre_scores_gemma":[0.9928394,0.000067029316,0.00598681,0.000111866706,0.00029456892,0.00006768623,0.000019553594,0.000014126795,0.000598935],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966271,0.0015501202,0.0004353632,0.0001765644,0.0006562175,0.0005546496],"domain_scores_gemma":[0.99792415,0.00014104338,0.00041845956,0.0001772463,0.0006562032,0.00068289804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012520376,0.000112965055,0.00019030634,0.00034485612,0.00057962234,0.000368641,0.00035284393,0.00009016725,0.0002567425],"category_scores_gemma":[0.0025317064,0.000088402456,0.00018867769,0.00038938876,0.00023565118,0.0007897926,0.000011920083,0.00015650567,0.000005682431],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009080249,0.000058058933,0.083216414,0.000008083118,0.00011110988,0.000017879103,0.027462043,0.00015376038,0.0012585185,0.0059845783,0.0019173772,0.8798031],"study_design_scores_gemma":[0.0042221793,0.0010341138,0.40225065,0.0012299903,0.0017160289,0.00013793168,0.10202906,0.008752345,0.004245048,0.10715608,0.3659497,0.0012768942],"about_ca_topic_score_codex":0.037094712,"about_ca_topic_score_gemma":0.65400946,"teacher_disagreement_score":0.8785262,"about_ca_system_score_codex":0.0008684031,"about_ca_system_score_gemma":0.012499098,"threshold_uncertainty_score":0.9930991},"labels":[],"label_agreement":null},{"id":"W2561874864","doi":"10.3138/cjpe.0023.009","title":"A Bumpy Journey to Evaluation Capacity: A Case Study of Evaluation Capacity Building in a Private Foundation","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Foundation (evidence); Officer; Capacity building; Process (computing); Function (biology); Business; Sample (material); Evaluation methods; Public relations; Knowledge management; Engineering; Political science; Computer science","score_opus":0.6621746987407026,"score_gpt":0.5495807547365068,"score_spread":0.11259394400419576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561874864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9886587,0.00009321041,0.0019081263,0.0012367854,0.0007471892,0.0068983044,0.0000046539612,0.000010443494,0.00044253888],"genre_scores_gemma":[0.9933648,0.0000028685017,0.0059666545,0.00017489908,0.0001792805,0.00027659457,0.000010859995,0.00001530462,0.000008733707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9844244,0.0039313426,0.0028009661,0.00053592806,0.0077960375,0.0005112903],"domain_scores_gemma":[0.98513615,0.00033728703,0.00201976,0.0006288432,0.011216745,0.00066123623],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08249955,0.00028530322,0.00059726456,0.0032319082,0.00034594486,0.00057627755,0.0005058338,0.00015100148,0.0012511249],"category_scores_gemma":[0.012535421,0.0002535303,0.00016338324,0.0032376419,0.00006780003,0.0017206399,0.000020457363,0.00039286184,0.000021843789],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006498079,0.0005214632,0.031022979,0.0000062778213,0.000043615953,0.000044396074,0.017936418,0.056328576,0.00056880957,0.00019403276,0.00017033578,0.8930981],"study_design_scores_gemma":[0.007834966,0.005344123,0.26259652,0.00028200247,0.00064947194,0.0010131788,0.018155582,0.67467844,0.00036806043,0.02747486,0.0011267532,0.0004760599],"about_ca_topic_score_codex":0.0043537845,"about_ca_topic_score_gemma":0.12585863,"teacher_disagreement_score":0.89262205,"about_ca_system_score_codex":0.0026127647,"about_ca_system_score_gemma":0.005930187,"threshold_uncertainty_score":0.9999917},"labels":[],"label_agreement":null},{"id":"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15746884,0.009492784,0.6903242,0.13383883,0.004996871,0.0029562365,0.000007784215,0.000031427622,0.00088304334],"genre_scores_gemma":[0.9354327,0.000036526828,0.06378107,0.00009067283,0.00014448141,0.000057677607,0.0000022310621,0.000007295024,0.0004473537],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993021,0.000031381864,0.00020171268,0.000081127946,0.00023358501,0.00015008962],"domain_scores_gemma":[0.9987388,0.000032738582,0.00008156568,0.00008524418,0.0008528003,0.0002088211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019658043,0.000049033635,0.000080761674,0.0001816384,0.000030721287,0.000077911405,0.00015281889,0.000026074915,0.000026676611],"category_scores_gemma":[0.0006956412,0.000037799615,0.00002570335,0.00012554463,0.000015143048,0.00027892337,0.00000470714,0.000036452868,0.00000539351],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012652681,0.0000120679615,0.0080540925,0.000020217025,0.000010598741,0.0000030415158,0.000297577,0.000320085,0.00005476678,0.0044211606,0.01731585,0.9694893],"study_design_scores_gemma":[0.0018497347,0.00048028457,0.3581625,0.00057165395,0.00005517145,0.00008864632,0.00008668033,0.15042233,0.00004357927,0.018281838,0.46961507,0.00034251253],"about_ca_topic_score_codex":0.000098954355,"about_ca_topic_score_gemma":0.00078565616,"teacher_disagreement_score":0.9691468,"about_ca_system_score_codex":0.00019593701,"about_ca_system_score_gemma":0.0007390308,"threshold_uncertainty_score":0.15414235},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9099111,0.01119096,0.000117343836,0.045927145,0.0010897826,0.004337028,0.0000044651597,0.000080831276,0.02734135],"genre_scores_gemma":[0.9985087,0.0001207182,0.00061577675,0.0001954805,0.00019240094,0.0001700618,0.000005341156,0.0000048106954,0.00018670339],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986962,0.0003481747,0.0002951817,0.00007730662,0.0003277786,0.0002553262],"domain_scores_gemma":[0.9990699,0.000042582084,0.0002086253,0.000112652655,0.00036146087,0.00020476928],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003332727,0.000059138783,0.00009506729,0.00023363774,0.00030938504,0.00015124865,0.00021378756,0.00008485762,0.0013343985],"category_scores_gemma":[0.0031028215,0.00004438234,0.000058742113,0.00070636556,0.000103445076,0.00023035984,0.000002728128,0.00029300028,0.000039183444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.88805e-7,0.00007875041,0.025323054,0.0000036251129,0.000007974644,0.0000069937114,0.011889866,0.0000026458617,0.000003871331,0.0033589394,0.0038771715,0.9554464],"study_design_scores_gemma":[0.0007837903,0.00026490114,0.056624316,0.000269584,0.00010540796,0.000023336714,0.05352081,0.0032627776,0.000026805688,0.0016913743,0.883221,0.00020592504],"about_ca_topic_score_codex":0.003291167,"about_ca_topic_score_gemma":0.22672334,"teacher_disagreement_score":0.9552405,"about_ca_system_score_codex":0.0004988497,"about_ca_system_score_gemma":0.0009575661,"threshold_uncertainty_score":0.99957854},"labels":[],"label_agreement":null},{"id":"W2591620871","doi":"10.3138/cjpe.0026.008","title":"Discussion: Practice-Based Evaluation as a Response to Adress Intervention Complexity","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal; Université du Québec à Montréal; McGill University; École Nationale d'Administration Publique","funders":"","keywords":"Intervention (counseling); Context (archaeology); Psychological intervention; Reading (process); Field (mathematics); Psychology; Management science; Computer science; Knowledge management; Political science; Engineering; History; Mathematics","score_opus":0.5295924933400027,"score_gpt":0.6233783243564389,"score_spread":0.09378583101643623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591620871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92752945,0.0006886818,0.009906607,0.04954772,0.0036148771,0.0043626395,0.000017761025,0.000024622448,0.0043076267],"genre_scores_gemma":[0.9896529,0.0000010950235,0.008610821,0.00092859013,0.00033986478,0.00023497407,0.000029713792,0.000014458063,0.00018762695],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98636687,0.00596091,0.001374991,0.00026019546,0.005572952,0.0004640821],"domain_scores_gemma":[0.9883575,0.00078523654,0.0012399629,0.0004842369,0.00793279,0.0012002806],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10586144,0.00017739073,0.00027733698,0.001226073,0.00035332385,0.000587415,0.0005304305,0.000104477695,0.008595042],"category_scores_gemma":[0.039588194,0.000116423485,0.00022428267,0.0012894633,0.00009964091,0.0021172776,0.000024234863,0.0002680081,0.00056722463],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078265363,0.00027542023,0.010059043,0.0000047012236,0.000033134984,0.0000029640225,0.0030417994,0.004060116,0.00010911019,0.0003531621,0.0047143754,0.9765635],"study_design_scores_gemma":[0.004782185,0.0030207592,0.41693148,0.0002870315,0.0005278156,0.00014268707,0.010173282,0.1267363,0.00050292205,0.008757734,0.42768154,0.00045628575],"about_ca_topic_score_codex":0.0005553988,"about_ca_topic_score_gemma":0.0052941465,"teacher_disagreement_score":0.97610724,"about_ca_system_score_codex":0.0013299799,"about_ca_system_score_gemma":0.006673217,"threshold_uncertainty_score":0.99895805},"labels":[],"label_agreement":null},{"id":"W2606229491","doi":"10.3138/cjpe.325","title":"Influential Mentoring Practices for Navigating Challenges and Optimizing Learning During an Evaluation Internship Experience","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Internship; Autonomy; Psychology; Context (archaeology); Medical education; Quality (philosophy); Professional development; Best practice; Pedagogy; Knowledge management; Applied psychology; Computer science; Medicine; Management; Political science","score_opus":0.6665644262235942,"score_gpt":0.6224087149164251,"score_spread":0.04415571130716911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606229491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99434316,0.0013646676,0.0003939591,0.0010037058,0.0009904205,0.0010810383,0.000001005596,0.000009144966,0.0008128818],"genre_scores_gemma":[0.9918654,0.00008594349,0.0073755,0.00001401586,0.00039796514,0.00019905786,0.0000047229214,0.00001290075,0.00004449122],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567574,0.0008516183,0.00080587715,0.00032680389,0.0020300294,0.00030994628],"domain_scores_gemma":[0.99246997,0.00033161527,0.0032664263,0.00035661907,0.0031665384,0.0004088156],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032381743,0.00013853285,0.00022076617,0.00027309256,0.0016424285,0.0021055865,0.00058262347,0.00007845411,0.00016869527],"category_scores_gemma":[0.024010178,0.00012172403,0.00007256873,0.000085164356,0.00010661362,0.0042371955,0.000038288304,0.0003476616,0.000002947896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003441652,0.000015863057,0.018203216,0.000013584399,0.000020991334,0.0000016857035,0.022805987,0.0035088032,0.00054827036,0.00008213355,0.0000027029687,0.95476234],"study_design_scores_gemma":[0.003819191,0.0012630994,0.2635199,0.00057202537,0.00027430477,0.00011852478,0.0770184,0.64273137,0.0020711282,0.0035674665,0.0046303365,0.00041424824],"about_ca_topic_score_codex":0.00041897138,"about_ca_topic_score_gemma":0.007719832,"teacher_disagreement_score":0.9543481,"about_ca_system_score_codex":0.00032561907,"about_ca_system_score_gemma":0.0013688362,"threshold_uncertainty_score":0.9996573},"labels":[],"label_agreement":null},{"id":"W2606650297","doi":"10.3138/cjpe.386","title":"In Tribute to Lyn Shulha: The Authentic Evaluator","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"LYN; Honour; Tribute; Scholarship; Kindness; Fidelity; Sociology; Field (mathematics); Psychology; Environmental ethics; Psychoanalysis; History; Political science; Computer science; Art history; Law; Philosophy; Medicine; Telecommunications","score_opus":0.43053183270283146,"score_gpt":0.5840601491356326,"score_spread":0.15352831643280118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606650297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8880172,0.00029857823,0.00062777847,0.101630285,0.003162472,0.0022990743,0.000009884513,0.000005132878,0.003949609],"genre_scores_gemma":[0.99697995,0.0000042265074,0.000816835,0.0006739964,0.00028170898,0.00010550046,0.0000018754521,0.000008099705,0.0011278337],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950305,0.0006786468,0.000982164,0.0002115927,0.0027510638,0.0003459827],"domain_scores_gemma":[0.9951383,0.00025400368,0.0008959509,0.00080236356,0.0024060553,0.00050331035],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037783016,0.000118605174,0.00024225126,0.00062361686,0.0006730651,0.0013911182,0.0015228671,0.000064856365,0.00275782],"category_scores_gemma":[0.0124409925,0.000073435396,0.00012829315,0.00047616535,0.00011877461,0.0009777821,0.0000350872,0.00024380561,0.00036650503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029468132,0.00004252007,0.05750627,0.0000022414536,0.000023030056,0.000014303844,0.0028893396,0.0019498012,0.000033516906,0.00072230946,0.030751582,0.9060356],"study_design_scores_gemma":[0.001592516,0.0004995288,0.61413723,0.00007168888,0.000087179265,0.000038711,0.0012233796,0.05430193,0.00008404856,0.028888682,0.29889563,0.00017949706],"about_ca_topic_score_codex":0.0011081678,"about_ca_topic_score_gemma":0.080567405,"teacher_disagreement_score":0.90585613,"about_ca_system_score_codex":0.00049372436,"about_ca_system_score_gemma":0.0053571686,"threshold_uncertainty_score":0.99964553},"labels":[],"label_agreement":null},{"id":"W2606670574","doi":"10.3138/cjpe.327","title":"The Oral History of Evaluation: An Interview with Lyn Shulha","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Formative assessment; Scholarship; LYN; Oral history; Psychology; Evaluation methods; Pedagogy; Medical education; Sociology; Political science; Medicine; Engineering; Anthropology","score_opus":0.6363883769916328,"score_gpt":0.5707644898010387,"score_spread":0.06562388719059409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606670574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9124907,0.009886858,0.00188707,0.021329576,0.007674767,0.0047476334,0.000012927525,0.000017725022,0.041952696],"genre_scores_gemma":[0.9974117,0.000026017007,0.0014923536,0.00014600401,0.00015600654,0.00007139397,0.000005821499,0.000009677075,0.0006809911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99360275,0.0013528846,0.0009702855,0.00019283062,0.0036468394,0.00023441474],"domain_scores_gemma":[0.9887887,0.00019072289,0.002088967,0.00093274977,0.007617545,0.00038130677],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05068516,0.00012273388,0.00025820546,0.00029442846,0.00055154104,0.00060013385,0.0011255959,0.000059345937,0.0024421879],"category_scores_gemma":[0.0038677317,0.00007018106,0.00011391179,0.00017729156,0.00042448915,0.0013618275,0.00001985237,0.00019202488,0.000027105372],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026638074,0.000029819485,0.010471033,0.000003279059,0.000032426895,0.000002256766,0.0011125536,0.00051329704,0.000008453749,0.0003907528,0.0058956407,0.98151386],"study_design_scores_gemma":[0.0021894048,0.0020746053,0.33506614,0.00015918573,0.00034359907,0.00007701368,0.0022348731,0.14517955,0.000043798223,0.009075994,0.5033405,0.00021533752],"about_ca_topic_score_codex":0.0006598737,"about_ca_topic_score_gemma":0.08782984,"teacher_disagreement_score":0.9812985,"about_ca_system_score_codex":0.0010599493,"about_ca_system_score_gemma":0.015386948,"threshold_uncertainty_score":0.9984697},"labels":[],"label_agreement":null},{"id":"W2606709931","doi":"10.3138/cjpe.349","title":"Developing the Program Evaluation Utility Standards: Scholarly Foundations and Collaborative Processes","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Task (project management); Task force; Political science; Engineering ethics; Program evaluation; Management science; Computer science; Process management; Knowledge management; Business; Public administration; Engineering; Management; Economics","score_opus":0.5392904759997819,"score_gpt":0.6027993397034421,"score_spread":0.06350886370366027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606709931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9153224,0.0040860237,0.006791781,0.042861804,0.0022846959,0.014553843,0.000114349736,0.00004252547,0.013942541],"genre_scores_gemma":[0.9899726,0.00006481805,0.008893352,0.0001399143,0.00018114183,0.0006607158,0.000018652874,0.000010310987,0.000058501555],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99230385,0.0011370424,0.0010200862,0.00032002514,0.0049047032,0.0003142668],"domain_scores_gemma":[0.9630292,0.00043310915,0.0016912267,0.00061475264,0.03388711,0.00034459212],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051086746,0.00017383324,0.00026492466,0.00039631085,0.0028436428,0.008061376,0.0009255117,0.000098292905,0.0008040296],"category_scores_gemma":[0.051395074,0.00011301118,0.00006821852,0.0008337854,0.00047473825,0.0044970587,0.000043351978,0.0003216254,0.000015962087],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019892565,0.000028963597,0.03116664,0.0000100302705,0.000040788436,0.0000010310246,0.0020993366,0.00011738134,0.0000031406325,0.00080568535,0.00095814327,0.964749],"study_design_scores_gemma":[0.0019031978,0.0006878989,0.54367244,0.00018116776,0.0003069609,0.0000365892,0.007164702,0.060432673,0.00009799578,0.052078888,0.33315745,0.0002800353],"about_ca_topic_score_codex":0.00035162765,"about_ca_topic_score_gemma":0.06403078,"teacher_disagreement_score":0.96446896,"about_ca_system_score_codex":0.00081284577,"about_ca_system_score_gemma":0.04390121,"threshold_uncertainty_score":0.9984545},"labels":[],"label_agreement":null},{"id":"W2607080017","doi":"10.3138/cjpe.387","title":"Introduction — Setting the Evaluation Use Context","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Business; History; Archaeology","score_opus":0.542769667312793,"score_gpt":0.5681665235554011,"score_spread":0.025396856242608123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607080017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8910594,0.0005604245,0.0012239626,0.09429299,0.006397847,0.0030210153,0.000008851775,0.000012834583,0.0034226722],"genre_scores_gemma":[0.9968839,0.00000769302,0.00094092474,0.00028770557,0.0014009231,0.00008397217,0.00001196608,0.000009361688,0.00037354731],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935149,0.0012531105,0.00097560557,0.00024358348,0.0037402653,0.00027256226],"domain_scores_gemma":[0.9882254,0.00033787417,0.001989384,0.000919414,0.008238472,0.00028943518],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05391779,0.00012577699,0.00019542748,0.00038063477,0.0016205147,0.003203803,0.00095190655,0.00007699969,0.0037490628],"category_scores_gemma":[0.0321604,0.000079201156,0.00014331014,0.0002671174,0.00027159232,0.0025705604,0.00002383344,0.00028715175,0.00015486713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001153426,0.00001363011,0.02201718,9.952984e-7,0.000023091543,0.0000010281663,0.00089745206,0.001912788,0.000028719582,0.00066004734,0.021439632,0.9529939],"study_design_scores_gemma":[0.0010934927,0.00024307618,0.5010826,0.0000318801,0.00020464777,0.000058237267,0.0023253844,0.18530788,0.00012895842,0.011581786,0.29780045,0.00014158688],"about_ca_topic_score_codex":0.0011129524,"about_ca_topic_score_gemma":0.03803256,"teacher_disagreement_score":0.9528523,"about_ca_system_score_codex":0.00053425005,"about_ca_system_score_gemma":0.0052626547,"threshold_uncertainty_score":0.99967927},"labels":[],"label_agreement":null},{"id":"W2607086309","doi":"10.3138/cjpe.335","title":"Reflections on the Meaning of Success in Collaborative Approaches to Evaluation: Results of an Empirical Study","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University; University of Ottawa; Carleton University","funders":"","keywords":"Meaning (existential); Set (abstract data type); Knowledge management; Core (optical fiber); Work (physics); Key (lock); Empirical research; Computer science; Conceptual framework; Psychology; Management science; Sociology; Epistemology; Engineering; Social science","score_opus":0.8398111028940528,"score_gpt":0.6344216308633112,"score_spread":0.20538947203074165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607086309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9773812,0.000027974209,0.000056611647,0.0065585165,0.00035963082,0.0026239478,0.000015439202,0.0000019797812,0.012974655],"genre_scores_gemma":[0.9982124,9.757964e-7,0.0014478213,0.000060466147,0.00008625419,0.00015271985,0.000004782412,0.0000062609365,0.0000283131],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99232435,0.0024458047,0.001369318,0.00025660754,0.0034191,0.00018484396],"domain_scores_gemma":[0.9918034,0.00054510584,0.00170024,0.0007544132,0.004947922,0.0002489194],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05158375,0.00011417402,0.00030823826,0.000827331,0.0004642102,0.00038455616,0.0009323044,0.000060032333,0.0002563511],"category_scores_gemma":[0.016011167,0.00007407186,0.00006748334,0.0011600712,0.0001422118,0.0007162368,0.000024405219,0.00021986732,0.0000065897466],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005548032,0.0009277689,0.17923789,0.0000053270564,0.00009828814,0.0000048829934,0.06965634,0.07971044,0.00007164557,0.0016190414,0.0010325597,0.667081],"study_design_scores_gemma":[0.0028276793,0.004373182,0.85937923,0.00010011043,0.00011958592,0.0000045935517,0.041031368,0.08270429,0.0005165667,0.0077411165,0.0010665316,0.00013571503],"about_ca_topic_score_codex":0.0010889642,"about_ca_topic_score_gemma":0.1882366,"teacher_disagreement_score":0.6801414,"about_ca_system_score_codex":0.00037213968,"about_ca_system_score_gemma":0.0058228215,"threshold_uncertainty_score":0.99981326},"labels":[],"label_agreement":null},{"id":"W2607364656","doi":"10.3138/cjpe.366","title":"Optimizing Use in the Field of Program Evaluation by Integrating Learning from the Knowledge Field","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University; Queen's University","funders":"","keywords":"Terminology; Field (mathematics); Knowledge translation; Body of knowledge; Health care; Engineering ethics; Psychology; Management science; Sociology; Knowledge management; Political science; Computer science; Engineering","score_opus":0.45805747849381845,"score_gpt":0.5653991971273034,"score_spread":0.1073417186334849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607364656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97405136,0.0015096564,0.001942047,0.013813051,0.0009744423,0.0033799775,0.0000057017173,0.000008804912,0.004314944],"genre_scores_gemma":[0.9960682,0.000021116946,0.0031306914,0.00032080914,0.00017704467,0.00020445675,0.000016898279,0.000007661043,0.000053115516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944365,0.001912694,0.0010488128,0.000213799,0.0021303317,0.00025787088],"domain_scores_gemma":[0.9916392,0.0035820121,0.0015261513,0.00059035607,0.0025293422,0.00013296741],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031399667,0.00013604583,0.00024133964,0.00023728298,0.00071852346,0.0015836356,0.0012687773,0.000111456815,0.0007946345],"category_scores_gemma":[0.03783556,0.0000770194,0.00013857176,0.00038589488,0.000105235515,0.0011186983,0.00003298311,0.0006096907,0.0000112324715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015972222,0.0000491308,0.07677548,0.0000019030516,0.00001845429,9.84005e-7,0.005818509,0.0013600666,0.00003966841,0.00008788368,0.0051574986,0.91067445],"study_design_scores_gemma":[0.0018616763,0.001623004,0.18045038,0.00040000322,0.00023839428,0.000009894348,0.015933596,0.7172247,0.00046389952,0.004109736,0.07744071,0.0002439893],"about_ca_topic_score_codex":0.0050949897,"about_ca_topic_score_gemma":0.115409,"teacher_disagreement_score":0.9104305,"about_ca_system_score_codex":0.00018978871,"about_ca_system_score_gemma":0.0023636092,"threshold_uncertainty_score":0.9994528},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26686925,0.00016839053,0.71183276,0.002117949,0.00022395902,0.004496273,0.0000015617634,0.00021685808,0.014072976],"genre_scores_gemma":[0.5259823,6.6250095e-7,0.4736697,0.00008503246,0.00015766684,0.00002144471,0.0000019754798,0.0000112662665,0.00006991254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857527,0.00014144016,0.00045421388,0.00013607349,0.00041497612,0.00027803276],"domain_scores_gemma":[0.998089,0.000064215084,0.00037241052,0.00011871015,0.0008626112,0.00049302436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002432738,0.00012039761,0.00018898965,0.00042703544,0.00011500697,0.00013266821,0.00015399713,0.00008096838,0.00005146261],"category_scores_gemma":[0.003924836,0.00011504136,0.00006313545,0.0005149436,0.00001506762,0.0003301929,0.0000035042772,0.00023088304,0.000004511462],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009009568,0.000051991425,0.00013685621,0.000011446013,0.000011997054,0.0000021330688,0.0013225864,0.0003566021,0.0008058513,0.0067985253,0.0034901705,0.98700285],"study_design_scores_gemma":[0.0011553556,0.0029469137,0.004345908,0.0006695044,0.00035158175,0.0004962102,0.0008937954,0.033354,0.010259695,0.9380491,0.006851304,0.0006266586],"about_ca_topic_score_codex":0.00022765363,"about_ca_topic_score_gemma":0.0012893153,"teacher_disagreement_score":0.98637617,"about_ca_system_score_codex":0.0006920162,"about_ca_system_score_gemma":0.001741407,"threshold_uncertainty_score":0.46986786},"labels":[],"label_agreement":null},{"id":"W2612736585","doi":"10.3138/cjpe.0023.010","title":"Using Evaluation Capacity Building (ECB) to Interpret Evaluation Strategy and Practice in the United States National Tobacco Control Program (NTCP): A Preliminary Study","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tobacco control; Control (management); Disease control; State (computer science); Tobacco use; Business; Program evaluation; Environmental health; Computer science; Medicine; Political science; Public administration; Public health; Nursing","score_opus":0.5351127052858893,"score_gpt":0.5825620174973914,"score_spread":0.04744931221150217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612736585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818653,0.00038441864,0.0015152005,0.0050140573,0.00032138775,0.009986403,0.000012714637,0.000013336899,0.00088719715],"genre_scores_gemma":[0.9922042,0.000006439852,0.0059205596,0.0011539186,0.0001648924,0.0004921638,0.00004297733,0.000011531703,0.0000033473034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98156536,0.007994354,0.0016957455,0.0004812572,0.007811853,0.00045144217],"domain_scores_gemma":[0.9841402,0.001749449,0.0009584496,0.0003445034,0.012429593,0.0003777744],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1077162,0.00025650449,0.00035092482,0.0018640122,0.00040924162,0.0013682245,0.00058945187,0.00011377118,0.00025676782],"category_scores_gemma":[0.029880203,0.00019060835,0.000089149886,0.0024907386,0.0000894835,0.0018999254,0.000016989234,0.00044038348,0.000007711529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023236145,0.000511258,0.010192063,0.000002243069,0.000051005314,0.0000053230633,0.01416997,0.21551448,0.00004956286,0.0001869866,0.00036496113,0.7587198],"study_design_scores_gemma":[0.00294467,0.004626964,0.2102683,0.00008854987,0.00042317357,0.00011803628,0.021064766,0.7491639,0.000006989595,0.009413617,0.0016757438,0.00020526575],"about_ca_topic_score_codex":0.0015659845,"about_ca_topic_score_gemma":0.010001388,"teacher_disagreement_score":0.7585145,"about_ca_system_score_codex":0.0013522357,"about_ca_system_score_gemma":0.0060971477,"threshold_uncertainty_score":0.9996685},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933901,0.0013866931,0.00000447486,0.0012451399,0.00025697277,0.00055149134,4.7681175e-7,0.0000071645186,0.003157516],"genre_scores_gemma":[0.9988348,0.00018969741,0.00045435695,0.00004657192,0.0003804276,0.000029620429,0.0000015874315,0.0000035979467,0.000059341895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988412,0.00021643015,0.00023348414,0.000078089004,0.00038781465,0.0002429772],"domain_scores_gemma":[0.9990737,0.000037567253,0.00010909783,0.00006094331,0.0004517984,0.00026689295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004231988,0.000053856216,0.00009858298,0.00016920817,0.00021298074,0.00020105654,0.0001147444,0.000066049775,0.00014541653],"category_scores_gemma":[0.0004785431,0.000051451683,0.000028170656,0.0003338945,0.0001973849,0.00063330773,0.0000028857175,0.00014683175,0.0000030424196],"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":[0.000004804463,0.000010019318,0.5173696,0.0000033619278,0.000002533476,0.00000273449,0.0057141767,0.0000052370337,9.269864e-7,0.000079179896,0.00005673636,0.47675067],"study_design_scores_gemma":[0.00060502614,0.0002525462,0.85237116,0.000108593566,0.000034266963,0.000020903413,0.012325136,0.00045339952,0.0000050702192,0.007677942,0.12601334,0.00013259986],"about_ca_topic_score_codex":0.032271516,"about_ca_topic_score_gemma":0.6520197,"teacher_disagreement_score":0.6197482,"about_ca_system_score_codex":0.00033071171,"about_ca_system_score_gemma":0.0022746911,"threshold_uncertainty_score":0.97417265},"labels":[],"label_agreement":null},{"id":"W261564656","doi":"10.3138/cjpe.23.008","title":"Moments of Truth: An Unexplored Dimension to Communicate Effectiveness","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Dimension (graph theory); Psychology; Mathematics; Computer science; Epistemology; Philosophy; Combinatorics","score_opus":0.6291875856848531,"score_gpt":0.5714788075621933,"score_spread":0.05770877812265984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W261564656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969319,0.00013502546,0.0005616374,0.00045170786,0.00059482385,0.00087215716,0.000008393598,0.0000055717605,0.0004387783],"genre_scores_gemma":[0.99678594,0.000011248179,0.002989018,0.00007481333,0.00004567781,0.000047186357,0.000017604032,0.000009277824,0.000019250134],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951123,0.0014562093,0.0009174533,0.00017203281,0.0021243284,0.000217704],"domain_scores_gemma":[0.9946983,0.00042152134,0.0006279519,0.000497424,0.0031541656,0.0006006549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014725799,0.00011066334,0.0003080802,0.00080852193,0.00024124622,0.000083638406,0.00063058734,0.000059234215,0.00043027633],"category_scores_gemma":[0.002363577,0.00008612325,0.00010323708,0.0009427145,0.00010727634,0.00070247817,0.000022989057,0.00014367653,0.000043947522],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024053075,0.00032037523,0.12953782,0.000012377579,0.00007552934,0.00001562613,0.007924815,0.01826162,0.0021265692,0.0005440908,0.0011546985,0.83978593],"study_design_scores_gemma":[0.002380152,0.0030950685,0.9360617,0.00015208252,0.000083987194,0.00007565042,0.0016786115,0.038870595,0.003587464,0.005433769,0.008351843,0.00022907942],"about_ca_topic_score_codex":0.0005378532,"about_ca_topic_score_gemma":0.0032763863,"teacher_disagreement_score":0.8395569,"about_ca_system_score_codex":0.0003034692,"about_ca_system_score_gemma":0.002510855,"threshold_uncertainty_score":0.5103697},"labels":[],"label_agreement":null},{"id":"W2616845762","doi":"10.3138/cjpe.328","title":"A Case Study of the Guiding Principles for Collaborative Approaches to Evaluation in a Developmental Evaluation Context","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Context (archaeology); Set (abstract data type); Reflection (computer programming); Engineering ethics; Sociology; Psychology; Knowledge management; Management science; Computer science; Engineering","score_opus":0.9106579329392426,"score_gpt":0.5628987801781327,"score_spread":0.3477591527611099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616845762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98442066,0.00012051433,0.00023358618,0.0014125762,0.0006805535,0.012077159,0.000012598627,0.000002218585,0.0010401321],"genre_scores_gemma":[0.99528795,7.1408266e-7,0.0030441347,0.000046588633,0.00008135614,0.0014899422,0.000005189169,0.000010834903,0.000033263954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920684,0.0018031584,0.0016006816,0.00032885684,0.003932361,0.00026653492],"domain_scores_gemma":[0.98879313,0.00037740733,0.0020797548,0.0005437232,0.007962837,0.00024315504],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.064809516,0.000163367,0.00034562,0.00073820323,0.00086905586,0.0006243639,0.0008291595,0.00007674073,0.00023190225],"category_scores_gemma":[0.021869153,0.00011448229,0.000102367085,0.0007839989,0.000097840944,0.00086140016,0.000053429198,0.00011883363,0.000004689034],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006512539,0.00020470709,0.12024122,0.0000059622143,0.000057240646,0.0000069408584,0.03357006,0.02023438,0.000033513228,0.00021929716,0.00022471698,0.82513684],"study_design_scores_gemma":[0.007303105,0.0014681276,0.29415387,0.00016177403,0.00039006304,0.00019132238,0.20697147,0.48342752,0.00036446797,0.0030249713,0.0022904216,0.00025288848],"about_ca_topic_score_codex":0.0019691044,"about_ca_topic_score_gemma":0.3927177,"teacher_disagreement_score":0.82488394,"about_ca_system_score_codex":0.0016204901,"about_ca_system_score_gemma":0.015704846,"threshold_uncertainty_score":0.9898752},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W262717460","doi":"10.3138/cjpe.018.010","title":"Reflections on the CES Case Competition: The Coaches’ Perspective","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Competition (biology); Enthusiasm; Perspective (graphical); Order (exchange); Curriculum; Psychology; Public relations; Mathematics education; Sociology; Pedagogy; Political science; Business; Computer science; Social psychology","score_opus":0.6127644386593305,"score_gpt":0.5922524016754245,"score_spread":0.020512036983906023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W262717460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5286001,0.0012151854,0.0024878094,0.11729461,0.0036896556,0.0037414415,0.00002180182,0.000024675644,0.34292474],"genre_scores_gemma":[0.9981166,0.0000068538448,0.00046956426,0.0008984897,0.00016843466,0.00007974619,0.0000012882274,0.0000058509463,0.00025316357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99574274,0.0017834615,0.00052154245,0.0001523529,0.0016029959,0.0001969161],"domain_scores_gemma":[0.9947631,0.00094383705,0.00046202887,0.00034382482,0.0032708314,0.00021639274],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018129919,0.000098916986,0.00012425489,0.00029797002,0.0011085868,0.0005587806,0.00034286687,0.00004429487,0.0037123358],"category_scores_gemma":[0.005531213,0.00004856716,0.00012725536,0.0009366641,0.00019607444,0.00028528922,0.0000046469327,0.0003261657,0.00013033174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002536927,0.00014285932,0.0034388138,0.0000018009523,0.00011810572,0.00010629598,0.015407433,0.008014999,0.000022311211,0.8113175,0.015307902,0.1460966],"study_design_scores_gemma":[0.0012203086,0.0015377138,0.0113380235,0.00006083179,0.00025286662,0.0046635484,0.25771245,0.016219238,0.00024826944,0.22175501,0.48469296,0.00029877934],"about_ca_topic_score_codex":0.00057869335,"about_ca_topic_score_gemma":0.045840163,"teacher_disagreement_score":0.5895625,"about_ca_system_score_codex":0.0005355977,"about_ca_system_score_gemma":0.0034574666,"threshold_uncertainty_score":0.9971984},"labels":[],"label_agreement":null},{"id":"W263836974","doi":"10.3138/cjpe.0014.003","title":"A Framework for Characterizing the Practice of Evaluation, with Application to Empowerment Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empowerment; Sanctions; Diversity (politics); Context (archaeology); Management science; Engineering ethics; Epistemology; Sociology; Psychology; Knowledge management; Computer science; Political science; Engineering; Law","score_opus":0.21391735746675264,"score_gpt":0.545183003893987,"score_spread":0.33126564642723433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W263836974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8251722,0.0009274751,0.09099039,0.0509442,0.0011207025,0.024979768,0.00004322712,0.00002062019,0.0058014216],"genre_scores_gemma":[0.965483,0.000011194619,0.031179613,0.0010516983,0.00027215455,0.001892018,0.000041281204,0.000017608772,0.000051398376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99084795,0.0013885824,0.0013917647,0.0003367239,0.005720144,0.00031483482],"domain_scores_gemma":[0.9810356,0.0011683265,0.0015007104,0.00061429146,0.015334818,0.00034627545],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058795504,0.00017171436,0.0002899406,0.00049632153,0.0003751426,0.00037190024,0.0005322826,0.00009806873,0.0031448484],"category_scores_gemma":[0.010573389,0.00011062345,0.00012658806,0.0013744435,0.000091249225,0.00093182706,0.000008573213,0.00020663966,0.00006094207],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019894581,0.00008204333,0.0011490446,0.000005275692,0.000059160866,2.6363762e-7,0.0036567694,0.019545028,0.00010831574,0.00091129617,0.0009336216,0.9733502],"study_design_scores_gemma":[0.0035280813,0.0033573993,0.082911536,0.00030296436,0.0015548486,0.000098027296,0.006785382,0.48069587,0.0007722619,0.042713832,0.3768523,0.00042749586],"about_ca_topic_score_codex":0.00021291888,"about_ca_topic_score_gemma":0.0023405068,"teacher_disagreement_score":0.97292274,"about_ca_system_score_codex":0.00070641766,"about_ca_system_score_gemma":0.0070281876,"threshold_uncertainty_score":0.998601},"labels":[],"label_agreement":null},{"id":"W268578929","doi":"10.3138/cjpe.018.012","title":"The CES Case Competition: A Valuable Resource for Community-Based Agencies","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Competition (biology); Resource (disambiguation); Public relations; Limited resources; Marketing; Business; Political science; Computer science","score_opus":0.5127025743481258,"score_gpt":0.5276762218078191,"score_spread":0.014973647459693318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W268578929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91354156,0.0029485498,0.023121523,0.016334567,0.0030101037,0.0066307615,0.00006996794,0.000040767576,0.03430223],"genre_scores_gemma":[0.993355,0.0000037115863,0.005424759,0.0005541494,0.00009342108,0.00017579123,0.000015286607,0.0000096868325,0.00036823688],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994419,0.002795329,0.00083482446,0.00011870395,0.0015316027,0.00030058768],"domain_scores_gemma":[0.9925592,0.0023485683,0.0006627161,0.00043221904,0.0036600397,0.0003372484],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.050125197,0.00011235072,0.0001817791,0.0003319853,0.0022589585,0.0008372051,0.00048987614,0.00005955789,0.0006915499],"category_scores_gemma":[0.0071553066,0.00007281335,0.00016324244,0.00063456985,0.00019794136,0.00032741588,0.000006216202,0.00027979558,0.000021906933],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098794735,0.00017314966,0.0064299973,0.000034715504,0.00010980764,0.0000685287,0.0069178985,0.041680392,0.00005321389,0.028084928,0.047683828,0.86866474],"study_design_scores_gemma":[0.0012181201,0.00075138157,0.0007816802,0.000035292407,0.00009030308,0.00040226796,0.01590375,0.04990901,0.00020145981,0.023820799,0.90675944,0.00012651214],"about_ca_topic_score_codex":0.00035356433,"about_ca_topic_score_gemma":0.040430177,"teacher_disagreement_score":0.86853826,"about_ca_system_score_codex":0.00038575497,"about_ca_system_score_gemma":0.0065175095,"threshold_uncertainty_score":0.99911463},"labels":[],"label_agreement":null},{"id":"W268891095","doi":"10.3138/cjpe.0015.009","title":"A Performance Measurement and Evaluation Framework for Continuing Education","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Continuing education; Performance measurement; Data collection; Evaluation methods; Computer science; Process management; Business; Medical education; Engineering; Statistics; Reliability engineering; Mathematics; Medicine; Marketing","score_opus":0.44393524640381515,"score_gpt":0.5410512913199274,"score_spread":0.0971160449161122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W268891095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803695,0.0018298466,0.009521586,0.0023344774,0.0014949843,0.0027592771,0.0000022229399,0.000007981344,0.0016800998],"genre_scores_gemma":[0.9827579,0.000057079655,0.016188208,0.00016942718,0.00036618678,0.00038196967,0.000008888714,0.00001049157,0.000059844046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99482846,0.00043623138,0.0009123235,0.00023409846,0.003322633,0.0002662792],"domain_scores_gemma":[0.9872529,0.0002450633,0.00081334595,0.00024467774,0.01106791,0.00037613354],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03751922,0.00012849465,0.00021743268,0.00063726894,0.00026263102,0.0004617994,0.00026671038,0.00009497721,0.00066309166],"category_scores_gemma":[0.008429529,0.00010576938,0.000088686014,0.0005812864,0.00006285819,0.0008269981,0.000007421845,0.00015645428,0.00001412521],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002704436,0.00003353739,0.037130494,0.000006142117,0.000013739291,1.655958e-7,0.0009971255,0.0007442045,0.000028425064,0.00053812837,0.00075333926,0.95972764],"study_design_scores_gemma":[0.002131611,0.0011757503,0.3358462,0.0005142589,0.00038750554,0.00009914981,0.004850159,0.49216226,0.00012663726,0.06531086,0.09708182,0.0003137914],"about_ca_topic_score_codex":0.0000808625,"about_ca_topic_score_gemma":0.0027450162,"teacher_disagreement_score":0.9594139,"about_ca_system_score_codex":0.00068691495,"about_ca_system_score_gemma":0.006253464,"threshold_uncertainty_score":0.9999229},"labels":[],"label_agreement":null},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98500234,0.00061983353,0.008586899,0.00071926136,0.0006035304,0.003897263,0.000017069558,0.000017875118,0.00053594616],"genre_scores_gemma":[0.9791241,0.0000032625908,0.01955904,0.00014429772,0.00019945376,0.00088020903,0.000030308265,0.0000070170486,0.000052258463],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985474,0.00018648722,0.0005464731,0.00019737807,0.00023765703,0.0002846261],"domain_scores_gemma":[0.99886286,0.000022602795,0.00035693537,0.000081133796,0.00046366762,0.00021280267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023602885,0.00012483787,0.00017427397,0.00017610051,0.0002325205,0.000095578136,0.00008883015,0.000060353254,0.0005213407],"category_scores_gemma":[0.00009965331,0.00010388287,0.00009599223,0.00014058077,0.000044427146,0.00014216667,0.0000059351546,0.0002090675,0.0000016302126],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010482461,0.00023232303,0.011687323,0.000009166824,0.00007639263,0.0000023540824,0.00021512716,0.000002568948,0.0006184877,0.00022790827,0.001382832,0.9854407],"study_design_scores_gemma":[0.00669504,0.01792409,0.94918674,0.00013925236,0.00040518946,0.00008559639,0.003713209,0.00045683613,0.00007047295,0.008649059,0.012361529,0.00031297852],"about_ca_topic_score_codex":0.0016939233,"about_ca_topic_score_gemma":0.0025662575,"teacher_disagreement_score":0.9851277,"about_ca_system_score_codex":0.00035880413,"about_ca_system_score_gemma":0.00027537378,"threshold_uncertainty_score":0.5708315},"labels":[],"label_agreement":null},{"id":"W2725327667","doi":"10.3138/cjpe.31124","title":"Finding Balance: An Evaluation Governance Model to Ease Tension between Independence and Inclusion","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Institutes of Health Research; Alberta Innovates","funders":"","keywords":"Independence (probability theory); Balance (ability); Inclusion (mineral); Corporate governance; Business; Psychology; Social psychology; Mathematics; Statistics; Neuroscience","score_opus":0.4753921117862232,"score_gpt":0.5589934326762455,"score_spread":0.08360132089002226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725327667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9881238,0.00022524985,0.0045976695,0.0041557867,0.00051554583,0.0013714407,0.000019880645,0.0000062532067,0.0009843743],"genre_scores_gemma":[0.9931535,0.000015934207,0.0061656474,0.00025760676,0.00025396745,0.000051380764,0.000014097754,0.000012145264,0.00007571142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924226,0.0005273378,0.0008826979,0.00039309022,0.005449278,0.00032502672],"domain_scores_gemma":[0.9920589,0.00014591907,0.0013831161,0.00070859067,0.0047691544,0.00093432923],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035944693,0.00016748648,0.00030061285,0.00042932178,0.002705105,0.0010113158,0.0010582507,0.00013918913,0.00036061084],"category_scores_gemma":[0.0099268695,0.00013703282,0.00006860624,0.0002879108,0.00010216281,0.0025979776,0.00032876845,0.00028780507,0.00002579897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022041486,0.000019170428,0.11894907,0.0000031370337,0.000008536799,0.000003005214,0.0020672851,0.013592883,0.00033972407,0.00014008333,0.00042841455,0.8644267],"study_design_scores_gemma":[0.00078610994,0.00032000893,0.37520728,0.000089635156,0.00007323924,0.0000106877715,0.00019252585,0.6054202,0.00013744434,0.016461622,0.0011643138,0.00013700176],"about_ca_topic_score_codex":0.00076657557,"about_ca_topic_score_gemma":0.013397373,"teacher_disagreement_score":0.86428964,"about_ca_system_score_codex":0.0006418607,"about_ca_system_score_gemma":0.0050816415,"threshold_uncertainty_score":0.9985932},"labels":[],"label_agreement":null},{"id":"W2725947572","doi":"10.3138/cjpe.31142","title":"La fidélité d’implantation d’un programme probant au-delà de son implantation initiale : l’exemple de Ces années incroyables en protection de l’enfance de 2003 à 2013","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Fidelity; Sustainability; Computer science; Humanities; Philosophy; Telecommunications","score_opus":0.21206354201125907,"score_gpt":0.48399008829918905,"score_spread":0.27192654628793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725947572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97911566,0.00019226645,0.014637342,0.002108095,0.0004105414,0.001969649,0.000030464798,0.00002906211,0.0015069024],"genre_scores_gemma":[0.98161596,0.00010778188,0.017091338,0.00012444163,0.0004023495,0.0005381055,0.00004119517,0.000023103601,0.00005570256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99458426,0.0018568834,0.0009687118,0.000318917,0.001456078,0.0008151754],"domain_scores_gemma":[0.9945914,0.00030407758,0.0016121654,0.00040726826,0.0024195304,0.00066555047],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.026995739,0.00022626367,0.00030222273,0.00057646004,0.0013159093,0.0016211974,0.00074672425,0.0002573352,0.0003130032],"category_scores_gemma":[0.0066975523,0.00019867158,0.00011574305,0.00045454566,0.00019247667,0.0016895252,0.000025988369,0.00043058651,0.000030504954],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113405586,0.000093704846,0.1101594,0.000042120788,0.000048621303,0.000033170527,0.014698196,0.0035951224,0.00084573997,0.00041086992,0.00079867424,0.86916095],"study_design_scores_gemma":[0.002129861,0.0009493543,0.81231374,0.00025918268,0.00022301101,0.0013895795,0.00633672,0.12762384,0.003984281,0.020786652,0.023592709,0.00041105403],"about_ca_topic_score_codex":0.018780673,"about_ca_topic_score_gemma":0.081707306,"teacher_disagreement_score":0.8687499,"about_ca_system_score_codex":0.0018060259,"about_ca_system_score_gemma":0.015971802,"threshold_uncertainty_score":0.99998426},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99501866,0.0000063017974,0.0012578018,0.0021750175,0.00017923859,0.001087367,0.0000076292154,0.0000071023155,0.00026089148],"genre_scores_gemma":[0.99102736,5.993451e-7,0.008665993,0.00008086935,0.00015240093,0.000029387318,0.000013434309,0.0000053659946,0.000024622066],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99162644,0.006970475,0.00033182785,0.000119703465,0.0006446393,0.00030693467],"domain_scores_gemma":[0.99778414,0.0003390686,0.0003121053,0.00008447958,0.0009485855,0.0005316048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026312524,0.00009449583,0.00026656923,0.00054548477,0.00018426047,0.000098326294,0.00019511853,0.00012446492,0.0000921439],"category_scores_gemma":[0.0051729335,0.00009715178,0.00006580052,0.0009170667,0.00010112513,0.00037250743,0.0000024914593,0.00020252379,0.000001539988],"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":[0.0020244138,0.0006193715,0.42511353,0.0000061219835,0.000026162712,0.000018075982,0.028920475,0.00074812863,0.0020533002,0.00059337507,0.0001474427,0.5397296],"study_design_scores_gemma":[0.0006271146,0.0010883718,0.9943884,0.000019461979,0.000025784348,4.8914353e-7,0.0016622975,0.0009795553,0.00018646091,0.00073536567,0.00018142947,0.00010527938],"about_ca_topic_score_codex":0.025886707,"about_ca_topic_score_gemma":0.33175036,"teacher_disagreement_score":0.56927484,"about_ca_system_score_codex":0.0010972032,"about_ca_system_score_gemma":0.02195337,"threshold_uncertainty_score":0.98359126},"labels":[],"label_agreement":null},{"id":"W2727038118","doi":"10.3138/cjpe.31039","title":"“Advocates Change the World; Evaluation Can Help”: A Literature Review and Key Insights from the Practice of Advocacy Evaluation","year":2017,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Public relations; Work (physics); Theory of change; Resource (disambiguation); Value (mathematics); Public administration; Sociology; Computer science","score_opus":0.5690707156508308,"score_gpt":0.5993917126532878,"score_spread":0.03032099700245705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727038118","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000061306855,0.9724339,0.000008450843,0.012914937,0.0012393304,0.011843903,0.00007788868,0.0000056346307,0.0014146438],"genre_scores_gemma":[0.0023616438,0.9926481,0.00040910498,0.001182943,0.0010108835,0.0017925188,0.0004442251,0.00003678213,0.000113763774],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9774043,0.011379148,0.0029359057,0.0006154536,0.00728634,0.0003788274],"domain_scores_gemma":[0.96919787,0.0039438736,0.008475054,0.0016219937,0.016402269,0.00035893766],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07291153,0.00051892555,0.0016248536,0.00093456573,0.00088806363,0.0015804203,0.0019270699,0.00027854033,0.0009794922],"category_scores_gemma":[0.041236766,0.00026016549,0.0005465642,0.0019677165,0.00034266914,0.001713788,0.000079622136,0.0010254161,0.000034517503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067116202,0.000031758973,0.000042130483,0.0006453435,0.00021229191,0.000002699908,0.0029606111,0.000010902661,7.416629e-8,0.000092189024,0.006089825,0.9899055],"study_design_scores_gemma":[0.0005992185,0.00021150189,0.0010808572,0.027334658,0.011349582,0.000101802514,0.00061449176,0.0033841284,4.3789782e-7,0.0026308363,0.95241934,0.00027311817],"about_ca_topic_score_codex":0.0014018117,"about_ca_topic_score_gemma":0.04540981,"teacher_disagreement_score":0.98963237,"about_ca_system_score_codex":0.0009126953,"about_ca_system_score_gemma":0.020629065,"threshold_uncertainty_score":0.99998504},"labels":[],"label_agreement":null},{"id":"W2727167739","doi":"10.3138/cjpe.32.1.146","title":"Thomas A. Schwandt. (2015). <i>Evaluation Foundations Revisited: Cultivating a Life of Mind for Practice</i> .","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy; Epistemology; Sociology","score_opus":0.5163532067272812,"score_gpt":0.6042933576740629,"score_spread":0.08794015094678165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727167739","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79167676,0.0047652544,0.047028646,0.06858322,0.006627358,0.019851228,0.00023921367,0.000030252724,0.061198052],"genre_scores_gemma":[0.95665854,0.000018205,0.04222947,0.00020444395,0.00041519527,0.00019025823,0.000053478238,0.000015222778,0.00021518725],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99346375,0.0008390518,0.0016722727,0.00029014243,0.0034296121,0.0003051728],"domain_scores_gemma":[0.9752511,0.001072118,0.0045607514,0.0007351005,0.017897617,0.0004833445],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050257515,0.00015915334,0.00037724894,0.0006146824,0.0010527811,0.0012349264,0.0008063904,0.00011479884,0.0013694151],"category_scores_gemma":[0.09772682,0.00013027938,0.00022079403,0.0004009839,0.0001853805,0.0027768346,0.000024834186,0.00020293202,0.00003212024],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007282833,0.00008912434,0.0156752,0.000016674032,0.00009813658,0.0000010908376,0.0016093518,0.0015794375,0.00023685605,0.0010932292,0.012971222,0.96655685],"study_design_scores_gemma":[0.0066972333,0.0015941561,0.08155417,0.0004572119,0.0012740826,0.00006776866,0.0066477736,0.29632238,0.0008054233,0.020859387,0.5832479,0.00047250246],"about_ca_topic_score_codex":0.0003339741,"about_ca_topic_score_gemma":0.004332546,"teacher_disagreement_score":0.96608436,"about_ca_system_score_codex":0.00038884542,"about_ca_system_score_gemma":0.01218033,"threshold_uncertainty_score":0.9998019},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81466395,0.008158428,0.0000043619484,0.16372213,0.0005658579,0.0014250978,6.374969e-7,0.000040421546,0.011419121],"genre_scores_gemma":[0.9953274,0.0027582056,0.00039620287,0.0001490756,0.00043434484,0.00016226705,0.0000043228792,0.000010043978,0.0007581091],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99748415,0.0011229886,0.0002899702,0.00012396483,0.0006594762,0.00031947953],"domain_scores_gemma":[0.99837387,0.00015116583,0.00024259496,0.000101483216,0.0006897646,0.00044110048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009377761,0.00008391648,0.000119813085,0.00013350401,0.00089084596,0.00031306563,0.00017890507,0.0000621762,0.00029999245],"category_scores_gemma":[0.0021032742,0.000067425186,0.000057302583,0.00014246332,0.00041423546,0.0003777244,0.000007782611,0.0002255729,0.00000539017],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052269697,0.00004471779,0.0010998542,0.0000055714727,0.000018653096,0.0000016141292,0.029627657,0.00009452025,0.0000020152963,0.010718393,0.00010654921,0.9582752],"study_design_scores_gemma":[0.0005560795,0.001142413,0.0237469,0.00010528814,0.00017505014,0.000026938,0.22476915,0.0026176437,0.0000022324352,0.026595376,0.7200588,0.00020414214],"about_ca_topic_score_codex":0.0035048504,"about_ca_topic_score_gemma":0.055020668,"teacher_disagreement_score":0.9580711,"about_ca_system_score_codex":0.00031045012,"about_ca_system_score_gemma":0.0035885575,"threshold_uncertainty_score":0.96222275},"labels":[],"label_agreement":null},{"id":"W2727296767","doi":"10.3138/cjpe.30975","title":"Building Evaluation Culture and Capacity in a Community-Level Program: Lessons Learned from Evaluating Youth Futures","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Futures contract; General partnership; Context (archaeology); Political science; Humanities; Sociology; Library science; Business; Computer science; Geography","score_opus":0.8259677997461102,"score_gpt":0.605372997880777,"score_spread":0.2205948018653332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727296767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918023,0.00063019426,0.00033806538,0.0031080977,0.0007284758,0.0020921335,0.0000578772,0.00001424614,0.0012286131],"genre_scores_gemma":[0.97430265,0.00002853809,0.025029054,0.00010272322,0.00026620345,0.00016962242,0.000049788985,0.000016956332,0.000034455043],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99026656,0.003785133,0.0012921749,0.00038526973,0.0038185092,0.0004523503],"domain_scores_gemma":[0.9918488,0.0004225737,0.0019212583,0.000889472,0.00440033,0.0005175504],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05743654,0.00025196388,0.00046298225,0.00071901904,0.0020670467,0.002353604,0.0011535832,0.00021916637,0.00043287585],"category_scores_gemma":[0.020869743,0.00020331745,0.00013925099,0.00044412242,0.0002927609,0.0016451012,0.000075991455,0.0010142889,0.000011465422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003027457,0.00008435847,0.034706958,0.000005991459,0.00003512235,0.000001925575,0.016085299,0.001241716,0.00022102185,0.00022590937,0.000118175885,0.9472433],"study_design_scores_gemma":[0.0035671259,0.0008472436,0.6877733,0.00032776978,0.0003237689,0.000017013137,0.01916118,0.20970999,0.00014337458,0.07583732,0.0019694238,0.0003225288],"about_ca_topic_score_codex":0.015488176,"about_ca_topic_score_gemma":0.20538081,"teacher_disagreement_score":0.9469207,"about_ca_system_score_codex":0.0007153561,"about_ca_system_score_gemma":0.0040806853,"threshold_uncertainty_score":0.9992321},"labels":[],"label_agreement":null},{"id":"W2727808690","doi":"10.3138/cjpe.018.008","title":"Students’ Perspective of the CES Case Competition","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Competition (biology); Presentation (obstetrics); Perspective (graphical); Task (project management); Relevance (law); Argument (complex analysis); Psychology; Medical education; Work (physics); Time limit; Management; Computer science; Medicine; Political science; Engineering; Law","score_opus":0.3255601195178861,"score_gpt":0.550185675195576,"score_spread":0.22462555567768994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727808690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98810875,0.000361183,0.00033489146,0.0013533976,0.0009130803,0.00077095337,0.000005712027,0.0000023498574,0.008149685],"genre_scores_gemma":[0.99896103,0.0000039752,0.0007535993,0.000087035354,0.00005016103,0.000015617863,7.2377804e-7,0.0000041055764,0.00012375168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99579173,0.0010197745,0.00065614306,0.00011888596,0.0022701365,0.00014335397],"domain_scores_gemma":[0.99426824,0.00018151857,0.0007543783,0.00024581255,0.0043585766,0.00019149376],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012928829,0.00007444649,0.0001551493,0.00032117194,0.00022977193,0.00019810846,0.00039213622,0.000041766372,0.0019839052],"category_scores_gemma":[0.0036637841,0.000046046967,0.00012995547,0.0007275511,0.00012587484,0.00033703592,0.0000083798905,0.00014583144,0.000017767628],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033236396,0.00037908848,0.5408571,0.000012317627,0.00017530183,0.00009887618,0.01761708,0.008520252,0.00016553413,0.0912168,0.0035285968,0.33739585],"study_design_scores_gemma":[0.004966115,0.0019128931,0.6008514,0.0002371217,0.00055633974,0.0037860307,0.11017147,0.01519459,0.0022224644,0.1756864,0.08393037,0.00048478803],"about_ca_topic_score_codex":0.0007318702,"about_ca_topic_score_gemma":0.029348806,"teacher_disagreement_score":0.33691105,"about_ca_system_score_codex":0.00040022124,"about_ca_system_score_gemma":0.0034395633,"threshold_uncertainty_score":0.9989284},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993766,0.00016528841,0.0019012855,0.0011699044,0.00009126906,0.0005063033,0.000015356254,0.000006830346,0.0023777715],"genre_scores_gemma":[0.9974496,0.000031263982,0.0022328356,0.000100417376,0.000066450855,0.000033796954,0.000019607709,0.000013170877,0.00005290552],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99796915,0.0006721977,0.00029960208,0.00012078026,0.00051258015,0.00042571453],"domain_scores_gemma":[0.99859804,0.00007414999,0.00042991556,0.00020930309,0.000085326894,0.00060324784],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004421197,0.00013644864,0.00017656184,0.000076209355,0.0011122674,0.0003319998,0.00031249222,0.00010697077,0.00095151295],"category_scores_gemma":[0.0009786496,0.00012454117,0.00017584894,0.000079728394,0.00040963123,0.00070317346,0.00003296284,0.00019794324,0.000020242434],"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":[0.000011918592,0.00014826423,0.67763937,0.0000027699218,0.00008175831,0.000016477074,0.0007625072,0.0023683286,0.0011264541,0.000025928986,0.0015154051,0.31630084],"study_design_scores_gemma":[0.0010859617,0.00020686281,0.984159,0.000040162453,0.0002189321,0.00004070641,0.0002842215,0.0075133466,0.0005317688,0.004089282,0.001699303,0.00013046512],"about_ca_topic_score_codex":0.0316712,"about_ca_topic_score_gemma":0.029456705,"teacher_disagreement_score":0.31617036,"about_ca_system_score_codex":0.002810373,"about_ca_system_score_gemma":0.00077998074,"threshold_uncertainty_score":0.99996173},"labels":[],"label_agreement":null},{"id":"W2728340321","doi":"10.3138/cjpe.31121","title":"Contribution Analysis: Theoretical and Practical Challenges and Prospects for Evaluators","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Toronto","funders":"","keywords":"Rigour; Management science; Causality (physics); Attribution; Engineering ethics; Psychological intervention; Epistemology; Psychology; Computer science; Sociology; Risk analysis (engineering); Medicine; Economics; Social psychology; Engineering; Philosophy","score_opus":0.35549175255489224,"score_gpt":0.5707339832883228,"score_spread":0.21524223073343057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2728340321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94927293,0.004151816,0.005194082,0.03644398,0.0006063743,0.0027080171,0.000015726248,0.000008719662,0.001598384],"genre_scores_gemma":[0.99621207,0.00015872982,0.0033090017,0.000065275744,0.00014305081,0.0000891916,0.000005224018,0.000005298758,0.000012134546],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971632,0.00040375965,0.00059334317,0.00024611957,0.0013601014,0.00023348672],"domain_scores_gemma":[0.9942558,0.00055270316,0.0006302605,0.00032593976,0.003740685,0.00049465185],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02515919,0.000106476524,0.0003099456,0.00046328467,0.00057531934,0.00094762,0.00019288098,0.000095247255,0.00020514925],"category_scores_gemma":[0.021706032,0.00007683884,0.00010625939,0.00014483731,0.00040575356,0.0008098275,0.000019078789,0.00013756774,0.0000033866665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006130395,0.000034732824,0.029322706,0.000006737375,0.000200528,0.000004189936,0.0007376529,0.000041589792,0.000012603744,0.12084187,0.0002034688,0.8485326],"study_design_scores_gemma":[0.001525595,0.00093599904,0.6283925,0.00003111747,0.0012894806,0.00006453919,0.0008333989,0.17872797,0.00006197354,0.18098138,0.007005973,0.00015007252],"about_ca_topic_score_codex":0.000027417384,"about_ca_topic_score_gemma":0.005266195,"teacher_disagreement_score":0.84838253,"about_ca_system_score_codex":0.00012719336,"about_ca_system_score_gemma":0.0016668714,"threshold_uncertainty_score":0.98653454},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9294466,0.0006869184,0.015614843,0.02774366,0.0013342181,0.0010883814,0.00001238589,0.000030752886,0.024042275],"genre_scores_gemma":[0.9913363,0.000051805113,0.0065389513,0.00012723371,0.0017409759,0.00009640921,0.000017713966,0.000009147259,0.0000815018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979103,0.0009592108,0.0003299953,0.00013262518,0.0003262532,0.00034160187],"domain_scores_gemma":[0.9974763,0.00019546768,0.0006632088,0.00018373523,0.0010793788,0.00040193935],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0115636205,0.000089396555,0.00015623518,0.00012639177,0.0034118134,0.00028412073,0.00050945714,0.00015044669,0.00005086963],"category_scores_gemma":[0.003710207,0.00009397538,0.00010101566,0.00012559479,0.0024285733,0.00042887847,0.0000052406044,0.00019648057,0.000004956629],"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":[0.000010189485,0.000115812596,0.4831615,0.000012467071,0.00011833611,0.0000018730502,0.114459746,0.00009379394,0.00013323387,0.12683366,0.0012495476,0.27380982],"study_design_scores_gemma":[0.00093238807,0.00017070743,0.6396018,0.000067411405,0.0001796551,0.000011618797,0.14025857,0.00048142267,0.00005250733,0.18826666,0.029741086,0.00023616638],"about_ca_topic_score_codex":0.031337116,"about_ca_topic_score_gemma":0.254442,"teacher_disagreement_score":0.27357364,"about_ca_system_score_codex":0.0006041099,"about_ca_system_score_gemma":0.0063499156,"threshold_uncertainty_score":0.99928313},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96540815,0.00012416192,0.004020247,0.019545693,0.0009053044,0.002270296,0.000065790286,0.000032627897,0.007627705],"genre_scores_gemma":[0.99480206,0.000047863978,0.0035335785,0.00078139175,0.00027394123,0.00023149716,0.00005681353,0.0000259333,0.00024690956],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9908957,0.0061185677,0.0014669975,0.00020675159,0.00068997836,0.0006220376],"domain_scores_gemma":[0.9928124,0.0014095582,0.002480008,0.0005787536,0.0018898358,0.0008294265],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.027043162,0.00016835923,0.00032853367,0.00048482345,0.0026414474,0.00023164182,0.00067518704,0.00023702485,0.00039638288],"category_scores_gemma":[0.014766585,0.0001654891,0.00015766174,0.00037668212,0.00021843385,0.0011419791,0.00003531972,0.0008443785,0.00006489754],"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":[0.00013597115,0.00018394874,0.26688847,0.00026633308,0.00013981787,0.000097366086,0.07883625,0.00028438342,0.0007367373,0.0011839186,0.018616997,0.6326298],"study_design_scores_gemma":[0.0065811924,0.00046220096,0.90473765,0.00074097945,0.00022265666,0.00009091996,0.023862882,0.010083311,0.00018497609,0.0040986147,0.048624907,0.00030971944],"about_ca_topic_score_codex":0.1808145,"about_ca_topic_score_gemma":0.63101953,"teacher_disagreement_score":0.63784915,"about_ca_system_score_codex":0.0018630408,"about_ca_system_score_gemma":0.010683782,"threshold_uncertainty_score":0.998657},"labels":[],"label_agreement":null},{"id":"W2731520452","doi":"10.3138/cjpe.32.1.143","title":"Patricia Burch and Carolyn J. Heinrich. (2015). <i>Mixed Methods for Policy Research and Program Evaluation</i> .","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Psychology; Psychoanalysis","score_opus":0.6318859600826949,"score_gpt":0.6992112929537181,"score_spread":0.06732533287102316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731520452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80369335,0.01880951,0.0131175285,0.12233289,0.0038860955,0.03026198,0.00007531469,0.000059298298,0.007764022],"genre_scores_gemma":[0.93178535,0.0001572233,0.06578954,0.0001336831,0.00065055804,0.0012166618,0.000014627119,0.000022446611,0.00022993276],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99189764,0.0024772235,0.001106126,0.00046817906,0.003388331,0.0006625167],"domain_scores_gemma":[0.98192334,0.0016700502,0.001085364,0.0007358346,0.013615108,0.0009703225],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10920446,0.00019559269,0.00040749906,0.0015140739,0.0019409007,0.0027247446,0.0008382624,0.00017506708,0.0001895421],"category_scores_gemma":[0.040108003,0.00015437852,0.00011172614,0.00075361907,0.0006045282,0.0011453605,0.00007995249,0.0003824219,0.000010870337],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027420967,0.000058195747,0.011492266,0.000010777912,0.000037613503,0.0000011489485,0.00059999904,0.000063261665,0.000040514595,0.0010915007,0.0042150384,0.9823623],"study_design_scores_gemma":[0.0041319616,0.003181826,0.1840824,0.000086947126,0.00024091276,0.000088407876,0.0018918394,0.2831626,0.00015791,0.13397364,0.38864943,0.00035211843],"about_ca_topic_score_codex":0.0015057649,"about_ca_topic_score_gemma":0.016240811,"teacher_disagreement_score":0.9820101,"about_ca_system_score_codex":0.00060706155,"about_ca_system_score_gemma":0.011684499,"threshold_uncertainty_score":0.9993584},"labels":[],"label_agreement":null},{"id":"W2732819684","doi":"10.3138/cjpe.20.006","title":"Evaluator Competencies in University-Based Evaluation Training Programs","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credentialing; Accreditation; Licensure; Certificate; Taxonomy (biology); Competence (human resources); Computer science; Medical education; Psychology; Medicine","score_opus":0.4101080033795569,"score_gpt":0.5034090358417598,"score_spread":0.09330103246220289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732819684","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9816959,0.00062371936,0.002328594,0.006192556,0.0008146368,0.0030898442,0.0000071885825,0.000023894792,0.0052236696],"genre_scores_gemma":[0.98323494,0.0000041461976,0.016183592,0.00020108884,0.00019793892,0.00004278359,0.00003061808,0.000011946847,0.00009296449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917924,0.0017565354,0.001146272,0.00031102216,0.0045495047,0.00044428452],"domain_scores_gemma":[0.99293274,0.00030854112,0.0008512482,0.00033177555,0.005067927,0.000507794],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.042099725,0.00017668224,0.0003380694,0.0017718719,0.00023997194,0.00036515866,0.00064361264,0.00011902698,0.00300078],"category_scores_gemma":[0.00302336,0.00015640634,0.00017624156,0.0018003136,0.0001472594,0.0011349069,0.0000111835725,0.0003088309,0.000102892554],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026108299,0.00007310702,0.023866137,0.0000026718121,0.000013397807,0.0000049270193,0.0025372135,0.052246507,0.000022200884,0.00036533788,0.00031678015,0.9205256],"study_design_scores_gemma":[0.0031356057,0.00052789313,0.05854617,0.000102561964,0.00012596555,0.000019128143,0.007297549,0.8207593,0.000028460357,0.0025597215,0.106688336,0.00020933995],"about_ca_topic_score_codex":0.0004243129,"about_ca_topic_score_gemma":0.08864555,"teacher_disagreement_score":0.9203163,"about_ca_system_score_codex":0.0018353434,"about_ca_system_score_gemma":0.018273171,"threshold_uncertainty_score":0.9979106},"labels":[],"label_agreement":null},{"id":"W273644060","doi":"10.3138/cjpe.17.007","title":"Evaluating Organizational Capacity Development","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Danish International Development Agency; International Fund for Agricultural Development; Australian Centre for International Agricultural Research; Ministerie van Buitenlandse Zaken; Concordia University; Direktion für Entwicklung und Zusammenarbeit; International Development Research Centre","keywords":"Capacity development; Agricultural development; Capacity building; Process management; Business; Latin Americans; Organization development; Agriculture; Management science; Environmental resource management; Knowledge management; Political science; Computer science; Economic growth; Engineering; Economics","score_opus":0.6856435831176912,"score_gpt":0.546893715148618,"score_spread":0.1387498679690733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W273644060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98220676,0.00048290618,0.003045828,0.002563382,0.0013521977,0.0010264877,0.000005451642,0.000017571754,0.0092994245],"genre_scores_gemma":[0.96302533,0.0000033173826,0.036003113,0.0002350955,0.00021933143,0.00003495821,0.000010680516,0.0000109729435,0.00045721958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99383044,0.00060989126,0.0012215291,0.00021127643,0.0038391,0.00028773563],"domain_scores_gemma":[0.99202603,0.00025733607,0.0008016487,0.00024176344,0.006172373,0.0005008579],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01948341,0.00012787351,0.0002104844,0.00069530774,0.00041550063,0.0004378934,0.00048786725,0.00007570252,0.026113644],"category_scores_gemma":[0.007731335,0.000102119375,0.000081227976,0.0011190163,0.00007589227,0.0006515527,0.000013223206,0.00020196545,0.0005803004],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030298504,0.00005327824,0.032548126,0.0000026396553,0.000026895757,0.0000023160053,0.0029181002,0.0037544828,0.00007221778,0.0004466684,0.0037937858,0.95637846],"study_design_scores_gemma":[0.0024939468,0.00081933825,0.1784929,0.00009324187,0.00013269702,0.00018540748,0.0013071537,0.5798509,0.0007311821,0.016401123,0.21900049,0.0004915818],"about_ca_topic_score_codex":0.00007124245,"about_ca_topic_score_gemma":0.0059288144,"teacher_disagreement_score":0.9558869,"about_ca_system_score_codex":0.00063846743,"about_ca_system_score_gemma":0.0039606327,"threshold_uncertainty_score":0.9747766},"labels":[],"label_agreement":null},{"id":"W274204648","doi":"10.3138/cjpe.16.008","title":"Do Evaluator and Program Practitioner Perspectives Converge in Collaborative Evaluation?","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Stakeholder; Participatory evaluation; Program evaluation; Citizen journalism; Collaborative model; Medical education; Psychology; Computer science; Knowledge management; Management science; Sociology; Public relations; Medicine; Political science; Engineering; World Wide Web","score_opus":0.21392616880582213,"score_gpt":0.5507446156045417,"score_spread":0.33681844679871953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W274204648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9724502,0.0053493935,0.00014951696,0.006474746,0.0009641022,0.00519776,0.000011170163,0.000018771134,0.009384329],"genre_scores_gemma":[0.9950497,0.00020051214,0.0036027452,0.0001272762,0.00024014036,0.0006078901,0.000017095323,0.000015112417,0.00013953935],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99165,0.002134522,0.0012575639,0.00043518055,0.004127073,0.0003956541],"domain_scores_gemma":[0.9861191,0.00044310628,0.0010227911,0.00033585323,0.011524617,0.0005545664],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035171587,0.00021007496,0.00037459,0.0014101504,0.0002839864,0.00085604854,0.000345369,0.00013414028,0.0059668273],"category_scores_gemma":[0.009294563,0.00017043049,0.00009702894,0.0023503243,0.0002370804,0.0017486694,0.000018090606,0.00034002122,0.000072658375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009695263,0.00023796545,0.08687122,0.000003773943,0.000051175073,0.000015334119,0.008455431,0.001615013,0.000020185436,0.0009387365,0.0025505575,0.89914364],"study_design_scores_gemma":[0.006864706,0.0027707107,0.5433184,0.00018747101,0.00034352855,0.00024144712,0.057153072,0.23429844,0.00004025505,0.029191665,0.12505315,0.00053718966],"about_ca_topic_score_codex":0.0003277641,"about_ca_topic_score_gemma":0.018702539,"teacher_disagreement_score":0.8986065,"about_ca_system_score_codex":0.0011007432,"about_ca_system_score_gemma":0.011161479,"threshold_uncertainty_score":0.99920356},"labels":[],"label_agreement":null},{"id":"W2771643987","doi":"10.3138/cjpe.31144","title":"Théories du changement : comment élaborer des modèles utiles","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Causality (physics); Epistemology; Intervention (counseling); Psychological intervention; Theory of change; Computer science; Sociology; Psychology; Philosophy; Physics","score_opus":0.5023497063004002,"score_gpt":0.5392922766264496,"score_spread":0.03694257032604942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771643987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9457531,0.0011182101,0.0018797952,0.031730004,0.00250622,0.001514196,0.000025180945,0.00001449938,0.015458795],"genre_scores_gemma":[0.9955312,0.00006271767,0.003418754,0.0003973605,0.0003222578,0.00007439488,0.0000069990247,0.000008398184,0.00017789114],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99635345,0.00033438954,0.000722031,0.00017839977,0.0021174382,0.00029430192],"domain_scores_gemma":[0.99418896,0.00012475636,0.0010554761,0.0005542157,0.003631063,0.0004455329],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013941428,0.00013069781,0.00022805222,0.00038549403,0.001242567,0.0015686755,0.0009060487,0.000057363868,0.0027138742],"category_scores_gemma":[0.0034697014,0.0000941544,0.000116445015,0.00018176807,0.00030862156,0.001108568,0.000038445043,0.00013570733,0.000069006164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012789222,0.0000434855,0.14187501,0.0000041700055,0.000033954122,0.0000054841335,0.0018314279,0.00045666896,0.000011004939,0.0015928565,0.013874839,0.8402583],"study_design_scores_gemma":[0.0009865595,0.00045517817,0.61870253,0.000074422984,0.00008793435,0.000019006102,0.0026416583,0.028825117,0.00017587084,0.028913075,0.31895617,0.00016248513],"about_ca_topic_score_codex":0.00089079636,"about_ca_topic_score_gemma":0.03625453,"teacher_disagreement_score":0.8400958,"about_ca_system_score_codex":0.0004118313,"about_ca_system_score_gemma":0.0025069483,"threshold_uncertainty_score":0.9994678},"labels":[],"label_agreement":null},{"id":"W2771770473","doi":"10.3138/cjpe.31128","title":"Using Rubrics for an Evaluation: A National Research Council Pilot","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Rubric; Excellence; Relevance (law); Context (archaeology); Psychology; Political science; Computer science; Medical education; Pedagogy; Medicine; Geography","score_opus":0.9730025773537614,"score_gpt":0.7170565067688764,"score_spread":0.25594607058488494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771770473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8876423,0.0012111469,0.010642959,0.00967995,0.0060327095,0.010795872,0.00010425991,0.000023342023,0.07386744],"genre_scores_gemma":[0.98470426,0.000004604855,0.013873204,0.00012343349,0.00088528066,0.00021522916,0.000012827835,0.000015305353,0.00016587308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9746389,0.001330455,0.0010430451,0.00033734995,0.022208577,0.00044170397],"domain_scores_gemma":[0.8787238,0.0005346013,0.0010955519,0.0005820711,0.118514165,0.0005498141],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26418558,0.00013146864,0.00024189812,0.00078465923,0.0022827906,0.002524644,0.0012490937,0.00009464572,0.0013717236],"category_scores_gemma":[0.08519602,0.00011039406,0.00011926915,0.00047096855,0.00027900952,0.0022541007,0.000026344198,0.00029091508,0.000042766234],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00012303914,0.00018348102,0.009522122,0.000009612614,0.000055562068,0.0000022962213,0.0016183474,0.018156866,0.00024167066,0.0039800135,0.027361965,0.938745],"study_design_scores_gemma":[0.0020936097,0.0015512388,0.028511992,0.000046503636,0.00008726859,0.000036370737,0.0008288218,0.76247776,0.00004408643,0.09416685,0.110001944,0.00015357237],"about_ca_topic_score_codex":0.0013355825,"about_ca_topic_score_gemma":0.07478361,"teacher_disagreement_score":0.9385915,"about_ca_system_score_codex":0.006140058,"about_ca_system_score_gemma":0.09513073,"threshold_uncertainty_score":0.99954116},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"commentary","about_ca_system":true,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627839,0.002995059,0.00060250226,0.003661604,0.00848577,0.008938716,0.0000128686,0.000033453474,0.012486132],"genre_scores_gemma":[0.99365324,0.000025305935,0.00368901,0.00012159103,0.0008706034,0.0010174077,0.00003253233,0.000024971505,0.000565352],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962915,0.0012931743,0.0009123893,0.00020131514,0.00091965304,0.00038194482],"domain_scores_gemma":[0.9932264,0.00014076044,0.0017405105,0.00040634617,0.0039733006,0.00051269244],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.010549838,0.00016493208,0.00034768204,0.0003423699,0.002275783,0.00023083664,0.00029338416,0.0001998391,0.00021684439],"category_scores_gemma":[0.0042596436,0.00014032083,0.00006523856,0.00013889151,0.00010978763,0.000666359,0.000018411965,0.00047995368,0.00004253071],"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":[0.00042763946,0.0005252518,0.10097483,0.01353593,0.0007289028,0.000015590487,0.22987987,0.00043750493,0.0018931935,0.0067555946,0.024048882,0.62077683],"study_design_scores_gemma":[0.014700667,0.0012417991,0.65398663,0.053969525,0.0039779907,0.00027848248,0.14027554,0.06415432,0.00008712669,0.014219166,0.051274445,0.0018343109],"about_ca_topic_score_codex":0.0010022302,"about_ca_topic_score_gemma":0.0062642302,"teacher_disagreement_score":0.6189425,"about_ca_system_score_codex":0.0008596788,"about_ca_system_score_gemma":0.01681928,"threshold_uncertainty_score":0.99902314},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.877463,0.010485234,0.012053969,0.068327196,0.0053688106,0.017302347,0.00010966838,0.000044148164,0.0088456515],"genre_scores_gemma":[0.9870029,0.00034265383,0.0049306448,0.0008824171,0.00088433514,0.0016592545,0.000043492433,0.000029630546,0.0042246445],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980005,0.00049957464,0.00051945983,0.0001766212,0.00045526985,0.00034856662],"domain_scores_gemma":[0.9966195,0.00043612,0.0007544613,0.00037710916,0.0014873534,0.00032543766],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.007209661,0.00012298836,0.00017389885,0.00020476137,0.003613622,0.00039867303,0.0002676055,0.00009470609,0.00037418745],"category_scores_gemma":[0.003844561,0.000095139636,0.000058008154,0.00008203182,0.00021563267,0.0008074806,0.000048781432,0.00025958018,0.000022174025],"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":[0.00039381348,0.00007197463,0.026383484,0.000332099,0.0003066633,0.000003645083,0.006628311,0.0001421489,0.00012637486,0.004611885,0.2843586,0.67664105],"study_design_scores_gemma":[0.0017461912,0.0002461591,0.119344875,0.00035287056,0.00055618555,0.00001807933,0.0014972398,0.0016060306,0.0000036913586,0.009111191,0.86537856,0.00013894224],"about_ca_topic_score_codex":0.0036766229,"about_ca_topic_score_gemma":0.06080391,"teacher_disagreement_score":0.6765021,"about_ca_system_score_codex":0.00026100583,"about_ca_system_score_gemma":0.003007577,"threshold_uncertainty_score":0.9976835},"labels":[],"label_agreement":null},{"id":"W2773692454","doi":"10.3138/cjpe.31130","title":"The Impact of Practice on Pedagogy: Reflections of Novice Evaluation Teachers","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Practicum; Syllabus; Pedagogy; Psychology; Mathematics education; Medical education; Sociology; Medicine","score_opus":0.5343895073017358,"score_gpt":0.6801314847072718,"score_spread":0.14574197740553596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773692454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9520902,0.00050610554,0.00034177385,0.007993322,0.0011751173,0.0017852497,0.000014226627,0.000004700592,0.036089294],"genre_scores_gemma":[0.99853766,0.000029121014,0.0010566171,0.000037779984,0.00014995027,0.0000442757,0.0000046324053,0.000008634332,0.00013134872],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.993353,0.0014508878,0.001183095,0.00017816042,0.0035984744,0.00023640052],"domain_scores_gemma":[0.9832164,0.0011141977,0.0037852006,0.00082920224,0.010785506,0.00026946442],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048882425,0.00012394822,0.00025198382,0.00050618075,0.0008988548,0.0004976697,0.0008841729,0.00008739465,0.00074493675],"category_scores_gemma":[0.041408867,0.00007575478,0.0002563493,0.00041935293,0.000260255,0.0011610065,0.000016102898,0.00029124675,0.000025880512],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088944216,0.00009633283,0.014360751,0.0000017555718,0.00011505143,7.512901e-7,0.0031738717,0.013428288,0.00019867564,0.00043828067,0.0023242123,0.9657731],"study_design_scores_gemma":[0.002477278,0.0037999447,0.8471397,0.00012497339,0.00055330724,0.000056686997,0.008631938,0.09125762,0.000488908,0.011792368,0.033472527,0.00020475779],"about_ca_topic_score_codex":0.004715839,"about_ca_topic_score_gemma":0.03071858,"teacher_disagreement_score":0.9655683,"about_ca_system_score_codex":0.0007365628,"about_ca_system_score_gemma":0.01378103,"threshold_uncertainty_score":0.9918099},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2773791117","doi":"10.3138/cjpe.0020.006","title":"Randomized and Quasi-Experimental Evaluations of Program Impact in Child Welfare in Canada: A Review","year":2006,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychological intervention; Welfare; Randomized controlled trial; Context (archaeology); Psychology; Impact evaluation; Applied psychology; Medicine; Political science; Psychiatry; Geography","score_opus":0.3183477250621403,"score_gpt":0.5792820356604422,"score_spread":0.2609343105983019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773791117","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010244915,0.9863102,0.0000060486623,0.00067585707,0.00032633988,0.010644915,0.00005538783,0.0000037053046,0.0009530772],"genre_scores_gemma":[0.052458085,0.94479847,0.0006321942,0.0000510965,0.00008916393,0.0017140523,0.00020267206,0.00003407319,0.000020188507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9863227,0.004552088,0.004797248,0.00043314043,0.0034166765,0.0004781319],"domain_scores_gemma":[0.9931383,0.0007085223,0.0034762903,0.0004475085,0.0017615785,0.0004677819],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03402999,0.00043484275,0.0034271735,0.0019991822,0.00013691971,0.00018506889,0.00063421496,0.00018279263,0.0013417087],"category_scores_gemma":[0.0047979313,0.00029883784,0.00067226175,0.0020192987,0.00016837062,0.0004341735,0.00002698498,0.0006299109,0.000004894221],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000090292844,0.00018202502,0.00051224494,0.0010629671,0.00006535382,0.00001277916,0.00012317984,0.0001623635,9.909797e-9,0.00004412255,0.00050575484,0.99723893],"study_design_scores_gemma":[0.051870394,0.0014901083,0.0054449043,0.062169127,0.0023714018,0.00046218483,0.0007283357,0.0142270485,7.1604904e-7,0.0004482992,0.85985214,0.00093536224],"about_ca_topic_score_codex":0.5622053,"about_ca_topic_score_gemma":0.97487724,"teacher_disagreement_score":0.99630356,"about_ca_system_score_codex":0.00415267,"about_ca_system_score_gemma":0.043822292,"threshold_uncertainty_score":0.99994636},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95711863,0.0009502914,0.00003350062,0.029675875,0.003590763,0.008310128,0.000019200435,0.000012652442,0.0002889335],"genre_scores_gemma":[0.9948082,0.00010866118,0.00039250782,0.0033321287,0.00017973964,0.0010863187,0.00006041332,0.000024331668,0.000007727056],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98692715,0.009391514,0.0015401233,0.00017493067,0.0012192961,0.0007469584],"domain_scores_gemma":[0.99199444,0.0004175897,0.0029621786,0.0008729354,0.0031515206,0.0006013263],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.030235413,0.00018228858,0.00030535372,0.00035786012,0.0059923935,0.00017842,0.00056390814,0.0001326415,0.00038252876],"category_scores_gemma":[0.0034818049,0.00014978168,0.0000657053,0.0002490143,0.000072935,0.0009900139,0.00006833963,0.001973431,0.000015509317],"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":[0.000020639614,0.000031006006,0.15672448,0.0002154932,0.000022936521,0.0000012853922,0.03811922,0.0010772529,0.000010250919,0.000054768316,0.00044677668,0.8032759],"study_design_scores_gemma":[0.002424856,0.001075597,0.89484656,0.0024116323,0.00007322899,0.0000046931727,0.07344169,0.015142017,0.000017268845,0.0020318124,0.008341784,0.0001888368],"about_ca_topic_score_codex":0.17089093,"about_ca_topic_score_gemma":0.8220043,"teacher_disagreement_score":0.80308706,"about_ca_system_score_codex":0.006842821,"about_ca_system_score_gemma":0.014635669,"threshold_uncertainty_score":0.9985767},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92522204,0.00043497884,0.00025796014,0.0076810676,0.0014610311,0.0013321277,0.000009118455,0.000039339036,0.06356232],"genre_scores_gemma":[0.99485207,0.00005392033,0.0019631176,0.00010266115,0.00094264856,0.00003642189,0.000009803931,0.000021840739,0.0020174903],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969752,0.00064651814,0.00045248316,0.00020172633,0.0010856678,0.0006384411],"domain_scores_gemma":[0.99657005,0.00006263915,0.0006996601,0.00037665214,0.0013764935,0.0009144825],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008662244,0.00015826935,0.00023129751,0.0003803527,0.0030520512,0.0012963902,0.0007618806,0.00019052008,0.0013384345],"category_scores_gemma":[0.0016768909,0.0001511037,0.00017272109,0.0001589012,0.00050284766,0.0010492301,0.000014946986,0.00029657548,0.00009136457],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025561518,0.00010985161,0.023389569,0.000019877249,0.00011053342,0.0000621478,0.051685825,0.00031586172,0.000074441705,0.044452503,0.006952306,0.87280154],"study_design_scores_gemma":[0.003439384,0.0010533897,0.33814594,0.0003878729,0.000862071,0.00007409084,0.011919588,0.010985208,0.00052052055,0.22572961,0.40592375,0.0009585402],"about_ca_topic_score_codex":0.029839853,"about_ca_topic_score_gemma":0.4095241,"teacher_disagreement_score":0.871843,"about_ca_system_score_codex":0.0012500365,"about_ca_system_score_gemma":0.011955564,"threshold_uncertainty_score":0.99974036},"labels":[],"label_agreement":null},{"id":"W2774864855","doi":"10.3138/10.3138/cjpe.31132","title":"Moving Beyond the Buzzword: A Framework for Teaching Culturally Responsive Approaches to Evaluation","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Sociology; Competence (human resources); Conceptual framework; Epistemology; Humanities; Psychology; Social science; Philosophy; Social psychology; Business","score_opus":0.6407724104552023,"score_gpt":0.5597165071488638,"score_spread":0.0810559033063385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774864855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7964171,0.0006996965,0.06172205,0.11679335,0.0039230823,0.010497101,0.000029389254,0.00001937502,0.009898834],"genre_scores_gemma":[0.9442305,0.0000020867046,0.053669736,0.0006807805,0.00062992965,0.0005111801,0.000010829728,0.000014514366,0.00025042123],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99375,0.0012998708,0.0009640276,0.00032071312,0.0032831854,0.00038220125],"domain_scores_gemma":[0.9916731,0.001200062,0.0015481611,0.00085052446,0.0042589023,0.0004692256],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06413532,0.00017211442,0.00027153068,0.00047589108,0.0025056505,0.002436947,0.0014618158,0.000120825745,0.00044665832],"category_scores_gemma":[0.05975384,0.00010669613,0.00021011101,0.00027187346,0.00015377066,0.0012010831,0.000033656175,0.00042033644,0.000043056185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063470805,0.000021310096,0.0030200302,0.0000031741024,0.00004120647,8.601991e-7,0.0076990915,0.0064308494,0.000034300905,0.012181978,0.0043913624,0.9661124],"study_design_scores_gemma":[0.0017336969,0.001117979,0.1500711,0.0002102308,0.0004454044,0.000045278404,0.01645248,0.3153688,0.00016640026,0.42197177,0.092011586,0.00040529348],"about_ca_topic_score_codex":0.00029378763,"about_ca_topic_score_gemma":0.012848757,"teacher_disagreement_score":0.96570706,"about_ca_system_score_codex":0.00061139866,"about_ca_system_score_gemma":0.005132222,"threshold_uncertainty_score":0.99879295},"labels":[],"label_agreement":null},{"id":"W2775174218","doi":"10.3138/cjpe.31122","title":"Theory of Change Analysis: Building Robust Theories of Change","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":145,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Computer science; Management science; Risk analysis (engineering); Positive economics; Econometrics; Economics; Business; Management","score_opus":0.7318312016170765,"score_gpt":0.5642255157815168,"score_spread":0.16760568583555968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775174218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858212,0.001821543,0.004568031,0.002264469,0.0010388135,0.0012550073,0.000034085555,0.000005312036,0.0031915265],"genre_scores_gemma":[0.9968542,0.000026881331,0.0026687658,0.00006407727,0.00024572315,0.000061056875,0.000005214231,0.0000067769884,0.000067304754],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960204,0.00062979443,0.0010030975,0.0001674196,0.001959151,0.00022013996],"domain_scores_gemma":[0.9925872,0.00026836395,0.0026439263,0.00062085094,0.0036190725,0.00026060364],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026955493,0.00011363576,0.0004325363,0.0012458136,0.00031206998,0.0002771632,0.0009126268,0.0000778667,0.0020791108],"category_scores_gemma":[0.0041024433,0.000083899016,0.00027305138,0.00072359474,0.00028276595,0.0012250163,0.000028463764,0.0001323784,0.000008144712],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030530093,0.000036060126,0.17731944,0.0000094595325,0.00021964867,0.0000020951818,0.004115089,0.0006708325,0.000042895455,0.010831987,0.00009081062,0.80663115],"study_design_scores_gemma":[0.0008044912,0.0005412624,0.9022572,0.00013624241,0.0010517199,0.0000071640447,0.003570409,0.03193347,0.00056329387,0.05624328,0.0027309563,0.00016050326],"about_ca_topic_score_codex":0.0013118197,"about_ca_topic_score_gemma":0.019375427,"teacher_disagreement_score":0.80647063,"about_ca_system_score_codex":0.00013321328,"about_ca_system_score_gemma":0.0014140626,"threshold_uncertainty_score":0.9988331},"labels":[],"label_agreement":null},{"id":"W2775784773","doi":"10.3138/cjpe.31119","title":"Making Evaluation More Responsive to Policy Needs: The Case of the Labour Market Development Agreements","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Statistics Canada; Employment and Social Development Canada","funders":"","keywords":"Process (computing); Business; Key (lock); Market development; Policy development; Process management; Public economics; Economics; Computer science; Economic policy","score_opus":0.4694491553349992,"score_gpt":0.586143825088606,"score_spread":0.11669466975360676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775784773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96954966,0.00012834888,0.00019388364,0.023378411,0.0009323553,0.0022909506,0.000012613222,0.0000025735808,0.0035111967],"genre_scores_gemma":[0.9963447,0.0000021674725,0.0017408866,0.00072858913,0.00020429313,0.0001185566,0.000001620592,0.000009228237,0.0008499662],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.993852,0.0013944159,0.0010876873,0.00018301174,0.0031801278,0.000302742],"domain_scores_gemma":[0.9900824,0.00029165242,0.0019094081,0.00093838596,0.0064996555,0.0002785183],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038803276,0.00014301541,0.00021354477,0.0012935508,0.0014616142,0.0007565008,0.0013913765,0.0000661596,0.0012851319],"category_scores_gemma":[0.020733798,0.000080100035,0.00012775812,0.0013392285,0.00016800381,0.00055311027,0.000091567745,0.00020208489,0.000027734412],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043336182,0.000022632594,0.02187172,0.000004446487,0.000049331422,0.000012434197,0.009437569,0.00201106,0.000025168205,0.0006912184,0.003750853,0.96208024],"study_design_scores_gemma":[0.001236979,0.00022518623,0.8503207,0.00020340901,0.00015637348,0.00030119502,0.01356567,0.04068647,0.00022086466,0.0054435194,0.08745911,0.00018050328],"about_ca_topic_score_codex":0.0011872062,"about_ca_topic_score_gemma":0.03437901,"teacher_disagreement_score":0.9618997,"about_ca_system_score_codex":0.0008860046,"about_ca_system_score_gemma":0.01505088,"threshold_uncertainty_score":0.99983835},"labels":[],"label_agreement":null},{"id":"W2779494915","doi":"10.3138/cjpe.19.002","title":"Using Multi-Site Core Evaluation to Provide “Scientific” Evidence","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fidelity; Excellence; Core (optical fiber); Computer science; Program evaluation; Order (exchange); Management science; Service (business); Knowledge management; Process management; Engineering ethics; Engineering management; Business; Engineering; Political science","score_opus":0.8288838258260318,"score_gpt":0.6324526320169,"score_spread":0.19643119380913177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2779494915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627763,0.0006880113,0.028316455,0.002516814,0.0023098576,0.0031719252,0.000008975952,0.000013137646,0.00019852127],"genre_scores_gemma":[0.946097,0.0000025031554,0.053163752,0.00029203363,0.0002055688,0.00009692521,0.000011515213,0.000014121919,0.00011657657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912465,0.00063695485,0.0013656901,0.00045379452,0.0058032055,0.00049382343],"domain_scores_gemma":[0.9861012,0.0002062887,0.0009676562,0.00054829364,0.011265336,0.00091120123],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049381033,0.00018357889,0.0002823768,0.0014633965,0.00063336827,0.0013689016,0.0006930419,0.00009786842,0.0014065749],"category_scores_gemma":[0.01606486,0.00014968491,0.00016263843,0.0021513659,0.00013657988,0.002308617,0.000031370582,0.00023525872,0.00032449877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029950843,0.000074271156,0.024392884,0.000006682376,0.000020262569,0.000007240859,0.004559657,0.20429613,0.0027180852,0.00019297081,0.00062220986,0.76307964],"study_design_scores_gemma":[0.0036402987,0.0011653336,0.17266774,0.00076240837,0.00043241284,0.00015432021,0.0025512222,0.7761448,0.0013505644,0.014276601,0.026309935,0.0005443512],"about_ca_topic_score_codex":0.001478979,"about_ca_topic_score_gemma":0.06279187,"teacher_disagreement_score":0.7625353,"about_ca_system_score_codex":0.0022106834,"about_ca_system_score_gemma":0.020473465,"threshold_uncertainty_score":0.99966776},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86002314,0.044184513,0.006619034,0.014557408,0.010558936,0.015725993,0.000017699,0.00009566866,0.04821759],"genre_scores_gemma":[0.98791033,0.0005584726,0.007897047,0.00083085836,0.0024839551,0.00019569082,0.00002015099,0.000016860631,0.00008665504],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967177,0.00085253915,0.0005565479,0.00018349655,0.0012650092,0.0004247236],"domain_scores_gemma":[0.9963296,0.000052462296,0.00043162907,0.00016035073,0.002356039,0.0006698974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014063448,0.00012394482,0.00021191349,0.00021064903,0.00071747374,0.0002725004,0.00027615504,0.00013839883,0.00064449443],"category_scores_gemma":[0.0022221461,0.00011198632,0.00012327784,0.00054033834,0.0001321713,0.00031996204,0.00000839032,0.00015158532,0.00011007932],"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":[0.000013210725,0.000035775636,0.0027836843,0.000019315361,0.000050992043,0.0000043541013,0.22107375,0.000081015656,0.000029444123,0.0009515199,0.09866008,0.67629683],"study_design_scores_gemma":[0.0009458684,0.0006064266,0.038048442,0.00070364936,0.00037341675,0.000015957285,0.024401035,0.001044224,0.00002808694,0.01825214,0.9151796,0.00040111472],"about_ca_topic_score_codex":0.023099229,"about_ca_topic_score_gemma":0.19047804,"teacher_disagreement_score":0.81651956,"about_ca_system_score_codex":0.0015035936,"about_ca_system_score_gemma":0.0058731227,"threshold_uncertainty_score":0.99976265},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97084963,0.008205653,0.00029771062,0.0115183415,0.0013242501,0.00054479874,0.000005628532,0.000015061172,0.0072389063],"genre_scores_gemma":[0.9932495,0.0003915466,0.0027850787,0.00010514777,0.0014906509,0.00002281379,0.0000012417518,0.000013639455,0.0019404168],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996132,0.0013591747,0.0004153403,0.0001988294,0.0010212731,0.00087338395],"domain_scores_gemma":[0.9964438,0.00017613314,0.0005595428,0.00013152625,0.0014120665,0.0012769115],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.007706408,0.00015980167,0.0002053464,0.000108923196,0.0017471068,0.00031952735,0.0005394854,0.00024870268,0.00040411047],"category_scores_gemma":[0.0027779748,0.00015165916,0.0001661655,0.0008999015,0.0041519115,0.0007613963,0.000017480561,0.0003164349,0.0000190967],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000012302172,0.000073950185,0.12294945,0.0000141185665,0.000014977501,0.00003337396,0.12818016,0.000031787793,0.000023044102,0.0007248389,0.009608702,0.7383333],"study_design_scores_gemma":[0.00041327416,0.00083140866,0.30860248,0.00044188023,0.00009386807,0.00016124659,0.0074456455,0.00411962,0.00006766202,0.0028193444,0.6748057,0.00019789055],"about_ca_topic_score_codex":0.89789236,"about_ca_topic_score_gemma":0.958459,"teacher_disagreement_score":0.7381354,"about_ca_system_score_codex":0.0051400736,"about_ca_system_score_gemma":0.043723214,"threshold_uncertainty_score":0.9995525},"labels":[],"label_agreement":null},{"id":"W2797491711","doi":"10.3138/cjpe.43180","title":"Expenditure Reviews and the Federal Experience: Program Evaluation and Its Contribution to Assurance Provision","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Function (biology); Business; Accounting; Public administration; Administration (probate law); Focus (optics); Public relations; Finance; Political science; Law","score_opus":0.2778351949623966,"score_gpt":0.5486718860554921,"score_spread":0.2708366910930955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797491711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.963474,0.0079164,0.0011068695,0.009961411,0.0014121142,0.015356447,0.000006611026,0.000017093593,0.00074906833],"genre_scores_gemma":[0.99546856,0.0001309349,0.0018563187,0.0005386712,0.00046573524,0.0014400651,0.00001168716,0.000008680671,0.00007934491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936644,0.001841773,0.0011515532,0.00035983755,0.0026424094,0.0003400538],"domain_scores_gemma":[0.99212295,0.00029600444,0.0008908103,0.0002944941,0.005869351,0.00052640314],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036498778,0.00018565216,0.0003792477,0.00037259576,0.00076191954,0.001068776,0.00036651018,0.00010553317,0.0007422859],"category_scores_gemma":[0.012842332,0.00010921902,0.00008890064,0.0007231594,0.0002756966,0.0010186115,0.000029845274,0.00021200208,0.00005719603],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102972655,0.000025597783,0.0036186562,0.0000055809433,0.0000117947875,7.061192e-7,0.0045437636,0.000053702064,0.00008176782,0.000510277,0.0026106075,0.98843455],"study_design_scores_gemma":[0.0073798196,0.0028977194,0.14882688,0.00038596528,0.00023501922,0.00016120079,0.003049907,0.31502858,0.0005540017,0.008502748,0.5125342,0.00044397902],"about_ca_topic_score_codex":0.00010977349,"about_ca_topic_score_gemma":0.0071976576,"teacher_disagreement_score":0.9879906,"about_ca_system_score_codex":0.00029401804,"about_ca_system_score_gemma":0.001968665,"threshold_uncertainty_score":0.99996823},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18407509,0.05766507,0.00091787736,0.013249926,0.008174929,0.00096703274,0.00012961736,0.000022289581,0.7347982],"genre_scores_gemma":[0.9839501,0.00014234566,0.0013413194,0.00021424955,0.011154443,0.000008770935,0.000011095383,0.000020275304,0.0031573947],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833846,0.00040993496,0.00041554426,0.00010650192,0.00036559207,0.00036395065],"domain_scores_gemma":[0.9964736,0.00009209455,0.00036816543,0.00013175055,0.0023525443,0.0005818561],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032152543,0.00012805813,0.00018466116,0.00035476443,0.00054757914,0.00077843474,0.00018284908,0.00011264752,0.010411143],"category_scores_gemma":[0.0009870362,0.0001236415,0.00017524936,0.00012789616,0.00070286077,0.00016770093,0.0000054687966,0.0002342628,0.00008651209],"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":[0.000012649467,0.00014624327,0.0012901517,0.000028046608,0.0003915749,0.00010786413,0.010578297,0.00010595668,0.0000047419835,0.3364197,0.018083297,0.63283145],"study_design_scores_gemma":[0.0004648803,0.000546443,0.0015459652,0.00011986147,0.0014936975,0.000067431385,0.0015366926,0.011952746,0.00003524284,0.030893652,0.9511872,0.00015618553],"about_ca_topic_score_codex":0.025262361,"about_ca_topic_score_gemma":0.052095737,"teacher_disagreement_score":0.9331039,"about_ca_system_score_codex":0.00046038712,"about_ca_system_score_gemma":0.004001158,"threshold_uncertainty_score":0.9904935},"labels":[],"label_agreement":null},{"id":"W2797550683","doi":"10.3138/cjpe.43179","title":"Strategic Evaluation Utilization in the Canadian Federal Government","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; École Nationale d'Administration Publique","funders":"","keywords":"Government (linguistics); Focus group; Program evaluation; Function (biology); Business; Public relations; Public policy; Content analysis; Key (lock); Qualitative research; Psychology; Marketing; Public administration; Political science; Sociology; Computer science","score_opus":0.6515255366463052,"score_gpt":0.5637168640848468,"score_spread":0.08780867256145841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797550683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91871685,0.00038755045,0.0002614475,0.009375454,0.0018030719,0.0029878246,0.000014139971,0.000006041015,0.066447645],"genre_scores_gemma":[0.998169,0.000004466714,0.00046074478,0.0007203966,0.0004412351,0.00010479941,0.00002210994,0.000008203179,0.00006903651],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990897,0.0016413016,0.00100835,0.00023338037,0.0058206157,0.00039936256],"domain_scores_gemma":[0.994249,0.00017290992,0.00060809916,0.00035802968,0.0041712136,0.0004407681],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.044159926,0.00013885184,0.0001792468,0.00060438324,0.00061701436,0.0011590645,0.0006729854,0.00010938925,0.0045465464],"category_scores_gemma":[0.0025493717,0.00009433388,0.000086693195,0.0013224176,0.00014919092,0.00069425703,0.0000067752353,0.0002468108,0.00013660223],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001898322,0.00005286507,0.050530616,0.000002223284,0.000017890485,0.000006681161,0.0041386806,0.002318686,0.000012724437,0.003154253,0.0053432933,0.9344031],"study_design_scores_gemma":[0.0017248044,0.0010806263,0.45951247,0.000054734617,0.00010096508,0.000056658584,0.0099863,0.42540658,0.00005872124,0.047508426,0.054271072,0.00023863462],"about_ca_topic_score_codex":0.049120218,"about_ca_topic_score_gemma":0.98032767,"teacher_disagreement_score":0.93416446,"about_ca_system_score_codex":0.0025127514,"about_ca_system_score_gemma":0.017308533,"threshold_uncertainty_score":0.9998778},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69825196,0.14451186,0.000056450564,0.0038405282,0.0015427528,0.0028089022,0.00002890147,0.0000056941644,0.14895296],"genre_scores_gemma":[0.9992001,0.0002776191,0.00017099049,0.0000813764,0.00021560377,0.00003219826,0.0000041062412,0.0000069943503,0.000011005126],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987258,0.000079929574,0.000828825,0.00009676257,0.000073063835,0.00019562356],"domain_scores_gemma":[0.9987491,0.000041012587,0.00071684294,0.00014341832,0.0002360273,0.000113650865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008460389,0.00006234991,0.00020970343,0.000257607,0.00008950214,0.000041966825,0.00016217533,0.00004433013,0.00035731052],"category_scores_gemma":[0.0012272161,0.00005742947,0.00007706982,0.00024656134,0.00009310763,0.00021087487,0.000005569586,0.00010415289,0.000063292566],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012943872,0.000031531625,0.106453136,0.000060688948,0.000051972143,8.3996184e-7,0.0007533815,0.000045740548,0.000008540369,0.06995996,0.0014192489,0.82120204],"study_design_scores_gemma":[0.00096780714,0.00042546008,0.18065897,0.00059481274,0.000067109286,0.000024340556,0.00024203476,0.042740412,0.00014064592,0.65866375,0.11528411,0.0001905538],"about_ca_topic_score_codex":0.0012615228,"about_ca_topic_score_gemma":0.011758829,"teacher_disagreement_score":0.8210115,"about_ca_system_score_codex":0.00039542763,"about_ca_system_score_gemma":0.000392016,"threshold_uncertainty_score":0.65617025},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7918113,0.19514857,0.00019745994,0.0010089371,0.00058470207,0.0011925069,0.0000120854775,0.000006913096,0.010037547],"genre_scores_gemma":[0.9935455,0.0044886232,0.0011164343,0.00005449621,0.0006994101,0.000038432936,0.0000074709783,0.00001213665,0.000037520753],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99874306,0.00008141695,0.00067596475,0.00021680277,0.0000616653,0.00022111394],"domain_scores_gemma":[0.99860245,0.00002657943,0.00076324627,0.0001334449,0.00024519186,0.00022909326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068071466,0.000111450296,0.000351133,0.00052000186,0.0001835796,0.00014374645,0.000093341696,0.00008618071,0.00021602745],"category_scores_gemma":[0.0007213068,0.00012363309,0.00006912321,0.00014160591,0.00010463637,0.0003870042,0.000008711316,0.000115857656,0.000055458393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055392,0.000014292296,0.04266453,0.00005444081,0.000060300405,0.0000013779337,0.0041084536,0.000010397397,0.0000045023776,0.019937478,0.00014463752,0.93299407],"study_design_scores_gemma":[0.0022320296,0.0011845054,0.517819,0.00054757966,0.00044869215,0.00011897787,0.0005295343,0.047129042,0.00005509749,0.21272165,0.21654586,0.00066803186],"about_ca_topic_score_codex":0.0006305258,"about_ca_topic_score_gemma":0.017541632,"teacher_disagreement_score":0.932326,"about_ca_system_score_codex":0.00026747276,"about_ca_system_score_gemma":0.00022589884,"threshold_uncertainty_score":0.97886425},"labels":[],"label_agreement":null},{"id":"W2798137084","doi":"10.3138/cjpe.43184","title":"Sunshine, Scrutiny, and Spending Review in Canada, Trudeau to Trudeau: From Program Evaluation and Policy to Commitment and Results","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Victoria","funders":"","keywords":"Scrutiny; Cabinet (room); Government (linguistics); Public administration; Public relations; Political science; Adaptation (eye); Public policy; Psychology; Law","score_opus":0.3498588876004434,"score_gpt":0.5499745996534898,"score_spread":0.2001157120530464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798137084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.954098,0.006808052,0.000072986564,0.030617349,0.0004389597,0.006806308,0.000071833165,0.000007583,0.0010789542],"genre_scores_gemma":[0.9905923,0.00029702342,0.0066248532,0.0018214693,0.00025608373,0.0003338271,0.000029577339,0.000012141395,0.000032751268],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.994385,0.00090254896,0.0014427624,0.0004395051,0.0024426868,0.00038749244],"domain_scores_gemma":[0.9956627,0.0003400702,0.00061452907,0.00032405864,0.0019621584,0.0010965199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01985883,0.00020551888,0.00048860017,0.0008552792,0.00023300853,0.00046772332,0.00029031714,0.000058468668,0.00047213212],"category_scores_gemma":[0.0072314753,0.00016198198,0.00004441044,0.0012630792,0.00008882903,0.0004522527,0.000048082384,0.00017790117,0.000010908838],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045518424,0.0000194658,0.03002815,0.000014102676,0.000042101674,0.0000033471078,0.0011365082,0.00011176697,0.000008516773,0.00007984013,0.004807351,0.96370333],"study_design_scores_gemma":[0.0021680577,0.0014199454,0.85272217,0.00071825396,0.00044017512,0.000038186772,0.0011336348,0.028520094,0.000033288823,0.002998393,0.109511614,0.0002961926],"about_ca_topic_score_codex":0.5291579,"about_ca_topic_score_gemma":0.98953867,"teacher_disagreement_score":0.96340716,"about_ca_system_score_codex":0.0014900164,"about_ca_system_score_gemma":0.008792443,"threshold_uncertainty_score":0.99682677},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97652644,0.004512383,0.0045996257,0.0024145967,0.0026870403,0.0014641546,0.0000042665783,0.0000100788875,0.0077813854],"genre_scores_gemma":[0.99407065,0.000037806425,0.0040219645,0.00007447038,0.0014020113,0.000029429775,0.0000020991167,0.000012167865,0.00034939006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97701114,0.002449771,0.0012602234,0.00041179423,0.01781584,0.0010512369],"domain_scores_gemma":[0.9448,0.0029591348,0.0005899289,0.0005033102,0.049523648,0.0016239565],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.29379565,0.00010802416,0.00024356083,0.054222804,0.000815444,0.0023955686,0.0024940083,0.00021799734,0.0022775638],"category_scores_gemma":[0.1838205,0.00007924805,0.0001336375,0.11574809,0.00064622494,0.0008133421,0.000110195964,0.0011714823,0.0003271445],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012741972,0.000014997523,0.02301316,8.175188e-7,0.000010017812,0.000006735338,0.0002449949,0.0005092912,0.00008613408,0.00023154373,0.020177541,0.95569205],"study_design_scores_gemma":[0.0010483181,0.0036163873,0.13800114,0.000067668814,0.000033672855,0.00009098042,0.0010699206,0.71032447,0.00025434117,0.046627134,0.098645724,0.00022023123],"about_ca_topic_score_codex":0.00081879756,"about_ca_topic_score_gemma":0.0035841395,"teacher_disagreement_score":0.9554718,"about_ca_system_score_codex":0.000794105,"about_ca_system_score_gemma":0.00760428,"threshold_uncertainty_score":0.99864006},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99134004,0.0003030781,0.0014360537,0.00059275737,0.0010824323,0.0013466878,0.00004374403,0.00001921501,0.003835999],"genre_scores_gemma":[0.9504638,0.00001752898,0.048899647,0.00012693828,0.00033425773,0.00007966548,0.00003558159,0.000022893484,0.000019736623],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984139,0.00013053133,0.0006778764,0.00011491386,0.00011404957,0.0005487022],"domain_scores_gemma":[0.9973308,0.00007008211,0.0005614459,0.00024481074,0.0010788513,0.00071401394],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0067417175,0.00015290917,0.00032226925,0.0010726885,0.0013181721,0.0003642167,0.0004890949,0.00014031169,0.000112936905],"category_scores_gemma":[0.0004327481,0.0001828838,0.00013325812,0.0007509337,0.000110103385,0.00045939395,0.0000152504535,0.0004724561,0.00001782322],"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":[0.000011740574,0.00017890001,0.31743267,0.000073899035,0.00030849554,0.0000018539818,0.00938173,0.000015883346,0.000010099892,0.012085438,0.002465701,0.6580336],"study_design_scores_gemma":[0.0029440105,0.0035107152,0.5045697,0.00019565482,0.00020231608,0.000053128868,0.0018889881,0.03382336,0.00012995207,0.040255014,0.41148803,0.000939088],"about_ca_topic_score_codex":0.18278927,"about_ca_topic_score_gemma":0.6323521,"teacher_disagreement_score":0.65709454,"about_ca_system_score_codex":0.0031700798,"about_ca_system_score_gemma":0.0035965412,"threshold_uncertainty_score":0.999982},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7696489,0.000009011195,0.00096979446,0.0006982738,0.001959623,0.22578375,0.00041210584,0.000021067995,0.000497471],"genre_scores_gemma":[0.7956596,5.988787e-7,0.0059746574,0.002620347,0.00105391,0.19416286,0.00047579804,0.000030318814,0.000021918175],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9937028,0.001704629,0.0017988908,0.00037999067,0.0012713609,0.0011423095],"domain_scores_gemma":[0.99090207,0.00080222375,0.001164087,0.00032646093,0.0040224753,0.002782702],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006823067,0.00028910773,0.00040858897,0.00050694944,0.0011539963,0.000076005395,0.00028125345,0.0001553134,0.0008288723],"category_scores_gemma":[0.003190416,0.00026136372,0.00010522838,0.0003146979,0.00013292236,0.0003044315,0.000029783458,0.0003362136,0.00013925241],"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":[0.0045586154,0.00093699835,0.3832102,0.0012598337,0.00041987764,0.000010138777,0.40031126,0.0014684353,0.0001772292,0.0003592864,0.0120876385,0.19520049],"study_design_scores_gemma":[0.077983215,0.07817028,0.20044583,0.03295233,0.0028176543,0.000027546534,0.33162984,0.11975343,0.00407983,0.012779082,0.13583237,0.0035285945],"about_ca_topic_score_codex":0.02853646,"about_ca_topic_score_gemma":0.5930584,"teacher_disagreement_score":0.56452197,"about_ca_system_score_codex":0.0035943647,"about_ca_system_score_gemma":0.024275616,"threshold_uncertainty_score":0.99998385},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9814614,0.00006005354,0.00045408265,0.012980948,0.00024455003,0.0046536317,0.000022141732,0.000004982113,0.00011820583],"genre_scores_gemma":[0.98845065,0.00000330115,0.009883733,0.001316025,0.00009234478,0.00022880177,0.000006267104,0.00001218901,0.00000669755],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9912252,0.0051757107,0.0020353477,0.00017742909,0.0008386836,0.0005476659],"domain_scores_gemma":[0.9910652,0.0021788697,0.0034326776,0.00023646568,0.0027623526,0.00032443923],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041211233,0.00010894009,0.00029909646,0.0004380851,0.00074323936,0.000044193523,0.00023315896,0.00007378159,0.000028410921],"category_scores_gemma":[0.042392556,0.000071057366,0.00004753762,0.0013155682,0.00013937555,0.0008519742,0.000018473373,0.00038782315,0.0000012144005],"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":[0.0000090131225,0.000030288935,0.67368394,0.00012384912,0.00001292721,2.3521071e-8,0.06047723,0.00018925186,0.000015006065,0.00011365543,0.00006621069,0.26527864],"study_design_scores_gemma":[0.0007226595,0.00046012338,0.9582166,0.00017668864,0.00005569982,0.0000021151666,0.0075994274,0.031112457,0.000010684042,0.0003693917,0.001204266,0.00006987342],"about_ca_topic_score_codex":0.007620018,"about_ca_topic_score_gemma":0.04540193,"teacher_disagreement_score":0.2845327,"about_ca_system_score_codex":0.00051123626,"about_ca_system_score_gemma":0.009714579,"threshold_uncertainty_score":0.99898833},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9286395,0.0006387416,0.0072226855,0.039576635,0.0023220575,0.0008803264,0.0000073082642,0.000032869324,0.020679934],"genre_scores_gemma":[0.98695487,0.000024210945,0.010564113,0.00037134255,0.0015370821,0.000015243794,6.8908565e-7,0.000005494087,0.00052692834],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980525,0.0006561132,0.00022216387,0.000107949796,0.0005363062,0.00042500137],"domain_scores_gemma":[0.9982867,0.00008021652,0.00027287923,0.000078374076,0.000780489,0.00050130807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067746323,0.00006734696,0.000108965505,0.000075436554,0.000531027,0.00018743658,0.0003465922,0.00010755224,0.0007345759],"category_scores_gemma":[0.0019982082,0.00005770485,0.00007963619,0.0003479315,0.0004653907,0.00027488775,0.0000064287874,0.00013299668,0.000026127265],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007252619,0.000021577729,0.037386302,0.0000014484195,0.00001630012,0.000011257569,0.021498445,0.000011196791,0.000031274445,0.00421602,0.009187879,0.92761105],"study_design_scores_gemma":[0.0008616004,0.00084027485,0.44308707,0.000084018015,0.00013575926,0.000026751914,0.023598488,0.0014784362,0.00023235763,0.11670781,0.4125722,0.00037523042],"about_ca_topic_score_codex":0.042750046,"about_ca_topic_score_gemma":0.52931994,"teacher_disagreement_score":0.92723584,"about_ca_system_score_codex":0.00065053714,"about_ca_system_score_gemma":0.007843762,"threshold_uncertainty_score":0.99778086},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98263234,0.00035471717,0.00067028636,0.0063231895,0.0018611462,0.006852294,0.000019129346,0.000023516892,0.0012633785],"genre_scores_gemma":[0.955987,0.000003765805,0.04223915,0.00022803483,0.001004576,0.00024620848,0.00025931324,0.000017558894,0.000014440956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99625957,0.000514124,0.0011506148,0.00027008454,0.0015018752,0.00030373957],"domain_scores_gemma":[0.9880922,0.00011107055,0.0010177497,0.0009097309,0.009636086,0.00023320752],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01629071,0.00014640177,0.0002879986,0.00031569085,0.00027653296,0.000082326726,0.00044063185,0.00014895595,0.00046051716],"category_scores_gemma":[0.018986152,0.00010568301,0.00007632082,0.00094133546,0.0009882684,0.00037996884,0.000028736611,0.00030517482,0.000008260369],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041591422,0.00013808376,0.008356509,0.000057187972,0.00006132885,9.4380636e-7,0.00074454804,0.000016071011,0.0005427998,0.00014634976,0.003925213,0.98596936],"study_design_scores_gemma":[0.008073479,0.0074139503,0.19493647,0.0012520283,0.0036622947,0.00052331126,0.008519897,0.705319,0.0053799194,0.008015725,0.05632451,0.0005794428],"about_ca_topic_score_codex":0.0006161238,"about_ca_topic_score_gemma":0.0026950198,"teacher_disagreement_score":0.98538995,"about_ca_system_score_codex":0.0006406739,"about_ca_system_score_gemma":0.008701171,"threshold_uncertainty_score":0.99691856},"labels":[],"label_agreement":null},{"id":"W2810759134","doi":"10.3138/cjpe.33.1.171","title":"Hallie Preskill and Darlene Russ-Eft. (2016). <i>Building Evaluation Capacity: Activities for Teaching and Training</i> . 2nd ed.","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Sociology; Physics","score_opus":0.41552976865334557,"score_gpt":0.5066036827221413,"score_spread":0.09107391406879572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810759134","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98489696,0.0010985237,0.0068154344,0.0021315473,0.0009715791,0.0018865152,0.000022173928,0.000012312132,0.002164947],"genre_scores_gemma":[0.9724831,0.00002903265,0.026318451,0.0002464341,0.0006517839,0.00013648655,0.000010207149,0.000017011329,0.00010750128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99547756,0.00092143903,0.0008644582,0.00034764508,0.0020064295,0.0003824472],"domain_scores_gemma":[0.99514854,0.00078928634,0.0008246227,0.00024324161,0.0025093406,0.00048498382],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04072903,0.00018424231,0.00032070107,0.00063409784,0.0008565719,0.00083603046,0.00026620584,0.00011634035,0.00048473064],"category_scores_gemma":[0.007307568,0.00015075042,0.00008303573,0.00022504399,0.00035899755,0.0014889393,0.000020020185,0.00028285556,0.0000041013786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030283485,0.000019617597,0.0021137912,0.000009356621,0.000040239975,4.4495678e-7,0.0077104876,0.00016593415,0.0003830463,0.0007895817,0.0029318137,0.9858054],"study_design_scores_gemma":[0.0063037467,0.003913138,0.049012747,0.0004926115,0.0008389927,0.00025892406,0.018221028,0.55820525,0.0010381668,0.08966454,0.27127668,0.00077416043],"about_ca_topic_score_codex":0.00039047835,"about_ca_topic_score_gemma":0.009109433,"teacher_disagreement_score":0.98503125,"about_ca_system_score_codex":0.00032574695,"about_ca_system_score_gemma":0.0034114087,"threshold_uncertainty_score":0.98777133},"labels":[],"label_agreement":null},{"id":"W2810879288","doi":"10.3138/cjpe.42116","title":"Using Logic Models and the Action Model/Change Model Schema in Planning the Learning Community Program: A Comparative Case Study","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Schema (genetic algorithms); Logic model; Computer science; Strengths and weaknesses; Logic program; Management science; Action (physics); Theory of change; Artificial intelligence; Process management; Knowledge management; Data science; Machine learning; Psychology; Logic programming; Sociology; Engineering; Social psychology","score_opus":0.9477306850220157,"score_gpt":0.6849694826574051,"score_spread":0.26276120236461065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810879288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9817613,0.00019929184,0.014129663,0.00060431194,0.00010896921,0.0028175893,0.000001086136,0.0000086177715,0.00036920587],"genre_scores_gemma":[0.9954032,0.000002377586,0.004129612,0.00013336804,0.00008724578,0.00022249369,0.0000016990567,0.00000727399,0.000012731555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943299,0.0032848977,0.0007350776,0.00016159206,0.0012321825,0.00025634965],"domain_scores_gemma":[0.9965197,0.00044875074,0.00069037464,0.00028154455,0.0018853834,0.00017427639],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.029921554,0.00014074324,0.00027798425,0.0004101466,0.0014334745,0.00058870995,0.0003645508,0.00006162608,0.00002844396],"category_scores_gemma":[0.0006666227,0.000077723606,0.00006168794,0.0007302986,0.00038942217,0.0010652675,0.000042600357,0.0007604981,0.0000020735101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007665419,0.00010682781,0.007909619,0.0000023815285,0.000025416728,0.000011292352,0.1150244,0.7675112,0.0000040564146,0.00021341098,0.000030480685,0.109084286],"study_design_scores_gemma":[0.0014612635,0.00054872857,0.0013274628,0.00003576399,0.00007681399,0.0002449971,0.09261434,0.891412,0.0000027021988,0.012160245,0.000035452143,0.00008021186],"about_ca_topic_score_codex":0.007919003,"about_ca_topic_score_gemma":0.11437771,"teacher_disagreement_score":0.12390085,"about_ca_system_score_codex":0.00030883652,"about_ca_system_score_gemma":0.0014232375,"threshold_uncertainty_score":0.99986655},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97245294,0.0012794941,0.00010937299,0.00050011266,0.00020802938,0.0011527891,0.0000015537528,0.000005381073,0.024290312],"genre_scores_gemma":[0.9978719,0.000011991628,0.0018497616,0.000023272445,0.00018120672,0.00004695659,9.574414e-7,0.00000726147,0.000006697115],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99564254,0.0022300163,0.0004003947,0.00011848295,0.0012515195,0.0003570432],"domain_scores_gemma":[0.99677527,0.0004787457,0.00049551093,0.0001008171,0.0019073905,0.0002422424],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03230811,0.00007021766,0.0001246911,0.00039505088,0.0003692464,0.00038707306,0.00014501551,0.000052026404,0.0001467658],"category_scores_gemma":[0.020564286,0.000059287082,0.000044459597,0.00064518163,0.0006538678,0.0010693879,0.000013658294,0.00019768033,0.0000019247698],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027624299,0.000030793628,0.07030805,0.0000041241015,0.000032605218,0.000004289312,0.07106406,0.000017045862,0.00045590717,0.0005884303,0.000026001886,0.85744107],"study_design_scores_gemma":[0.00443378,0.0025947304,0.10182411,0.0011460019,0.0010356819,0.00012127483,0.5633338,0.08467016,0.0052795825,0.10332368,0.13146165,0.0007755229],"about_ca_topic_score_codex":0.004389246,"about_ca_topic_score_gemma":0.029917112,"teacher_disagreement_score":0.85666555,"about_ca_system_score_codex":0.00037087998,"about_ca_system_score_gemma":0.0032865156,"threshold_uncertainty_score":0.99644244},"labels":[],"label_agreement":null},{"id":"W2811284056","doi":"10.3138/cjpe.33.1.168","title":"Colin Robson. (2017). <i>Small-Scale Evaluation: Principles and Practice</i> . 2nd ed.","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Waterloo","funders":"","keywords":"Scale (ratio); Psychology; Sociology; Applied psychology; Psychoanalysis; Geography; Cartography","score_opus":0.4912241652614992,"score_gpt":0.5469421384034869,"score_spread":0.05571797314198773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811284056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8887343,0.006920687,0.0043371245,0.02406544,0.0044455905,0.0053121136,0.000027681492,0.000037229474,0.06611983],"genre_scores_gemma":[0.9730451,0.00009546449,0.024455061,0.000849152,0.00097576855,0.0001239315,0.000016662972,0.000017334138,0.00042153415],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99289495,0.001621646,0.001250312,0.0003604044,0.0034917619,0.00038089894],"domain_scores_gemma":[0.98466134,0.00079579995,0.001312239,0.0004539389,0.012053107,0.00072356354],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05080273,0.00018134424,0.00029737764,0.0005497739,0.0005145842,0.00089528423,0.00050370954,0.00013185332,0.0045615905],"category_scores_gemma":[0.015495425,0.00014539731,0.00009852074,0.00074165856,0.00033387155,0.0016240836,0.000032317217,0.00024833623,0.00019116346],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008033689,0.00007703857,0.010419814,0.0000056854033,0.00005331878,0.0000063074544,0.0026323427,0.0009693421,0.000080880134,0.00051009667,0.018974837,0.96619],"study_design_scores_gemma":[0.0022843245,0.0015562455,0.08029883,0.00009794321,0.0004285792,0.0004768852,0.0039356346,0.15209009,0.00019604294,0.0066832486,0.7516378,0.000314348],"about_ca_topic_score_codex":0.000401122,"about_ca_topic_score_gemma":0.03967019,"teacher_disagreement_score":0.9658756,"about_ca_system_score_codex":0.0004675948,"about_ca_system_score_gemma":0.008665908,"threshold_uncertainty_score":0.996954},"labels":[],"label_agreement":null},{"id":"W281362470","doi":"10.3138/cjpe.23.004","title":"Challenges in Applying Indigenous Evaluation Practices in Mainstream Grant Programs to Indigenous Communities","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Mainstream; Government (linguistics); Substance abuse prevention; Competence (human resources); Cultural competence; Traditional knowledge; Political science; Culturally appropriate; Public relations; Substance use; Sociology; Psychology; Medicine; Pedagogy; Gerontology; Social psychology","score_opus":0.6836246640574786,"score_gpt":0.5359148392352847,"score_spread":0.14770982482219386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W281362470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874831,0.003014898,0.000053148,0.0011996025,0.000467846,0.0053914245,0.000003227307,0.000012009694,0.0023747478],"genre_scores_gemma":[0.99566954,0.00039184786,0.002439309,0.00012468305,0.000116357514,0.0011869711,0.00003243436,0.000018866305,0.00001998828],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990861,0.0023435503,0.0016722241,0.00031553773,0.004174825,0.0006328358],"domain_scores_gemma":[0.993859,0.00045303363,0.0016524073,0.0005076333,0.0030332222,0.00049469015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041886877,0.00022860302,0.00045645054,0.0028721574,0.00042561057,0.00036328787,0.00085173553,0.00015545532,0.00030928114],"category_scores_gemma":[0.0034687035,0.00019820184,0.000105307365,0.0018952156,0.00012316594,0.0013000737,0.000029974368,0.0005348659,0.000062017585],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029644563,0.00018659937,0.20170644,0.0000075378057,0.0000137263505,0.000026981354,0.06978314,0.006109251,0.0000058644982,0.000025210951,0.000023555047,0.722082],"study_design_scores_gemma":[0.0028897785,0.0019354913,0.86680204,0.00034294525,0.0000798074,0.00040500044,0.08073063,0.029028755,0.000037726026,0.004880816,0.01242668,0.000440351],"about_ca_topic_score_codex":0.0118608,"about_ca_topic_score_gemma":0.63693124,"teacher_disagreement_score":0.7216417,"about_ca_system_score_codex":0.0015564553,"about_ca_system_score_gemma":0.010329314,"threshold_uncertainty_score":0.9952812},"labels":[],"label_agreement":null},{"id":"W285975702","doi":"10.3138/cjpe.23.005","title":"Using Technology to Enhance Aboriginal Evaluations","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Focus (optics); Sociology; Data collection; Knowledge management; Engineering ethics; Computer science; Social science; Engineering; History; Archaeology","score_opus":0.4108376583250716,"score_gpt":0.6419507109411706,"score_spread":0.23111305261609905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W285975702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97145474,0.00036759186,0.019411402,0.0047402983,0.0010171836,0.0010814486,0.0000054993443,0.000015170038,0.001906652],"genre_scores_gemma":[0.9571604,0.000009700276,0.04210057,0.00025043444,0.0002100486,0.00006191687,0.0000031189327,0.000009944887,0.00019387783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99532825,0.00037170865,0.0010133714,0.00024929104,0.0026911928,0.00034618884],"domain_scores_gemma":[0.991846,0.0001318697,0.0006001761,0.00038039987,0.006469931,0.0005716277],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010592289,0.00012916709,0.0002538125,0.002035391,0.0004956335,0.00016683611,0.0005983008,0.00009900635,0.002402062],"category_scores_gemma":[0.0034544477,0.00010809454,0.00010209737,0.0026721566,0.0001445196,0.0006140793,0.000010768164,0.00023183001,0.00027697138],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000175076,0.000060667746,0.06388902,0.0000019500783,0.000030090925,0.00002109441,0.0018842606,0.025485653,0.00096392183,0.0009238864,0.004424878,0.9022971],"study_design_scores_gemma":[0.0018077698,0.0023494011,0.18278107,0.00018318782,0.00029851694,0.0013976241,0.0030588023,0.23724146,0.005465108,0.036098067,0.5285443,0.0007746545],"about_ca_topic_score_codex":0.00040374586,"about_ca_topic_score_gemma":0.009029506,"teacher_disagreement_score":0.9015224,"about_ca_system_score_codex":0.00066717196,"about_ca_system_score_gemma":0.01418327,"threshold_uncertainty_score":0.9985099},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W286621326","doi":"10.3138/cjpe.017.002","title":"A Peer Support Approach to Evaluation: Assessing Supported Employment Programs for People with Developmental Disabilities","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Agency (philosophy); Peer support; Psychology; Peer review; Medical education; Applied psychology; Knowledge management; Computer science; Sociology; Political science; Medicine","score_opus":0.4885163999449404,"score_gpt":0.4936480799662604,"score_spread":0.005131680021320029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W286621326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9295927,0.0001825192,0.016632583,0.00954464,0.0010729538,0.012963536,0.000031365355,0.00004561225,0.029934071],"genre_scores_gemma":[0.9410963,0.0000010206213,0.054942477,0.00022250577,0.0001885235,0.0017841096,0.00013630878,0.000026608577,0.001602159],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99060816,0.00049618806,0.0013423471,0.00045408128,0.0065270094,0.00057220605],"domain_scores_gemma":[0.9871219,0.00027811623,0.0006515754,0.0003337563,0.010770808,0.0008438645],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023960588,0.00025285684,0.00043172072,0.0007340269,0.00045825244,0.0014151711,0.00054644747,0.00009470644,0.0054486683],"category_scores_gemma":[0.0048733843,0.00018508629,0.00016334365,0.0013047126,0.00012026534,0.0012767116,0.000019114634,0.00017873428,0.000096883516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033046912,0.00031466727,0.0714994,0.00001370759,0.00007680376,0.000001178943,0.0146707045,0.0025432997,0.000009170708,0.00012183259,0.021994794,0.8887214],"study_design_scores_gemma":[0.0076958532,0.0050624446,0.15464248,0.00018998851,0.000826647,0.00062587013,0.087198496,0.41407746,0.00015301928,0.003992982,0.3243736,0.0011611521],"about_ca_topic_score_codex":0.0001876257,"about_ca_topic_score_gemma":0.011842891,"teacher_disagreement_score":0.88756025,"about_ca_system_score_codex":0.0013247981,"about_ca_system_score_gemma":0.006248266,"threshold_uncertainty_score":0.99962145},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9549768,0.00053669175,0.004929952,0.019825935,0.00026278073,0.001370921,0.000019719553,0.00004652606,0.0180307],"genre_scores_gemma":[0.9959994,0.00015010644,0.0029287878,0.00012349387,0.00024276922,0.00005553717,0.000034124547,0.000012669524,0.00045313765],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99694717,0.00087663427,0.0005315448,0.00021015188,0.0007747783,0.0006596924],"domain_scores_gemma":[0.9968358,0.00031605104,0.00035324262,0.00015420071,0.0015875378,0.0007531638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074154483,0.00015286544,0.00021132258,0.0004748094,0.0011088287,0.0009342321,0.00044047044,0.00015943055,0.00030801224],"category_scores_gemma":[0.0026706033,0.00014685332,0.00011462501,0.00054664497,0.001308849,0.0020343426,0.000014852866,0.00024389138,0.000019947218],"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":[0.00004848014,0.00026263852,0.07260606,0.000087454304,0.000100472374,0.000025380627,0.048306417,0.0015127934,0.00026435172,0.3151928,0.0014498931,0.5601433],"study_design_scores_gemma":[0.002923721,0.0034875341,0.55255944,0.0008587106,0.00022191399,0.00014132002,0.11592011,0.018585922,0.0039017033,0.15852287,0.14156048,0.0013162901],"about_ca_topic_score_codex":0.091477394,"about_ca_topic_score_gemma":0.78925145,"teacher_disagreement_score":0.69777405,"about_ca_system_score_codex":0.0013833918,"about_ca_system_score_gemma":0.04216092,"threshold_uncertainty_score":0.9632691},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98616886,0.0005239712,0.0034498626,0.0060681063,0.00038191373,0.00092993176,0.00002612492,0.00003411434,0.0024171318],"genre_scores_gemma":[0.9972901,0.00007957593,0.0016284878,0.00005517319,0.00045474072,0.00028731168,0.000017905275,0.000012120216,0.00017458852],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966139,0.0015693521,0.000456582,0.00017920797,0.00069908355,0.0004818689],"domain_scores_gemma":[0.9967806,0.00020709544,0.00071297336,0.000085681066,0.001880325,0.00033332335],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005590952,0.00013124618,0.00017611313,0.00012623738,0.0017568247,0.00033753974,0.00023474322,0.00013880561,0.00047560676],"category_scores_gemma":[0.0030448206,0.00012447366,0.00016266036,0.00063136104,0.0013292048,0.0008035352,0.0000067322553,0.00016674283,0.0000083454],"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":[0.000024540934,0.0001358985,0.08700706,0.000008409551,0.000055454053,0.0000015954766,0.12870426,0.000041222716,0.0001301166,0.0067098243,0.0005548119,0.7766268],"study_design_scores_gemma":[0.00083809055,0.0007642257,0.85043293,0.00032523688,0.00023589308,0.000005172526,0.08255092,0.0013386278,0.001197506,0.05571432,0.0063760066,0.00022108517],"about_ca_topic_score_codex":0.2131237,"about_ca_topic_score_gemma":0.7966925,"teacher_disagreement_score":0.7764057,"about_ca_system_score_codex":0.0007624099,"about_ca_system_score_gemma":0.00250676,"threshold_uncertainty_score":0.9995428},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91707313,0.02832693,0.0026359514,0.045014802,0.004180864,0.0007122244,0.000021775813,0.000018870802,0.0020154389],"genre_scores_gemma":[0.991597,0.00052159466,0.0011213645,0.000029238618,0.006054686,0.000028246648,0.000003673209,0.0000095370715,0.00063464907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968029,0.0013383239,0.00040562832,0.00018434488,0.0006656281,0.0006031435],"domain_scores_gemma":[0.99724346,0.00012056677,0.00045671058,0.00008653261,0.0016098733,0.00048283706],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.006221259,0.00013915516,0.00019890115,0.00010287319,0.0013524658,0.00038064082,0.0002575153,0.00021947398,0.0009316065],"category_scores_gemma":[0.0021330921,0.00012879084,0.0001481201,0.00058904587,0.0042012814,0.00090310443,0.0000057090674,0.00022475,0.000012926073],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031355117,0.00008010382,0.039322715,0.000020916943,0.000061453706,0.0000047415747,0.062136702,0.00015030247,0.00006958131,0.016138012,0.016740102,0.86524403],"study_design_scores_gemma":[0.00080871524,0.0011380931,0.39771783,0.00041199065,0.00047407407,0.00004393601,0.024969213,0.0031593218,0.0005758731,0.11091932,0.45944646,0.00033516777],"about_ca_topic_score_codex":0.08593398,"about_ca_topic_score_gemma":0.6335512,"teacher_disagreement_score":0.8649089,"about_ca_system_score_codex":0.0012618608,"about_ca_system_score_gemma":0.0042004343,"threshold_uncertainty_score":0.9999817},"labels":[],"label_agreement":null},{"id":"W2902333961","doi":"10.3138/cjpe.31156","title":"Applications of Social Network Analysis in Evaluation: Challenges, Suggestions, and Opportunities for the Future","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Social network analysis; Value (mathematics); Social network (sociolinguistics); Work (physics); Computer science; Network analysis; Data science; Coding (social sciences); Management science; Knowledge management; Sociology; World Wide Web; Engineering; Social media; Social science","score_opus":0.41063426937091085,"score_gpt":0.5169534008564959,"score_spread":0.10631913148558503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902333961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38970292,0.12976791,0.08812535,0.3430818,0.005487611,0.028525766,0.00026713006,0.0000451266,0.014996394],"genre_scores_gemma":[0.99616253,0.00030990673,0.0017310063,0.00012816994,0.0010889475,0.0004936965,0.000023659126,0.0000054396887,0.000056635945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674386,0.0006173459,0.0008363725,0.00015899219,0.0014581089,0.0001853282],"domain_scores_gemma":[0.99302846,0.00050718774,0.00074601336,0.00022539403,0.0053512105,0.00014170687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028573781,0.00008793011,0.00024377427,0.00071820075,0.00041024128,0.00014337662,0.000317808,0.00007941323,0.0007180628],"category_scores_gemma":[0.00061463774,0.00006122147,0.00012521812,0.0012306742,0.00022732149,0.00027834467,0.000010294542,0.00010994487,0.000002131532],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013599276,0.00001823754,0.0042043077,0.000003878431,0.00009982216,1.246814e-7,0.0016285463,0.001422014,4.5254282e-7,0.0074631493,0.0019193756,0.9832265],"study_design_scores_gemma":[0.0010312013,0.00038701142,0.3371518,0.000020281619,0.0012824682,0.0000072768194,0.015342525,0.21549246,0.0000031427346,0.032955617,0.39619476,0.00013146627],"about_ca_topic_score_codex":0.00009044239,"about_ca_topic_score_gemma":0.06934499,"teacher_disagreement_score":0.98309505,"about_ca_system_score_codex":0.00016176306,"about_ca_system_score_gemma":0.0030386378,"threshold_uncertainty_score":0.9903159},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038516536,0.0001349788,0.9555813,0.0026396676,0.0009773192,0.0017569937,0.000019155297,0.00006056983,0.00031347165],"genre_scores_gemma":[0.9178414,4.525484e-7,0.08146979,0.00007292143,0.00048088914,0.00004677706,0.000054236338,0.000017742455,0.000015808699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99761355,0.00013094596,0.0006877454,0.00046410938,0.0006190263,0.00048460474],"domain_scores_gemma":[0.9911451,0.00010665935,0.0005026123,0.0011177212,0.006597815,0.0005301471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004004817,0.0001761991,0.00036570057,0.00069670356,0.00043224805,0.0007524944,0.0017584387,0.00009568535,0.000081051716],"category_scores_gemma":[0.0015460801,0.00016024457,0.00015248409,0.0022309383,0.00008515903,0.00073621486,0.00012471898,0.00013539639,0.000022202867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026815338,0.00008705081,0.0382156,0.00020069961,0.0022060545,0.00005062636,0.0064493073,0.00456368,0.00002558129,0.016944457,0.0072415727,0.9239886],"study_design_scores_gemma":[0.00070974417,0.00064727606,0.016211962,0.000058014968,0.0017673927,0.00007885123,0.00081844436,0.9693715,0.00011028941,0.003856492,0.0061020246,0.0002680313],"about_ca_topic_score_codex":0.0041484945,"about_ca_topic_score_gemma":0.02010103,"teacher_disagreement_score":0.9648078,"about_ca_system_score_codex":0.0008881703,"about_ca_system_score_gemma":0.005296111,"threshold_uncertainty_score":0.99777955},"labels":[],"label_agreement":null},{"id":"W2902608297","doi":"10.3138/cjpe.42195","title":"One-Room School: The Summer Institute in Program Evaluation","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"General partnership; Medical education; Program evaluation; Community service; Service-learning; Service (business); Psychology; Sociology; Pedagogy; Political science; Public relations; Business; Medicine; Public administration; Marketing","score_opus":0.5726173863159311,"score_gpt":0.5775178005696558,"score_spread":0.004900414253724783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902608297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9569183,0.0006618337,0.0006776168,0.011977748,0.003135796,0.007272449,0.0000039621705,0.00002414537,0.019328145],"genre_scores_gemma":[0.9943823,0.000011138792,0.0037983507,0.000546677,0.0006614618,0.0004012694,0.00001871875,0.000013493477,0.00016655854],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99191654,0.001380231,0.0013880923,0.00031828592,0.004550449,0.00044639682],"domain_scores_gemma":[0.9920212,0.00018444234,0.0008788648,0.000552563,0.005845926,0.0005169774],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.043301262,0.0001686297,0.0002718938,0.0008518868,0.0003986523,0.00080015353,0.00085718906,0.0001265022,0.006005001],"category_scores_gemma":[0.0079377545,0.00011768917,0.0001378748,0.002052488,0.00032424534,0.0015062948,0.000028528377,0.00040501315,0.00047547976],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002242133,0.00009095615,0.05424099,0.0000017344258,0.000022343065,0.0000013620232,0.001035823,0.0019507059,0.00001153321,0.00023606942,0.0050763725,0.9373097],"study_design_scores_gemma":[0.0019656373,0.0011448793,0.4624439,0.00009577483,0.00016729887,0.000025418927,0.0011693275,0.22397609,0.00006966419,0.017795136,0.29091918,0.00022771144],"about_ca_topic_score_codex":0.0014360775,"about_ca_topic_score_gemma":0.22115166,"teacher_disagreement_score":0.937082,"about_ca_system_score_codex":0.0010139961,"about_ca_system_score_gemma":0.01021763,"threshold_uncertainty_score":0.9953935},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93764246,0.0006378669,0.0019340306,0.015236272,0.0019406932,0.0033394126,0.000017088214,0.000052393214,0.03919978],"genre_scores_gemma":[0.9916209,0.000054239666,0.004864999,0.0009362707,0.0012908063,0.0002984618,0.000021371989,0.000047979735,0.000864978],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9744856,0.0226123,0.0011595258,0.00025637654,0.0008414823,0.0006447228],"domain_scores_gemma":[0.991569,0.0020286727,0.0013101932,0.0003170768,0.0039921645,0.00078290806],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057525616,0.0002055098,0.00035014996,0.00042428123,0.00066476327,0.00015021022,0.00024390778,0.00048810264,0.0014438978],"category_scores_gemma":[0.011072785,0.00018299259,0.00011456151,0.00046222867,0.0001235126,0.00069001917,0.00001566179,0.001220179,0.00014203509],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012355734,0.00016177379,0.11212886,0.00037202786,0.00018987998,0.00008068544,0.038234938,0.00014966867,0.00079089904,0.0050869994,0.027018476,0.81566226],"study_design_scores_gemma":[0.0022767389,0.0010206291,0.30805138,0.0010819582,0.00035767854,0.00025921865,0.0069837314,0.0061754193,0.00013880715,0.008950576,0.6643385,0.00036530566],"about_ca_topic_score_codex":0.0077865296,"about_ca_topic_score_gemma":0.058576073,"teacher_disagreement_score":0.81529695,"about_ca_system_score_codex":0.00068530167,"about_ca_system_score_gemma":0.03202365,"threshold_uncertainty_score":0.9994689},"labels":[],"label_agreement":null},{"id":"W2902911821","doi":"10.3138/cjpe.42238","title":"Readiness in Evaluation: Three Prompts for Evaluators","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Process (computing); Tacit knowledge; Psychology; Knowledge management; Power (physics); Public relations; Process management; Computer science; Business; Sociology; Political science","score_opus":0.5904033203647878,"score_gpt":0.6029827397166689,"score_spread":0.012579419351881116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902911821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.974455,0.0006214544,0.004366106,0.0042742123,0.003394602,0.006868071,0.000014665269,0.000014090732,0.005991822],"genre_scores_gemma":[0.9922478,0.000002455108,0.006028073,0.0001818686,0.0007800759,0.000612942,0.000021829956,0.000017605775,0.00010732543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925593,0.0008169703,0.0015730489,0.00037048152,0.004219698,0.00046046352],"domain_scores_gemma":[0.9834032,0.00042138976,0.000971183,0.0004668885,0.014282627,0.00045468996],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.063497104,0.00018392658,0.00036253623,0.001427281,0.00029207984,0.00043687422,0.00071096094,0.00013516708,0.0045139906],"category_scores_gemma":[0.011495357,0.00014558913,0.00016386225,0.0016242337,0.0002010507,0.00096285314,0.000014890153,0.00018898059,0.0001271397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058497266,0.000055500383,0.053284712,0.000005511319,0.000023490213,0.0000014415118,0.0011127853,0.0012200288,0.00003359584,0.0005938663,0.0047049485,0.9389056],"study_design_scores_gemma":[0.0039932807,0.0017148533,0.2812471,0.00012298237,0.0001966492,0.00003758544,0.00090690714,0.56305295,0.0002200274,0.09448003,0.05374289,0.00028475016],"about_ca_topic_score_codex":0.0003880509,"about_ca_topic_score_gemma":0.124534816,"teacher_disagreement_score":0.93862087,"about_ca_system_score_codex":0.0009836396,"about_ca_system_score_gemma":0.013365749,"threshold_uncertainty_score":0.99683124},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9202136,0.00227352,0.000044735723,0.07439713,0.0007661675,0.0010109119,0.000012664914,0.0000037451355,0.0012775343],"genre_scores_gemma":[0.9976053,0.00012940736,0.0009142116,0.0006107385,0.00056993036,0.000042423708,0.0000051402217,0.000005009832,0.00011781147],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99837047,0.00022869551,0.0004310374,0.00010622427,0.0006481288,0.00021547482],"domain_scores_gemma":[0.9982869,0.00022086663,0.000295259,0.00007628693,0.00097033905,0.00015033824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060016485,0.00007619466,0.00008880156,0.00016542681,0.00047265447,0.00018552986,0.00038276505,0.000046940786,0.000030711166],"category_scores_gemma":[0.0020557614,0.00004323342,0.000020959658,0.00023003477,0.00032604893,0.00026780585,0.00003153313,0.00013015623,0.0000030666397],"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":[0.000095809686,0.000043264135,0.055207476,0.000015432588,0.00010401272,0.000008286113,0.36762622,0.000022859504,0.00008120037,0.009264644,0.004349423,0.5631814],"study_design_scores_gemma":[0.0008327542,0.00019853115,0.7136616,0.0006808555,0.000055090648,0.000027257147,0.0080886325,0.0012346542,0.00030525238,0.004728968,0.2699772,0.00020917784],"about_ca_topic_score_codex":0.0074194456,"about_ca_topic_score_gemma":0.13586539,"teacher_disagreement_score":0.6584541,"about_ca_system_score_codex":0.00028099836,"about_ca_system_score_gemma":0.0015513087,"threshold_uncertainty_score":0.9991902},"labels":[],"label_agreement":null},{"id":"W2903094745","doi":"10.3138/cjpe.42205","title":"L’implication des parties prenantes dans la démarche évaluative : facteurs de succès et leçons à retenir","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; École Nationale d'Administration Publique","funders":"","keywords":"Stakeholder; Thematic analysis; Key (lock); Political science; Public relations; Business; Psychology; Sociology; Knowledge management; Computer science; Qualitative research; Social science","score_opus":0.4102600005407451,"score_gpt":0.539958481627281,"score_spread":0.12969848108653592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903094745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97662634,0.0002226841,0.008569239,0.0037658336,0.0003152077,0.00087462395,0.000017138025,0.00001964352,0.009589287],"genre_scores_gemma":[0.9923123,0.00002917872,0.006955755,0.00017452195,0.00018061796,0.00011688642,0.000015913834,0.000014532102,0.00020031042],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943791,0.002193024,0.00089503796,0.00025775217,0.0018631608,0.00041193597],"domain_scores_gemma":[0.99262106,0.00071948237,0.0007717054,0.00035185856,0.005006821,0.00052908243],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027883003,0.0001595814,0.00023711976,0.00057352206,0.00045384438,0.0006168356,0.0005629035,0.000107230815,0.0010655256],"category_scores_gemma":[0.008218068,0.00012066512,0.00013537647,0.0008608154,0.00067395944,0.001044375,0.000021296759,0.0002572313,0.00008624572],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038226477,0.000060825158,0.10918338,0.0000059042472,0.00005410992,0.0000033785898,0.026036035,0.0007300276,0.0013110123,0.002643142,0.002723782,0.85721016],"study_design_scores_gemma":[0.0008858505,0.0013111995,0.8154436,0.00012308669,0.00015420669,0.0001347727,0.009967046,0.042537358,0.0045674457,0.07781396,0.046813548,0.00024797476],"about_ca_topic_score_codex":0.0008304385,"about_ca_topic_score_gemma":0.047647312,"teacher_disagreement_score":0.8569622,"about_ca_system_score_codex":0.0007755132,"about_ca_system_score_gemma":0.009789729,"threshold_uncertainty_score":0.99984765},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13989581,0.050893966,0.0019375883,0.51889354,0.02831277,0.09250122,0.00017802522,0.00031559583,0.16707145],"genre_scores_gemma":[0.94104654,0.00031862786,0.020389857,0.03167227,0.0033897806,0.0024451965,0.00012818117,0.00008852608,0.00052099774],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9899518,0.005222581,0.002061759,0.00024296215,0.0016284257,0.0008924918],"domain_scores_gemma":[0.9849317,0.0007857537,0.003020494,0.0005420085,0.009988802,0.000731236],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034709867,0.00020849028,0.0005229257,0.00040103015,0.0014983997,0.000048351903,0.0005032848,0.00021296805,0.0015687462],"category_scores_gemma":[0.0059484784,0.00015367579,0.00016211909,0.0007694952,0.0003165781,0.00058912707,0.000031489755,0.00087756355,0.00012669527],"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":[0.000055625045,0.00010148533,0.0060166297,0.00013393289,0.00008002917,0.0000023039465,0.0052883495,0.000010202379,0.0000053467006,0.0003979147,0.11202137,0.8758868],"study_design_scores_gemma":[0.001965302,0.0023633414,0.03521231,0.00034143616,0.00041406046,0.000046102425,0.0035129178,0.0010798745,0.000010338606,0.0016777378,0.9532103,0.00016625754],"about_ca_topic_score_codex":0.009100793,"about_ca_topic_score_gemma":0.03954108,"teacher_disagreement_score":0.87572056,"about_ca_system_score_codex":0.0026729126,"about_ca_system_score_gemma":0.075202934,"threshold_uncertainty_score":0.9998015},"labels":[],"label_agreement":null},{"id":"W2903255761","doi":"10.3138/cjpe.42202","title":"Où en sommes-nous avec l’implication des parties prenantes?","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Theme (computing); Value (mathematics); Selection (genetic algorithm); Process (computing); Business; Political science; Psychology; Sociology; Knowledge management; Computer science","score_opus":0.23400314505815445,"score_gpt":0.493716958982599,"score_spread":0.25971381392444454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903255761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862912,0.0005325228,0.0034401685,0.0030045772,0.0009113044,0.0009506615,0.0000066801244,0.000018967256,0.0048438804],"genre_scores_gemma":[0.9942583,0.000020173855,0.0046801423,0.0001831505,0.000528773,0.000070739276,0.0000087567105,0.000010760923,0.00023921828],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960597,0.00060031895,0.0009482897,0.0002127676,0.001801183,0.00037772144],"domain_scores_gemma":[0.9931751,0.00026352322,0.000728655,0.00036404026,0.004955831,0.0005128528],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016074164,0.00012816628,0.0002093578,0.00058068667,0.00040481574,0.00053529994,0.00053884863,0.0000858601,0.0029916372],"category_scores_gemma":[0.0048389705,0.000094982635,0.00011289928,0.0007522766,0.00029746242,0.0009388545,0.000015338575,0.00016023594,0.0003397349],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015234046,0.000037192167,0.03615075,0.0000035731994,0.0000217872,0.0000016750705,0.007449638,0.00022045741,0.0001377707,0.00041916655,0.004403139,0.9511396],"study_design_scores_gemma":[0.001708612,0.002648927,0.655597,0.00015773585,0.00019237498,0.00021637544,0.005439134,0.07684338,0.0031000064,0.075677395,0.17802893,0.00039018554],"about_ca_topic_score_codex":0.00029590502,"about_ca_topic_score_gemma":0.018703792,"teacher_disagreement_score":0.95074946,"about_ca_system_score_codex":0.00048714064,"about_ca_system_score_gemma":0.0044645364,"threshold_uncertainty_score":0.9992023},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2903412726","doi":"10.3138/cjpe.53091","title":"Chris Fox, Robert Grimm, and Rute Caldeira. (2017). <i>An Introduction to Evaluation</i> .","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Law and economics; Economics","score_opus":0.31517400767919956,"score_gpt":0.5246237159077208,"score_spread":0.20944970822852127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903412726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9581528,0.00076053414,0.0034144947,0.026602188,0.0044811065,0.0027252417,0.000013570102,0.000022985345,0.003827112],"genre_scores_gemma":[0.98982704,0.000009393306,0.0064064935,0.00078746217,0.0025463742,0.000118299926,0.00003136172,0.000016558923,0.00025703214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99356186,0.001014976,0.0011063475,0.00046269392,0.0034641528,0.00038995003],"domain_scores_gemma":[0.9883607,0.00012056514,0.0006646491,0.0005637801,0.009413137,0.0008771641],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032562997,0.00018716094,0.000294466,0.0010474768,0.0005016501,0.0007887737,0.0004912984,0.00011417064,0.004276345],"category_scores_gemma":[0.0050625326,0.00015203221,0.00008463969,0.0011175085,0.00018109458,0.001503692,0.000025006808,0.00021531027,0.00022532536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035348497,0.000042255557,0.00478878,0.000002365624,0.000025039131,0.0000014947403,0.0018610748,0.00087997474,0.00022225778,0.0005099515,0.034462847,0.95716864],"study_design_scores_gemma":[0.0021974768,0.0035944714,0.16613711,0.000049062055,0.00032993444,0.00023260122,0.0017113676,0.14282677,0.00064990966,0.021870352,0.65994114,0.00045978805],"about_ca_topic_score_codex":0.0007660686,"about_ca_topic_score_gemma":0.036319513,"teacher_disagreement_score":0.95670885,"about_ca_system_score_codex":0.0005678689,"about_ca_system_score_gemma":0.004797442,"threshold_uncertainty_score":0.9966339},"labels":[],"label_agreement":null},{"id":"W2918217012","doi":"10.3138/cjpe.33.3.v","title":"Editor’s Remarks","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Biography; Bourgeoisie; Library science; Administration (probate law); Art; Sociology; Classics; Art history; Political science; Law; Computer science; Politics","score_opus":0.1939142377051118,"score_gpt":0.5103476077944012,"score_spread":0.31643337008928946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918217012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8903803,0.0007796113,0.0010940575,0.007369858,0.033882048,0.0024164557,0.000007655057,0.000017961283,0.064052045],"genre_scores_gemma":[0.9945535,0.0000042425263,0.002310582,0.00024660016,0.0017992201,0.000018256687,0.0000062085837,0.0000073997803,0.0010539576],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957334,0.0003893848,0.000780041,0.00016049185,0.002708953,0.00022775575],"domain_scores_gemma":[0.99502933,0.0002124901,0.0006084361,0.00031886273,0.0034112644,0.0004195894],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.017465403,0.000087109074,0.00019397795,0.000594865,0.000100492136,0.00037638712,0.0004689298,0.00007643017,0.013963623],"category_scores_gemma":[0.0023161462,0.00006435177,0.000121319354,0.0005989142,0.0000420602,0.0006992981,0.000008622969,0.00019573164,0.0009399457],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011668981,0.000021642663,0.07553242,0.000002787023,0.000017781982,0.0000024716303,0.0005119273,0.0016953893,0.0000516872,0.00043413255,0.086646706,0.8350714],"study_design_scores_gemma":[0.001007516,0.00060231244,0.11905751,0.000044720116,0.000044218355,0.000034789133,0.0010668371,0.044468597,0.00006800765,0.009475812,0.82398474,0.00014493152],"about_ca_topic_score_codex":0.00019767114,"about_ca_topic_score_gemma":0.005671551,"teacher_disagreement_score":0.8349264,"about_ca_system_score_codex":0.00031822285,"about_ca_system_score_gemma":0.0057051787,"threshold_uncertainty_score":0.9999316},"labels":[],"label_agreement":null},{"id":"W2918531645","doi":"10.3138/cjpe.53007","title":"Can’t See the Wood for the Logframe: Integrating Logframes and Theories of Change in Development Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Development theory; Context (archaeology); Development (topology); Computer science; Management science; Epistemology; Engineering ethics; Process management; Sociology; Business; Engineering; History; Economics; Economic growth","score_opus":0.41664340785434323,"score_gpt":0.5285682281708979,"score_spread":0.11192482031655465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918531645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9814272,0.002256337,0.0008935125,0.009641843,0.0008040027,0.0044940864,0.000006350735,0.0000028394895,0.00047382698],"genre_scores_gemma":[0.9975199,0.000019264464,0.0016331354,0.00028150543,0.00009056255,0.00040018006,0.0000073926976,0.0000068764,0.00004116578],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99642843,0.0006255941,0.0008747222,0.00016358547,0.0016905587,0.00021710877],"domain_scores_gemma":[0.994965,0.0013373848,0.0007830294,0.00025090892,0.0025634773,0.000100189354],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03489376,0.00011216264,0.00021644677,0.0003493059,0.00020887855,0.0002453584,0.000416894,0.000068899935,0.0005709764],"category_scores_gemma":[0.0041038324,0.000057377383,0.0000649528,0.0005354771,0.00013033075,0.00036448086,0.00001831719,0.00020022038,0.0000057391135],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018516563,0.000014146167,0.07169965,0.000008256921,0.000023538107,1.2439425e-7,0.013799457,0.00097314274,0.000015876896,0.0029626687,0.000104562765,0.91038007],"study_design_scores_gemma":[0.002063588,0.00066532724,0.5796239,0.000187103,0.00016002795,0.000018104038,0.029431442,0.31715912,0.0002969416,0.054930437,0.015267801,0.0001962089],"about_ca_topic_score_codex":0.00060900784,"about_ca_topic_score_gemma":0.072579734,"teacher_disagreement_score":0.91018385,"about_ca_system_score_codex":0.0003027027,"about_ca_system_score_gemma":0.0042320355,"threshold_uncertainty_score":0.99377996},"labels":[],"label_agreement":null},{"id":"W2918728998","doi":"10.3138/cjpe.53008","title":"Does Your Implementation Fit Your Theory of Change?","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Coding (social sciences); Action (physics); Theory of change; Domain (mathematical analysis); Management science; Computer science; Psychology; Epistemology; Sociology; Mathematics; Social science; Economics","score_opus":0.6341084431107532,"score_gpt":0.590531744540158,"score_spread":0.04357669857059521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918728998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99262387,0.00025631985,0.0003059684,0.0020418856,0.0017399305,0.0015187337,0.000020654661,0.0000053651843,0.0014872565],"genre_scores_gemma":[0.9979985,0.0000130167655,0.0011163095,0.00019478735,0.00022055572,0.000052041138,0.000015030971,0.000008791767,0.00038097362],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995879,0.0006088117,0.000997297,0.00017245168,0.0021064973,0.00023597614],"domain_scores_gemma":[0.9953947,0.0001842591,0.0011260464,0.00029220877,0.0027337743,0.00026901427],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017324403,0.000107509295,0.00024370993,0.00070464343,0.00009210351,0.00017833315,0.0004155836,0.00006325653,0.014674017],"category_scores_gemma":[0.00075004896,0.00006369216,0.00013894949,0.0005764769,0.000052155083,0.0008901159,0.000012735531,0.00013272253,0.00013909933],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019545325,0.000022393879,0.14117639,0.000006584108,0.000026766362,8.9606226e-7,0.0030798123,0.00020239544,0.00011810056,0.0009821492,0.0005172043,0.85384774],"study_design_scores_gemma":[0.0026434797,0.0014155568,0.8455896,0.00010393392,0.00018894553,0.000021829892,0.028685048,0.012956357,0.0013210052,0.0469795,0.059818845,0.00027592696],"about_ca_topic_score_codex":0.00051435875,"about_ca_topic_score_gemma":0.008799,"teacher_disagreement_score":0.85357183,"about_ca_system_score_codex":0.00023004354,"about_ca_system_score_gemma":0.0025075749,"threshold_uncertainty_score":0.9862267},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7878033,0.005113309,0.14490835,0.0055659413,0.00046404655,0.004983328,0.000015104214,0.00005103095,0.051095575],"genre_scores_gemma":[0.9909398,0.000005871431,0.008609752,0.000057982234,0.000111179674,0.00011401843,0.0000039427673,0.000013147316,0.00014430152],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940674,0.0036374151,0.0004254007,0.00018040572,0.0012884325,0.00040098166],"domain_scores_gemma":[0.9961079,0.00072095555,0.0003034513,0.00016974987,0.002241205,0.0004567919],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021612085,0.00011606692,0.00037445885,0.000616413,0.0005079445,0.00030367015,0.000370879,0.00007740662,0.0033493387],"category_scores_gemma":[0.003360784,0.000097438504,0.00033964895,0.000816779,0.00020458516,0.0003756629,0.000005980842,0.00023286293,0.00006939694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017069912,0.00040755747,0.017030803,0.00013803273,0.0066946973,0.000019440764,0.0738709,0.5770175,0.0001087557,0.06422301,0.0011234778,0.25919518],"study_design_scores_gemma":[0.0005335952,0.00019648731,0.00033365254,0.00007898937,0.0026936363,0.0000015673463,0.016048383,0.95174825,0.000091267626,0.013230894,0.014756865,0.00028641688],"about_ca_topic_score_codex":0.005304205,"about_ca_topic_score_gemma":0.045489375,"teacher_disagreement_score":0.3747308,"about_ca_system_score_codex":0.0007436305,"about_ca_system_score_gemma":0.005303248,"threshold_uncertainty_score":0.99756175},"labels":[],"label_agreement":null},{"id":"W2919316438","doi":"10.3138/cjpe.52946","title":"Using Actor-Based Theories of Change to Conduct Robust Evaluation in Complex Settings","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Theory of change; Democracy; Management science; Computer science; Psychological intervention; Process management; Sociology; Operations research; Business; Risk analysis (engineering); Political science; Economics; Psychology; Management; Mathematics; Law","score_opus":0.8242816801062659,"score_gpt":0.5913763997790368,"score_spread":0.23290528032722912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919316438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99249005,0.0001423871,0.00090859155,0.0022231971,0.00063527666,0.0026914706,0.000013263653,0.000004061136,0.0008917177],"genre_scores_gemma":[0.9892964,9.1057893e-7,0.0100545,0.00043291895,0.000104139894,0.000060899692,0.000024607289,0.000010769389,0.00001487729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941851,0.0010733135,0.0011359302,0.00023342537,0.0030871928,0.00028505654],"domain_scores_gemma":[0.99334073,0.00030242527,0.0009710562,0.0003228837,0.0047645583,0.00029831912],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02935395,0.00013656079,0.00035426617,0.0013700267,0.00008731398,0.00019568374,0.0004205964,0.00008156753,0.0051683895],"category_scores_gemma":[0.0030540356,0.000111795154,0.00010506507,0.0013844414,0.000070241455,0.0007741345,0.000013495534,0.0001642238,0.00004565926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086323744,0.00009187051,0.23291358,0.000029403365,0.000028110888,0.0000021015053,0.0056777806,0.16465184,0.0032307147,0.00079433364,0.00065428007,0.5918397],"study_design_scores_gemma":[0.0019713049,0.00067215326,0.26882827,0.00018975577,0.00008196938,0.000010167144,0.0034029854,0.7147289,0.00052002195,0.0040310663,0.0053707864,0.00019262913],"about_ca_topic_score_codex":0.001092077,"about_ca_topic_score_gemma":0.013825445,"teacher_disagreement_score":0.591647,"about_ca_system_score_codex":0.0007504324,"about_ca_system_score_gemma":0.0055170534,"threshold_uncertainty_score":0.99948436},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914202,0.0044700885,0.00035013095,0.000111383844,0.0007864907,0.0022518954,0.000010323694,0.00000930428,0.0005901793],"genre_scores_gemma":[0.99878275,5.7996317e-7,0.000895132,0.000011080472,0.000100394434,0.000047884434,0.000005066173,0.000015020419,0.00014207652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948915,0.0007662011,0.0017829613,0.00033087947,0.0019111183,0.00031733207],"domain_scores_gemma":[0.9916979,0.00066707627,0.0025298796,0.00041832932,0.004324163,0.00036262008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014725863,0.00018617441,0.0006864585,0.00078340346,0.00015772822,0.00044050612,0.0004706732,0.00012292441,0.0001309398],"category_scores_gemma":[0.0045911553,0.00014056121,0.00015086267,0.00082353695,0.00021499803,0.0005722004,0.00005516398,0.00019144217,0.00001295437],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018087748,0.00007623053,0.41796586,0.00025627215,0.000095192365,0.00004839004,0.01269777,0.007717518,0.00015702315,0.006102588,0.00021782998,0.5544844],"study_design_scores_gemma":[0.003324848,0.006066958,0.16832878,0.0044713495,0.0002826735,0.0005935789,0.049789656,0.43031886,0.00005602106,0.31908175,0.016802609,0.0008829032],"about_ca_topic_score_codex":0.0024267463,"about_ca_topic_score_gemma":0.0011946957,"teacher_disagreement_score":0.55360156,"about_ca_system_score_codex":0.0003166037,"about_ca_system_score_gemma":0.0017299382,"threshold_uncertainty_score":0.573192},"labels":[],"label_agreement":null},{"id":"W2920077988","doi":"10.3138/cjpe.53070","title":"How We Model Matters: A Manifesto for the Next Generation of Program Theorizing","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Manifesto; Sociology; Epistemology; Scale (ratio); Engineering ethics; Computer science; Political science; Law; Philosophy; Engineering","score_opus":0.63617589694431,"score_gpt":0.5222816882781216,"score_spread":0.11389420866618838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920077988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7653458,0.0029399346,0.091503456,0.120403744,0.003802947,0.014759521,0.000038428076,0.00003263684,0.0011735184],"genre_scores_gemma":[0.97999334,0.00002482475,0.018571932,0.00034587987,0.0002812015,0.00027379097,0.000012369602,0.000013359978,0.0004833028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967915,0.00028127787,0.00074674294,0.00019366242,0.001729505,0.00025735216],"domain_scores_gemma":[0.9952627,0.00036819524,0.00094800285,0.00036417152,0.0028633534,0.00019359117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011904376,0.00012453682,0.00023121016,0.00039006557,0.00019970303,0.0008930155,0.0005328915,0.0000733669,0.00034662455],"category_scores_gemma":[0.00091945,0.00007754261,0.00019229857,0.00044322494,0.000073382835,0.0010497767,0.000011603154,0.00014418284,0.000018752175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002237348,0.0000403628,0.0012313017,0.000014926434,0.000039863826,3.6024744e-7,0.0013742368,0.029753353,0.0009324981,0.0024893174,0.005059359,0.9590421],"study_design_scores_gemma":[0.00075117557,0.0006346413,0.0010831871,0.00004762301,0.00009995811,0.000013992449,0.0023600745,0.94673336,0.0002726646,0.008275365,0.039629653,0.00009833817],"about_ca_topic_score_codex":0.000078239274,"about_ca_topic_score_gemma":0.0033183105,"teacher_disagreement_score":0.9589437,"about_ca_system_score_codex":0.00021335023,"about_ca_system_score_gemma":0.002761089,"threshold_uncertainty_score":0.86113685},"labels":[],"label_agreement":null},{"id":"W2920130717","doi":"10.3138/cjpe.56900","title":"The Current Landscape of Program Theorizing","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Current (fluid); Sociology; Epistemology; Environmental resource management; Environmental planning; Geography; Engineering; Environmental science; Philosophy","score_opus":0.2918100568654653,"score_gpt":0.5403306206497496,"score_spread":0.24852056378428428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920130717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97421235,0.0041946545,0.00025894112,0.0025999674,0.0037185408,0.0028202506,0.0000058724236,0.00001299443,0.012176403],"genre_scores_gemma":[0.99868745,0.000043315747,0.00088190124,0.000028749197,0.00014968136,0.000055762368,0.0000048190786,0.000006896895,0.00014141068],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957864,0.0005308062,0.00096995995,0.00014588445,0.0023034487,0.0002634435],"domain_scores_gemma":[0.9949149,0.00046074303,0.000980477,0.00035411623,0.0030308736,0.00025892988],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019763533,0.00009758104,0.00020732557,0.00035508163,0.00019631007,0.00039627164,0.0006150327,0.000040628165,0.0011592256],"category_scores_gemma":[0.0018362779,0.000055600212,0.00015354918,0.0007179559,0.000092528455,0.00039178447,0.000014679746,0.00024168925,0.00011407867],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013198411,0.000030785835,0.047659647,0.0000042640972,0.00001585896,3.3870063e-7,0.00043738543,0.000544439,0.00001221604,0.0013676899,0.0013778592,0.94853634],"study_design_scores_gemma":[0.0015096443,0.0015630123,0.18109518,0.00014738954,0.00010505905,0.000021537098,0.0025627138,0.10402803,0.00013503616,0.026763093,0.68187094,0.00019838697],"about_ca_topic_score_codex":0.00005809148,"about_ca_topic_score_gemma":0.0033131791,"teacher_disagreement_score":0.9483379,"about_ca_system_score_codex":0.00012954845,"about_ca_system_score_gemma":0.0041720234,"threshold_uncertainty_score":0.99975383},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995278,0.00026520036,0.00003248468,0.00018182052,0.00073657546,0.0005106492,2.058064e-7,0.0000061731425,0.0029889024],"genre_scores_gemma":[0.99811673,0.000038775448,0.001585199,0.00005086804,0.000078715406,0.000025628025,9.3069417e-7,0.000003852152,0.000099287805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99850273,0.0002538876,0.0002939059,0.00010771944,0.0005241764,0.00031756947],"domain_scores_gemma":[0.9991721,0.00010200299,0.00018110884,0.00006008245,0.00033907828,0.0001456383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005822517,0.0000718817,0.00013436112,0.00037229012,0.00022696251,0.00010720775,0.00024207008,0.000087659435,0.0002784523],"category_scores_gemma":[0.0003218465,0.00007372357,0.000027684255,0.0007074132,0.00009081236,0.00073554536,0.000010801548,0.00021367206,0.000014868054],"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":[0.000012169009,0.000004736765,0.6177065,0.000011636709,0.0000032164662,0.0000029859557,0.1821861,0.00010475981,4.1552914e-7,0.00082466623,0.000009956263,0.19913287],"study_design_scores_gemma":[0.0007441883,0.00017439642,0.5698552,0.0009896235,0.000013299825,0.000004316463,0.4122935,0.0014757413,0.000047278743,0.00086690247,0.01323187,0.00030371666],"about_ca_topic_score_codex":0.0015778767,"about_ca_topic_score_gemma":0.03199558,"teacher_disagreement_score":0.23010738,"about_ca_system_score_codex":0.001272217,"about_ca_system_score_gemma":0.0048912163,"threshold_uncertainty_score":0.985668},"labels":[],"label_agreement":null},{"id":"W292912147","doi":"10.3138/cjpe.0023.007","title":"Informing Evaluation Capacity Building Through Profiling Organizational Capacity for Evaluation: An Empirical Examination of four Canadian Federal Government Organizations","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Organization development; Government (linguistics); Capacity building; Evaluation methods; Knowledge management; Organizational effectiveness; Order (exchange); Business; Organizational performance; Process management; Computer science; Political science; Finance; Engineering","score_opus":0.43136025450021587,"score_gpt":0.49320319992613026,"score_spread":0.0618429454259144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W292912147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96257776,0.00010753138,0.026954634,0.0015845749,0.0010402565,0.0047394773,0.000114798924,0.00001870385,0.0028622583],"genre_scores_gemma":[0.93372524,0.0000042007964,0.06513943,0.00035139653,0.00034136453,0.0001530328,0.00024093466,0.00002384734,0.000020587893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890794,0.0013611984,0.0020397787,0.00045729493,0.0065244283,0.000537857],"domain_scores_gemma":[0.9726164,0.00035447848,0.0017248876,0.00044526538,0.02412206,0.0007369062],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03494162,0.0002917699,0.00044475333,0.0008179623,0.00089793175,0.0005133454,0.00064041634,0.0002475207,0.0019789713],"category_scores_gemma":[0.021273157,0.0002728158,0.00015247424,0.0022839366,0.000122062695,0.0028506843,0.000013187531,0.00028680038,0.000008773877],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00004452928,0.00025195343,0.057077993,0.000025874782,0.000107715525,0.0000014461366,0.0111073395,0.029975351,0.0011084991,0.007622771,0.00071500806,0.8919615],"study_design_scores_gemma":[0.003482548,0.0017048524,0.3033331,0.00011555928,0.00054087205,0.00007850716,0.0031794973,0.6312014,0.003301753,0.049142353,0.0034211685,0.0004984108],"about_ca_topic_score_codex":0.0039387695,"about_ca_topic_score_gemma":0.14069767,"teacher_disagreement_score":0.8914631,"about_ca_system_score_codex":0.0040651406,"about_ca_system_score_gemma":0.018856525,"threshold_uncertainty_score":0.9999724},"labels":[],"label_agreement":null},{"id":"W293512544","doi":"10.3138/cjpe.23.012","title":"Latent Profiles of Evaluators’ Self-Reported Practices","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Facilitator; Latent class model; Stakeholder; Psychology; Class (philosophy); Degree (music); Social psychology; Applied psychology; Computer science; Artificial intelligence; Machine learning; Political science; Public relations","score_opus":0.5814887145472366,"score_gpt":0.5616080822872708,"score_spread":0.019880632259965836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W293512544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99293286,0.0006430646,0.0001482256,0.0014110977,0.0008322634,0.0011823389,0.000005123616,0.000013569769,0.0028314618],"genre_scores_gemma":[0.99154526,0.00005252934,0.007916519,0.000074526724,0.00016564688,0.000053252672,0.000009888255,0.000010707884,0.0001716425],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9926705,0.00089791714,0.0017381602,0.00023115968,0.0041855094,0.0002767981],"domain_scores_gemma":[0.9849579,0.0003603647,0.006011795,0.0003982901,0.007799379,0.00047230473],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022268007,0.00014197422,0.00034496628,0.00085312274,0.00024868644,0.00013648976,0.0004982556,0.00009855489,0.0028093366],"category_scores_gemma":[0.012050672,0.00010516012,0.0001811323,0.0010621985,0.00013897486,0.0009972592,0.000014213339,0.00022328961,0.00007210086],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052074774,0.00027899176,0.6419588,0.000016823877,0.0002813472,0.000049860788,0.0048400243,0.0023293616,0.00032184017,0.00029596346,0.009152956,0.340422],"study_design_scores_gemma":[0.0022883597,0.0016992621,0.84812826,0.00009793846,0.00059849967,0.0007575934,0.0015673955,0.079181805,0.0016727896,0.004581058,0.059105992,0.00032104773],"about_ca_topic_score_codex":0.00062972895,"about_ca_topic_score_gemma":0.003488513,"teacher_disagreement_score":0.34010097,"about_ca_system_score_codex":0.00032250004,"about_ca_system_score_gemma":0.013678312,"threshold_uncertainty_score":0.99810225},"labels":[],"label_agreement":null},{"id":"W2945068297","doi":"10.3138/cjpe.42239","title":"20 Years Later: Reflections on the CES Student Evaluation Case Competition","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland; University of Waterloo","funders":"","keywords":"Competition (biology); Teamwork; Psychology; Computer-assisted web interviewing; Medical education; Social psychology; Applied psychology; Marketing; Management; Medicine; Business; Economics","score_opus":0.44939411653968636,"score_gpt":0.5776639702248278,"score_spread":0.1282698536851415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945068297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789716,0.00013211329,0.00008415222,0.0049438532,0.0018195275,0.0020791965,0.000009155751,0.000009293989,0.011951136],"genre_scores_gemma":[0.9985334,0.0000069631355,0.000326697,0.0004500573,0.00021407862,0.00011779294,0.000017668259,0.000010090428,0.0003232264],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9936551,0.0014545912,0.0008274062,0.00023279172,0.00358929,0.00024081246],"domain_scores_gemma":[0.9948979,0.000471921,0.00068348466,0.00042665948,0.0032624174,0.00025760574],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02542967,0.00012576167,0.00018885329,0.00065622677,0.0003478065,0.000628839,0.00040729943,0.000075484306,0.010573201],"category_scores_gemma":[0.0012415783,0.000083462255,0.00013862333,0.00082682696,0.000069060465,0.0005393895,0.000012778354,0.00028965127,0.0007281159],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004867686,0.00019914132,0.031515446,0.0000048133074,0.00013741199,0.000060476385,0.007351899,0.040245887,0.0002253376,0.0062595713,0.008096869,0.90585446],"study_design_scores_gemma":[0.0046717892,0.0040882183,0.4377646,0.00022808967,0.0006627877,0.0015411051,0.028565425,0.23492722,0.0003385663,0.03249306,0.25407,0.0006491061],"about_ca_topic_score_codex":0.00028917153,"about_ca_topic_score_gemma":0.027114308,"teacher_disagreement_score":0.90520537,"about_ca_system_score_codex":0.0007010905,"about_ca_system_score_gemma":0.0028614542,"threshold_uncertainty_score":0.9906383},"labels":[],"label_agreement":null},{"id":"W2945107123","doi":"10.3138/cjpe.43216","title":"Scaling Up Programs: Reflections on the Importance of Process Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"General partnership; Scale (ratio); Process (computing); Program evaluation; Public relations; Process management; Computer science; Psychology; Business; Political science; Medical education; Public administration; Medicine; Finance","score_opus":0.569979886420681,"score_gpt":0.6000537481211533,"score_spread":0.030073861700472326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945107123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822758,0.00022808254,0.00012959873,0.0030712285,0.0013266329,0.0029974524,0.00000368896,0.0000087007675,0.0099588465],"genre_scores_gemma":[0.99869084,0.0000050078734,0.0005214552,0.00024853455,0.00013459877,0.00019875726,0.00001342946,0.000011970893,0.00017539803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927678,0.0008966335,0.0012745698,0.00026000367,0.0045195026,0.000281486],"domain_scores_gemma":[0.989517,0.00045469345,0.0015260866,0.0005027297,0.0077579673,0.00024155353],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030280655,0.00014318166,0.0002662771,0.00061000127,0.00025037103,0.0003013512,0.00061499036,0.00008893325,0.004272085],"category_scores_gemma":[0.005381511,0.00008963368,0.0001699629,0.0015521661,0.00011050127,0.0006012254,0.000009154422,0.0002987204,0.00011771631],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044303397,0.000093228846,0.11744577,0.00001267294,0.000053093296,6.2073036e-7,0.0034874715,0.013808727,0.00007848767,0.0022817403,0.00086256716,0.8618313],"study_design_scores_gemma":[0.004249359,0.0036771758,0.28124124,0.00071991375,0.0005864564,0.000088102635,0.035927888,0.515883,0.0017677472,0.10899662,0.0462128,0.0006496539],"about_ca_topic_score_codex":0.00013058631,"about_ca_topic_score_gemma":0.007188798,"teacher_disagreement_score":0.8611817,"about_ca_system_score_codex":0.0004575102,"about_ca_system_score_gemma":0.0070746485,"threshold_uncertainty_score":0.9985543},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98975587,0.00048333564,0.0032832562,0.001436579,0.0014304415,0.0019372713,0.00012782097,0.000016090786,0.0015293129],"genre_scores_gemma":[0.9923098,0.000010352205,0.006678373,0.000052126958,0.0005915013,0.000012151894,0.00028245835,0.00000864959,0.00005455234],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981528,0.00039059238,0.00030900797,0.00019084197,0.00066607195,0.00029067358],"domain_scores_gemma":[0.9980952,0.000085843945,0.0003023991,0.00032059645,0.00073564105,0.00046031945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077068643,0.00007166736,0.00016045656,0.00019241375,0.0004121108,0.00035687367,0.00077505916,0.00004856876,0.00048727138],"category_scores_gemma":[0.0009911299,0.00006734535,0.00007232663,0.00023980219,0.0001038757,0.0009912249,0.000017084036,0.00011166786,0.000010200092],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020488,0.000073360075,0.02616245,0.000022178729,0.00012092533,0.000003952449,0.008028612,0.00078768324,0.00024305675,0.006102124,0.0025738685,0.95586133],"study_design_scores_gemma":[0.0020974893,0.0009358752,0.014488371,0.0002521274,0.0010611915,0.000012306903,0.014794992,0.3954763,0.00007059538,0.01004127,0.560243,0.00052646],"about_ca_topic_score_codex":0.00460739,"about_ca_topic_score_gemma":0.18277958,"teacher_disagreement_score":0.95533484,"about_ca_system_score_codex":0.0001505358,"about_ca_system_score_gemma":0.005144327,"threshold_uncertainty_score":0.9125815},"labels":[],"label_agreement":null},{"id":"W2945573974","doi":"10.3138/cjpe.42118","title":"Community, Theory, and Guidance: Benefits and Lessons Learned in Evaluation Peer Mentoring","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Peer mentoring; Psychology; Professional development; Work (physics); Medical education; Peer review; Field (mathematics); Empirical research; Public relations; Pedagogy; Political science; Medicine; Engineering","score_opus":0.5039995996250785,"score_gpt":0.5605583430272246,"score_spread":0.05655874340214617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945573974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98806876,0.002138193,0.000046283712,0.0050463043,0.00043423058,0.0010164857,0.0000039945403,0.000003950654,0.0032418042],"genre_scores_gemma":[0.99891293,0.00004709651,0.0005223871,0.00011131919,0.000051556108,0.000043612003,0.0000092017035,0.000008259383,0.00029362997],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933965,0.0028238653,0.0007374327,0.00018902127,0.0026064466,0.00024669606],"domain_scores_gemma":[0.99568325,0.00055200385,0.00047319612,0.00028631097,0.0027165462,0.00028868427],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.09360075,0.00011425745,0.0002288172,0.0007116532,0.0002286931,0.00048011515,0.00028923282,0.00008059616,0.0009964942],"category_scores_gemma":[0.0058898046,0.00009444395,0.000040678126,0.0005097326,0.00007593689,0.000767669,0.000033314325,0.00035189747,0.000024202294],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021230246,0.000021152186,0.13945095,0.000005020059,0.000011196041,4.483416e-7,0.003949973,0.0024729073,0.000054714754,0.002685616,0.00015975306,0.851167],"study_design_scores_gemma":[0.002634881,0.0005229262,0.83827204,0.00019083843,0.00008870807,0.000030003594,0.009006835,0.077206425,0.00007135074,0.06131295,0.010476469,0.00018660194],"about_ca_topic_score_codex":0.000731035,"about_ca_topic_score_gemma":0.025972513,"teacher_disagreement_score":0.85098046,"about_ca_system_score_codex":0.00037276716,"about_ca_system_score_gemma":0.001969437,"threshold_uncertainty_score":0.99991673},"labels":[],"label_agreement":null},{"id":"W2945587103","doi":"10.3138/cjpe.42190","title":"Evaluation Literacy: Perspectives of Internal Evaluators in Non-Government Organizations","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Context (archaeology); Conversation; Narrative; Literacy; Public relations; Psychology; Knowledge management; Sociology; Political science; Pedagogy; Computer science","score_opus":0.11217340830553922,"score_gpt":0.49166201961879946,"score_spread":0.3794886113132602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945587103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988338,0.0005250182,0.00096734683,0.0003672165,0.00072740985,0.0019031598,0.000010092537,0.0000037115324,0.0071580214],"genre_scores_gemma":[0.99765503,0.000011888241,0.001982821,0.000055116216,0.00008194984,0.000056636152,0.000008067348,0.000014285508,0.0001342282],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99063265,0.0010884447,0.0015130106,0.00029044788,0.0062136995,0.00026176544],"domain_scores_gemma":[0.9866698,0.00022772785,0.0012894727,0.0003903839,0.011148372,0.00027428873],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03273753,0.00015611255,0.0003470908,0.00096450356,0.000071383656,0.00020202358,0.0005638409,0.00009066147,0.013834994],"category_scores_gemma":[0.0063263634,0.0001297231,0.00012694576,0.0018757058,0.00007851945,0.001103741,0.00002421308,0.0002389864,0.000113253845],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042638552,0.00019767939,0.35430497,0.000008992573,0.000071447015,0.000002043431,0.024654655,0.014929004,0.00042007217,0.0004715461,0.00045493853,0.604442],"study_design_scores_gemma":[0.0023781375,0.00085058715,0.6150318,0.00015501617,0.00018722026,0.00001861289,0.0155196525,0.356939,0.0004990225,0.006571633,0.0016613477,0.00018801285],"about_ca_topic_score_codex":0.0005865979,"about_ca_topic_score_gemma":0.006461604,"teacher_disagreement_score":0.604254,"about_ca_system_score_codex":0.0016860537,"about_ca_system_score_gemma":0.0074044554,"threshold_uncertainty_score":0.99822265},"labels":[],"label_agreement":null},{"id":"W2945590379","doi":"10.3138/cjpe.53169","title":"Anne Markiewicz and Ian Patrick. (2016). <i>Developing Monitoring and Evaluation Frameworks</i> .","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sociology; Psychology; Environmental ethics; Philosophy","score_opus":0.2223609311383748,"score_gpt":0.4917329420662098,"score_spread":0.269372010927835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945590379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865752,0.005018654,0.00066642644,0.0031961564,0.001669073,0.0014953176,0.000003321999,0.000008852363,0.0013670406],"genre_scores_gemma":[0.9917065,0.00013384712,0.007566867,0.00014069796,0.0002675623,0.00004560436,0.000006529002,0.000012434208,0.0001199735],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952849,0.00064872246,0.0008971205,0.0003091275,0.002547225,0.0003128797],"domain_scores_gemma":[0.9948875,0.0003241504,0.00070722814,0.00027024758,0.0033565739,0.0004543059],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023412876,0.0001583682,0.00028341424,0.00071277365,0.00024046651,0.0007321034,0.00025860858,0.00018316432,0.00093629357],"category_scores_gemma":[0.002396365,0.00012858973,0.00006141421,0.00071926607,0.00006983977,0.0010867199,0.000023804236,0.00038124545,0.000051989133],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010285377,0.000008045622,0.16664045,0.0000083885825,0.00001887262,0.0000013332643,0.00092660997,0.0005010816,0.000046006244,0.00012405614,0.00058136345,0.83113354],"study_design_scores_gemma":[0.002341093,0.00063661544,0.81088686,0.0003854809,0.00022092678,0.000104843195,0.004346906,0.11532637,0.00014480254,0.019364638,0.045841347,0.0004001174],"about_ca_topic_score_codex":0.00016726648,"about_ca_topic_score_gemma":0.00079487223,"teacher_disagreement_score":0.8307334,"about_ca_system_score_codex":0.00041690498,"about_ca_system_score_gemma":0.004007644,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W2946489075","doi":"10.3138/cjpe.43050","title":"Principles, Approaches, and Methods for Evaluation in Indigenous Contexts: A Grey Literature Scoping Review","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Public Health Ontario","funders":"","keywords":"Grey literature; Indigenous; Interpretation (philosophy); Management science; Engineering ethics; Sociology; Psychology; Computer science; MEDLINE; Political science; Engineering; Ecology","score_opus":0.47385647968230576,"score_gpt":0.5813766564612814,"score_spread":0.10752017677897568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946489075","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41089696,0.509248,0.011964579,0.0071091764,0.0025603173,0.05472733,0.0000317711,0.000022475804,0.0034393815],"genre_scores_gemma":[0.86594206,0.0027798393,0.12681027,0.0014155649,0.00030615166,0.0021820306,0.00017572124,0.00004563891,0.00034271402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945547,0.0018850226,0.0013968758,0.0003221797,0.0015410224,0.00030017958],"domain_scores_gemma":[0.99394125,0.00058617507,0.0010157336,0.00031231242,0.0038492791,0.00029523432],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.076048516,0.00015139609,0.00045894596,0.0007774321,0.00012376843,0.0005091424,0.00032607507,0.00011581561,0.00048710444],"category_scores_gemma":[0.008845795,0.00011712507,0.00011231565,0.0009619015,0.000042289885,0.0009457357,0.00001425945,0.00024040678,0.000010938573],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001655477,0.000022462222,0.01280837,0.00036322477,0.000015017811,6.6132185e-7,0.001959103,0.0006451087,0.000007874664,0.00026581992,0.00008643279,0.98380935],"study_design_scores_gemma":[0.01474622,0.0032930507,0.17256986,0.07188507,0.00084114546,0.00033776442,0.0022124392,0.61992586,0.00015067127,0.028791813,0.08408332,0.001162786],"about_ca_topic_score_codex":0.0000841212,"about_ca_topic_score_gemma":0.008692618,"teacher_disagreement_score":0.9826466,"about_ca_system_score_codex":0.0005066055,"about_ca_system_score_gemma":0.007721358,"threshold_uncertainty_score":0.99950314},"labels":[],"label_agreement":null},{"id":"W2946538741","doi":"10.3138/cjpe.56975","title":"David M. Fetterman, Liliana Rodríguez-Campos, Ann P. Zukoski, et al. (2018). <i>Collaborative, Participatory, and Empowerment Evaluation: Stakeholder Involvement Approaches</i> .","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; University of Toronto","funders":"","keywords":"Empowerment; Sociology; Citizen journalism; Stakeholder; Participatory evaluation; Humanities; Social science; Management; Computer science; Political science; Philosophy; Economics; World Wide Web","score_opus":0.5392699120588643,"score_gpt":0.4912646171455749,"score_spread":0.04800529491328942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946538741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9574175,0.0032217093,0.00031267293,0.027545234,0.0019325389,0.0051903464,0.000039251063,0.000019373261,0.004321414],"genre_scores_gemma":[0.99119514,0.00007281698,0.002323682,0.0054337997,0.00013616301,0.00036606358,0.000083405015,0.000027388338,0.00036156052],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901044,0.0019624152,0.0016024994,0.00060502987,0.0051780557,0.00054759695],"domain_scores_gemma":[0.9930749,0.0002386558,0.0012665966,0.0007015519,0.0038876703,0.00083064387],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.036944594,0.00031495735,0.00047906235,0.00072415336,0.00030060313,0.0009874084,0.00055080355,0.00012100073,0.0043748477],"category_scores_gemma":[0.00097305776,0.00025466757,0.00012931488,0.001027682,0.00016015432,0.0015778227,0.000048175392,0.00038629887,0.00019915603],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008175473,0.00027977565,0.14124162,0.00002684485,0.00019737725,0.0000113777805,0.0081537375,0.0069123763,0.00019219119,0.00051848346,0.13863748,0.703747],"study_design_scores_gemma":[0.004360776,0.0014598891,0.22410859,0.00015145652,0.00031762538,0.000035146884,0.006468556,0.0945344,0.00020427426,0.0029644922,0.66484416,0.0005506665],"about_ca_topic_score_codex":0.00018084633,"about_ca_topic_score_gemma":0.0071782987,"teacher_disagreement_score":0.7031963,"about_ca_system_score_codex":0.0007814866,"about_ca_system_score_gemma":0.007334775,"threshold_uncertainty_score":0.9999906},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9814367,0.00048390092,0.000068868765,0.0005474191,0.0007983315,0.0042485134,0.000002272581,0.000010154653,0.012403816],"genre_scores_gemma":[0.9957002,0.000006752482,0.0039127893,0.000026669408,0.00014603509,0.00011949525,0.000020316795,0.0000113789965,0.00005640191],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933888,0.003144334,0.0008314218,0.0001897792,0.0020039033,0.00044176442],"domain_scores_gemma":[0.995499,0.00015080377,0.0007946879,0.00016817493,0.0031304723,0.0002568757],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.049918067,0.00012443072,0.00028301377,0.00026541037,0.00032077834,0.00012943224,0.00042310724,0.00015161384,0.0012033893],"category_scores_gemma":[0.0037119912,0.000100468824,0.00013510337,0.0010460773,0.00025799754,0.00042304277,0.0000091009515,0.00028374858,0.000006911276],"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":[0.000012730735,0.000037217458,0.2456595,0.000014691793,0.000024399196,4.7381815e-7,0.07175716,0.00005209516,0.0000070633864,0.00012164676,0.000011152996,0.6823019],"study_design_scores_gemma":[0.0033583853,0.0009521916,0.6770949,0.0005742293,0.0009021809,0.000005327936,0.21752587,0.07239528,0.00018452697,0.023109099,0.003308595,0.0005894154],"about_ca_topic_score_codex":0.010821793,"about_ca_topic_score_gemma":0.07622743,"teacher_disagreement_score":0.68171245,"about_ca_system_score_codex":0.00059632526,"about_ca_system_score_gemma":0.015366139,"threshold_uncertainty_score":0.99970967},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807668,0.000061050174,0.007819762,0.0050689685,0.00038650408,0.0027395028,0.000023457565,0.000041179956,0.0030927986],"genre_scores_gemma":[0.99027765,0.00006324762,0.0072800955,0.0011872778,0.00045351865,0.00041644365,0.00008078842,0.000035373465,0.00020563044],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99198556,0.0046411473,0.0012831937,0.00024951217,0.0009788829,0.00086171314],"domain_scores_gemma":[0.9924751,0.0024817472,0.0013472703,0.00019710323,0.002964915,0.0005338851],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030982712,0.0001929941,0.00027310842,0.0007851162,0.0006769623,0.00012831819,0.00032042002,0.00036404573,0.00049007736],"category_scores_gemma":[0.011833209,0.00018483549,0.000060834405,0.0010722631,0.00009103996,0.0007524049,0.000020532298,0.0007375904,0.000035259964],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012671488,0.00008615259,0.5135307,0.00060157105,0.00003951644,0.000014121174,0.054867942,0.0012119206,0.00613805,0.0038794873,0.0056212796,0.41388255],"study_design_scores_gemma":[0.0071249506,0.00087687874,0.78763354,0.00095638237,0.00024818644,0.00034338917,0.014801292,0.081346005,0.00063726807,0.021696351,0.08380488,0.000530875],"about_ca_topic_score_codex":0.006537757,"about_ca_topic_score_gemma":0.009671287,"teacher_disagreement_score":0.41335168,"about_ca_system_score_codex":0.0025064577,"about_ca_system_score_gemma":0.02724662,"threshold_uncertainty_score":0.9978072},"labels":[],"label_agreement":null},{"id":"W2946752631","doi":"10.3138/cjpe.43118","title":"Perceived Facilitators and Barriers to Evaluative Thinking in a Small Development NGO","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Work (physics); Sustainability; Process (computing); Psychology; Quality (philosophy); Political science; Public relations; Business; Computer science; Epistemology","score_opus":0.2243927961696357,"score_gpt":0.47516494741048165,"score_spread":0.25077215124084595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946752631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99456257,0.0001415243,0.00019002036,0.0019013648,0.00050804036,0.0016951979,0.0000023196217,0.000004559406,0.0009944065],"genre_scores_gemma":[0.98975265,0.0000028381742,0.0095756,0.00039078484,0.000030459198,0.000076387965,0.0000027276567,0.000007577778,0.00016096952],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960177,0.0006608391,0.00092835765,0.00028338615,0.001798287,0.00031141398],"domain_scores_gemma":[0.99634886,0.00026339563,0.00036004285,0.00020368153,0.0019069611,0.00091703306],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021451585,0.00013765013,0.0002734676,0.001143197,0.00019334063,0.0003481035,0.00038041174,0.000071128314,0.0027582573],"category_scores_gemma":[0.0052909874,0.00010994935,0.000056327626,0.00079870323,0.00004676431,0.00044840085,0.00002366146,0.00020948969,0.00015992235],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020681402,0.000011571871,0.34001687,0.000004828294,0.00002013628,0.0000031728155,0.042144794,0.0036845508,0.00005971524,0.00013869638,0.00020283014,0.61369216],"study_design_scores_gemma":[0.0015280568,0.0007237788,0.92706126,0.0001516088,0.000027374928,0.000011803174,0.01818771,0.021630462,0.00006725837,0.0057293116,0.024638088,0.00024327585],"about_ca_topic_score_codex":0.00041600727,"about_ca_topic_score_gemma":0.043125454,"teacher_disagreement_score":0.61344886,"about_ca_system_score_codex":0.00077939616,"about_ca_system_score_gemma":0.009304243,"threshold_uncertainty_score":0.9981533},"labels":[],"label_agreement":null},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946393,0.00013853711,0.000031005184,0.00086091633,0.0029063,0.0013266572,0.000012292777,0.0000025150255,0.00008252726],"genre_scores_gemma":[0.99806875,0.000011291433,0.0015640517,0.00011849155,0.00015419353,0.00004380832,0.0000039376787,0.000010186621,0.000025289724],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997885,0.00040347877,0.0009845042,0.00014463578,0.0003251519,0.00025722114],"domain_scores_gemma":[0.9983811,0.00007678054,0.00061787706,0.0002462424,0.00054286816,0.00013516546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038363333,0.00007945724,0.00025529007,0.00020321262,0.00005371353,0.0000119162705,0.00020088679,0.000112076916,0.000110695415],"category_scores_gemma":[0.00009281497,0.00006522145,0.00014887689,0.00023290575,0.00004712228,0.00016157636,0.000004844069,0.00023064241,0.0000027480799],"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":[0.000102236205,0.00012977832,0.49102464,0.000045564502,0.000026634501,3.1701495e-7,0.004544111,0.00014858515,0.00008184501,0.000046495225,0.000038619473,0.5038112],"study_design_scores_gemma":[0.0022239133,0.0010137318,0.9878358,0.00017074976,0.00009051721,0.000011931094,0.00560961,0.0008755685,0.0000136043445,0.00011541249,0.0019703184,0.00006881049],"about_ca_topic_score_codex":0.0015077835,"about_ca_topic_score_gemma":0.025042651,"teacher_disagreement_score":0.50374234,"about_ca_system_score_codex":0.00020720063,"about_ca_system_score_gemma":0.0009577383,"threshold_uncertainty_score":0.9927478},"labels":[],"label_agreement":null},{"id":"W2992485618","doi":"10.3138/cjpe.024.001","title":"The Lay of the Land: Evaluation Practice in Canada in 2009","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Public Health Agency of Canada; University of Victoria; Ministère des Ressources naturelles et des Forêts (Québec)","funders":"","keywords":"CLARITY; Certification; Public relations; Sophistication; Psychology; Business; Political science; Sociology; Law; Social science","score_opus":0.2269249594352962,"score_gpt":0.5186252407657015,"score_spread":0.29170028133040526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992485618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95909154,0.0019888359,0.000022318227,0.030077958,0.0010505493,0.001746175,0.000005010187,0.0000013176827,0.0060163136],"genre_scores_gemma":[0.99914694,0.00003004908,0.00021285658,0.00049115135,0.00005270179,0.000025798934,0.0000020186628,0.0000030215717,0.000035445802],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9929708,0.0018526858,0.0011424373,0.00013054762,0.0036564649,0.00024704504],"domain_scores_gemma":[0.9947879,0.00088501495,0.0010098121,0.0003206749,0.0028545652,0.00014208855],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037399307,0.00008436508,0.0001689367,0.0003030457,0.00014624007,0.0001501726,0.00058783364,0.00004300949,0.00027069834],"category_scores_gemma":[0.014444146,0.000046782687,0.000058601556,0.0012919919,0.00004515422,0.00050596695,0.000007518226,0.00027451722,0.000004201376],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002127575,0.000024845347,0.093446024,6.7706657e-7,0.0000054518728,0.000002164742,0.00066036347,0.024111876,0.000006605267,0.00012133274,0.0021844564,0.8794149],"study_design_scores_gemma":[0.0010121004,0.00016098021,0.8824714,0.000054980974,0.000039768307,0.00001861807,0.0021578704,0.07850322,0.00004098916,0.007083922,0.028385468,0.00007069565],"about_ca_topic_score_codex":0.41859367,"about_ca_topic_score_gemma":0.99549276,"teacher_disagreement_score":0.8793442,"about_ca_system_score_codex":0.0015295643,"about_ca_system_score_gemma":0.03426833,"threshold_uncertainty_score":0.9938576},"labels":[],"label_agreement":null},{"id":"W2994626447","doi":"10.3138/cjpe.68444","title":"Increasing Cultural Competence in Support of Indigenous-Led Evaluation: A Necessary Step toward Indigenous-Led Evaluation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Aotearoa; Competence (human resources); Traditional knowledge; Sociology; Political science; Psychology; Gender studies; Social psychology","score_opus":0.23459713410538083,"score_gpt":0.4965004891018339,"score_spread":0.2619033549964531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994626447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9883426,0.0008667771,0.00016476431,0.00081442756,0.0013594069,0.0054914006,0.000019748628,0.000012602982,0.0029282856],"genre_scores_gemma":[0.99554497,0.00002824983,0.0035477236,0.00024389407,0.00017323153,0.00022095816,0.00015115683,0.000024477393,0.00006532084],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98294663,0.004004569,0.0028889873,0.0005613554,0.008903108,0.00069531705],"domain_scores_gemma":[0.9835783,0.0005971664,0.002608703,0.0006444506,0.012018427,0.00055294344],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07576697,0.00034001734,0.00080697954,0.001982501,0.0002648956,0.00051849446,0.0010683374,0.00024690517,0.00821133],"category_scores_gemma":[0.005116344,0.00028336412,0.0002720531,0.0023534186,0.00016673312,0.0021276455,0.000044467022,0.0005204178,0.0001879124],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014709767,0.00017521658,0.3895294,0.00003430238,0.00008108084,0.0000074580653,0.019461432,0.015890762,0.00049540465,0.000060102433,0.00044166474,0.57367605],"study_design_scores_gemma":[0.0071242787,0.0019528256,0.7230923,0.00028526736,0.00047842457,0.00019704588,0.013789161,0.24381931,0.00034957632,0.003905556,0.004450884,0.0005553263],"about_ca_topic_score_codex":0.0030234598,"about_ca_topic_score_gemma":0.030246148,"teacher_disagreement_score":0.5731208,"about_ca_system_score_codex":0.0022026543,"about_ca_system_score_gemma":0.024563756,"threshold_uncertainty_score":0.99996185},"labels":[],"label_agreement":null},{"id":"W2994882198","doi":"10.3138/cjpe.67976","title":"Creating New Stories: The Role of Evaluation in Truth and Reconciliation","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Status quo; Commission; Environmental ethics; Sociology; Truth telling; Political science; Natural (archaeology); Public relations; Engineering ethics; Law; Psychology; History; Archaeology","score_opus":0.25760580415152334,"score_gpt":0.4974978039906295,"score_spread":0.23989199983910614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994882198","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99083614,0.0013029111,0.0000838405,0.0008101741,0.00055178645,0.0012275261,0.0000020435423,0.0000021353396,0.005183435],"genre_scores_gemma":[0.9988111,0.000013432769,0.00089716766,0.0000426826,0.000103117076,0.000024985862,0.000005565466,0.0000051994853,0.0000967511],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957664,0.00075931865,0.0009447525,0.00016060258,0.0022082129,0.00016071011],"domain_scores_gemma":[0.9956576,0.00061986,0.00092485116,0.00023008691,0.0023923721,0.0001752038],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027874209,0.00008496038,0.00020505846,0.0004868151,0.00008961497,0.0001879236,0.0002135285,0.00006341657,0.0016667311],"category_scores_gemma":[0.006205806,0.00005768594,0.0000563129,0.000716829,0.00004630179,0.0006852831,0.00000883512,0.00015786405,0.00001797004],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001420644,0.000009271231,0.16499883,0.0000023572745,0.0000087881135,1.3155972e-7,0.0051982547,0.0041885483,0.00008142915,0.0006637444,0.00008685907,0.82474756],"study_design_scores_gemma":[0.0018113762,0.00054554275,0.51075685,0.000105100225,0.00008740577,0.000015183851,0.016732162,0.41414517,0.00027898586,0.043682627,0.01172129,0.00011831416],"about_ca_topic_score_codex":0.0019669363,"about_ca_topic_score_gemma":0.024470696,"teacher_disagreement_score":0.82462925,"about_ca_system_score_codex":0.00041603003,"about_ca_system_score_gemma":0.006260116,"threshold_uncertainty_score":0.9993735},"labels":[],"label_agreement":null},{"id":"W2994962470","doi":"10.3138/cjpe.67978","title":"White Privilege and the Decolonization Work Needed in Evaluation to Support Indigenous Sovereignty and Self-Determination","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; White privilege; Aotearoa; Privilege (computing); Sovereignty; Injustice; Sociology; Colonialism; White (mutation); Economic Justice; Gender studies; Decolonization; Law; Environmental ethics; Political science; Racism; Politics","score_opus":0.1310915805611923,"score_gpt":0.4568472619130539,"score_spread":0.3257556813518616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994962470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914626,0.00018266797,0.000315216,0.0020145143,0.00047128438,0.0039577,0.000002496274,0.000006673958,0.0015868476],"genre_scores_gemma":[0.9974996,0.00001700502,0.0017899034,0.00038568032,0.00006643281,0.0001445218,0.000013495923,0.000009673773,0.000073702584],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99540925,0.0010812597,0.00088797614,0.0002536018,0.0020892033,0.0002786938],"domain_scores_gemma":[0.9962924,0.00036034975,0.0006272521,0.0002469846,0.0021892905,0.00028373013],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.033757873,0.00013029414,0.00025781788,0.0008849495,0.00020150664,0.0005574243,0.0002637154,0.00009552192,0.0013789647],"category_scores_gemma":[0.0022264011,0.0000918598,0.00004635516,0.0012049444,0.00006322687,0.00096501014,0.000026148111,0.0001776806,0.000046898545],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006757222,0.000033416625,0.30775836,0.000006197089,0.000011926319,0.0000012271261,0.012755985,0.0031694958,0.000002894782,0.00036440272,0.00018120969,0.6756473],"study_design_scores_gemma":[0.00411493,0.0006756629,0.819358,0.00006006864,0.00010499905,0.000037616308,0.0028973157,0.1607082,0.000014401012,0.010073731,0.0017928788,0.00016218297],"about_ca_topic_score_codex":0.00019888495,"about_ca_topic_score_gemma":0.012322445,"teacher_disagreement_score":0.67548513,"about_ca_system_score_codex":0.0005412967,"about_ca_system_score_gemma":0.0031051403,"threshold_uncertainty_score":0.9995339},"labels":[],"label_agreement":null},{"id":"W2995189513","doi":"10.3138/cjpe.67977","title":"Nation-to-Nation Evaluation: Governance, Tribal Sovereignty, and Systems Thinking through Culturally Responsive Indigenous Evaluations","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Sovereignty; Transformative learning; Corporate governance; Colonialism; Environmental ethics; Sociology; Harm; Political science; Doctrine; Law; Politics; Management","score_opus":0.2965348623635574,"score_gpt":0.5006583896229647,"score_spread":0.2041235272594073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995189513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9638072,0.002814789,0.0015419498,0.004953009,0.0042963317,0.008771175,0.00005483246,0.000030014207,0.013730689],"genre_scores_gemma":[0.9948762,0.00004184067,0.0033086927,0.00045599844,0.00041353973,0.00028798156,0.00007263215,0.000022129349,0.000521002],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98732865,0.0018810881,0.0017056535,0.00051832537,0.008100214,0.0004660771],"domain_scores_gemma":[0.98220885,0.00075397384,0.0017274836,0.0004915474,0.014318357,0.000499782],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034960285,0.00027245004,0.00046783898,0.000810233,0.00066877215,0.0015308344,0.0007049016,0.00018976282,0.0030059223],"category_scores_gemma":[0.008518373,0.00022182046,0.00015302897,0.0017904718,0.00008097034,0.0024136135,0.000040741197,0.0003528431,0.00032319583],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018165636,0.00013711042,0.050341997,0.00003549753,0.00022983224,0.000008393704,0.03415691,0.15024294,0.00021925544,0.02906812,0.006938763,0.7284395],"study_design_scores_gemma":[0.007999031,0.0029275292,0.34720963,0.0006088712,0.000784237,0.00035206694,0.016739797,0.3930645,0.00015580718,0.14566414,0.08340969,0.0010847129],"about_ca_topic_score_codex":0.0010861453,"about_ca_topic_score_gemma":0.011309673,"teacher_disagreement_score":0.7273548,"about_ca_system_score_codex":0.0021142513,"about_ca_system_score_gemma":0.011347497,"threshold_uncertainty_score":0.9998333},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8567167,0.018420532,0.00015004528,0.07193298,0.005060039,0.0014812149,0.00001792751,0.000017766508,0.04620283],"genre_scores_gemma":[0.98725945,0.00075034675,0.0035660877,0.00068735506,0.0009902203,0.000028098724,0.000008187865,0.000014924791,0.0066953357],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957985,0.0015938312,0.0005255706,0.00019068207,0.001290245,0.0006011157],"domain_scores_gemma":[0.99518514,0.0001254522,0.0007162413,0.00012346198,0.0031565174,0.0006931862],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010495648,0.00014978588,0.00023899613,0.00018541861,0.000385512,0.0006193707,0.00036662788,0.0002072637,0.0027996139],"category_scores_gemma":[0.0020196093,0.00015063662,0.00017325189,0.000874515,0.0007132922,0.0022315513,0.000008726604,0.0002760392,0.00009314795],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005601974,0.00005100329,0.042767137,0.000024937357,0.000036225105,0.0000044161006,0.038997963,0.0001911674,0.000011186845,0.08503845,0.009730053,0.8231419],"study_design_scores_gemma":[0.00069801253,0.0012871241,0.23884213,0.0005556873,0.00019663172,0.000021850507,0.020426275,0.0031527788,0.00004584096,0.23283955,0.5015442,0.00038995815],"about_ca_topic_score_codex":0.26214093,"about_ca_topic_score_gemma":0.55376875,"teacher_disagreement_score":0.8227519,"about_ca_system_score_codex":0.0016533417,"about_ca_system_score_gemma":0.020383285,"threshold_uncertainty_score":0.99811196},"labels":[],"label_agreement":null},{"id":"W2995471644","doi":"10.3138/cjpe.53365","title":"“Deliverology” and Evaluation: A Tale of Two Worlds","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Corporate governance; Politics; Context (archaeology); Value (mathematics); Public value; Public management; Critical reflection; Political science; Public relations; Reflection (computer programming); Complement (music); Public administration; Sociology; Economics; Management; Law; Computer science; History","score_opus":0.2895418597302168,"score_gpt":0.5351081862029722,"score_spread":0.2455663264727554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995471644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895191,0.0010354174,0.00014846357,0.0014547864,0.00075663876,0.0011845322,0.0000047501862,0.0000033007245,0.0058929822],"genre_scores_gemma":[0.9972029,0.00001129433,0.0022805808,0.00014774688,0.00009443718,0.000031638752,0.0000071015334,0.000006363542,0.00021797554],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99534523,0.0007313894,0.0009349275,0.0001996878,0.0025839752,0.0002047985],"domain_scores_gemma":[0.99351025,0.00027307376,0.0008720677,0.00029221518,0.0047485894,0.00030382507],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023854697,0.00010314461,0.00028066934,0.0007245962,0.000090406174,0.0001506062,0.0003197215,0.000065017986,0.008132076],"category_scores_gemma":[0.001372368,0.000081268554,0.00009321247,0.00066197314,0.00012354899,0.00058929046,0.00001583324,0.00015886106,0.00009447731],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022555674,0.000029260014,0.17141713,0.000005754183,0.000033868277,0.0000012258374,0.0010388236,0.004560333,0.0001661509,0.0007125015,0.0011614258,0.82085097],"study_design_scores_gemma":[0.005691311,0.00178551,0.47055805,0.00011063158,0.0003282061,0.000117759395,0.0022925683,0.4569342,0.00029920175,0.03400551,0.027616452,0.00026061578],"about_ca_topic_score_codex":0.00032130643,"about_ca_topic_score_gemma":0.008731012,"teacher_disagreement_score":0.8205904,"about_ca_system_score_codex":0.00020468554,"about_ca_system_score_gemma":0.004307778,"threshold_uncertainty_score":0.9927746},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2995480421","doi":"10.3138/cjpe.43685","title":"Self-Evaluation Tool for Action in Partnership: Translation and Cultural Adaptation of the Original Quebec French Tool to Canadian English","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Equivalence (formal languages); Adaptation (eye); General partnership; Action (physics); Process (computing); Computer science; Linguistics; Sociology; Knowledge management; Psychology; Political science; Law","score_opus":0.3247910086417194,"score_gpt":0.4861257559367303,"score_spread":0.1613347472950109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995480421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99184716,0.00020975413,0.00046648923,0.0020207756,0.0010143947,0.00396321,0.000013270612,0.0000051554807,0.00045978703],"genre_scores_gemma":[0.9952596,0.0000056402573,0.0041436227,0.00011607488,0.00014601038,0.00018504281,0.000029917728,0.000008219616,0.00010591393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961118,0.0006235496,0.00093596533,0.00023584189,0.0018161137,0.0002766961],"domain_scores_gemma":[0.9938768,0.00024706373,0.0005764444,0.00022673557,0.0048184143,0.0002545494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014080497,0.00013215614,0.0002264427,0.0007713825,0.0001637696,0.0003021826,0.0002707685,0.00011421181,0.00044574784],"category_scores_gemma":[0.0025520509,0.00009753017,0.00010427619,0.00095357414,0.00003802684,0.0011854358,0.0000047916647,0.00016796445,0.000010712111],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033721797,0.000023946192,0.069045484,0.000019958656,0.000019300487,1.8386308e-7,0.013011036,0.021486478,0.00006667981,0.00040034478,0.00060865463,0.89528424],"study_design_scores_gemma":[0.0023986346,0.00049680076,0.4117397,0.000105254025,0.00015256218,0.000007381887,0.0061705755,0.47389725,0.00017200441,0.0017891956,0.10285396,0.0002166769],"about_ca_topic_score_codex":0.07168238,"about_ca_topic_score_gemma":0.9481723,"teacher_disagreement_score":0.8950675,"about_ca_system_score_codex":0.0013684297,"about_ca_system_score_gemma":0.010800431,"threshold_uncertainty_score":0.9948074},"labels":[],"label_agreement":null},{"id":"W2995564338","doi":"10.3138/cjpe.44172","title":"Dramatizing Learning, Performing Ourselves: Stories of Theatre-Based Evaluation in Vancouver's Downtown Eastside","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Downtown; Experiential learning; Citizen journalism; Process (computing); Sociology; Work (physics); Psychology; Visual arts; Pedagogy; Computer science; Art; History; Engineering; World Wide Web; Archaeology","score_opus":0.18181349197951518,"score_gpt":0.4904914886895171,"score_spread":0.3086779967100019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995564338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9855655,0.00046379643,0.00046738802,0.00044207808,0.0015601135,0.0016500336,0.0000030058397,0.000008375837,0.009839722],"genre_scores_gemma":[0.9972687,0.000004992527,0.0023384225,0.000053410186,0.00010603935,0.000061625535,0.000013721236,0.00001443405,0.00013869365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99232984,0.0013163689,0.0015123226,0.00027466088,0.004205612,0.0003612012],"domain_scores_gemma":[0.9930707,0.0005055747,0.0015343054,0.00034268826,0.0042610457,0.00028565133],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.036004562,0.00017995702,0.0004281971,0.0015251042,0.00016065875,0.000250658,0.00046974467,0.00012006815,0.0050746603],"category_scores_gemma":[0.0036732862,0.0001455251,0.00017616311,0.0012183039,0.00008591976,0.0011396545,0.000012985259,0.00040299603,0.00005305765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003095126,0.000038587837,0.2787705,0.000014416648,0.000016180436,0.0000011836049,0.003197883,0.13831022,0.0001033102,0.00006762804,0.0002698348,0.5791793],"study_design_scores_gemma":[0.0031385398,0.0011170144,0.14502928,0.00037817936,0.00013676978,0.000009295919,0.017680077,0.8150024,0.0004770867,0.0024769932,0.014298973,0.00025541012],"about_ca_topic_score_codex":0.0015546337,"about_ca_topic_score_gemma":0.08052174,"teacher_disagreement_score":0.6766922,"about_ca_system_score_codex":0.0010329253,"about_ca_system_score_gemma":0.010339598,"threshold_uncertainty_score":0.9958348},"labels":[],"label_agreement":null},{"id":"W2995590052","doi":"10.3138/cjpe.67854","title":"Anne Vo and Christina A. Christie (Eds.). (2015). <i>Evaluation Use and Decision Making in Society: A Tribute to Marvin C. Alkin.</i>","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tribute; Sociology; Psychology; Art history; Art","score_opus":0.19169266228507312,"score_gpt":0.4845022894400607,"score_spread":0.2928096271549876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995590052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892122,0.002665345,0.0019279723,0.0029177377,0.0006654882,0.0023857716,0.000019148652,0.000007739707,0.00019860158],"genre_scores_gemma":[0.98328537,0.000090285335,0.015734907,0.0005734625,0.0001137198,0.0000773916,0.000019106594,0.000016142396,0.00008961911],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945235,0.000560677,0.0011996992,0.00044248372,0.0028663215,0.00040728177],"domain_scores_gemma":[0.99475086,0.00075429364,0.00068533566,0.00035204442,0.0029269296,0.00053055707],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02814925,0.00020311175,0.0003983124,0.00088186574,0.00018976748,0.0010077455,0.0003078034,0.00013434829,0.0011356416],"category_scores_gemma":[0.004693377,0.0001713324,0.00009761785,0.0011246265,0.00007407059,0.0013687981,0.00004709563,0.00027666576,0.00005959097],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006330317,0.000026382186,0.100490265,0.000007847206,0.000014411098,0.0000036410233,0.0010919342,0.0024972316,0.00006644265,0.0000318404,0.01052303,0.8851837],"study_design_scores_gemma":[0.0029498588,0.0007857153,0.5986203,0.00035775735,0.00010274767,0.00007849902,0.0011042304,0.32843113,0.000025038926,0.0072170557,0.06004484,0.000282835],"about_ca_topic_score_codex":0.00060719886,"about_ca_topic_score_gemma":0.020773504,"teacher_disagreement_score":0.88490087,"about_ca_system_score_codex":0.00056851015,"about_ca_system_score_gemma":0.002841292,"threshold_uncertainty_score":0.99977744},"labels":[],"label_agreement":null},{"id":"W2995666448","doi":"10.3138/cjpe.67892","title":"Scott G. Chaplowe and J. Bradley Cousins. (2016). <i>Monitoring and Evaluation Training: A Systematic Approach.</i>","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Gerontology; Psychology; Training (meteorology); Sociology; Geography; Medicine","score_opus":0.3839926982165331,"score_gpt":0.4813167098258325,"score_spread":0.09732401160929943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995666448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872955,0.0038791357,0.00039532466,0.0006145721,0.0011494705,0.0036090838,0.0000034999186,0.000011678131,0.00304175],"genre_scores_gemma":[0.99643505,0.000045865454,0.0030065016,0.000069320624,0.00017468687,0.00012744864,0.0000060139446,0.0000151581735,0.00011996411],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939752,0.0009991007,0.0011402321,0.00033384436,0.0032324297,0.00031918343],"domain_scores_gemma":[0.9950581,0.00035922322,0.0009910926,0.00032742246,0.0027300133,0.0005341174],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034183476,0.00018047621,0.00046177502,0.00076517725,0.00022782579,0.00078894995,0.00029081304,0.00010737555,0.000334229],"category_scores_gemma":[0.0024638395,0.0001371327,0.00008021481,0.00055876083,0.00010242432,0.0010427341,0.000018200728,0.000220966,0.00004069405],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003799381,0.00007759279,0.061807334,0.00078916765,0.00013167995,0.0000040882956,0.018564316,0.0032491835,0.0003438074,0.000598879,0.00048797022,0.913908],"study_design_scores_gemma":[0.0050849053,0.0014172853,0.1693644,0.0031238045,0.0008223418,0.00050674344,0.0251038,0.78334564,0.000084909705,0.007182245,0.0033632661,0.00060069404],"about_ca_topic_score_codex":0.0001311894,"about_ca_topic_score_gemma":0.00054337806,"teacher_disagreement_score":0.9133073,"about_ca_system_score_codex":0.0003403353,"about_ca_system_score_gemma":0.0043828106,"threshold_uncertainty_score":0.99451137},"labels":[],"label_agreement":null},{"id":"W2995777958","doi":"10.3138/cjpe.67979","title":"Introduction to Articles Prepared by CES Calgary 2018 Keynote Panel Members on Reconciliation and Culturally Responsive Evaluation—Rhetoric or Reality?","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rhetoric; Sociology; Psychology; Political science; Linguistics; Philosophy","score_opus":0.298192845152364,"score_gpt":0.482247239067281,"score_spread":0.184054393914917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995777958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9761372,0.00023500859,0.00017909451,0.017889727,0.0017230528,0.0027318601,0.000017725419,0.0000145467975,0.0010717621],"genre_scores_gemma":[0.9952994,0.000027499595,0.0016232658,0.0005583528,0.0004838044,0.0001436715,0.00005880754,0.000013844937,0.001791329],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.993245,0.0015151884,0.0011384514,0.00047723515,0.003310933,0.00031319665],"domain_scores_gemma":[0.9927671,0.00047081342,0.00086730486,0.00042481304,0.0049016173,0.0005683263],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022021532,0.00018793074,0.00030826274,0.000699971,0.00025404838,0.0005248135,0.00030064216,0.0001167867,0.004492309],"category_scores_gemma":[0.010061924,0.00013409636,0.00008185433,0.0010666715,0.000065301836,0.0011661878,0.00001621337,0.00020015302,0.00022687107],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006380213,0.000055873392,0.0048941756,0.000008929792,0.000056648598,0.0000015823399,0.0046376507,0.009062464,0.0011347575,0.000116311705,0.11601484,0.86337876],"study_design_scores_gemma":[0.0054957643,0.0073133586,0.20588025,0.00022965304,0.0004767996,0.00012550698,0.010398343,0.29143617,0.0023208032,0.00691701,0.46857592,0.0008304217],"about_ca_topic_score_codex":0.0007140054,"about_ca_topic_score_gemma":0.014762315,"teacher_disagreement_score":0.86254835,"about_ca_system_score_codex":0.001257533,"about_ca_system_score_gemma":0.0036308572,"threshold_uncertainty_score":0.99827677},"labels":[],"label_agreement":null},{"id":"W2995932983","doi":"10.3138/cjpe.56989","title":"Comparison of Canadian and American Graduate Evaluation Education Programs","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Professionalization; Graduate education; Graduate students; Population; Political science; Medical education; Program evaluation; Higher education; Library science; Sociology; Public administration; Medicine; Demography; Computer science","score_opus":0.5628449880548297,"score_gpt":0.5884740088916572,"score_spread":0.0256290208368275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995932983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98841536,0.00045183432,0.000043712353,0.0024320518,0.0010606807,0.0022928086,0.0000047240637,0.000005103905,0.0052936957],"genre_scores_gemma":[0.997087,0.000016307999,0.002420412,0.00010174786,0.00010004623,0.000090777416,0.000048408336,0.0000122604615,0.00012305652],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99422926,0.00079220283,0.0012606959,0.00027178004,0.0031124535,0.00033362122],"domain_scores_gemma":[0.99010825,0.00013214955,0.0015076274,0.00036459192,0.0070752725,0.00081212196],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01694237,0.00015530927,0.0004243647,0.0026569616,0.00015652191,0.00033460572,0.00038861015,0.00006462626,0.0009349904],"category_scores_gemma":[0.0017376688,0.0001303522,0.0001048131,0.0022188833,0.00018314627,0.0006522115,0.0000100976895,0.00022998768,0.00006905767],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007503712,0.000046015073,0.30157816,0.0000054795,0.000016930211,1.593056e-7,0.0014368043,0.00056732184,0.000024335699,0.0001776186,0.001020863,0.6951188],"study_design_scores_gemma":[0.0009514865,0.0015771285,0.73783344,0.00012380326,0.00021716475,0.000026198019,0.012098402,0.19784367,0.00012437576,0.0042591714,0.044700127,0.0002450168],"about_ca_topic_score_codex":0.08616996,"about_ca_topic_score_gemma":0.6335765,"teacher_disagreement_score":0.6948738,"about_ca_system_score_codex":0.00063683133,"about_ca_system_score_gemma":0.020397993,"threshold_uncertainty_score":0.9999783},"labels":[],"label_agreement":null},{"id":"W2995943763","doi":"10.3138/cjpe.53185","title":"Applying the Collaborative Approaches to Evaluation (CAE) Principles in an Educational Evaluation: Reflections from the Field","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reflection (computer programming); Context (archaeology); Field (mathematics); Engineering ethics; Pedagogy; Sociology; Computer science; Engineering","score_opus":0.7739294717178385,"score_gpt":0.5731835285755595,"score_spread":0.200745943142279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995943763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9156168,0.00096763956,0.0005060228,0.056760304,0.002129241,0.01417696,0.000018075996,0.000008083501,0.009816851],"genre_scores_gemma":[0.99106425,0.00000535505,0.0027874857,0.0014363214,0.0005307214,0.003986441,0.00006611864,0.000012346681,0.00011095253],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9899672,0.003352681,0.0011689557,0.0004000222,0.004810856,0.00030023],"domain_scores_gemma":[0.9903373,0.002336147,0.00079622306,0.0007047181,0.0055249343,0.00030065625],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04425557,0.00017611706,0.0002406613,0.0005537582,0.00054104027,0.000923956,0.0009380155,0.000106062515,0.005897981],"category_scores_gemma":[0.009477187,0.00010670657,0.00009865348,0.0022950734,0.00007304966,0.001075723,0.000028834682,0.00038581208,0.00015427737],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047168513,0.00008829075,0.110185996,0.0000016433381,0.000040411483,2.3552985e-7,0.009364973,0.12333262,0.00005904006,0.0027204214,0.0027823832,0.7513768],"study_design_scores_gemma":[0.0012793286,0.0005991411,0.43605182,0.00007843647,0.00019636832,0.0000075983285,0.019700248,0.42519706,0.000096506075,0.031145396,0.085421585,0.00022652697],"about_ca_topic_score_codex":0.0012480197,"about_ca_topic_score_gemma":0.18605772,"teacher_disagreement_score":0.7511503,"about_ca_system_score_codex":0.0010866381,"about_ca_system_score_gemma":0.015527327,"threshold_uncertainty_score":0.9988664},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99171704,0.00041551667,0.00058727735,0.0039084135,0.00068136066,0.0020900876,0.000010431395,0.000029655395,0.00056023273],"genre_scores_gemma":[0.9963561,0.000062127394,0.0024747234,0.00024508606,0.00033343653,0.00024432712,0.000084820254,0.000035121102,0.00016422219],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967406,0.0010212089,0.0008123408,0.00029386755,0.0005190526,0.0006129403],"domain_scores_gemma":[0.99847883,0.000053694814,0.00051965367,0.00015635756,0.0003374999,0.00045397805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043715397,0.00024405548,0.00030233414,0.00031807565,0.00018627962,0.000130634,0.00025195978,0.00021451524,0.00041168704],"category_scores_gemma":[0.00010533587,0.00024219773,0.000206248,0.00042728812,0.00009290604,0.00023403091,0.000013572201,0.00029068676,0.000014550478],"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":[0.00009733306,0.00091848045,0.69423586,0.00009670877,0.000108708264,0.000050984032,0.015182961,0.00034774136,0.0006203104,0.0004676115,0.00057657016,0.2872967],"study_design_scores_gemma":[0.0037598829,0.00039767526,0.97450405,0.0009958367,0.00014024036,0.00014203232,0.0075118947,0.0019362089,0.00014411577,0.0031935351,0.006993823,0.00028068124],"about_ca_topic_score_codex":0.018326899,"about_ca_topic_score_gemma":0.113296226,"teacher_disagreement_score":0.28701603,"about_ca_system_score_codex":0.0013410681,"about_ca_system_score_gemma":0.0022174811,"threshold_uncertainty_score":0.98821014},"labels":[],"label_agreement":null},{"id":"W2996731041","doi":"10.3138/cjpe.68004","title":"Revisiting Contribution Analysis","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Set (abstract data type); Epistemology; Positive economics; Causal analysis; Narrative; Key (lock); Sociology; Economics; Computer science; Econometrics; Philosophy","score_opus":0.27443773986693065,"score_gpt":0.5383881020311411,"score_spread":0.2639503621642104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996731041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866833,0.00046629415,0.0037096005,0.002203968,0.0007378972,0.00083728903,0.0000056753033,0.0000071678496,0.005348801],"genre_scores_gemma":[0.9981985,0.0000044282547,0.0012129195,0.0001518297,0.00016783855,0.000013104472,0.00002285508,0.0000041001513,0.00022441258],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99591315,0.00055921596,0.0009378265,0.00017066041,0.0021922209,0.00022693958],"domain_scores_gemma":[0.99318534,0.00025444053,0.0009064205,0.00028257983,0.0050380845,0.0003331445],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023719734,0.00008365711,0.00029382145,0.0012265887,0.00012999315,0.00043305822,0.00033473456,0.00006114939,0.009356517],"category_scores_gemma":[0.003447909,0.000063875035,0.0002472199,0.0021739725,0.0000301729,0.00063461316,0.0000072127737,0.0001533913,0.0003742027],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007729902,0.000008769211,0.39414802,0.0000016082862,0.00011861573,0.0000017811099,0.00023417248,0.009463499,0.000045570356,0.0009116623,0.00039593328,0.59466267],"study_design_scores_gemma":[0.0009944829,0.00027390235,0.6328114,0.000035177458,0.0006561247,0.000016848502,0.00080946204,0.29135343,0.00008634327,0.0047493842,0.0680642,0.00014919335],"about_ca_topic_score_codex":0.00022371278,"about_ca_topic_score_gemma":0.0037138762,"teacher_disagreement_score":0.5945134,"about_ca_system_score_codex":0.00038281828,"about_ca_system_score_gemma":0.0026944184,"threshold_uncertainty_score":0.9915491},"labels":[],"label_agreement":null},{"id":"W300774755","doi":"10.3138/cjpe.23.007","title":"Bureaucratic Competence as an Essential Factor in Cross-Cultural/Multicultural Program Evaluations","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Bureaucracy; Multiculturalism; Competence (human resources); Equity (law); Affirmative action; Public relations; Social psychology; Political science; Cultural diversity; Sociology; Psychology; Law","score_opus":0.3771933823224479,"score_gpt":0.5862658034914479,"score_spread":0.20907242116899993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W300774755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945583,0.00019803066,0.00008534468,0.0009954217,0.00087271293,0.0021789982,0.000011282918,0.000027334278,0.0010725855],"genre_scores_gemma":[0.9929322,0.000017188464,0.006149189,0.00013418359,0.00025695065,0.00023451603,0.00006587774,0.000013793145,0.00019612719],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99265766,0.0010453827,0.0016408833,0.00040048157,0.0037461678,0.00050943776],"domain_scores_gemma":[0.98987716,0.0002350305,0.0008945939,0.00041194874,0.0077772494,0.00080400746],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070461854,0.00024405567,0.0003973906,0.0007787645,0.0005883127,0.0010989958,0.00079567166,0.00014818159,0.003436092],"category_scores_gemma":[0.005345708,0.00017533042,0.0001940205,0.0014256849,0.0004226934,0.0032585477,0.000018401368,0.00040576974,0.00021043487],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000641251,0.0005481958,0.27398023,0.000009828437,0.000052757947,0.00007214364,0.015050718,0.01665554,0.00063055387,0.0004711248,0.0008486017,0.6916162],"study_design_scores_gemma":[0.0022523978,0.0013585372,0.82542735,0.00006243756,0.00006213352,0.0003515336,0.0025946004,0.15825309,0.0002782136,0.0028937403,0.006136364,0.0003296135],"about_ca_topic_score_codex":0.0020875402,"about_ca_topic_score_gemma":0.048617553,"teacher_disagreement_score":0.69128656,"about_ca_system_score_codex":0.0006613167,"about_ca_system_score_gemma":0.0066077597,"threshold_uncertainty_score":0.99993795},"labels":[],"label_agreement":null},{"id":"W3009054679","doi":"10.3138/cjpe.69006","title":"Section 35 Legal Framework: Implications for Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Government (linguistics); General partnership; Duty; Political science; Public administration; Indigenous rights; Law; Work (physics); Sociology; Human rights; Engineering","score_opus":0.5534072977341611,"score_gpt":0.5909154903539823,"score_spread":0.03750819261982119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009054679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44655108,0.0017130167,0.35658816,0.16698115,0.0064507634,0.012559269,0.00012521794,0.000081430284,0.008949903],"genre_scores_gemma":[0.98389304,0.0000076041497,0.013195954,0.0011748625,0.001186455,0.00042606756,0.00005258479,0.00001574349,0.000047679892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99554497,0.0005734653,0.0011464745,0.00030726852,0.0021245296,0.00030328188],"domain_scores_gemma":[0.99009866,0.0004836185,0.0009429463,0.00029695357,0.007489684,0.0006881476],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016546195,0.00014254224,0.00025357067,0.0004883128,0.0004020646,0.0006439135,0.00049959036,0.00014386415,0.00201134],"category_scores_gemma":[0.013675429,0.00012145561,0.00021728204,0.0011678138,0.00006476268,0.0010487306,0.000010697622,0.0002742028,0.000052580595],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037730053,0.000033093736,0.009371821,0.000005935498,0.000036026493,3.362799e-7,0.0010871249,0.00981047,0.00014167008,0.0046389718,0.015298781,0.95953804],"study_design_scores_gemma":[0.0023751727,0.0013637771,0.11855814,0.00005084904,0.00038103506,0.00003625012,0.0013582102,0.4505213,0.00017204584,0.0799541,0.34494758,0.00028155756],"about_ca_topic_score_codex":0.00012660725,"about_ca_topic_score_gemma":0.0033389695,"teacher_disagreement_score":0.9592565,"about_ca_system_score_codex":0.0005514292,"about_ca_system_score_gemma":0.007864307,"threshold_uncertainty_score":0.99890095},"labels":[],"label_agreement":null},{"id":"W3009478627","doi":"10.3138/cjpe.68831","title":"Indigenous Health Service Evaluation: Principles and Guidelines from a Provincial “Three Ribbon” Expert Panel","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; Public Health Ontario","funders":"","keywords":"Indigenous; Service (business); Public relations; Sociology; Set (abstract data type); Political science; Business; Computer science; Marketing","score_opus":0.7302785118808507,"score_gpt":0.5552141874564791,"score_spread":0.1750643244243716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009478627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89072096,0.009654939,0.0027791688,0.091490515,0.0009891173,0.0038093426,0.000067793415,0.000028141872,0.00046000566],"genre_scores_gemma":[0.9669251,0.00010678961,0.019760048,0.011229036,0.001634093,0.0001948338,0.00009552366,0.000026661823,0.000027934084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99258554,0.000867268,0.001775779,0.00040346239,0.003998872,0.0003690956],"domain_scores_gemma":[0.98908085,0.00020762038,0.0013622433,0.00030560623,0.007908078,0.0011355871],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017671054,0.00020277924,0.00041917295,0.00035514616,0.00043079254,0.0006117627,0.0005757693,0.00010725164,0.0016701567],"category_scores_gemma":[0.006003613,0.00016124475,0.00009748613,0.00088632264,0.00006485543,0.00075220934,0.000038035425,0.00025069574,0.00006562448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003333134,0.000025569636,0.015670396,0.000007344054,0.000035311186,0.0000035901653,0.013738582,0.002473857,0.000022486112,0.000043837088,0.003788402,0.9641573],"study_design_scores_gemma":[0.0027765213,0.0012867481,0.1605062,0.0001498738,0.00014057558,0.00004254852,0.005972902,0.6925935,0.00004772913,0.00814747,0.12798578,0.00035015057],"about_ca_topic_score_codex":0.006869617,"about_ca_topic_score_gemma":0.1951328,"teacher_disagreement_score":0.96380717,"about_ca_system_score_codex":0.00054132345,"about_ca_system_score_gemma":0.02119541,"threshold_uncertainty_score":0.9997437},"labels":[],"label_agreement":null},{"id":"W3009649701","doi":"10.3138/cjpe.68866","title":"Identifying Key Epistemological Challenges Evaluating in Indigenous Contexts: Achieving <i>Bimaadiziwin</i> through Youth Futures","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Futures contract; Sociology; General partnership; Privilege (computing); Reciprocity (cultural anthropology); Field (mathematics); Agency (philosophy); Accountability; Government (linguistics); Work (physics); Public relations; Epistemology; Political science; Social science; Business; Law","score_opus":0.6425698594806223,"score_gpt":0.5452973114993448,"score_spread":0.09727254798127749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009649701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704447,0.011715303,0.0013109728,0.011262826,0.0009729837,0.0017865726,0.000012532323,0.000025149711,0.0024689834],"genre_scores_gemma":[0.99187154,0.00015113842,0.0063426886,0.0010780026,0.00045947,0.000052595333,0.000013577396,0.000017673,0.000013329947],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99222016,0.0018849988,0.0017925012,0.00044378926,0.0031299416,0.0005286331],"domain_scores_gemma":[0.99553305,0.00046060808,0.001220473,0.00028625963,0.0019202069,0.00057939993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021124378,0.00023041847,0.0005319702,0.00047919087,0.0003889843,0.00062078383,0.0008330968,0.00016772695,0.0007350711],"category_scores_gemma":[0.007796255,0.00018114444,0.00020406661,0.000985398,0.000116363466,0.00121468,0.000040054485,0.00057881785,0.000072882634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004969902,0.000047869715,0.027518125,0.000021815207,0.000032156364,0.000033176682,0.092896394,0.0027209271,0.00008399691,0.00034392017,0.00016666365,0.8760853],"study_design_scores_gemma":[0.010369391,0.006811726,0.6213431,0.0011551111,0.0006196181,0.00030315787,0.21807195,0.07200786,0.00036265855,0.04461674,0.022707483,0.0016312342],"about_ca_topic_score_codex":0.0005425654,"about_ca_topic_score_gemma":0.0153312255,"teacher_disagreement_score":0.874454,"about_ca_system_score_codex":0.00050436356,"about_ca_system_score_gemma":0.0038178444,"threshold_uncertainty_score":0.93334085},"labels":[],"label_agreement":null},{"id":"W3009664453","doi":"10.3138/cjpe.69095","title":"Reflections on Evaluating in Indigenous Contexts: Looking to the Future","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Sociology; Psychology; Environmental ethics; Political science; Philosophy; Ecology; Biology","score_opus":0.4296188597017498,"score_gpt":0.5859342152437196,"score_spread":0.1563153555419698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009664453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8813077,0.0008253325,0.0014002031,0.10671417,0.0020853668,0.0032135693,0.0000093289145,0.000015666059,0.00442867],"genre_scores_gemma":[0.9924153,0.000005764923,0.0015783014,0.005030607,0.00082658365,0.00009089896,0.0000035308904,0.000009652992,0.00003932431],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951438,0.0009285959,0.00091605267,0.00022481088,0.0024956956,0.0002910798],"domain_scores_gemma":[0.9965827,0.0002866592,0.0005031605,0.0002419806,0.0018856596,0.0004998369],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016687317,0.000116283976,0.00020490993,0.00058846874,0.00038109763,0.00045118504,0.0005917189,0.000065201944,0.00091461954],"category_scores_gemma":[0.004981509,0.00007565875,0.00009651227,0.0018435741,0.00003211284,0.00033333586,0.000013571195,0.0004150244,0.0001979785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033136243,0.000019470132,0.0067109233,0.000001568052,0.000011359283,0.000004849759,0.01721953,0.03247473,0.000044409633,0.000257227,0.002404424,0.94081837],"study_design_scores_gemma":[0.0030898112,0.006915718,0.29632738,0.00022875678,0.00013996415,0.000072532755,0.029120129,0.08666131,0.00018281494,0.008205314,0.5685603,0.000495959],"about_ca_topic_score_codex":0.000291784,"about_ca_topic_score_gemma":0.06980285,"teacher_disagreement_score":0.9403224,"about_ca_system_score_codex":0.00052790873,"about_ca_system_score_gemma":0.004617613,"threshold_uncertainty_score":0.9999987},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3009813686","doi":"10.3138/cjpe.68857","title":"Reflections on Being a Learner: The Value of Relationship-based Community Evaluations in Indigenous Communities","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Transformative learning; Indigenous; General partnership; Sociology; Value (mathematics); Power (physics); Work (physics); Process (computing); Traditional knowledge; Epistemology; Pedagogy; Political science; Computer science; Law","score_opus":0.6524773854460769,"score_gpt":0.5870706981648242,"score_spread":0.06540668728125276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009813686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787988,0.0001374298,0.0015642487,0.0130535485,0.00025947182,0.001337982,0.000012325649,0.000010594343,0.0048255767],"genre_scores_gemma":[0.997423,0.0000044722397,0.0013081626,0.0010608787,0.00006358239,0.00008429823,0.000024973331,0.000010713787,0.000019907708],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9906331,0.005716719,0.0012372332,0.00010293906,0.0020833218,0.00022672978],"domain_scores_gemma":[0.99339694,0.0027063477,0.00088692526,0.00047630572,0.0022801799,0.00025329957],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02528478,0.000125601,0.0002623462,0.0008652313,0.001002804,0.00022837188,0.00082539726,0.00008716528,0.0004767702],"category_scores_gemma":[0.008371669,0.00009164471,0.00014474177,0.0019903712,0.00021743796,0.0003846402,0.000018737459,0.0010197817,0.000024258798],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073596,0.00023008125,0.18238169,0.000013768752,0.00004290515,0.0000018634754,0.09603457,0.48141873,0.000048551046,0.008548895,0.000550102,0.23065524],"study_design_scores_gemma":[0.001624266,0.002003457,0.70621216,0.0001618988,0.00013963455,0.00001021236,0.037084613,0.22037613,0.00012853528,0.02580227,0.0062763,0.00018048806],"about_ca_topic_score_codex":0.0053115166,"about_ca_topic_score_gemma":0.11690757,"teacher_disagreement_score":0.5238305,"about_ca_system_score_codex":0.00044441392,"about_ca_system_score_gemma":0.006550034,"threshold_uncertainty_score":0.9999812},"labels":[],"label_agreement":null},{"id":"W3010143613","doi":"10.3138/cjpe.68914","title":"EvalIndigenous Origin Story: Effective Practices within Local Contexts to Inform the Field and Practice of Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Politics; Sovereignty; Field (mathematics); Traditional knowledge; Work (physics); Political science; Sociology; Environmental ethics; Law; Ecology; Engineering","score_opus":0.32734472912731394,"score_gpt":0.5695930311312456,"score_spread":0.24224830200393166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010143613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85992855,0.0018672509,0.008729443,0.11660341,0.0012760576,0.007814335,0.000011972434,0.00001242518,0.0037565602],"genre_scores_gemma":[0.99425024,0.000008897059,0.002043542,0.0033815992,0.00016546197,0.00012117763,0.0000040130994,0.000007844037,0.00001724159],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99245626,0.0025733288,0.00094113016,0.00022826916,0.0035861498,0.00021484584],"domain_scores_gemma":[0.9845653,0.004781647,0.0025803305,0.00024726978,0.007302778,0.00052263675],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051345635,0.00013437125,0.00027253886,0.0003212947,0.00035194773,0.0003473058,0.00036549827,0.00008543205,0.0005006816],"category_scores_gemma":[0.09824252,0.00008789764,0.00007596283,0.0010242583,0.0001189766,0.0013404123,0.000022957101,0.00036749706,0.00004171483],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028776142,0.00002962938,0.0025682691,0.000009965671,0.000073227435,0.0000034211805,0.024401965,0.009710553,0.000051975312,0.00043556886,0.0029276384,0.9595],"study_design_scores_gemma":[0.004589737,0.012473122,0.08205338,0.0001883021,0.001445532,0.00024757982,0.059299994,0.3801858,0.0012761599,0.0036418464,0.4541048,0.00049372256],"about_ca_topic_score_codex":0.0010170129,"about_ca_topic_score_gemma":0.013314665,"teacher_disagreement_score":0.9590063,"about_ca_system_score_codex":0.0003493222,"about_ca_system_score_gemma":0.006500561,"threshold_uncertainty_score":0.9991317},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3010351954","doi":"10.3138/cjpe.68837","title":"Indigenous Evaluation in the Northwest Territories: Opportunities and Challenges","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Service (business); Service delivery framework; Traditional knowledge; Service provider; Culturally appropriate; Economic growth; Political science; Business; Environmental planning; Geography; Medicine; Marketing; Economics; Gerontology","score_opus":0.6396488333319937,"score_gpt":0.4982009790427576,"score_spread":0.14144785428923612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010351954","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91979605,0.010290704,0.000050874438,0.06516319,0.0005776486,0.0019932468,0.000016132984,0.000006819404,0.002105323],"genre_scores_gemma":[0.997995,0.0006004435,0.00025663676,0.00071907474,0.0002990058,0.0000979168,0.000020861864,0.0000058356404,0.000005192246],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948937,0.0012267957,0.0007591508,0.00017596825,0.0027389983,0.0002053809],"domain_scores_gemma":[0.9968227,0.00030958414,0.00046562683,0.00018183081,0.0019009131,0.00031930328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023105726,0.000106611245,0.00018942554,0.0003808051,0.00019120576,0.00043403305,0.00044396255,0.00006256071,0.0004085932],"category_scores_gemma":[0.002749425,0.000070150236,0.00005235402,0.00046031558,0.00009619689,0.000665913,0.000009772127,0.00019547885,0.000008982055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008717841,0.00001816756,0.02345221,0.0000067338074,0.000009551516,0.000008074901,0.036292862,0.0004733738,0.000001417863,0.00030809877,0.00021937735,0.9392014],"study_design_scores_gemma":[0.0015400398,0.0013818659,0.6056171,0.000056843382,0.00013909019,0.0000843817,0.07781883,0.051145673,0.0000095252835,0.008036376,0.25395826,0.00021201753],"about_ca_topic_score_codex":0.0015881844,"about_ca_topic_score_gemma":0.1533991,"teacher_disagreement_score":0.9389894,"about_ca_system_score_codex":0.0001831499,"about_ca_system_score_gemma":0.0046953037,"threshold_uncertainty_score":0.86204916},"labels":[],"label_agreement":null},{"id":"W3010495354","doi":"10.3138/cjpe.69010","title":"Evaluation in Indigenous Contexts: An Introduction to Practice","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indigenous; Sociology; Psychology; Engineering ethics; Engineering; Ecology","score_opus":0.34926966146980354,"score_gpt":0.5540992470149855,"score_spread":0.20482958554518194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010495354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84315354,0.0006812068,0.004719151,0.14238529,0.0024902779,0.005166205,0.000008729239,0.000020476362,0.0013751101],"genre_scores_gemma":[0.9902486,0.0000048401807,0.0062493384,0.0022653902,0.0010549932,0.0001235934,0.000021195818,0.000011896358,0.00002014373],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99091893,0.0024892965,0.001243691,0.00036196536,0.004681341,0.00030478154],"domain_scores_gemma":[0.98831254,0.00021670181,0.00076405954,0.00030028555,0.009499016,0.00090739963],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051512063,0.00013146516,0.0002558008,0.0009070607,0.00015966692,0.0005227878,0.00048204866,0.000086033135,0.0021655636],"category_scores_gemma":[0.03342957,0.00011453134,0.00006704102,0.0018458207,0.000039242124,0.0022637988,0.000011757835,0.00029345634,0.00017803098],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006636264,0.00006706417,0.004245333,0.0000017800385,0.000016270527,0.0000052840564,0.01262439,0.029319735,0.00010181698,0.00012938968,0.0037860628,0.9496365],"study_design_scores_gemma":[0.003563789,0.005398589,0.102948755,0.000041327734,0.00037034802,0.000112905975,0.013690037,0.22158216,0.00026316184,0.0063542826,0.6452383,0.0004363784],"about_ca_topic_score_codex":0.00068151386,"about_ca_topic_score_gemma":0.032439716,"teacher_disagreement_score":0.94920015,"about_ca_system_score_codex":0.0010616806,"about_ca_system_score_gemma":0.009450715,"threshold_uncertainty_score":0.9987466},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89104307,0.0035452817,0.00019310563,0.02335192,0.0016240166,0.00081684394,0.00000405985,0.000024224559,0.07939746],"genre_scores_gemma":[0.99628276,0.0010311841,0.00092581625,0.00029873507,0.0010458874,0.000002446275,0.000004893458,0.000006500752,0.0004017681],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883896,0.0003318549,0.00022935426,0.00008028766,0.00029255403,0.00022699413],"domain_scores_gemma":[0.99821687,0.000036160814,0.0001848336,0.000039170343,0.0006829809,0.00084000453],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0016620625,0.00004927086,0.00009145509,0.0000913471,0.0018715065,0.000090838774,0.00009698987,0.00006962468,0.0002491881],"category_scores_gemma":[0.00007744691,0.000043992928,0.000030559906,0.00020023138,0.00010718791,0.00023642549,1.6832207e-7,0.00009069052,0.000005523693],"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":[0.000009644784,0.000022855987,0.0043939366,0.000017511811,0.000024247714,0.000007944461,0.37698087,0.0000137413435,0.0000018250462,0.058165792,0.0013254454,0.5590362],"study_design_scores_gemma":[0.00017371621,0.00017007942,0.0015312714,0.00001462925,0.000033135606,0.000006297592,0.0029841468,0.00025000595,0.000013382391,0.0036238283,0.9911372,0.00006231867],"about_ca_topic_score_codex":0.18282335,"about_ca_topic_score_gemma":0.9614127,"teacher_disagreement_score":0.9898117,"about_ca_system_score_codex":0.00030194703,"about_ca_system_score_gemma":0.05275208,"threshold_uncertainty_score":0.9994279},"labels":[],"label_agreement":null},{"id":"W301099006","doi":"","title":"Impacts of the Canadian Evaluation Society's Evaluation Competitions for Students: Guest Editors' Introduction.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Psychology; Sociology","score_opus":0.24853880815214335,"score_gpt":0.5377223463397195,"score_spread":0.28918353818757614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W301099006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84002084,0.0022584307,0.0020296304,0.04579933,0.07929932,0.024100538,0.0002445575,0.000028753737,0.0062186196],"genre_scores_gemma":[0.99269277,0.000008747716,0.002345321,0.00023176115,0.00409263,0.00044596117,0.00008535042,0.000019040308,0.00007839857],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882254,0.002079307,0.0015623869,0.0003478333,0.007310762,0.0004743019],"domain_scores_gemma":[0.9759462,0.00037160478,0.0015456983,0.00062382483,0.020848611,0.0006640707],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06580941,0.00020892154,0.00033610818,0.0007488673,0.0010249864,0.00060726865,0.00081641617,0.00018142421,0.0031228694],"category_scores_gemma":[0.018468855,0.00015440721,0.0004050302,0.0015616355,0.00022911547,0.000925958,0.000013217442,0.00030327376,0.000027418182],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004631585,0.00044486782,0.1639483,0.000046442296,0.00047851563,6.505608e-7,0.0066594807,0.04518969,0.00041546114,0.0052741705,0.53971344,0.23778266],"study_design_scores_gemma":[0.005851022,0.0009816992,0.20896375,0.00016863442,0.0015873831,0.00006127154,0.005440706,0.10948841,0.0010776299,0.028345883,0.6375509,0.0004827059],"about_ca_topic_score_codex":0.014352034,"about_ca_topic_score_gemma":0.69269085,"teacher_disagreement_score":0.6783388,"about_ca_system_score_codex":0.0032694072,"about_ca_system_score_gemma":0.0356213,"threshold_uncertainty_score":0.9977884},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98466885,0.00050691114,0.000090313675,0.004037621,0.0009739758,0.007663618,0.000009212794,0.00002623686,0.0020232727],"genre_scores_gemma":[0.99388504,0.000011433652,0.0032835673,0.0016264177,0.00027280394,0.00059851655,0.000070894166,0.00002323012,0.00022807391],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910512,0.0051456895,0.0015355218,0.000233637,0.0011623665,0.00087158586],"domain_scores_gemma":[0.9948646,0.00028893256,0.00080134865,0.00042938764,0.0018706918,0.0017450559],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022375213,0.0001961977,0.00041050327,0.00057439547,0.0021099597,0.000095960946,0.0002458866,0.00014469094,0.013643927],"category_scores_gemma":[0.0008134555,0.00019327387,0.00008104905,0.00049836154,0.000041596453,0.00042716027,0.000016464102,0.0012704064,0.00013348984],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000018842626,0.00017824766,0.06110146,0.000031342275,0.00007664071,0.00013521133,0.1549982,0.00003968055,6.3396396e-7,0.00000844875,0.0011161362,0.78229517],"study_design_scores_gemma":[0.010736182,0.0027614895,0.5487777,0.0008207959,0.00048806783,0.00063108624,0.22076526,0.004504899,0.0000016108557,0.0024566888,0.20741053,0.0006456715],"about_ca_topic_score_codex":0.8437783,"about_ca_topic_score_gemma":0.996617,"teacher_disagreement_score":0.7816495,"about_ca_system_score_codex":0.009808199,"about_ca_system_score_gemma":0.05883122,"threshold_uncertainty_score":0.99918914},"labels":[],"label_agreement":null},{"id":"W3028612984","doi":"10.3138/cjpe.61841","title":"Predicting Credentialed Evaluator Status: Characteristics, Comparisons, and Implications for the CE Program","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria; University of Saskatchewan","funders":"","keywords":"Scope (computer science); Sustainability; Order (exchange); Accounting; Political science; Actuarial science; Sociology; Public economics; Business; Economics; Computer science; Finance","score_opus":0.4209077424068388,"score_gpt":0.5372251137668627,"score_spread":0.11631737136002385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028612984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8664732,0.004367845,0.030133888,0.082273774,0.0019376079,0.013718896,0.00029748798,0.00007871394,0.0007186214],"genre_scores_gemma":[0.9901622,0.000053613116,0.008222036,0.0005213452,0.00046726022,0.0004969058,0.000041104642,0.0000136880035,0.000021881862],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966795,0.0003925508,0.001099409,0.00025462292,0.0012295794,0.00034435015],"domain_scores_gemma":[0.9936703,0.00077994436,0.0009936683,0.00025810557,0.0035665457,0.0007314287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009374411,0.00013554555,0.0002728821,0.00019377764,0.00061480753,0.0010362909,0.000472483,0.000064709326,0.00046095822],"category_scores_gemma":[0.008119296,0.000092448994,0.00012371225,0.0005406236,0.00014400398,0.0004892527,0.000022779162,0.00021358799,0.000012759049],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028100872,0.00003086979,0.22060452,0.000008293332,0.000048612732,2.5202615e-7,0.0011805607,0.00021846846,0.0000309982,0.0002503714,0.006717866,0.7708811],"study_design_scores_gemma":[0.00092362874,0.00066474243,0.5238436,0.000020973639,0.00024960094,0.000010938259,0.0018674121,0.32515803,0.000012149773,0.00091746694,0.1462282,0.000103281374],"about_ca_topic_score_codex":0.0001556882,"about_ca_topic_score_gemma":0.003321597,"teacher_disagreement_score":0.7707778,"about_ca_system_score_codex":0.00016536018,"about_ca_system_score_gemma":0.0041843103,"threshold_uncertainty_score":0.9992976},"labels":[],"label_agreement":null},{"id":"W3029887321","doi":"10.3138/cjpe.61270","title":"A Rapid Review of Evaluation Capacity-Building Strategies for Chronic Disease Prevention","year":2020,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Impact; University of Waterloo","funders":"","keywords":"CLARITY; Context (archaeology); Capacity building; Grey literature; Medicine; Political science; Public relations; Psychology; Business; MEDLINE; Biology","score_opus":0.6926985361281605,"score_gpt":0.6014460517410005,"score_spread":0.09125248438715994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029887321","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020472615,0.9845556,0.0031098344,0.0006435616,0.0009905531,0.010271683,0.00010119213,0.000008464499,0.00029866325],"genre_scores_gemma":[0.0004967671,0.9935335,0.0034513634,0.00008267113,0.000621253,0.0014681706,0.0002847773,0.000036179244,0.000025323041],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9881361,0.0029641236,0.0035386595,0.0004810693,0.004511487,0.00036856145],"domain_scores_gemma":[0.9845138,0.0006176855,0.0054684123,0.00055017805,0.008098514,0.00075141387],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041885644,0.00038473768,0.001776932,0.0010992808,0.00020355567,0.0004248145,0.0007797296,0.00018702711,0.0026366143],"category_scores_gemma":[0.011071915,0.00029382392,0.0013189891,0.0015533676,0.00011926923,0.0010467762,0.000021853397,0.00039858563,0.000028827246],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071317227,0.000030236552,0.0000034580203,0.016836375,0.00012720644,0.0000014491815,0.00010278455,0.0001524076,2.9020524e-7,0.0005258355,0.002577225,0.9796356],"study_design_scores_gemma":[0.0005918743,0.000767686,0.00003236463,0.059179787,0.0045991703,0.00002259059,0.00010472386,0.014274045,6.297901e-7,0.0100628575,0.9101128,0.0002514677],"about_ca_topic_score_codex":0.000043287517,"about_ca_topic_score_gemma":0.0011036523,"teacher_disagreement_score":0.9793841,"about_ca_system_score_codex":0.0018964339,"about_ca_system_score_gemma":0.080941595,"threshold_uncertainty_score":0.99995136},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9234629,0.00025934642,0.0645714,0.005904754,0.0004613101,0.0038185748,0.000009409074,0.000093551185,0.0014187113],"genre_scores_gemma":[0.97386026,0.00002123014,0.0232258,0.0004136615,0.001326848,0.000604467,0.00024563834,0.000068869806,0.00023319479],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9863473,0.009960681,0.0012277826,0.00044832958,0.00092587335,0.0010899972],"domain_scores_gemma":[0.995219,0.0004737166,0.0012179145,0.00027017784,0.0016328673,0.0011863046],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.028144283,0.00029549006,0.00038153472,0.00033210512,0.0019425405,0.00010458158,0.00025853052,0.00043624724,0.00010584537],"category_scores_gemma":[0.00584219,0.00029196803,0.0001224826,0.00089572574,0.00033512485,0.00060872,0.000024846207,0.00091188273,0.000016587817],"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":true,"study_design_scores_codex":[0.00021409758,0.00063668116,0.19558178,0.0009082733,0.000105052175,0.000016574219,0.25978243,0.0022582868,0.007933362,0.0011300808,0.00083370705,0.53059965],"study_design_scores_gemma":[0.004413199,0.0012313721,0.8849305,0.0005525639,0.00039947755,0.00017378834,0.040055156,0.028088143,0.0011651574,0.03497808,0.0035896013,0.0004229885],"about_ca_topic_score_codex":0.00705472,"about_ca_topic_score_gemma":0.010724952,"teacher_disagreement_score":0.6893487,"about_ca_system_score_codex":0.0055850567,"about_ca_system_score_gemma":0.031282593,"threshold_uncertainty_score":0.99995327},"labels":[],"label_agreement":null},{"id":"W3031036335","doi":"10.3138/cjpe.61624","title":"Evaluation in the Provinces and Territories: A Cross-Canada Snapshot and Call to Action","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island; University of Victoria; Université Laval; Dalhousie University","funders":"","keywords":"Snapshot (computer storage); Government (linguistics); Public administration; Political science; State (computer science); Action (physics); Regional science; Public relations; Geography; Computer science","score_opus":0.4273514882657697,"score_gpt":0.5421958438593792,"score_spread":0.11484435559360956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031036335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739662,0.00040697056,0.00008848599,0.022966756,0.0004173494,0.001498191,0.000007812656,0.0000021011424,0.00064613257],"genre_scores_gemma":[0.99785733,0.000007943819,0.0004521502,0.0013414884,0.00022712896,0.00009305065,0.000008911477,0.0000042609245,0.000007739226],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950007,0.0008113966,0.0006576784,0.00021962263,0.0031216752,0.00018892932],"domain_scores_gemma":[0.99687696,0.00028095525,0.0003256682,0.00013491616,0.0019774141,0.00040411792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018768318,0.00010061355,0.00016289369,0.00022607928,0.00019460155,0.00074834574,0.00028534824,0.00004704018,0.00032963883],"category_scores_gemma":[0.0064143785,0.00006705979,0.000025749649,0.00065639993,0.00006897769,0.0006411579,0.000012589803,0.00018228496,0.0000025414586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027556813,0.000011466481,0.10977822,0.0000070778865,0.000011134509,0.000004017509,0.0062019904,0.0020795176,0.000033787317,0.00007475714,0.0033232195,0.87844723],"study_design_scores_gemma":[0.001131879,0.0008097955,0.74557894,0.000037175574,0.00008816783,0.00003826668,0.007100509,0.14606667,0.000050244707,0.0021127698,0.09683095,0.00015465372],"about_ca_topic_score_codex":0.09195006,"about_ca_topic_score_gemma":0.94499004,"teacher_disagreement_score":0.8782926,"about_ca_system_score_codex":0.00046496475,"about_ca_system_score_gemma":0.008853809,"threshold_uncertainty_score":0.9967651},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789098,0.0063520176,0.0060989866,0.0063870186,0.0008636888,0.000882234,0.00002832455,0.000026415573,0.00045152192],"genre_scores_gemma":[0.99297124,0.0001588241,0.006147014,0.00036302244,0.00020329829,0.000017784601,0.000018972845,0.000011991331,0.000107874825],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96741784,0.031175412,0.0004638681,0.00019578802,0.00041317838,0.00033393453],"domain_scores_gemma":[0.99479365,0.0032848932,0.0003268721,0.00009438503,0.0007892344,0.000710981],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.084262095,0.00011483771,0.00026436627,0.00016891396,0.00064040825,0.00016600724,0.00018607057,0.00018693716,0.00024978808],"category_scores_gemma":[0.04004244,0.00011570446,0.00006572783,0.0004980759,0.00035603123,0.000309341,0.0000075906028,0.0003218471,0.000009254706],"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":[0.0011916899,0.00004790481,0.45937458,0.000021129377,0.00014223703,0.00004141359,0.018860668,0.00024723198,0.00026688224,0.0005912226,0.0070118443,0.5122032],"study_design_scores_gemma":[0.0006375079,0.00024568886,0.9665632,0.00004793554,0.00008886682,0.0000090464,0.0016307433,0.00028010432,0.000052316467,0.0007834591,0.029499019,0.0001620901],"about_ca_topic_score_codex":0.04341823,"about_ca_topic_score_gemma":0.3798405,"teacher_disagreement_score":0.5120411,"about_ca_system_score_codex":0.00023384848,"about_ca_system_score_gemma":0.0049848026,"threshold_uncertainty_score":0.9680437},"labels":[],"label_agreement":null},{"id":"W3031535673","doi":"10.3138/cjpe.61660","title":"A Transdisciplinary Model of Program Outcomes for Enhanced Evaluation Practice","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Taxonomy (biology); Management science; Context (archaeology); Psychology; Program evaluation; Cognition; Computer science; Knowledge management; Process management; Political science; Ecology; Business; Engineering","score_opus":0.6071453782410605,"score_gpt":0.6059684492511166,"score_spread":0.0011769289899439261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031535673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7731614,0.00089898065,0.1348249,0.0658646,0.0013137662,0.017281484,0.000103000835,0.00005265678,0.006499202],"genre_scores_gemma":[0.9364724,0.00000849848,0.062105753,0.000577876,0.0001291014,0.0006191282,0.00003251037,0.000016760645,0.00003792903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931051,0.00071531394,0.0016600806,0.00032286556,0.0038766414,0.00032001224],"domain_scores_gemma":[0.98621047,0.0006718162,0.0016157718,0.00029348666,0.010623391,0.0005850527],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021927936,0.00018204197,0.00045643927,0.00044809058,0.00020346706,0.00024649285,0.0005685971,0.00011592322,0.00059628434],"category_scores_gemma":[0.013926356,0.00014202688,0.00031794567,0.00086551136,0.00010358208,0.0013410931,0.000012989241,0.00021055536,0.000016246235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001721246,0.0001750773,0.00065671373,0.000025826708,0.00008635393,6.70479e-7,0.010795212,0.09600993,0.00053590175,0.00029180964,0.0013935665,0.8898568],"study_design_scores_gemma":[0.0025944225,0.002137423,0.0031941812,0.000041627383,0.00050853414,0.000005687465,0.005649282,0.9694816,0.00075795903,0.009220995,0.0062376033,0.00017072202],"about_ca_topic_score_codex":0.00003765104,"about_ca_topic_score_gemma":0.0014601893,"teacher_disagreement_score":0.8896861,"about_ca_system_score_codex":0.0003075083,"about_ca_system_score_gemma":0.009650147,"threshold_uncertainty_score":0.9959642},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9050521,0.0036642668,0.0011009731,0.08619331,0.00059295725,0.0019810514,0.000016153517,0.000021704895,0.0013774872],"genre_scores_gemma":[0.9868133,0.00005829354,0.011485739,0.00091356813,0.00049342477,0.000056476794,0.000121418074,0.000022506572,0.00003527823],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975493,0.00021676152,0.0007415388,0.0001988623,0.0010580849,0.00023543004],"domain_scores_gemma":[0.9964584,0.000047275957,0.0005830609,0.00017866056,0.0022802355,0.0004523297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031112544,0.00014050606,0.00030299058,0.00033714995,0.00012830121,0.00005848734,0.00012715126,0.00013896235,0.0005616183],"category_scores_gemma":[0.005929621,0.0001309433,0.00007918136,0.00055513,0.00023580197,0.00022608605,0.0000056697263,0.00038143317,0.000008942019],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006104126,0.00009390626,0.004782101,0.0001775348,0.000103830986,0.0000069064736,0.0033119796,0.00014347547,0.0020304825,0.0006960993,0.024474405,0.96411824],"study_design_scores_gemma":[0.015097037,0.006426771,0.17399465,0.002152898,0.005378109,0.0008043015,0.026588313,0.12233237,0.0052652275,0.0076570795,0.63324577,0.0010574864],"about_ca_topic_score_codex":0.00039796464,"about_ca_topic_score_gemma":0.0006098129,"teacher_disagreement_score":0.96306074,"about_ca_system_score_codex":0.00035629462,"about_ca_system_score_gemma":0.0049162903,"threshold_uncertainty_score":0.8721288},"labels":[],"label_agreement":null},{"id":"W3031765893","doi":"10.3138/cjpe.56949","title":"Reflections on Inter-University Collaboration to Deliver a Graduate Certificate in Evaluation to Government of the Northwest Territories Employees","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Northwest Territories; Carleton University; University of Victoria","funders":"","keywords":"Credential; Negotiation; Government (linguistics); Certificate; Public relations; Higher education; Process (computing); sort; Political science; Sociology; Medical education; Business; Computer science; Medicine","score_opus":0.596189237013459,"score_gpt":0.5212415559789882,"score_spread":0.0749476810344708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031765893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9713792,0.000010998118,0.00077692984,0.024779137,0.0007096737,0.0016938751,0.000053832176,0.000004389304,0.0005919391],"genre_scores_gemma":[0.99843675,0.0000022763425,0.0008979903,0.0004977463,0.00009248853,0.00003281315,0.0000063723614,0.0000061623364,0.000027413742],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99462956,0.0008391772,0.0007048129,0.00022398864,0.0034249085,0.00017753118],"domain_scores_gemma":[0.99557906,0.0001229563,0.00048826332,0.00024814744,0.003197532,0.00036403688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006448949,0.00010516255,0.00018289484,0.00036153238,0.00019675579,0.00016449769,0.0004680901,0.000045587818,0.0002527598],"category_scores_gemma":[0.0038280317,0.00007991156,0.00008196738,0.0022787962,0.000044025393,0.00048566228,0.000028819113,0.00015932642,0.00002168186],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030780677,0.00013904415,0.08329698,0.0000070290334,0.00003427497,0.000002743056,0.027245285,0.0934075,0.000830339,0.00039551212,0.0032378538,0.7910956],"study_design_scores_gemma":[0.0012094956,0.0021262784,0.9046745,0.00014816773,0.00012862576,0.0000028424347,0.01664973,0.036879472,0.0015685492,0.001029724,0.035385873,0.00019675095],"about_ca_topic_score_codex":0.0018672079,"about_ca_topic_score_gemma":0.308831,"teacher_disagreement_score":0.8213775,"about_ca_system_score_codex":0.0013332188,"about_ca_system_score_gemma":0.0021979646,"threshold_uncertainty_score":0.703781},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9880835,0.00019661458,0.0000048197203,0.011175544,0.000041174026,0.00039001307,0.00000619805,0.0000044556905,0.000097689335],"genre_scores_gemma":[0.99712634,0.000005219107,0.0020411212,0.0005542388,0.0002144562,0.000012776332,0.00004206503,5.0068263e-7,0.0000033068086],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990825,0.00020411726,0.00032719012,0.00007691886,0.00018800072,0.000121245415],"domain_scores_gemma":[0.9987858,0.00014095282,0.00039324668,0.000015880136,0.0005221787,0.00014192294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012991114,0.00005893785,0.00011410633,0.000029590337,0.00007768181,0.000077005454,0.00012455111,0.000043157164,0.0004485727],"category_scores_gemma":[0.0007391934,0.000023584604,0.00004194865,0.00061985716,0.000034148547,0.00054800697,0.0000074643813,0.000120411336,0.0000023142254],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010969954,0.000015910515,0.026219776,0.000007651324,0.000008991039,0.000003758557,0.0013270662,0.000013799694,0.009539213,0.00033996513,0.0004946965,0.9620182],"study_design_scores_gemma":[0.00024599227,0.00070727995,0.93182087,0.0000743317,0.000043735647,0.000015351627,0.0031043566,0.0017334456,0.00036975238,0.0023929381,0.059365463,0.00012648405],"about_ca_topic_score_codex":0.0032401443,"about_ca_topic_score_gemma":0.024232762,"teacher_disagreement_score":0.9618917,"about_ca_system_score_codex":0.000047552483,"about_ca_system_score_gemma":0.000063396415,"threshold_uncertainty_score":0.9935725},"labels":[],"label_agreement":null},{"id":"W3032165765","doi":"10.3138/cjpe.56898","title":"Scope Creep and Purposeful Pivots in Developmental Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Scope (computer science); Stakeholder; Set (abstract data type); Session (web analytics); Psychology; Knowledge management; Engineering ethics; Plenary session; Process management; Pedagogy; Public relations; Business; Political science; Computer science; Engineering; World Wide Web; Library science","score_opus":0.5926935965616887,"score_gpt":0.5368839960960672,"score_spread":0.055809600465621556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032165765","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98544574,0.0012897893,0.00037335407,0.00688785,0.00035673205,0.0016624707,0.000003820924,0.0000065259924,0.003973745],"genre_scores_gemma":[0.994355,0.000022535525,0.004783292,0.0006097408,0.00012441778,0.000066492335,0.000011121617,0.000008250393,0.000019150388],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99493706,0.0007133594,0.0010264624,0.00025693263,0.0028167001,0.00024949227],"domain_scores_gemma":[0.9964918,0.000152528,0.00049663434,0.00011443268,0.002129491,0.00061510067],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0176788,0.00012463312,0.00024220053,0.0005970921,0.00013759386,0.00041325914,0.00032171898,0.000074262025,0.0028606656],"category_scores_gemma":[0.0054082414,0.00010407021,0.00005573801,0.0010182856,0.000075287746,0.0008916627,0.00001915441,0.00021327351,0.00008777385],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021863862,0.000018454064,0.07771953,0.0000038823086,0.000011049327,0.000005652514,0.0027110144,0.0015088392,0.00008957023,0.00007871567,0.0013270733,0.9165044],"study_design_scores_gemma":[0.0034426353,0.0007915074,0.60869676,0.00009285744,0.00009378631,0.00007198458,0.0050374456,0.33856526,0.00024600243,0.005414617,0.037270658,0.00027652952],"about_ca_topic_score_codex":0.0002498645,"about_ca_topic_score_gemma":0.01895737,"teacher_disagreement_score":0.9162278,"about_ca_system_score_codex":0.0005846668,"about_ca_system_score_gemma":0.008260373,"threshold_uncertainty_score":0.9989441},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9621668,0.0004690399,0.0034550047,0.02607693,0.00047798007,0.0008642599,0.0000030626236,0.000034719567,0.006452229],"genre_scores_gemma":[0.9781009,0.000067086425,0.019678423,0.00035349093,0.0016656122,0.000067347915,0.0000327628,0.000009265982,0.000025123973],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9931501,0.0056557753,0.00037102346,0.000114474606,0.00047718725,0.00023139661],"domain_scores_gemma":[0.99698395,0.00061158324,0.0003785752,0.000057591144,0.0014999178,0.000468379],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020973744,0.0000807682,0.00012564851,0.00015965577,0.0007614664,0.00014940804,0.00016474127,0.00014726067,0.00020838316],"category_scores_gemma":[0.012637582,0.00008085381,0.00007418157,0.00059476396,0.0006320188,0.00045157116,0.0000026329155,0.00026577196,0.0000046538453],"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":[0.000009512697,0.000061978106,0.08136961,0.000023989858,0.00007477677,0.0000024569015,0.58491015,0.0007151325,0.00024453521,0.017900655,0.0020679596,0.31261924],"study_design_scores_gemma":[0.0011018866,0.00052418455,0.29427287,0.00019819073,0.00042875163,0.000014126124,0.5912863,0.008128283,0.00017936082,0.066267915,0.03725536,0.00034278873],"about_ca_topic_score_codex":0.005731813,"about_ca_topic_score_gemma":0.023214519,"teacher_disagreement_score":0.31227645,"about_ca_system_score_codex":0.00050195336,"about_ca_system_score_gemma":0.011670923,"threshold_uncertainty_score":0.9956794},"labels":[],"label_agreement":null},{"id":"W304700293","doi":"10.3138/cjpe.0025.007","title":"Program Evaluation without a Client: The Case of the Disappearing Intended Users","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Negotiation; Meaning (existential); Business; Knowledge management; Process management; Public relations; Computer science; Psychology; Sociology; Political science","score_opus":0.5459869971696891,"score_gpt":0.541121227098997,"score_spread":0.00486577007069211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W304700293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98685867,0.00024956593,0.00028325166,0.0013104124,0.0012845367,0.004485179,0.0000051393563,0.000010758688,0.0055125128],"genre_scores_gemma":[0.9974064,0.0000041191956,0.0019745934,0.00011356086,0.00009987418,0.00031556372,0.0000032481641,0.000012315653,0.00007027721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939367,0.0016206357,0.0012595516,0.00023233287,0.002629548,0.0003212037],"domain_scores_gemma":[0.99243283,0.00018537161,0.0014944772,0.0006563702,0.0049312636,0.00029968438],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030844795,0.00015668097,0.00024807875,0.00039228125,0.00045261014,0.00028690163,0.00088864483,0.00008385684,0.0014410826],"category_scores_gemma":[0.0045776744,0.00008147099,0.0002461696,0.0012042788,0.00033847528,0.00061010214,0.000041316573,0.0003371756,0.000023262173],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026860904,0.00008473519,0.05782231,0.0000046426617,0.000049162976,0.0000073553238,0.0072370055,0.00078131526,0.000014808085,0.0006124868,0.0003905117,0.9329688],"study_design_scores_gemma":[0.0028931757,0.0014746679,0.43494707,0.00024299831,0.0009517064,0.0011508828,0.026392564,0.49136388,0.00058262947,0.026480231,0.013171706,0.00034847893],"about_ca_topic_score_codex":0.0020402046,"about_ca_topic_score_gemma":0.0654992,"teacher_disagreement_score":0.93262035,"about_ca_system_score_codex":0.0003972367,"about_ca_system_score_gemma":0.00456622,"threshold_uncertainty_score":0.9994717},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907132,0.00063663675,0.00034094375,0.0023934273,0.00025587904,0.0006419641,0.0000074847626,0.00002865983,0.004981804],"genre_scores_gemma":[0.99015296,0.00016232903,0.008322428,0.0000670628,0.0008453473,0.00008878903,0.000071481874,0.00001666021,0.0002729452],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99679697,0.0014940111,0.000462901,0.00016270348,0.00042898097,0.0006544453],"domain_scores_gemma":[0.99774706,0.0001791034,0.00032973196,0.00010087106,0.0008671045,0.0007761209],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00968769,0.00013759977,0.00020028508,0.0002560004,0.0011716827,0.00022288077,0.00024511904,0.00016343294,0.0013438943],"category_scores_gemma":[0.0010361287,0.00014214597,0.00019577313,0.00052960496,0.0006324151,0.00042652467,0.0000019420297,0.0002466928,0.000010574479],"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":[0.000018573706,0.00015817687,0.12208024,0.000018006427,0.00016070818,0.000013452652,0.1454531,0.0009271369,0.00003343793,0.0010498151,0.00075561577,0.72933173],"study_design_scores_gemma":[0.0015363185,0.0005256103,0.86627144,0.00013306606,0.00039392267,0.00035041076,0.093831316,0.0017574386,0.00011745535,0.023122042,0.011606626,0.00035438262],"about_ca_topic_score_codex":0.012295231,"about_ca_topic_score_gemma":0.0695367,"teacher_disagreement_score":0.74419117,"about_ca_system_score_codex":0.0011041802,"about_ca_system_score_gemma":0.008569257,"threshold_uncertainty_score":0.999569},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9218054,0.011377812,0.014114326,0.026113035,0.00022509394,0.005984315,0.00004711722,0.000024318017,0.020308577],"genre_scores_gemma":[0.9797064,0.000059025744,0.019444015,0.00011609769,0.00016565205,0.00021187238,0.00005714964,0.000012046589,0.00022774344],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.951624,0.043256447,0.0009769272,0.000445473,0.0030084706,0.0006887292],"domain_scores_gemma":[0.98482096,0.0031574867,0.00046839644,0.00020863756,0.010166116,0.0011784065],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08490693,0.00019487503,0.00075869495,0.002000415,0.00067761185,0.00042655267,0.0004866014,0.00013863578,0.0024745425],"category_scores_gemma":[0.011873214,0.00018524165,0.00019809001,0.0075779166,0.0013485489,0.00063630653,0.000033934914,0.00076406763,0.00006799763],"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":[0.00012066448,0.00017690581,0.010246177,0.000020581429,0.0014682523,0.000008098804,0.8368463,0.0025607657,0.00043532922,0.008535389,0.011667338,0.1279142],"study_design_scores_gemma":[0.0036411935,0.0018226497,0.06940025,0.00014993046,0.0020608783,0.0000034066377,0.56485385,0.089386635,0.0003795467,0.067799315,0.199631,0.00087135186],"about_ca_topic_score_codex":0.017122848,"about_ca_topic_score_gemma":0.39590827,"teacher_disagreement_score":0.37878543,"about_ca_system_score_codex":0.0012888983,"about_ca_system_score_gemma":0.006643245,"threshold_uncertainty_score":0.99898815},"labels":[],"label_agreement":null},{"id":"W3099471317","doi":"10.3138/cjpe.70004","title":"Sustainability Analysis of Intervention Benefits: A Theory of Change Approach","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sustainability; Intervention (counseling); Spell; Sustainability organizations; Work (physics); Environmental economics; Business; Environmental resource management; Economics; Psychology; Engineering; Sociology; Ecology","score_opus":0.6214875283452821,"score_gpt":0.5413536083546764,"score_spread":0.0801339199906057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099471317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98255146,0.0010922652,0.011808764,0.002313226,0.00016530626,0.0012737425,0.000034112167,0.0000047861386,0.0007563237],"genre_scores_gemma":[0.99839,0.0000059218273,0.0013700711,0.000090294794,0.000059766506,0.000043418157,0.000024719511,0.0000044368203,0.000011323392],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99562496,0.0010028692,0.0012988154,0.00017837128,0.0017391881,0.0001557717],"domain_scores_gemma":[0.99189144,0.00020184646,0.0014336187,0.00024655458,0.0059143566,0.00031217796],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019280892,0.00008898947,0.00041678766,0.0010742384,0.00005517175,0.0000713291,0.00042073455,0.00006246421,0.0014010329],"category_scores_gemma":[0.0052697198,0.000069008885,0.00039992196,0.002886235,0.0001155159,0.0005020531,0.000016918622,0.00012208727,0.0000022864515],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005865338,0.00009999217,0.06936284,0.00003405463,0.00027119258,5.039697e-7,0.0066078305,0.00864966,0.000007777219,0.0030077226,0.000102567785,0.9117972],"study_design_scores_gemma":[0.0010083291,0.0012537453,0.6038186,0.000041698324,0.0017153384,0.000002748413,0.01683423,0.36118963,0.00012940465,0.012241746,0.0016357858,0.0001287778],"about_ca_topic_score_codex":0.0004851808,"about_ca_topic_score_gemma":0.0032415525,"teacher_disagreement_score":0.9116684,"about_ca_system_score_codex":0.00023722743,"about_ca_system_score_gemma":0.0017338933,"threshold_uncertainty_score":0.99951184},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803661,0.00009232506,0.0009339378,0.016003372,0.00017945825,0.000771507,0.0000018092846,0.000023506971,0.0016279629],"genre_scores_gemma":[0.9961604,9.271861e-7,0.0016341145,0.0011574753,0.000966491,0.000041520943,0.000018045968,0.000013594309,0.0000074410373],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987444,0.000048308862,0.00046329031,0.00017527334,0.000330065,0.0002386518],"domain_scores_gemma":[0.9981307,0.000015614698,0.00034548875,0.000045575136,0.0014288138,0.000033835804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028054377,0.00011918336,0.00021261086,0.00074008945,0.0002459484,0.00016235223,0.00016008105,0.00011679076,0.000048456786],"category_scores_gemma":[0.0013708529,0.00012433407,0.000024786694,0.001835688,0.00008995219,0.00054789067,0.000039040777,0.00029899436,0.000013294877],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003641228,0.000028473805,0.20388918,0.00006590075,0.00009641594,0.00001334554,0.031270042,0.00003487123,0.0001749629,0.03610888,0.0020213271,0.7262602],"study_design_scores_gemma":[0.0020811036,0.00018630322,0.89591736,0.000119127464,0.00015211992,0.000002337094,0.028905598,0.0026981982,0.000149065,0.041216563,0.028062847,0.00050937553],"about_ca_topic_score_codex":0.0002460868,"about_ca_topic_score_gemma":0.0018352312,"teacher_disagreement_score":0.7257508,"about_ca_system_score_codex":0.00031235273,"about_ca_system_score_gemma":0.00056995085,"threshold_uncertainty_score":0.50701964},"labels":[],"label_agreement":null},{"id":"W3101505332","doi":"10.3138/cjpe.69796","title":"Application of an Evaluation Framework for Extra-Organizational Communities of Practice: Assessment and Refinement","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; University of Toronto","funders":"","keywords":"Knowledge management; Community of practice; Reflection (computer programming); Work (physics); Content analysis; Value (mathematics); Qualitative research; Psychology; Sociology; Computer science; Pedagogy","score_opus":0.39468624739554886,"score_gpt":0.5735482175325376,"score_spread":0.17886197013698873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101505332","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5844133,0.0007600186,0.39189678,0.01631832,0.00043101294,0.0050588483,0.000085355554,0.000011601284,0.001024785],"genre_scores_gemma":[0.8624265,0.000016459508,0.13693596,0.00027078882,0.00010800297,0.0001303033,0.000100089586,0.000009485617,0.0000023656787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99495184,0.00090320036,0.0012512258,0.00016051382,0.0025945976,0.00013861185],"domain_scores_gemma":[0.98655564,0.00088383025,0.0018417946,0.00026981652,0.010152747,0.00029620464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017980173,0.0001093446,0.00027657417,0.00033130933,0.00017017053,0.0001381568,0.0003518717,0.00008813043,0.0006926258],"category_scores_gemma":[0.005154195,0.00009546447,0.00006631176,0.00064104603,0.00011910054,0.0007936285,0.000015747682,0.00016239511,0.0000016386068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077104865,0.00015807421,0.0233405,0.00003696322,0.00007181567,1.894008e-7,0.007891189,0.0116040055,0.00036827454,0.020631703,0.00021968823,0.9356005],"study_design_scores_gemma":[0.0017278092,0.0022523266,0.096228786,0.00007029239,0.00040701116,0.0000114715585,0.0151813775,0.824194,0.0004683102,0.049169097,0.010135074,0.00015443032],"about_ca_topic_score_codex":0.00024647475,"about_ca_topic_score_gemma":0.0016281464,"teacher_disagreement_score":0.9354461,"about_ca_system_score_codex":0.0002292271,"about_ca_system_score_gemma":0.0046716174,"threshold_uncertainty_score":0.8287249},"labels":[],"label_agreement":null},{"id":"W3102015017","doi":"10.3138/cjpe.61723","title":"Anticipating and Addressing Stakeholders’ Stereotypes of Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Process (computing); Psychology; Focus (optics); Applied psychology; Knowledge management; Social psychology; Public relations; Computer science; Political science","score_opus":0.8194598612454987,"score_gpt":0.5817553033009218,"score_spread":0.2377045579445769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102015017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912761,0.0009585619,0.0016633159,0.0034825956,0.00028807123,0.0008615734,0.0000061900237,0.0000049241703,0.001458669],"genre_scores_gemma":[0.99582136,0.0000069455523,0.0037990683,0.00021384751,0.00012184085,0.000015586342,0.000006443446,0.0000073186993,0.0000075817175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952951,0.00073061587,0.0010128025,0.00018090005,0.0025988796,0.0001817008],"domain_scores_gemma":[0.99427783,0.00024023325,0.0010761688,0.0001459437,0.0038474703,0.00041233253],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015764358,0.0000977372,0.0002550548,0.00037221113,0.00014379494,0.00027916458,0.0001999865,0.000055773733,0.0015061442],"category_scores_gemma":[0.0055506895,0.00007835988,0.0000702759,0.0006264579,0.0000986505,0.0006800175,0.000013502483,0.00014955524,0.000009215393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016615553,0.000013826747,0.037047863,0.000013681823,0.000022824495,0.0000017448846,0.004993834,0.0031406991,0.0002853249,0.000077829434,0.00052192225,0.95386386],"study_design_scores_gemma":[0.0017748896,0.00091749954,0.16140446,0.00015852704,0.0002596739,0.000021547177,0.00713078,0.82040095,0.0006078466,0.0031361787,0.0040228735,0.00016474577],"about_ca_topic_score_codex":0.0001763856,"about_ca_topic_score_gemma":0.00209044,"teacher_disagreement_score":0.9536991,"about_ca_system_score_codex":0.0001154148,"about_ca_system_score_gemma":0.0034779427,"threshold_uncertainty_score":0.99940664},"labels":[],"label_agreement":null},{"id":"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011401389,0.031379305,0.6150454,0.2505924,0.031659078,0.041784365,0.0084015485,0.00034947172,0.009387003],"genre_scores_gemma":[0.94406486,0.00011805949,0.00097546505,0.014875434,0.027182512,0.00037435544,0.012146488,0.00009414508,0.00016867073],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982968,0.00006816979,0.00045605868,0.00032744763,0.00056648906,0.00028505467],"domain_scores_gemma":[0.99685544,0.00021012679,0.0006101855,0.0007831449,0.0014672707,0.00007382842],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003045944,0.00017289698,0.0001870135,0.000120775934,0.00066859135,0.00089453295,0.0021050018,0.00006993555,0.0024340786],"category_scores_gemma":[0.0012778473,0.0001029478,0.000058775557,0.0006835958,0.00014174357,0.0035519826,0.00017116067,0.00020662356,0.000092852526],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005033773,0.000034712306,0.00044846412,0.00008953428,0.0001394272,0.000006907769,0.00008823016,0.00011000965,0.000015973701,0.00287464,0.8016954,0.19444634],"study_design_scores_gemma":[0.0004099364,0.000044591903,0.00204698,0.000051814306,0.00037859564,0.000013009436,0.00013106482,0.118125916,0.000036468642,0.0010604862,0.8775637,0.00013743842],"about_ca_topic_score_codex":0.0005797228,"about_ca_topic_score_gemma":0.017249873,"teacher_disagreement_score":0.9326635,"about_ca_system_score_codex":0.00006410142,"about_ca_system_score_gemma":0.0006733353,"threshold_uncertainty_score":0.9984778},"labels":[],"label_agreement":null},{"id":"W3103082364","doi":"10.3138/cjpe.69230","title":"The Use and Benefits of Evaluation Framework Modules at the Canadian Foundation for Healthcare Improvement: Engaged Capacity Building and Collaborative Program Evaluation Planning","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Public Health; Canadian Foundation for Healthcare Improvement","funders":"","keywords":"Foundation (evidence); Participatory evaluation; Citizen journalism; Health care; Process management; Computer science; Knowledge management; Program evaluation; Capacity building; Engineering management; Management science; Business; Engineering; Sociology; Political science; World Wide Web","score_opus":0.5503134362738925,"score_gpt":0.515309111644216,"score_spread":0.03500432462967651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103082364","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9678161,0.0028790396,0.0012219856,0.017584652,0.0004907303,0.00990196,0.00006343205,0.00000871249,0.000033402237],"genre_scores_gemma":[0.9888532,0.00005531249,0.009348217,0.00041698103,0.00019597888,0.0010461829,0.0000619748,0.000016343718,0.000005813844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99214256,0.0028073683,0.0011822381,0.00038068378,0.0030803496,0.00040678892],"domain_scores_gemma":[0.982356,0.0023703766,0.0014307993,0.00029195956,0.012907173,0.0006436524],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04529775,0.00020359039,0.00029539163,0.0003389568,0.0030119496,0.0013480929,0.00029174917,0.00015551418,0.00009006776],"category_scores_gemma":[0.03141608,0.00013468767,0.000075816366,0.0010914024,0.00028506338,0.0009911429,0.00002724756,0.0004821217,0.0000016703282],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007137342,0.0000122515885,0.011973148,0.00002140684,0.00006252884,2.4240018e-7,0.009899853,0.019746631,0.00005535333,0.001096052,0.0002839925,0.95677716],"study_design_scores_gemma":[0.0018194274,0.0016995125,0.14034507,0.00019703427,0.00041685477,0.000012646784,0.0075124595,0.81800234,0.0003349686,0.013119352,0.016313853,0.00022647728],"about_ca_topic_score_codex":0.0095621245,"about_ca_topic_score_gemma":0.54916793,"teacher_disagreement_score":0.9565507,"about_ca_system_score_codex":0.0012247888,"about_ca_system_score_gemma":0.0075859954,"threshold_uncertainty_score":0.9996886},"labels":[],"label_agreement":null},{"id":"W3103842672","doi":"10.3138/cjpe.68127","title":"Comparing and Contrasting a Program versus System Approach to Evaluation: The Example of a Cardiac Care System","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Perspective (graphical); Set (abstract data type); Systems theory; Management science; Computer science; Systems thinking; Risk analysis (engineering); Medicine; Artificial intelligence; Engineering; Programming language","score_opus":0.5917953680574175,"score_gpt":0.4872887842568676,"score_spread":0.10450658380054989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103842672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97356254,0.0024872741,0.0016924606,0.0010664184,0.001252901,0.007667538,0.000019416138,0.000040985928,0.012210451],"genre_scores_gemma":[0.99457914,0.0000012915149,0.004719719,0.00003948381,0.00022140559,0.00041061998,0.000013963922,0.000011820786,0.0000025627974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99373543,0.0012830779,0.001152212,0.00030762205,0.0032354833,0.00028618527],"domain_scores_gemma":[0.9926455,0.000419087,0.0008512164,0.00030889036,0.0051465444,0.0006287539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016202027,0.00016330808,0.0004986289,0.00027894526,0.00033956757,0.00049654447,0.0004887957,0.00006659338,0.000029494186],"category_scores_gemma":[0.002375698,0.0001093098,0.00014725719,0.0010073942,0.00008817219,0.00031108342,0.000032516407,0.00019963314,0.00001013486],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010823102,0.000029904368,0.040696498,0.00016371868,0.00016865646,0.0000012028114,0.01986929,0.016226813,0.000027057305,0.001931404,0.00046486518,0.92031235],"study_design_scores_gemma":[0.0022163135,0.0012021216,0.078981206,0.0002205522,0.0006141992,0.000019689833,0.09186068,0.8151121,0.000046386507,0.000024727682,0.009508091,0.00019394209],"about_ca_topic_score_codex":0.0011575806,"about_ca_topic_score_gemma":0.0016035581,"teacher_disagreement_score":0.9201184,"about_ca_system_score_codex":0.00064672384,"about_ca_system_score_gemma":0.003296984,"threshold_uncertainty_score":0.5848708},"labels":[],"label_agreement":null},{"id":"W3105492687","doi":"10.3138/cjpe.69535","title":"Toward Learning from Change Pathways: Reviewing Theory of Change and Its Discontents","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Underpinning; Vagueness; Theory of change; Context (archaeology); Stakeholder; Process (computing); Stakeholder engagement; Epistemology; Management science; Knowledge management; Sociology; Computer science; Political science; Public relations; Economics; Engineering; Artificial intelligence","score_opus":0.918735116591738,"score_gpt":0.5122009043033375,"score_spread":0.4065342122884005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105492687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97238964,0.018003825,0.00045675572,0.006803091,0.00048648426,0.0014744519,0.000016269696,0.000008239178,0.00036121858],"genre_scores_gemma":[0.9982341,0.00026243457,0.00037701966,0.0006695898,0.00036322346,0.000062485946,0.0000119636225,0.000008143978,0.000011054998],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967198,0.00085095933,0.00075575995,0.00018200437,0.0013165972,0.00017490466],"domain_scores_gemma":[0.99706817,0.00022081891,0.0008225329,0.00010439384,0.0013323546,0.00045174247],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008744089,0.00010391631,0.00030417967,0.00022715415,0.000107031025,0.0001526376,0.0002821319,0.000053033265,0.0010590168],"category_scores_gemma":[0.0043763984,0.000077629826,0.00009439585,0.00041896195,0.000042015996,0.0009068071,0.00002240047,0.00020059934,0.000025901212],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017488468,0.000009742632,0.023970192,0.000016942678,0.00002328758,0.0000041396956,0.017120501,0.000030458998,0.00010318835,0.00030707257,0.00006208722,0.9583349],"study_design_scores_gemma":[0.004172196,0.003367363,0.65621674,0.0015609455,0.00064144173,0.000034286437,0.032176528,0.223127,0.0007680103,0.019987805,0.057268564,0.0006791361],"about_ca_topic_score_codex":0.00025435392,"about_ca_topic_score_gemma":0.00076927635,"teacher_disagreement_score":0.9576558,"about_ca_system_score_codex":0.00008091484,"about_ca_system_score_gemma":0.00066466996,"threshold_uncertainty_score":0.99985415},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842717,0.003389371,0.000019100267,0.00032183158,0.0006957039,0.002219611,0.0000037582124,0.0000059443337,0.009072996],"genre_scores_gemma":[0.9992324,0.00025715886,0.00013952407,0.00001800373,0.00030527296,0.000015520787,0.000016269443,0.000008141671,0.000007670726],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9920956,0.0060939146,0.00070708647,0.00009509353,0.00070010964,0.00030821035],"domain_scores_gemma":[0.9958184,0.00022168932,0.0005849812,0.00009421374,0.0029115693,0.0003691857],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.009853915,0.00009259527,0.00025604843,0.0005083304,0.0013800944,0.00007405597,0.00021019364,0.00013523374,0.00006077238],"category_scores_gemma":[0.00021959409,0.00009257606,0.000047048434,0.000887277,0.00018319632,0.00048003966,7.57618e-7,0.00043833593,0.000003994377],"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":[0.000015536285,0.00015956342,0.007588304,0.000110506175,0.00001840241,0.0000022079323,0.931653,0.0014549922,0.0000081037,0.001270732,0.000012055985,0.057706565],"study_design_scores_gemma":[0.0035853328,0.0011989783,0.34844813,0.0011490651,0.00026618337,0.000019219826,0.553348,0.0145587465,0.00012522696,0.0031016613,0.07375134,0.0004480892],"about_ca_topic_score_codex":0.37482807,"about_ca_topic_score_gemma":0.97162014,"teacher_disagreement_score":0.5967921,"about_ca_system_score_codex":0.0020370767,"about_ca_system_score_gemma":0.08636552,"threshold_uncertainty_score":0.99991995},"labels":[],"label_agreement":null},{"id":"W310937889","doi":"10.3138/cjpe.0014.008","title":"Building Capacity for School Improvement through Evaluation: Experiences of the Manitoba School Improvement Program Inc.","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Empowerment; Context (archaeology); Capacity building; Perspective (graphical); Program evaluation; Sociology; Pedagogy; Medical education; Political science; Medicine; Public administration; Computer science; Geography","score_opus":0.28399040238513046,"score_gpt":0.49536869734142874,"score_spread":0.21137829495629828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W310937889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859704,0.0004154865,0.00092825486,0.0014612571,0.0015956064,0.008289523,0.000019519988,0.000015620444,0.0013043372],"genre_scores_gemma":[0.9683853,0.000014383563,0.0278922,0.000407945,0.00043867808,0.0027056711,0.0000111647505,0.000018012817,0.00012667438],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913845,0.0006382205,0.0020010653,0.00043036873,0.005011192,0.00053467514],"domain_scores_gemma":[0.9908492,0.00021446917,0.0015456002,0.0006777025,0.0061623575,0.000550681],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020459356,0.00026205578,0.00040580065,0.00034204967,0.00063757825,0.0006353807,0.0011850046,0.00013459493,0.009022727],"category_scores_gemma":[0.0036907396,0.0001744118,0.00032547401,0.0010480263,0.00026667974,0.0013138187,0.00003199249,0.00031553442,0.000034315995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039081384,0.00014180942,0.0024906327,0.00001383314,0.000061144245,3.2681857e-7,0.003229478,0.0016927881,0.00041104498,0.00017420613,0.0023313903,0.9894143],"study_design_scores_gemma":[0.013594025,0.013666087,0.11362757,0.0007060917,0.0014584586,0.00007802564,0.07137163,0.30638275,0.023023315,0.08422739,0.37036663,0.0014980285],"about_ca_topic_score_codex":0.0010672663,"about_ca_topic_score_gemma":0.008927734,"teacher_disagreement_score":0.98791623,"about_ca_system_score_codex":0.0013338315,"about_ca_system_score_gemma":0.008725105,"threshold_uncertainty_score":0.9968945},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.972138,0.00081971014,0.0033935413,0.014303344,0.00031069914,0.001369625,0.00001584757,0.000028591345,0.007620661],"genre_scores_gemma":[0.9924744,0.00021428306,0.00469461,0.0008477915,0.0011998619,0.00027828242,0.000025660951,0.00003099644,0.00023413052],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99114954,0.006474748,0.0008987074,0.00017974073,0.0005789891,0.0007182679],"domain_scores_gemma":[0.9953165,0.0009411797,0.0009224091,0.00018276123,0.0016704808,0.00096664706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015659891,0.00015846099,0.00030467767,0.00035000694,0.0012548009,0.000045599096,0.0002100512,0.00033787233,0.0002401281],"category_scores_gemma":[0.0042633987,0.00015135827,0.000116266994,0.00054733705,0.00013148553,0.00044541314,0.000007674548,0.0008159194,0.000018670724],"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":[0.00005094482,0.0001036327,0.83861375,0.0002822057,0.00009226261,0.00017434936,0.04837339,0.00082558795,0.00023137494,0.001049921,0.0040687094,0.10613385],"study_design_scores_gemma":[0.0014719231,0.00032161808,0.8791951,0.0004392444,0.00016602212,0.0006397243,0.009234895,0.009410052,0.00005861919,0.0048058755,0.094046205,0.0002107405],"about_ca_topic_score_codex":0.13412586,"about_ca_topic_score_gemma":0.2268493,"teacher_disagreement_score":0.10592311,"about_ca_system_score_codex":0.0018933737,"about_ca_system_score_gemma":0.051627494,"threshold_uncertainty_score":0.9651041},"labels":[],"label_agreement":null},{"id":"W3136354237","doi":"10.3138/cjpe.69703","title":"UEval: Bringing Community-Based Experiential Learning to the Evaluation Classroom","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Patient Safety Institute; University of Alberta","funders":"","keywords":"Experiential learning; Curriculum; Citizen journalism; Pedagogy; Psychology; Experiential education; Participatory action research; Engineering ethics; Medical education; Sociology; Political science; Engineering; Medicine","score_opus":0.4370275756617095,"score_gpt":0.5432201279952923,"score_spread":0.10619255233358277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136354237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9688201,0.00051509315,0.011173976,0.011887356,0.0022284742,0.0014488269,0.0000044460853,0.000018819826,0.003902938],"genre_scores_gemma":[0.9950172,0.0000023059583,0.0032568593,0.001017068,0.00029784013,0.00013343267,0.00004640814,0.000015037538,0.00021389793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98832387,0.0056635574,0.001010481,0.00021894088,0.004428613,0.0003545698],"domain_scores_gemma":[0.98915535,0.0006719451,0.00063830294,0.0005464165,0.008511859,0.0004761083],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052164398,0.00014454313,0.00023264553,0.00061154255,0.0011698308,0.0010817653,0.00068064773,0.00007730879,0.004186662],"category_scores_gemma":[0.012679966,0.00010743241,0.00018526759,0.0015583376,0.00007104506,0.00048960425,0.000035393594,0.0006728011,0.00014687581],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015659594,0.000045953086,0.007763531,0.000003515436,0.000024459194,0.0000043074174,0.006367557,0.15349004,0.00018395057,0.00007005888,0.0034826875,0.8285483],"study_design_scores_gemma":[0.0015060583,0.00052142545,0.04616685,0.000104743376,0.00019270368,0.00005097486,0.018792639,0.58845913,0.0010190508,0.0018092564,0.34115764,0.00021951836],"about_ca_topic_score_codex":0.0005040291,"about_ca_topic_score_gemma":0.031057104,"teacher_disagreement_score":0.8283288,"about_ca_system_score_codex":0.0007104546,"about_ca_system_score_gemma":0.010812149,"threshold_uncertainty_score":0.99995524},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9551468,0.00045657347,0.00000478696,0.02767035,0.001308926,0.0008586877,0.0000016437298,0.0000055629894,0.014546677],"genre_scores_gemma":[0.9979517,0.00029057977,0.00013742705,0.0005106661,0.00063234905,0.00009175953,0.000009345568,0.000004268343,0.0003719363],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99643,0.0011429734,0.00023985514,0.0001677568,0.0017138409,0.00030562197],"domain_scores_gemma":[0.9966459,0.00015755916,0.0002151526,0.00008937906,0.0024639207,0.00042809013],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0056123086,0.000079394114,0.00010662226,0.0001272842,0.000677254,0.00050283567,0.00030246397,0.000076825374,0.001587959],"category_scores_gemma":[0.0045330036,0.00006478862,0.000052150932,0.0005453348,0.00019009589,0.0005592988,0.000019586432,0.00024165232,0.000016244187],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045300076,0.00009270182,0.020058628,0.0000023419072,0.00005033395,0.00001807787,0.086000845,0.0000203603,0.00022296543,0.0012920565,0.0025542579,0.8896421],"study_design_scores_gemma":[0.0036564653,0.0012510779,0.052034896,0.00040288648,0.00016550354,0.00010469183,0.47311583,0.0013795288,0.0025224397,0.01563942,0.44917083,0.0005564475],"about_ca_topic_score_codex":0.005373457,"about_ca_topic_score_gemma":0.038393077,"teacher_disagreement_score":0.8890857,"about_ca_system_score_codex":0.00082217774,"about_ca_system_score_gemma":0.0055243145,"threshold_uncertainty_score":0.99932474},"labels":[],"label_agreement":null},{"id":"W3136555995","doi":"10.3138/cjpe.69601","title":"In Their Own Words: Student Key Learning Experiences in an Introductory Evaluation Course","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Key (lock); Psychology; Taxonomy (biology); Mathematics education; Grounded theory; Pedagogy; Reflective practice; Medical education; Computer science; Qualitative research; Sociology; Medicine","score_opus":0.3004856471172792,"score_gpt":0.5460008305135504,"score_spread":0.2455151833962712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136555995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99300796,0.0016568552,0.00008310242,0.0022634363,0.0014282252,0.00081683794,0.0000010699605,0.0000051600978,0.0007373744],"genre_scores_gemma":[0.99847054,0.000022764376,0.00070397736,0.00017905862,0.00030095642,0.00021005464,0.000019492238,0.000010024898,0.00008310154],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9912131,0.0032249668,0.0013261394,0.00038616871,0.0034850477,0.00036457786],"domain_scores_gemma":[0.9943844,0.0002517065,0.00067496643,0.0003482431,0.0039712554,0.00036943896],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037638105,0.00015615427,0.000320679,0.000947509,0.00016578793,0.0006072193,0.00050196215,0.00009474828,0.0060878736],"category_scores_gemma":[0.004405719,0.00012683732,0.00008587003,0.0016421422,0.00009816337,0.0017482262,0.000020376066,0.00044364439,0.000029893452],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016359138,0.00019076728,0.23499136,0.0000021768212,0.000011685599,0.000023838396,0.06911349,0.034797367,0.000117337484,0.00007544222,0.0002681127,0.66039205],"study_design_scores_gemma":[0.0020874536,0.0006361747,0.5431609,0.000093060946,0.00005104526,0.000044819295,0.24312393,0.19424066,0.0002939992,0.003568417,0.012444334,0.00025517397],"about_ca_topic_score_codex":0.00029876406,"about_ca_topic_score_gemma":0.11728419,"teacher_disagreement_score":0.6601369,"about_ca_system_score_codex":0.0009943933,"about_ca_system_score_gemma":0.010381027,"threshold_uncertainty_score":0.9952292},"labels":[],"label_agreement":null},{"id":"W3136672375","doi":"10.3138/cjpe.69698","title":"Praxis Makes Perfect? Transcending Textbooks to Learning Evaluation Experientially and in Cultural Contexts","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Praxis; Transformative learning; Experiential learning; Value (mathematics); White privilege; Sociology; Professional development; Harm; Pedagogy; Psychology; Privilege (computing); Epistemology; Engineering ethics; Racism; Social psychology; Law; Computer science","score_opus":0.3037025959764343,"score_gpt":0.5365116728649787,"score_spread":0.2328090768885444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136672375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99158823,0.0013201667,0.00054956175,0.0022528376,0.0005995813,0.0010366024,0.0000021013186,0.000006373819,0.0026445303],"genre_scores_gemma":[0.99741626,0.000015727064,0.0018924413,0.00017109017,0.00011342184,0.000104894214,0.0000143299485,0.000009402418,0.000262416],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99472946,0.0013778318,0.00092193275,0.00030650647,0.0023646797,0.00029958354],"domain_scores_gemma":[0.9947652,0.00020604926,0.0003664052,0.00016514148,0.0040458683,0.00045133146],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01655265,0.00013689997,0.00026693146,0.00069394195,0.0002802042,0.00075062463,0.00020029914,0.00008034825,0.0025730862],"category_scores_gemma":[0.005984348,0.000115309,0.000092158974,0.0007854334,0.00006053195,0.0007780063,0.000012251125,0.00027129133,0.000027521535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029481116,0.000026180973,0.040971465,0.0000046481046,0.000016026612,0.00001302594,0.01477202,0.007228677,0.0013972193,0.00009025961,0.00029399444,0.935157],"study_design_scores_gemma":[0.0062453393,0.0015431658,0.6091605,0.0005116861,0.0002710367,0.00035444566,0.05367481,0.2280794,0.0031268944,0.003949814,0.09238772,0.00069523155],"about_ca_topic_score_codex":0.00022673253,"about_ca_topic_score_gemma":0.04398987,"teacher_disagreement_score":0.9344618,"about_ca_system_score_codex":0.00049598416,"about_ca_system_score_gemma":0.004210208,"threshold_uncertainty_score":0.9983387},"labels":[],"label_agreement":null},{"id":"W3137000688","doi":"10.3138/cjpe.69691","title":"Collaborative Evaluation Designs as an Authentic Course Assessment","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Authentic assessment; Computer science; Evaluation methods; Graduate students; Authentic learning; Instructional design; Knowledge management; Psychology; Mathematics education; Pedagogy; Curriculum; Multimedia; Engineering","score_opus":0.36482317151236154,"score_gpt":0.5893866504709884,"score_spread":0.22456347895862683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137000688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9690569,0.0014604473,0.004543146,0.006147327,0.0034469704,0.0026499897,0.000025084368,0.000020764817,0.012649379],"genre_scores_gemma":[0.988532,0.000015814729,0.010323825,0.000296206,0.00026118965,0.00016722358,0.00009164624,0.000016409249,0.00029568854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9884252,0.0036153018,0.0012884726,0.0003946455,0.005902145,0.0003742486],"domain_scores_gemma":[0.9753858,0.00043398014,0.0010967017,0.00055171206,0.021676373,0.00085541967],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.036915123,0.00019126628,0.00034612845,0.00057251874,0.0004316792,0.001171792,0.00050394144,0.00012514103,0.015462528],"category_scores_gemma":[0.006553598,0.00016136793,0.00014794982,0.0018355697,0.000118694115,0.001539735,0.000016010054,0.0002956272,0.00017102678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016477741,0.00026987356,0.01649594,0.0000037693662,0.000095709234,0.000035865054,0.0032991555,0.0077280686,0.0002514436,0.002511824,0.0034264436,0.96586543],"study_design_scores_gemma":[0.004017423,0.0023502673,0.26874328,0.00012397548,0.0010483796,0.00025746968,0.024794089,0.5616567,0.0010181216,0.08269292,0.05276803,0.0005293419],"about_ca_topic_score_codex":0.00020467104,"about_ca_topic_score_gemma":0.02224159,"teacher_disagreement_score":0.9653361,"about_ca_system_score_codex":0.001115312,"about_ca_system_score_gemma":0.059748795,"threshold_uncertainty_score":0.9998651},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884766,0.00029247304,0.00009680328,0.007331121,0.0010934375,0.0006104242,0.0000013350718,0.000008228521,0.0020896157],"genre_scores_gemma":[0.99412113,0.000023392437,0.002045006,0.002839612,0.00062278466,0.00005919077,0.000035292618,0.000014772514,0.00023881871],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99818563,0.00016935811,0.00041305507,0.00012957907,0.00087199244,0.00023040485],"domain_scores_gemma":[0.997634,0.000040532963,0.00021758332,0.00021824458,0.0017077898,0.00018188255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027644325,0.00010226613,0.00015948815,0.00024416024,0.00023326429,0.00009668648,0.00018751873,0.0000736144,0.0004259791],"category_scores_gemma":[0.0015059097,0.00006968454,0.000081054655,0.0006168279,0.0001025848,0.00013858244,0.000009139763,0.0005144938,0.000026499269],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003078409,0.00024780456,0.03240775,0.000030407156,0.00009200708,0.000010826493,0.003477607,0.00005602638,0.00019233483,0.000027238037,0.00862072,0.9548065],"study_design_scores_gemma":[0.004240984,0.0031555726,0.788655,0.003204029,0.00061997,0.0018933981,0.011878366,0.02135173,0.0057269256,0.00041727486,0.15847605,0.0003807297],"about_ca_topic_score_codex":0.00004333533,"about_ca_topic_score_gemma":0.0005598191,"teacher_disagreement_score":0.95442575,"about_ca_system_score_codex":0.0008714278,"about_ca_system_score_gemma":0.00368718,"threshold_uncertainty_score":0.6540899},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739891,0.0050819498,0.00034637508,0.0047093863,0.0006528764,0.0016329167,0.0000057637108,0.000002461161,0.013579152],"genre_scores_gemma":[0.9981844,0.000022932856,0.0015000071,0.00009511161,0.00009105185,0.00006534847,0.000008596547,0.0000060905672,0.000026500107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9855009,0.005973899,0.0016548142,0.00019148132,0.0064227404,0.0002561956],"domain_scores_gemma":[0.98870754,0.0018873108,0.0015428147,0.000457453,0.0072968006,0.000108106695],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11268065,0.000108724416,0.00026213707,0.00042197443,0.00040886374,0.00028921125,0.0007104042,0.00006774315,0.00049660535],"category_scores_gemma":[0.018781073,0.00006147524,0.00016592629,0.001069772,0.00014804835,0.00050109735,0.000021826516,0.00038560215,0.00000641969],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015667412,0.000057153182,0.025405893,0.0000030687595,0.000031967473,0.0000017104029,0.0152725,0.0069030575,0.00021852083,0.0053015063,0.00024390464,0.94654506],"study_design_scores_gemma":[0.0016695907,0.00057163794,0.25522164,0.00021128445,0.00029883755,0.0000669618,0.07973544,0.3315874,0.0016153846,0.3102633,0.018600918,0.00015758014],"about_ca_topic_score_codex":0.000536356,"about_ca_topic_score_gemma":0.022764822,"teacher_disagreement_score":0.94638747,"about_ca_system_score_codex":0.00034010297,"about_ca_system_score_gemma":0.0098233465,"threshold_uncertainty_score":0.99579006},"labels":[],"label_agreement":null},{"id":"W3137926421","doi":"10.3138/cjpe.71156","title":"Establishing and Developing Professional Evaluator Dispositions","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Professional development; Order (exchange); Engineering ethics; Pedagogy; Medical education; Medicine","score_opus":0.36322189242453295,"score_gpt":0.5554788230819199,"score_spread":0.19225693065738692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137926421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96704614,0.0018843308,0.005285447,0.01879032,0.002610283,0.0008227226,0.000013909806,0.000011613924,0.0035352043],"genre_scores_gemma":[0.97631264,0.000017895081,0.022482185,0.0004950491,0.00022488326,0.000046499168,0.000025047984,0.000008594936,0.00038718566],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99555826,0.0009885748,0.00079687673,0.00021317758,0.002206206,0.0002368876],"domain_scores_gemma":[0.99287,0.0006633142,0.00045997763,0.0001998035,0.0053597367,0.00044718749],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016522573,0.00010072309,0.000197057,0.00045050305,0.0004350578,0.00081989914,0.0002407655,0.00007155799,0.0020280923],"category_scores_gemma":[0.01047772,0.00007957473,0.00007561288,0.00087453047,0.000079025274,0.001119025,0.00002613432,0.00020554477,0.000027699929],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010574214,0.000034629353,0.032439306,0.000007526275,0.000030879717,0.0000218283,0.001687429,0.00045402843,0.00027085087,0.0038104558,0.004487643,0.95674485],"study_design_scores_gemma":[0.0022139468,0.00033055907,0.69249564,0.00042679827,0.000242665,0.000828733,0.009525881,0.06382074,0.0006879315,0.0712019,0.15778068,0.0004445138],"about_ca_topic_score_codex":0.00007727207,"about_ca_topic_score_gemma":0.008813517,"teacher_disagreement_score":0.9563003,"about_ca_system_score_codex":0.00034499384,"about_ca_system_score_gemma":0.015797568,"threshold_uncertainty_score":0.9988842},"labels":[],"label_agreement":null},{"id":"W3138644234","doi":"10.3138/cjpe.69751","title":"Offering Graduate Evaluation Degrees Online: Comparing Student Engagement in Two Canadian Programs","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University; University of Victoria","funders":"","keywords":"Certificate; Set (abstract data type); Graduate students; Online learning; Medical education; Tone (literature); Psychology; Mathematics education; Pedagogy; Computer science; Multimedia; Medicine","score_opus":0.7266241610460255,"score_gpt":0.6005049424468304,"score_spread":0.12611921859919506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138644234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895706,0.0007940456,0.00020292273,0.0025174737,0.0014346341,0.0019523867,0.0000066418006,0.000010979849,0.0035103115],"genre_scores_gemma":[0.99489045,0.000022271744,0.004315734,0.00016148934,0.00022805038,0.00017521076,0.00012326174,0.00001877174,0.00006473485],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9900941,0.0021119146,0.0017107845,0.00043295563,0.004994947,0.0006552452],"domain_scores_gemma":[0.9909709,0.00019387256,0.0007200874,0.00047052768,0.0066582947,0.0009863353],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034219045,0.000231422,0.00044336336,0.0015359933,0.00035333738,0.0010186881,0.00065764127,0.00007291124,0.0015055762],"category_scores_gemma":[0.003187007,0.00020906335,0.00016950218,0.0018170357,0.00007547331,0.00080234365,0.00003833986,0.0005541185,0.00005573633],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007130722,0.00013815839,0.27582768,0.000004804293,0.000036964746,0.000041229876,0.0023514593,0.036925707,0.000013769956,0.00015629025,0.0002146492,0.6842822],"study_design_scores_gemma":[0.0023278897,0.00025672693,0.5973503,0.00018973755,0.00014618953,0.000048840528,0.0073814243,0.37949428,0.000055306573,0.0024317296,0.0100598615,0.0002577075],"about_ca_topic_score_codex":0.05136699,"about_ca_topic_score_gemma":0.97369856,"teacher_disagreement_score":0.9223316,"about_ca_system_score_codex":0.0028765395,"about_ca_system_score_gemma":0.02137033,"threshold_uncertainty_score":0.9994072},"labels":[],"label_agreement":null},{"id":"W3138688726","doi":"10.3138/cjpe.69697","title":"Pinpointing Where to Start: A Reflective Analysis on the Introductory Evaluation Course","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Course (navigation); Reflective practice; Mathematics education; Process (computing); Psychology; Graduate students; Computer science; Course evaluation; Learning theory; Pedagogy; Higher education; Engineering","score_opus":0.33797496032700913,"score_gpt":0.5470026099765712,"score_spread":0.2090276496495621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138688726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93397015,0.0009903025,0.0021289825,0.05197724,0.0014775429,0.0019543,0.000013414508,0.0000111337995,0.007476907],"genre_scores_gemma":[0.99611807,0.0000063584134,0.0019807105,0.0011162749,0.00038359792,0.00012187791,0.000017141363,0.000010310101,0.00024563383],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910305,0.0025853186,0.0010029208,0.00037506304,0.004685971,0.00032024083],"domain_scores_gemma":[0.9849547,0.0006497936,0.00076073565,0.0006342299,0.012549805,0.00045071368],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04227577,0.00015170996,0.00031847376,0.00095986674,0.0004537653,0.00071028504,0.0004704127,0.00006883236,0.009441528],"category_scores_gemma":[0.013813416,0.00010272705,0.00026382878,0.004166788,0.00006717819,0.00043827953,0.000019926587,0.00032188857,0.00018383902],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031877953,0.00008974557,0.019523783,0.000002302498,0.00042228855,0.00000811473,0.0040179607,0.07032957,0.0001596682,0.0008994016,0.016453918,0.88806134],"study_design_scores_gemma":[0.0015448086,0.0012792561,0.4732085,0.00013095864,0.0031557588,0.000042269363,0.016951598,0.38992432,0.0010521838,0.017841253,0.094408214,0.00046089952],"about_ca_topic_score_codex":0.00025254494,"about_ca_topic_score_gemma":0.08043789,"teacher_disagreement_score":0.8876005,"about_ca_system_score_codex":0.000988707,"about_ca_system_score_gemma":0.010367366,"threshold_uncertainty_score":0.99524295},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3138870977","doi":"10.3138/cjpe.69577","title":"Competency-Based Evaluation Education: Four Essential Things to Know and Do","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Pace; Lifelong learning; Perspective (graphical); Context (archaeology); Psychology; Knowledge management; Pedagogy; Computer science; Medical education; Medicine","score_opus":0.1726522912841817,"score_gpt":0.5158863399418671,"score_spread":0.34323404865768536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138870977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91070044,0.004596017,0.007503259,0.05248715,0.005382741,0.003292026,0.000013955,0.000023096758,0.016001299],"genre_scores_gemma":[0.97141993,0.000011173821,0.026324736,0.001512276,0.00035304305,0.00011908737,0.000031599637,0.0000115379235,0.00021661833],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99401236,0.0010441015,0.000925693,0.00032911,0.0034293197,0.00025944228],"domain_scores_gemma":[0.9866195,0.00025408593,0.00056290824,0.00036159361,0.01148398,0.00071798783],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017445194,0.00014393199,0.00024973377,0.0007667732,0.00031421264,0.0009984743,0.00032929404,0.0000851383,0.005250778],"category_scores_gemma":[0.0058904397,0.00012527473,0.000111484755,0.0011818744,0.00006627875,0.000829813,0.000018684208,0.00019503957,0.00009218212],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013120047,0.000065714856,0.00981653,0.000006657208,0.000017775568,0.000004635895,0.00094621745,0.0032645303,0.00018395785,0.0013297439,0.0072101066,0.977141],"study_design_scores_gemma":[0.0041212244,0.0012099538,0.22613129,0.0005254904,0.00069628493,0.00036834306,0.0075978045,0.33287865,0.0015933291,0.07103066,0.35310367,0.0007432946],"about_ca_topic_score_codex":0.00018378547,"about_ca_topic_score_gemma":0.008656777,"teacher_disagreement_score":0.9763977,"about_ca_system_score_codex":0.00048110346,"about_ca_system_score_gemma":0.04616685,"threshold_uncertainty_score":0.9956586},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9608826,0.0045735654,0.0038196913,0.019478226,0.0030612908,0.0021049273,0.00004220602,0.00003884528,0.005998643],"genre_scores_gemma":[0.9797387,0.000020587504,0.019226696,0.00035122357,0.00017501286,0.00017439891,0.00015717025,0.000019799812,0.00013639996],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99816483,0.00066445634,0.00050316524,0.00015360366,0.00027721672,0.00023671683],"domain_scores_gemma":[0.9963387,0.00017759706,0.0004794235,0.00041501047,0.0023148453,0.0002743711],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016681736,0.00010434341,0.00016913963,0.00033682698,0.00046961053,0.00012982014,0.00026150036,0.000103440936,0.0016670091],"category_scores_gemma":[0.00035791547,0.00011703495,0.00011675585,0.00033946265,0.000061172585,0.00012747404,0.000009397909,0.0003422975,0.000010234428],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112096284,0.0005126595,0.04781711,0.000042554362,0.00014915796,0.000005500394,0.031838313,0.00064451306,0.00030901347,0.019984588,0.0065196017,0.89206487],"study_design_scores_gemma":[0.0062276046,0.0023184102,0.571735,0.0016009578,0.0010338014,0.001423088,0.17948969,0.02512792,0.0006547313,0.009123782,0.200187,0.0010779633],"about_ca_topic_score_codex":0.0025427714,"about_ca_topic_score_gemma":0.046549466,"teacher_disagreement_score":0.8909869,"about_ca_system_score_codex":0.00086522195,"about_ca_system_score_gemma":0.002532066,"threshold_uncertainty_score":0.9992456},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4349505,0.0068995506,0.0020358597,0.41360897,0.042807557,0.027062906,0.00027697356,0.000032360986,0.07232531],"genre_scores_gemma":[0.93800545,0.000051522853,0.033974253,0.0029507787,0.023924204,0.00027916854,0.000054164644,0.00006410362,0.0006963618],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9798015,0.0050469376,0.0030420162,0.00052543695,0.010924893,0.0006592428],"domain_scores_gemma":[0.94655645,0.0011415437,0.004621824,0.00094479637,0.04565459,0.0010807859],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06987218,0.00035246808,0.0008631083,0.0016663139,0.0007087049,0.0012307347,0.0014567306,0.00026463543,0.029244103],"category_scores_gemma":[0.087878235,0.00027221988,0.0005200518,0.0035758882,0.00039349162,0.0018159377,0.000058971385,0.000825694,0.00005968627],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006844619,0.00020603937,0.0058324276,0.000021064006,0.00017259551,0.000009130698,0.009290119,0.010762363,0.00024295927,0.00015354065,0.17491527,0.7983261],"study_design_scores_gemma":[0.002572744,0.0013692505,0.030265993,0.00036087196,0.0013234676,0.00025964784,0.006819787,0.01830423,0.0030522447,0.0024805677,0.9328463,0.0003448694],"about_ca_topic_score_codex":0.0050358167,"about_ca_topic_score_gemma":0.34417912,"teacher_disagreement_score":0.7979812,"about_ca_system_score_codex":0.0019008227,"about_ca_system_score_gemma":0.059477583,"threshold_uncertainty_score":0.999973},"labels":[],"label_agreement":null},{"id":"W3139404955","doi":"10.3138/cjpe.71359","title":"Re-Envisioning Evaluation Pedagogy with a Community of Scholar Teachers","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Pedagogy; Sociology; Psychology","score_opus":0.4830094280355481,"score_gpt":0.5808736776311207,"score_spread":0.09786424959557266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139404955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9871038,0.001158081,0.001820396,0.0022656322,0.00047953398,0.000729851,0.000007968247,0.0000065527447,0.0064281635],"genre_scores_gemma":[0.9891923,0.000010037468,0.0104125235,0.00015234012,0.00007789606,0.00003480575,0.000027372822,0.000011714994,0.00008098659],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9892265,0.0048483093,0.0011538008,0.00019542669,0.0043196366,0.0002563244],"domain_scores_gemma":[0.98471016,0.00074576505,0.0011975296,0.00058616936,0.012363056,0.00039735084],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06028845,0.00013626923,0.00032739507,0.0006522639,0.00056799833,0.00039129678,0.0004975359,0.00009949244,0.004504783],"category_scores_gemma":[0.017450782,0.000104354585,0.00012973612,0.0012922498,0.0001604897,0.001100686,0.000023141152,0.00073024706,0.000024415172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025188745,0.000093227194,0.039268084,0.000008311757,0.00005092723,0.0000059867507,0.0090071745,0.010733493,0.00018535621,0.00011866768,0.00049552927,0.94000804],"study_design_scores_gemma":[0.006494834,0.0036557515,0.62329996,0.0008667283,0.0010888187,0.00025280094,0.141557,0.14814982,0.003413462,0.020270122,0.05032657,0.00062412425],"about_ca_topic_score_codex":0.0008491144,"about_ca_topic_score_gemma":0.059673004,"teacher_disagreement_score":0.9393839,"about_ca_system_score_codex":0.00052431866,"about_ca_system_score_gemma":0.01780586,"threshold_uncertainty_score":0.99640524},"labels":[],"label_agreement":null},{"id":"W3139438442","doi":"10.3138/cjpe.69696","title":"Teaching Africa-Rooted Evaluation: Using a “Model Client” Innovation to Help Shift the Locus of Knowledge Production","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Economic shortage; Space (punctuation); Sociology; Vulnerability (computing); Knowledge management; Pedagogy; Computer science; Public relations; Psychology; Political science","score_opus":0.5584913811322083,"score_gpt":0.5574010113067539,"score_spread":0.001090369825454407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139438442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96564645,0.0007533433,0.019718863,0.0077952896,0.001552085,0.0018856776,0.000006020072,0.000009251716,0.002633011],"genre_scores_gemma":[0.99142563,0.0000022940621,0.007729404,0.000115726165,0.000355585,0.000071705836,0.00001699527,0.000013525213,0.0002691236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924194,0.0017993109,0.001661536,0.0003398037,0.0034762132,0.00030373601],"domain_scores_gemma":[0.984128,0.00022143142,0.0012278974,0.00052554486,0.013657614,0.00023951032],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044269573,0.00015952745,0.0002946802,0.0011705606,0.0005057216,0.00032811836,0.0004643265,0.000093017385,0.00059179554],"category_scores_gemma":[0.013003292,0.00011630211,0.00012663784,0.0033498975,0.00008847314,0.0007795881,0.000035524947,0.00034696324,0.000027231064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027485581,0.00013427665,0.0041642,0.000012215932,0.000047808444,0.0000018651332,0.011361034,0.23516737,0.0019876675,0.0015411525,0.0017742713,0.7437807],"study_design_scores_gemma":[0.0008982946,0.00031489396,0.01797185,0.00019114354,0.00025884452,0.00007208741,0.003988757,0.9421484,0.0013524719,0.021420829,0.01116322,0.00021924537],"about_ca_topic_score_codex":0.00024506837,"about_ca_topic_score_gemma":0.008828208,"teacher_disagreement_score":0.7435614,"about_ca_system_score_codex":0.0008580882,"about_ca_system_score_gemma":0.014076194,"threshold_uncertainty_score":0.9953106},"labels":[],"label_agreement":null},{"id":"W3139526458","doi":"10.3138/cjpe.69797","title":"If Building Trust Is Important, How Do We Teach Novice Evaluators to Do It?","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Focus (optics); Work (physics); Knowledge management; Key (lock); Psychology; Computer science; Engineering ethics; Pedagogy; Engineering","score_opus":0.2393113993722523,"score_gpt":0.5137830673082322,"score_spread":0.2744716679359799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139526458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8829754,0.0040656747,0.0026733717,0.1017481,0.00292013,0.0018008135,0.000041477386,0.000021708194,0.0037533287],"genre_scores_gemma":[0.9840023,0.00009548244,0.012814244,0.0016206332,0.0005583201,0.00007380082,0.000009286539,0.000025052697,0.0008009155],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916103,0.00089282583,0.0014548397,0.0005230023,0.004957507,0.00056156464],"domain_scores_gemma":[0.98953545,0.00031100985,0.0010398101,0.0006649641,0.007184106,0.0012646625],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02561283,0.00024740346,0.0004396426,0.0011130165,0.00042254006,0.0019871357,0.0007833277,0.0001505018,0.010169667],"category_scores_gemma":[0.0072870827,0.00020590557,0.00027032298,0.0024110759,0.00007077864,0.0010171174,0.000041797666,0.00040642053,0.00016764867],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017067225,0.000054584223,0.04965117,0.0000077986415,0.000061951454,0.00003831617,0.004390271,0.0011191483,0.00030160166,0.00047384834,0.050936747,0.8929475],"study_design_scores_gemma":[0.0016819974,0.0006903505,0.03259426,0.0002856553,0.0002732562,0.00024034578,0.014356154,0.038246553,0.0012521141,0.01136781,0.89852035,0.0004911434],"about_ca_topic_score_codex":0.00016248068,"about_ca_topic_score_gemma":0.005597321,"teacher_disagreement_score":0.89245635,"about_ca_system_score_codex":0.0008633043,"about_ca_system_score_gemma":0.01282772,"threshold_uncertainty_score":0.9990489},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9586832,0.0023246736,0.007944513,0.0089315,0.0007433108,0.0018276295,0.000024054645,0.000030536834,0.019490587],"genre_scores_gemma":[0.9906234,0.00009985268,0.0073577063,0.00046714226,0.00085275463,0.00035300886,0.00002332734,0.000033749428,0.00018903421],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97094244,0.026933426,0.00080471445,0.00018603135,0.00051134254,0.00062203803],"domain_scores_gemma":[0.9940289,0.002292072,0.00084498886,0.00022413427,0.0016880061,0.0009218443],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030067386,0.00015952173,0.00031921547,0.000199338,0.001142822,0.000108262255,0.00017586986,0.0003910994,0.00037770846],"category_scores_gemma":[0.009112366,0.00014953411,0.00009951437,0.00043152727,0.0001636644,0.00045720037,0.000016025146,0.0011917932,0.000017245775],"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":[0.000083399194,0.00021625137,0.15554386,0.00048004847,0.00027324678,0.0009084338,0.22062522,0.0004484591,0.0027725114,0.0111071635,0.006181887,0.6013595],"study_design_scores_gemma":[0.003854089,0.0007969638,0.44846538,0.0022143442,0.00035670912,0.0009768531,0.16624583,0.0034369037,0.00088751793,0.016442437,0.3558319,0.0004910946],"about_ca_topic_score_codex":0.021833774,"about_ca_topic_score_gemma":0.20703264,"teacher_disagreement_score":0.6008684,"about_ca_system_score_codex":0.0031268082,"about_ca_system_score_gemma":0.08781379,"threshold_uncertainty_score":0.9992343},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9833816,0.0014956904,0.00047947656,0.012674362,0.00033539248,0.0013802093,0.0000644082,0.000006462035,0.00018235312],"genre_scores_gemma":[0.99577004,0.000046074834,0.0039047585,0.000100933394,0.000063148385,0.00005325695,0.0000077892155,0.0000040358937,0.00004995243],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9758424,0.023138558,0.00043569953,0.00010054004,0.00024958508,0.00023321735],"domain_scores_gemma":[0.9748668,0.022893699,0.00033556917,0.00012607919,0.001514159,0.00026366676],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15019456,0.00006557796,0.00014656573,0.00019642952,0.0010682172,0.00009960675,0.00012244556,0.00009248321,0.000047178622],"category_scores_gemma":[0.13709128,0.00005230707,0.000065503074,0.00030243097,0.00042744164,0.00013825326,0.0000020052676,0.0000984813,4.9746603e-7],"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":[0.007006568,0.00009362523,0.051539574,0.000004594763,0.00012380477,0.0000023739742,0.020665107,0.0001240472,0.0006094121,0.010476048,0.010805834,0.898549],"study_design_scores_gemma":[0.000523538,0.00049781834,0.95892614,0.000010445434,0.00008230004,0.000009521743,0.0012232303,0.00009985429,0.000072705334,0.0249092,0.013580926,0.00006432987],"about_ca_topic_score_codex":0.0018423739,"about_ca_topic_score_gemma":0.25852653,"teacher_disagreement_score":0.90738654,"about_ca_system_score_codex":0.00013350972,"about_ca_system_score_gemma":0.005919577,"threshold_uncertainty_score":0.9997159},"labels":[],"label_agreement":null},{"id":"W3205038101","doi":"10.3138/cjpe.69949","title":"Evaluation Advisory Groups: Considerations for Design and Management","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Advisory committee; Resource (disambiguation); Scale (ratio); Political science; Computer science; Public administration; Geography","score_opus":0.5679625182669052,"score_gpt":0.5376190604386261,"score_spread":0.030343457828279186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205038101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3019251,0.014297578,0.59732836,0.03727256,0.0068354104,0.024816278,0.000059050893,0.000059275757,0.0174064],"genre_scores_gemma":[0.86125714,0.000071513736,0.13733998,0.00045400538,0.0001532918,0.00051619235,0.000020161151,0.000011401406,0.0001763193],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948416,0.0013195511,0.0008631463,0.00025883215,0.0024920527,0.00022485916],"domain_scores_gemma":[0.98895794,0.00084930577,0.0004868468,0.00025544522,0.009117982,0.00033248763],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035933033,0.00011236477,0.00020311496,0.00051499123,0.00037391207,0.0006305628,0.00014232438,0.000065119035,0.0021271678],"category_scores_gemma":[0.0074075907,0.000097579956,0.00009672814,0.00045809703,0.00006805038,0.00061143015,0.000011981665,0.00009910088,0.00001868562],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001222341,0.00004494325,0.0008849272,0.000010045488,0.00008611879,0.000007702852,0.0008316045,0.0132241845,0.000048402955,0.0049866773,0.009357181,0.970506],"study_design_scores_gemma":[0.0033571478,0.00056389516,0.029927393,0.00008055454,0.00080955605,0.00015758586,0.0032193777,0.60074145,0.00028187278,0.3216194,0.039009474,0.0002323403],"about_ca_topic_score_codex":0.00002279899,"about_ca_topic_score_gemma":0.0041610417,"teacher_disagreement_score":0.9702737,"about_ca_system_score_codex":0.00037610994,"about_ca_system_score_gemma":0.0066483007,"threshold_uncertainty_score":0.9989831},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91842085,0.012421424,0.0008195146,0.017980773,0.0007309025,0.00131257,0.000021833426,0.000017911563,0.04827423],"genre_scores_gemma":[0.9873939,0.00005289306,0.011728769,0.000043914202,0.00025052746,0.000037882943,0.000006180313,0.000013467533,0.0004724633],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932875,0.0048417016,0.00041842277,0.00017896727,0.0008342746,0.00043914645],"domain_scores_gemma":[0.9965021,0.001108363,0.00016831297,0.00008679798,0.001641224,0.00049319485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021786865,0.0000812939,0.0002030023,0.00050585286,0.00033032472,0.0005287662,0.00012509519,0.00006068437,0.00012452631],"category_scores_gemma":[0.004204241,0.00007853891,0.000058094953,0.0015043542,0.00049708487,0.00059899327,0.0000138955775,0.0003869279,0.0000038828625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010604119,0.000038179125,0.0017639803,0.000011009037,0.000016034655,0.0000744021,0.12962918,0.0000069317116,0.000014540105,0.011146893,0.0004577743,0.8568305],"study_design_scores_gemma":[0.0017153433,0.00054521294,0.0074777333,0.00065810484,0.0000496999,0.000024983257,0.3682438,0.00045947914,0.000079925725,0.11683097,0.50357634,0.00033842784],"about_ca_topic_score_codex":0.005355317,"about_ca_topic_score_gemma":0.3501594,"teacher_disagreement_score":0.85649204,"about_ca_system_score_codex":0.00058128353,"about_ca_system_score_gemma":0.0049458225,"threshold_uncertainty_score":0.8773677},"labels":[],"label_agreement":null},{"id":"W3205524844","doi":"10.3138/cjpe.72833","title":"Beverly Parsons, Lovely Dhillon, and Matt Keene (Eds.). (2020). <i>Visionary Evaluation for a Sustainable, Equitable Future.</i>","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Environmental ethics; Philosophy","score_opus":0.148458665966718,"score_gpt":0.471744497342231,"score_spread":0.32328583137551303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205524844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8222727,0.08297923,0.010188577,0.055929463,0.005664478,0.012524782,0.00014779798,0.000060822873,0.010232156],"genre_scores_gemma":[0.9784409,0.00036103372,0.016235001,0.0010240001,0.0009958644,0.00038785048,0.00017730745,0.00003673722,0.0023412963],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930063,0.00095297577,0.0013311304,0.00047625214,0.0035494573,0.0006839219],"domain_scores_gemma":[0.98201156,0.00048863346,0.0009183522,0.00043089228,0.01543825,0.0007123336],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03302183,0.00022819625,0.00042330127,0.0005906903,0.0006360946,0.0010824027,0.0004131886,0.00016424365,0.002368441],"category_scores_gemma":[0.005753581,0.00019440823,0.00019538365,0.0012598354,0.00009368411,0.0013920938,0.000047908252,0.00024518828,0.000032688786],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006165507,0.00007908014,0.0031334357,0.00003225529,0.00006196437,0.000041437517,0.0006367396,0.001426764,0.00009232748,0.0015194573,0.038387626,0.95452726],"study_design_scores_gemma":[0.004852736,0.0013158879,0.06423739,0.00011967938,0.0005943261,0.00051878137,0.013568314,0.115267016,0.00023152785,0.061473124,0.73733556,0.00048567238],"about_ca_topic_score_codex":0.00022126915,"about_ca_topic_score_gemma":0.0055705095,"teacher_disagreement_score":0.9540416,"about_ca_system_score_codex":0.00064575765,"about_ca_system_score_gemma":0.016241966,"threshold_uncertainty_score":0.9999546},"labels":[],"label_agreement":null},{"id":"W3206030918","doi":"10.3138/cjpe.70053","title":"Cultivating Cultural Competence","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conceptualization; Cultural competence; Competence (human resources); Cultural diversity; Psychology; Epistemology; Sociology; Engineering ethics; Social psychology; Pedagogy; Anthropology; Computer science; Philosophy","score_opus":0.5646603306791933,"score_gpt":0.585671718843883,"score_spread":0.021011388164689726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206030918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97222656,0.0009773767,0.001428187,0.005547762,0.0015634169,0.00048249622,0.000005277107,0.000010420657,0.017758504],"genre_scores_gemma":[0.9865387,0.000007810978,0.012477984,0.00030970704,0.00019774328,0.000015317786,0.000012258557,0.0000048247357,0.00043563783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961861,0.0005375145,0.00079777575,0.00016439623,0.0020944453,0.00021976983],"domain_scores_gemma":[0.99105585,0.00021409393,0.00055452494,0.00021344607,0.0075829383,0.00037913377],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008819484,0.00008510931,0.00018198039,0.00024718334,0.00023971392,0.0005948459,0.0003295388,0.00004812279,0.0048154327],"category_scores_gemma":[0.007083871,0.00006239675,0.00011828052,0.0008936829,0.00006923576,0.000768074,0.000012420665,0.00018497519,0.000106351305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037235159,0.000025936133,0.05044012,0.0000025286085,0.000019404024,0.000022605962,0.0015348201,0.0022185692,0.00060057914,0.0009954803,0.00589111,0.9382451],"study_design_scores_gemma":[0.0024125068,0.0005717378,0.3676543,0.00021089312,0.00014561474,0.00061664026,0.020256635,0.14435723,0.0035293014,0.020683134,0.43910983,0.0004521807],"about_ca_topic_score_codex":0.00016869631,"about_ca_topic_score_gemma":0.009303224,"teacher_disagreement_score":0.93779296,"about_ca_system_score_codex":0.0002668147,"about_ca_system_score_gemma":0.0065571596,"threshold_uncertainty_score":0.99907476},"labels":[],"label_agreement":null},{"id":"W3206200039","doi":"10.3138/cjpe.68386","title":"Practice Notes from a Participatory Impact Evaluation of a Leadership Development Program for People Living with HIV","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Pacific AIDS Network","funders":"","keywords":"Participatory evaluation; Citizen journalism; Participatory GIS; Work (physics); Sociology; Participatory development; Participatory action research; Knowledge management; Public relations; Management science; Political science; Computer science; Engineering; Social science","score_opus":0.6469295512114422,"score_gpt":0.5709009173924243,"score_spread":0.07602863381901792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206200039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98668903,0.0012683261,0.0059734154,0.0028516867,0.00032355383,0.00252686,0.000016274293,0.000012231337,0.0003386174],"genre_scores_gemma":[0.95130163,0.0000038175103,0.04774964,0.000130958,0.00012651208,0.00059079676,0.00005360824,0.000016664475,0.000026380754],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99201965,0.0016969563,0.0012495308,0.00031532656,0.0043182224,0.000400327],"domain_scores_gemma":[0.97846407,0.0023314864,0.0015003022,0.00034851226,0.016894743,0.00046086923],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03496646,0.00017817014,0.000394306,0.00043571586,0.00023214758,0.00043594025,0.0003046738,0.00009616488,0.0017913593],"category_scores_gemma":[0.028378608,0.0001333421,0.00016947175,0.0009979885,0.00007640812,0.0010565415,0.000013788664,0.0001852829,0.000018499111],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006790581,0.00028346144,0.092819124,0.000016306858,0.00019048183,0.0000022546778,0.008907839,0.011386874,0.000071176626,0.000023926968,0.00052435364,0.8857063],"study_design_scores_gemma":[0.0030295649,0.0014265429,0.7619543,0.00043130308,0.0011574839,0.000051604613,0.02329472,0.19787803,0.0013222421,0.0009447814,0.008195052,0.00031435213],"about_ca_topic_score_codex":0.00045820983,"about_ca_topic_score_gemma":0.05967409,"teacher_disagreement_score":0.88539195,"about_ca_system_score_codex":0.00085041916,"about_ca_system_score_gemma":0.032293357,"threshold_uncertainty_score":0.9991211},"labels":[],"label_agreement":null},{"id":"W3207991248","doi":"10.3138/cjpe.71575","title":"The Rights of Nature: An Emerging Transformation Opportunity for Evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"David and Lucile Packard Foundation","keywords":"Anthropocene; Generative grammar; Coronavirus disease 2019 (COVID-19); Natural (archaeology); Sociology; Epistemology; Environmental ethics; Law and economics; Political science; Business; Knowledge management; Computer science; Geography","score_opus":0.4074894549911969,"score_gpt":0.5699416873127253,"score_spread":0.16245223232152844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207991248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9708458,0.0019344179,0.007729346,0.0086907735,0.0029928149,0.0032277943,0.00005331214,0.0000095633095,0.004516185],"genre_scores_gemma":[0.9977262,0.000018511184,0.0017018319,0.00011393058,0.00016325407,0.00010908634,0.00009141803,0.000006653601,0.00006911708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939553,0.0012842121,0.0012688068,0.00017006882,0.0030873278,0.00023425979],"domain_scores_gemma":[0.9839411,0.00047595787,0.0010056606,0.0003534713,0.013835491,0.00038832158],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041446622,0.000105606254,0.00020575202,0.00035081676,0.0006125628,0.00036380964,0.00041021686,0.00012141864,0.0008217791],"category_scores_gemma":[0.0047812383,0.00007023361,0.0001738991,0.00072779035,0.000080455226,0.0011760498,0.000004984181,0.0002336137,0.0000034022733],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029854578,0.00004829717,0.0004571396,0.0000057238262,0.00003250334,6.632631e-7,0.001820113,0.0028432235,0.00011947926,0.005782241,0.0009354482,0.9879253],"study_design_scores_gemma":[0.0029660512,0.0010466878,0.018726725,0.00006492158,0.00031013796,0.00004840915,0.007041048,0.61964184,0.0034382795,0.16743219,0.17907737,0.00020634755],"about_ca_topic_score_codex":0.00014662342,"about_ca_topic_score_gemma":0.043657333,"teacher_disagreement_score":0.98771894,"about_ca_system_score_codex":0.00029769653,"about_ca_system_score_gemma":0.0113180755,"threshold_uncertainty_score":0.99428684},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W3209623811","doi":"10.3138/cjpe.71630","title":"Evaluation in Transition: The Promise and Challenge of South-South Cooperation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Salience (neuroscience); Political science; Narrative; Engineering ethics; International development; Narrative review; Public relations; Sociology; Psychology; Engineering","score_opus":0.37214611116267754,"score_gpt":0.4892118189386274,"score_spread":0.11706570777594988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209623811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98309743,0.002479419,0.00087125826,0.009609517,0.00043440258,0.0015800842,0.0000102540525,0.0000033084216,0.001914351],"genre_scores_gemma":[0.9989932,0.000027962342,0.0006305281,0.00011133274,0.00010251064,0.000083602965,0.000014871496,0.000006046948,0.000029909143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99443156,0.0016532209,0.0009827991,0.00019839864,0.0025665502,0.00016749772],"domain_scores_gemma":[0.9923603,0.00017380316,0.0005498011,0.00024895582,0.006492117,0.00017500915],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029420597,0.000098684926,0.00021988462,0.00039410635,0.00015393869,0.00022833029,0.00019236704,0.00007643716,0.0014119096],"category_scores_gemma":[0.0034120611,0.000068762194,0.00007382288,0.00085561693,0.000102115635,0.00049578794,0.000007752502,0.00018695393,0.000008827177],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027840022,0.000069785834,0.0057949745,0.000011025729,0.00003350067,0.0000056827666,0.03214069,0.013104532,0.00012967293,0.0006881572,0.00015186262,0.9478423],"study_design_scores_gemma":[0.0064108153,0.0011062141,0.16798979,0.00028352643,0.000554305,0.00009582436,0.028454036,0.76482564,0.00087777013,0.022940671,0.006126537,0.0003348499],"about_ca_topic_score_codex":0.00009815287,"about_ca_topic_score_gemma":0.01931494,"teacher_disagreement_score":0.94750744,"about_ca_system_score_codex":0.00023110125,"about_ca_system_score_gemma":0.0071850717,"threshold_uncertainty_score":0.99950093},"labels":[],"label_agreement":null},{"id":"W3209748599","doi":"10.3138/cjpe.72730","title":"Conclusion: Transforming Evaluation Practice for “Business Unusual”","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Key (lock); Business; Business practice; Clinical Practice; Process management; Knowledge management; Psychology; Computer science; Business administration; Medicine; Nursing; Computer security","score_opus":0.4903320513145368,"score_gpt":0.5952244765647577,"score_spread":0.10489242525022097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209748599","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6239059,0.012214959,0.17091143,0.11276736,0.015591614,0.015607432,0.00010580922,0.000064305204,0.04883117],"genre_scores_gemma":[0.97882676,0.00004020732,0.019138826,0.0008152381,0.00053548586,0.0002624045,0.000091719055,0.000018361652,0.00027098545],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99279594,0.0011544512,0.0013129049,0.0003012361,0.004104727,0.0003307622],"domain_scores_gemma":[0.96296585,0.0010958882,0.0009589397,0.00032395462,0.03423322,0.00042215476],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04070078,0.00015030327,0.00030264148,0.0005659637,0.00047928,0.0006516006,0.00037002287,0.000119326156,0.0027248478],"category_scores_gemma":[0.03094228,0.00012575854,0.0001854823,0.001646834,0.000070372625,0.0018173065,0.000012174462,0.00018740035,0.000036267375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042743348,0.00007584614,0.00065430556,0.000009464031,0.000043030235,0.000008779004,0.0014552906,0.005563769,0.00019616715,0.0009417412,0.003131662,0.9878772],"study_design_scores_gemma":[0.0044186823,0.00064733677,0.010085114,0.00013730608,0.00077008974,0.00038968347,0.008948181,0.23079948,0.0014045577,0.02012387,0.72195953,0.0003162017],"about_ca_topic_score_codex":0.00015461243,"about_ca_topic_score_gemma":0.009886202,"teacher_disagreement_score":0.987561,"about_ca_system_score_codex":0.00072086847,"about_ca_system_score_gemma":0.025052872,"threshold_uncertainty_score":0.99818677},"labels":[],"label_agreement":null},{"id":"W3209866185","doi":"10.3138/cjpe.71527","title":"Catching the Wave: Harnessing Data Science to Support Evaluation’s Capacity for Making a Transformational Contribution to Sustainable Development","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Transformational leadership; Sustainable development; Field (mathematics); Set (abstract data type); Engineering ethics; Key (lock); Politics; Political science; Knowledge management; Data science; Computer science; Sociology; Management science; Public relations; Engineering","score_opus":0.584620824737506,"score_gpt":0.5460516450026884,"score_spread":0.03856917973481755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209866185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7313297,0.00017175399,0.23587987,0.0240574,0.0014583722,0.0059438604,0.00006666326,0.000013308514,0.0010791174],"genre_scores_gemma":[0.95196164,7.607994e-7,0.046276245,0.0010811855,0.00013804427,0.000321141,0.00012326999,0.000008464659,0.000089257315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99220943,0.0005265535,0.0012426011,0.0004248606,0.0049971603,0.0005993773],"domain_scores_gemma":[0.9772136,0.0003751121,0.00051698775,0.0005821313,0.020768374,0.0005437626],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.084088124,0.00014414072,0.00023131185,0.000815806,0.0017983981,0.0018477717,0.0010884372,0.000052551506,0.00085667917],"category_scores_gemma":[0.020993616,0.000107218504,0.00007205677,0.0022759524,0.00010074252,0.0026855678,0.0000801012,0.00018064857,0.000025659589],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025735477,0.000036392372,0.0008737087,0.000010450138,0.00002420434,0.000003639689,0.008664751,0.012840588,0.0002471782,0.0027531467,0.0020745755,0.9724456],"study_design_scores_gemma":[0.0017680108,0.0003527948,0.07739492,0.00014845096,0.000206787,0.00015705562,0.012177737,0.32731932,0.0018573742,0.0079523,0.57029974,0.00036551515],"about_ca_topic_score_codex":0.00009599246,"about_ca_topic_score_gemma":0.011472904,"teacher_disagreement_score":0.9720801,"about_ca_system_score_codex":0.002401685,"about_ca_system_score_gemma":0.051625237,"threshold_uncertainty_score":0.9995011},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9227369,0.00047902286,0.00013407478,0.008361218,0.0027180035,0.0021316828,0.000007990714,0.000014836574,0.063416265],"genre_scores_gemma":[0.98567307,0.0002244579,0.0059907273,0.00069503277,0.0014668945,0.000037323098,0.00003524186,0.000023632992,0.005853622],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974278,0.0006457294,0.0004989354,0.00018572988,0.0006556821,0.0005861213],"domain_scores_gemma":[0.99491304,0.00006482058,0.0001648661,0.00014531653,0.0034952282,0.0012167252],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047492436,0.0001005727,0.00019448459,0.00049897085,0.0011842123,0.00015234099,0.00021019715,0.000115528,0.0012391995],"category_scores_gemma":[0.00047133572,0.00009802572,0.000041015264,0.002152344,0.000060891165,0.00023680532,8.4999385e-7,0.00018531305,0.000100375786],"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":[0.00002024032,0.00027692958,0.011769781,0.000032724132,0.00003176558,0.0001540339,0.55812997,0.0003882991,0.000027639171,0.008520153,0.0068795737,0.41376886],"study_design_scores_gemma":[0.0003503038,0.00033200352,0.014365362,0.00006934937,0.00003158602,0.000022436774,0.0063153673,0.000028906643,0.00012115196,0.0005484192,0.9776627,0.00015244118],"about_ca_topic_score_codex":0.15524195,"about_ca_topic_score_gemma":0.9951284,"teacher_disagreement_score":0.9707831,"about_ca_system_score_codex":0.0013410981,"about_ca_system_score_gemma":0.13764147,"threshold_uncertainty_score":0.9996738},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9359495,0.0014280248,0.006906791,0.049487744,0.002183961,0.0023547267,0.0000076062042,0.00005598396,0.0016256752],"genre_scores_gemma":[0.9693941,0.00015608087,0.02622273,0.0005591798,0.0028589957,0.00047906948,0.000105830106,0.000055935645,0.00016809818],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9922104,0.0041997847,0.0011638959,0.00028907816,0.00081704924,0.0013198094],"domain_scores_gemma":[0.9908644,0.00032158502,0.0011973602,0.00025041966,0.0055686235,0.0017976228],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.018965894,0.0002442118,0.00035224354,0.0005081646,0.001795797,0.00023180906,0.00026170968,0.00039174885,0.00018365151],"category_scores_gemma":[0.0068817693,0.00025278734,0.00019769934,0.0008874575,0.00012754906,0.0005337062,0.000012266627,0.0013582762,0.000016470303],"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":[0.00014602981,0.00038659372,0.4044495,0.00013045438,0.000119705,0.00013195357,0.12854238,0.00037630158,0.00028305198,0.0012836789,0.013074148,0.45107624],"study_design_scores_gemma":[0.0030456558,0.00095805526,0.81078297,0.00059272023,0.0005274895,0.002244461,0.12740475,0.008429792,0.00018340038,0.01930207,0.026189772,0.00033889362],"about_ca_topic_score_codex":0.03184463,"about_ca_topic_score_gemma":0.13579847,"teacher_disagreement_score":0.45073733,"about_ca_system_score_codex":0.012529684,"about_ca_system_score_gemma":0.107260086,"threshold_uncertainty_score":0.99999243},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869532,0.0005537237,0.0009154744,0.004084623,0.0004184363,0.0062483703,0.00044751394,0.000017606413,0.0003610784],"genre_scores_gemma":[0.9713944,0.000034842808,0.024584575,0.0009888862,0.00015957466,0.0025233591,0.00025473037,0.000033499437,0.000026134456],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99085397,0.004863629,0.0021804504,0.0004241293,0.00076226227,0.0009155859],"domain_scores_gemma":[0.99111384,0.004347435,0.0012217707,0.0001844024,0.0024798042,0.0006527427],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013634214,0.00014870966,0.0005164135,0.0004096945,0.0012562755,0.00022287568,0.00024824106,0.00016134643,0.00069378363],"category_scores_gemma":[0.02678436,0.00022444341,0.00008443548,0.0011238151,0.00009691465,0.0005843186,0.000038325707,0.0005924801,0.000008940765],"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":[0.000024581463,0.00005371277,0.72023326,0.00033738563,0.000027322978,0.000050293314,0.026124585,0.0006657709,0.00003067277,0.000113496455,0.00012082071,0.2522181],"study_design_scores_gemma":[0.0046010315,0.00026188017,0.9535683,0.0022550728,0.000027460945,0.00002186396,0.028124414,0.0021678742,0.00001953901,0.0011111564,0.0076505826,0.00019085791],"about_ca_topic_score_codex":0.19601186,"about_ca_topic_score_gemma":0.9941799,"teacher_disagreement_score":0.798168,"about_ca_system_score_codex":0.0064295884,"about_ca_system_score_gemma":0.06564102,"threshold_uncertainty_score":0.99738455},"labels":[],"label_agreement":null},{"id":"W3211253945","doi":"10.3138/cjpe.70502","title":"L’évaluation évolutive, de la théorie à la pratique : perspectives de praticiens québécois","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique; University of Victoria; Université de Sherbrooke","funders":"","keywords":"Summative assessment; Formative assessment; Valuation (finance); Sociology; Business; Knowledge management; Political science; Pedagogy; Computer science; Accounting","score_opus":0.17542502317927477,"score_gpt":0.5004563917657058,"score_spread":0.325031368586431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211253945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9174394,0.0015301866,0.018256744,0.009775922,0.0004391438,0.000925301,0.000011044995,0.000021623691,0.051600616],"genre_scores_gemma":[0.9767365,0.000051187388,0.022244789,0.00023379781,0.00021634363,0.000075116775,0.000008584959,0.000013222661,0.0004204984],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99190634,0.004674658,0.0007829025,0.00026003164,0.0020184184,0.000357631],"domain_scores_gemma":[0.9918192,0.0013696612,0.0006296541,0.00029577932,0.005389079,0.0004966171],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03574267,0.00014259898,0.0002415141,0.00048831035,0.0002828095,0.0007955001,0.00033622826,0.00016464358,0.0019126786],"category_scores_gemma":[0.01982739,0.00012172256,0.00015626548,0.0010313172,0.00019108893,0.0006571781,0.000014814705,0.00039078234,0.000025605643],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027934018,0.00024306148,0.07356227,0.000009973277,0.00010047268,0.00008342543,0.059814937,0.015684903,0.000819913,0.027446184,0.00437294,0.81783396],"study_design_scores_gemma":[0.001800678,0.000634942,0.5358978,0.000117494,0.0002796279,0.00079863146,0.066593334,0.20261626,0.0010546647,0.12641373,0.06343729,0.00035554575],"about_ca_topic_score_codex":0.00198681,"about_ca_topic_score_gemma":0.054482147,"teacher_disagreement_score":0.8174784,"about_ca_system_score_codex":0.001676209,"about_ca_system_score_gemma":0.056570835,"threshold_uncertainty_score":0.9989997},"labels":[],"label_agreement":null},{"id":"W3211298722","doi":"","title":"Strategies for Mentoring and Advising Evaluation Graduate Students of Color","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Honor; Ethnic group; Cultural competence; Psychology; Graduate students; Competence (human resources); Salient; Pedagogy; Women of color; Medical education; Identity (music); People of color; Sociology; Social psychology; Gender studies; Medicine","score_opus":0.6184423513416186,"score_gpt":0.611127572966471,"score_spread":0.007314778375147601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211298722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99326473,0.0009176636,0.0020720558,0.00083160144,0.00080062664,0.001236416,0.000008037573,0.0000032342673,0.0008656189],"genre_scores_gemma":[0.99461496,0.000020709289,0.0050370414,0.00004602126,0.000106385705,0.000082615596,0.000015190219,0.0000072500616,0.00006982729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994865,0.00055135356,0.000940796,0.00019471784,0.003241936,0.00020617832],"domain_scores_gemma":[0.98992974,0.00030695877,0.00080152217,0.0001807806,0.00853189,0.00024909567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024425633,0.00009849399,0.00024842055,0.00040279594,0.00018614439,0.0006131785,0.00024152808,0.000053278778,0.00035362676],"category_scores_gemma":[0.0031072819,0.00008297307,0.00009345673,0.00050302985,0.00006675594,0.000805272,0.000016057136,0.00009705216,0.0000026041105],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028437204,0.00005988226,0.021165296,0.000020819025,0.00007231212,0.0000021409364,0.0033395165,0.0052167317,0.00079551677,0.0010410678,0.0005835025,0.9676748],"study_design_scores_gemma":[0.0067952843,0.0018102941,0.40897396,0.000367012,0.00089604914,0.000079036494,0.047668163,0.42453632,0.003241296,0.08868765,0.016555456,0.00038947904],"about_ca_topic_score_codex":0.0001075498,"about_ca_topic_score_gemma":0.00546609,"teacher_disagreement_score":0.9672853,"about_ca_system_score_codex":0.00029280194,"about_ca_system_score_gemma":0.0077399113,"threshold_uncertainty_score":0.9978853},"labels":[],"label_agreement":null},{"id":"W3213734767","doi":"10.3138/cjpe.0027.007","title":"Dissemination and Early Use of the Paris Declaration Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Champion; Declaration; Transparency (behavior); Stakeholder; Corporate governance; Politics; Stakeholder engagement; Evaluation methods; Public relations; Impact evaluation; Political science; Business; Process management; Engineering; Medicine; Law","score_opus":0.4155863677781072,"score_gpt":0.5210278673679903,"score_spread":0.10544149958988314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213734767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99386144,0.00030291703,0.000625494,0.0024107834,0.00049132,0.0018651226,0.0000029351672,0.0000029840394,0.000436978],"genre_scores_gemma":[0.99807847,0.000012296646,0.0015145052,0.00005801152,0.00006350608,0.0001081314,0.000005532843,0.0000062606937,0.0001532737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949454,0.00094456685,0.0009608702,0.00015679494,0.0028328237,0.00015952282],"domain_scores_gemma":[0.99101144,0.00041367358,0.0011192008,0.00029299158,0.0069465926,0.00021612472],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012757239,0.00009776883,0.00017504177,0.0004361675,0.00021150547,0.0006203068,0.00025961184,0.0000830599,0.0013253152],"category_scores_gemma":[0.0059820767,0.00006242411,0.00009185366,0.00071386335,0.000118619595,0.0018382984,0.000014784493,0.00014397813,0.000019209696],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044009907,0.000020487872,0.19754364,0.0000026456037,0.000014168495,9.324842e-8,0.0013395965,0.001144875,0.00035878018,0.00022152704,0.0030836186,0.79626614],"study_design_scores_gemma":[0.00034860018,0.0001763283,0.8567335,0.00004853402,0.00009819625,0.000008472744,0.00044679016,0.13117541,0.0003910125,0.0068443846,0.0036604777,0.00006828654],"about_ca_topic_score_codex":0.0014492159,"about_ca_topic_score_gemma":0.005755063,"teacher_disagreement_score":0.7961979,"about_ca_system_score_codex":0.00024113075,"about_ca_system_score_gemma":0.00206068,"threshold_uncertainty_score":0.9995876},"labels":[],"label_agreement":null},{"id":"W3217770674","doi":"10.3138/cjpe.69191","title":"Toward an Evidence-Based Approach to Building Evaluation Capacity","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Children's Hospital Foundation; Stollery Children’s Hospital Foundation; Women and Children's Health Research Institute; Social Sciences and Humanities Research Council of Canada; Children's Health Research Institute","keywords":"Work (physics); Accountability; Process management; Capacity building; Computer science; Knowledge management; Management science; Risk analysis (engineering); Business; Political science; Engineering","score_opus":0.8095482787308166,"score_gpt":0.5628469968990902,"score_spread":0.24670128183172635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217770674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92625,0.0008857236,0.060252145,0.0059129666,0.0014782461,0.002121676,0.0000092558885,0.00001842693,0.0030715484],"genre_scores_gemma":[0.9302196,0.0000040724817,0.068436705,0.00079104013,0.0003129798,0.00016300082,0.000022651013,0.000013013541,0.00003696992],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896759,0.0025370251,0.001191207,0.00045760916,0.0057450337,0.00039322127],"domain_scores_gemma":[0.9836304,0.00038399542,0.00067163113,0.00057621923,0.013653912,0.0010838091],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04746416,0.00017723921,0.00032572672,0.00094354554,0.00030694544,0.0010474311,0.0006645575,0.00011659425,0.0023800232],"category_scores_gemma":[0.01809813,0.00015029388,0.00017927958,0.0019293197,0.000069538975,0.0018242605,0.00001732523,0.00027606776,0.00006494322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023978326,0.00012668582,0.008591261,0.000009613138,0.00002355364,0.000004699953,0.0018592644,0.11769326,0.00068787124,0.0007262862,0.0013623858,0.8688911],"study_design_scores_gemma":[0.0013871861,0.0008111352,0.077352144,0.00021844318,0.00026640703,0.00008834276,0.0026428066,0.8873598,0.0025474578,0.010446219,0.0165401,0.00033998457],"about_ca_topic_score_codex":0.00048195166,"about_ca_topic_score_gemma":0.0062028076,"teacher_disagreement_score":0.86855114,"about_ca_system_score_codex":0.0012200825,"about_ca_system_score_gemma":0.019382784,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984944,0.0007677609,0.000025886211,0.00024259771,0.000043362008,0.00028319308,0.000024798974,4.8306083e-7,0.00011752567],"genre_scores_gemma":[0.9995802,0.000070376984,0.0001503441,0.00004208971,0.00005768729,0.0000032421697,0.00007695312,0.000001898737,0.000017222115],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99886584,0.00036416185,0.00022727106,0.000083048195,0.00034193398,0.00011774485],"domain_scores_gemma":[0.999294,0.000012597889,0.00015366414,0.00014932707,0.00031953678,0.00007087773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002106239,0.00005551833,0.000076887074,0.000076613156,0.00011944845,0.00005303921,0.000217264,0.000050237086,0.00017502838],"category_scores_gemma":[0.0001178408,0.000034410496,0.000065937165,0.00020902422,0.000055982164,0.000006549589,0.0000028042577,0.000064923275,3.3525944e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044152024,0.000044688684,0.029505579,0.000006293925,0.00021888314,0.0000032018193,0.001236102,0.085125834,0.010396913,0.00003918822,0.00042903758,0.87295014],"study_design_scores_gemma":[0.0021405467,0.0026705954,0.8604784,0.00006958994,0.002492927,0.000099537996,0.006437699,0.07887475,0.006268214,0.0034574263,0.036594044,0.00041625617],"about_ca_topic_score_codex":0.00081175246,"about_ca_topic_score_gemma":0.024494747,"teacher_disagreement_score":0.87253386,"about_ca_system_score_codex":0.000028341155,"about_ca_system_score_gemma":0.0006046489,"threshold_uncertainty_score":0.9933057},"labels":[],"label_agreement":null},{"id":"W326774523","doi":"10.3138/cjpe.025.003","title":"Constructing and Verifying Program Theory Using Source Documentation","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Documentation; Computer science; A priori and a posteriori; Logic model; Management science; Program Design Language; Software engineering; Programming language; Epistemology; Engineering; Sociology","score_opus":0.31697774328765216,"score_gpt":0.5515263442620003,"score_spread":0.23454860097434815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W326774523","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918916,0.0001448177,0.0040497826,0.00040248863,0.0010763374,0.00088277645,0.0000017769812,0.000013448602,0.001536927],"genre_scores_gemma":[0.95885795,0.0000025239453,0.040777028,0.00007224337,0.0002023786,0.000026193118,0.0000049744626,0.000009293197,0.000047390666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970371,0.00046439684,0.0007370986,0.0001825588,0.0013398926,0.00023894697],"domain_scores_gemma":[0.9966684,0.00030414545,0.00075373164,0.00017890196,0.0017147737,0.00038002207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016690766,0.000107819185,0.0001760961,0.00053083105,0.0003426129,0.0009502098,0.00022739201,0.00008258521,0.0015182454],"category_scores_gemma":[0.002989497,0.00008727966,0.0000665346,0.00047905056,0.00019504166,0.0010487577,0.000013430033,0.0003289716,0.00001189746],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008375517,0.000012543366,0.051273536,0.0000030096155,0.00001351708,0.0000015018933,0.000916287,0.00027363462,0.00039764305,0.0013816262,0.00004268438,0.9456757],"study_design_scores_gemma":[0.004126844,0.0012552211,0.10528817,0.00018418187,0.00049053883,0.0012151119,0.035284746,0.7035756,0.001581367,0.08118825,0.0651,0.00070996047],"about_ca_topic_score_codex":0.0002764753,"about_ca_topic_score_gemma":0.0082802465,"teacher_disagreement_score":0.94496566,"about_ca_system_score_codex":0.00017784216,"about_ca_system_score_gemma":0.0024156186,"threshold_uncertainty_score":0.9993945},"labels":[],"label_agreement":null},{"id":"W327931636","doi":"10.3138/cjpe.018.007","title":"CES Student Essay Award: Student and Professor Perspectives","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Sociology","score_opus":0.26322550767730857,"score_gpt":0.5604918523129583,"score_spread":0.2972663446356497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W327931636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9852477,0.0026607155,0.00027408815,0.0032498115,0.0009813952,0.0012341669,0.0000029591786,0.0000074168247,0.0063417773],"genre_scores_gemma":[0.9972999,0.000040334533,0.0017108108,0.000102910155,0.00010906896,0.00007341614,0.0000014928222,0.000008730134,0.0006533067],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948212,0.0010931662,0.00080342626,0.00025485732,0.0027480733,0.00027928528],"domain_scores_gemma":[0.99544424,0.00025134932,0.00060214015,0.00024192047,0.0029687274,0.0004916116],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018892711,0.00013712855,0.0002575398,0.00056964776,0.00031214402,0.0006614123,0.00036841872,0.00006450045,0.0015242525],"category_scores_gemma":[0.002500721,0.00009933455,0.00008995281,0.000510632,0.00012947385,0.00062721706,0.000013876464,0.00021291467,0.00003816709],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017645401,0.00029825314,0.42974398,0.000008222142,0.00013690526,0.000016123186,0.048655726,0.0008023021,0.00004623619,0.011652595,0.0027788917,0.5058431],"study_design_scores_gemma":[0.0021945885,0.0011233223,0.7510324,0.00006723229,0.00017899543,0.000087507105,0.13104555,0.0019670147,0.00011434815,0.013222282,0.09867879,0.00028794497],"about_ca_topic_score_codex":0.00008620943,"about_ca_topic_score_gemma":0.007914201,"teacher_disagreement_score":0.50555515,"about_ca_system_score_codex":0.0005943541,"about_ca_system_score_gemma":0.0054057813,"threshold_uncertainty_score":0.9993885},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W334332912","doi":"10.3138/cjpe.017.007","title":"Evaluation in the Context of the Social Union Framework Agreement: A Case Study of the National Child Benefit","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Aside; Context (archaeology); Government (linguistics); Attribution; Joint (building); Political science; Program evaluation; Test (biology); Public administration; Public relations; Public economics; Economics; Business; Psychology; Social psychology; Engineering","score_opus":0.4168994987204216,"score_gpt":0.5202938594688366,"score_spread":0.10339436074841496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W334332912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98735654,0.00024308628,0.000025725807,0.007401568,0.00054351403,0.0025918293,0.000010818179,0.0000011746398,0.0018257593],"genre_scores_gemma":[0.9993108,0.0000030843707,0.000058320733,0.00035214477,0.00015046188,0.00009500908,0.0000014467557,0.000005181685,0.00002355477],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98791575,0.0032476643,0.0012588891,0.00016672382,0.0072273933,0.00018357414],"domain_scores_gemma":[0.9925118,0.00045621878,0.001480135,0.0003177653,0.005161969,0.000072090465],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03921446,0.00011485607,0.00020980381,0.00037059674,0.0005605418,0.00014503676,0.00085664034,0.0000846465,0.0012867177],"category_scores_gemma":[0.004614322,0.000058371937,0.00016982172,0.0017396538,0.00014800823,0.00031714622,0.000026484904,0.0003796266,0.000005666444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012990397,0.00062909146,0.07732988,0.0000054365564,0.000082935134,0.000004297789,0.08355642,0.009617474,0.0000075105722,0.0016289483,0.001672622,0.8254524],"study_design_scores_gemma":[0.003582366,0.00088246894,0.7039659,0.00017804794,0.00043572567,0.00028053933,0.12343308,0.14609851,0.00004044284,0.018045962,0.0028876232,0.00016932513],"about_ca_topic_score_codex":0.001649763,"about_ca_topic_score_gemma":0.11252994,"teacher_disagreement_score":0.82528305,"about_ca_system_score_codex":0.000488171,"about_ca_system_score_gemma":0.0015221854,"threshold_uncertainty_score":0.9996262},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99586594,0.00012376551,0.000070318456,0.0018863955,0.00025968673,0.0014580388,0.0000076163915,0.00002084935,0.00030739565],"genre_scores_gemma":[0.997282,0.000007393697,0.001712084,0.00049297436,0.000288715,0.00006916274,0.00008475592,0.000023679757,0.000039195627],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99820155,0.00022282584,0.00046969953,0.0001742531,0.0006299711,0.00030170952],"domain_scores_gemma":[0.9962598,0.000049646664,0.00036462425,0.0002108896,0.0014504563,0.0016645945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038974967,0.0001670073,0.00027511822,0.00041741112,0.00021687851,0.0002631875,0.00008196275,0.00016006418,0.00038674223],"category_scores_gemma":[0.0012166629,0.00015080803,0.00005884371,0.0001518348,0.0002329114,0.00036585092,0.0000047218664,0.00046278664,6.717214e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059602662,0.00007457751,0.44912818,0.0000227928,0.000028334995,0.000026538819,0.0003069721,0.000007281048,0.000781115,0.00009320934,0.00004175352,0.54942966],"study_design_scores_gemma":[0.0057424507,0.0036378808,0.9716414,0.000241296,0.0011171653,0.0005131561,0.0024283843,0.012595914,0.00015581361,0.00040440657,0.0012689868,0.0002531278],"about_ca_topic_score_codex":0.0016176237,"about_ca_topic_score_gemma":0.0061188573,"teacher_disagreement_score":0.5491765,"about_ca_system_score_codex":0.00016910759,"about_ca_system_score_gemma":0.004800905,"threshold_uncertainty_score":0.85165995},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8344199,0.0026286494,0.000082393606,0.009036445,0.0006941894,0.0012592049,0.0000050070325,0.000013348686,0.15186083],"genre_scores_gemma":[0.99841845,0.0000562345,0.0011317184,0.000046245277,0.00021834439,0.000014561771,3.1634997e-7,0.0000035925586,0.00011052212],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99827033,0.00056066766,0.00016083436,0.00010560423,0.00063064985,0.00027192832],"domain_scores_gemma":[0.99789625,0.00009094028,0.00013169179,0.00004900431,0.0011934309,0.0006386666],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004918194,0.00005608751,0.00009444295,0.00016073929,0.0008799938,0.00036498453,0.00010544845,0.00005248674,0.001262552],"category_scores_gemma":[0.0019205841,0.000050768165,0.000038288814,0.00030719888,0.00071863784,0.0004621605,0.0000029670236,0.00012704222,0.0000054583497],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006106292,0.000029277431,0.01829491,0.0000043557056,0.000033781194,0.00046174505,0.06660537,0.000010703703,0.0000075664852,0.6559067,0.00020109792,0.2584384],"study_design_scores_gemma":[0.0015225549,0.001023459,0.018864587,0.00009704168,0.00013508649,0.001673491,0.32463798,0.00037444808,0.000016114578,0.1596206,0.49161425,0.00042037218],"about_ca_topic_score_codex":0.111270405,"about_ca_topic_score_gemma":0.76498616,"teacher_disagreement_score":0.6537157,"about_ca_system_score_codex":0.0006787906,"about_ca_system_score_gemma":0.0029023213,"threshold_uncertainty_score":0.9996504},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97458386,0.0025375946,0.00016689139,0.001562279,0.0013081584,0.015869724,0.000010067856,0.000024266888,0.003937127],"genre_scores_gemma":[0.99603647,0.000015925489,0.0010184699,0.00006486781,0.00050875277,0.0020792864,0.00007242467,0.000017268801,0.00018651987],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99101555,0.0063446932,0.000951182,0.00025826914,0.00095628144,0.0004740461],"domain_scores_gemma":[0.9925279,0.0005302921,0.0008636916,0.0003202831,0.0052254624,0.0005323817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017191391,0.00017787065,0.00034927131,0.0002643136,0.0010767801,0.000037447157,0.00023401948,0.00014120889,0.0008860756],"category_scores_gemma":[0.001369172,0.00012263133,0.00011255822,0.0006200642,0.00025315018,0.00024407473,0.00000581047,0.0006601445,0.00007412896],"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":[0.0009396947,0.0007376849,0.15760587,0.00038067845,0.000099791054,0.0000011234853,0.0015367144,0.0017479125,0.00006505567,0.00040685484,0.0021342067,0.8343444],"study_design_scores_gemma":[0.0027025891,0.0013845577,0.9493808,0.0013516946,0.0003183854,0.000011733958,0.0024463644,0.009698762,0.00010307391,0.0024256445,0.029988334,0.00018807215],"about_ca_topic_score_codex":0.001270185,"about_ca_topic_score_gemma":0.005790957,"teacher_disagreement_score":0.83415633,"about_ca_system_score_codex":0.0014759016,"about_ca_system_score_gemma":0.029131252,"threshold_uncertainty_score":0.97637266},"labels":[],"label_agreement":null},{"id":"W347468065","doi":"10.3138/cjpe.0023.005","title":"The Road to Evaluation Capacity Building: A Case Study from Israel","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Presentation (obstetrics); Curriculum; Outcome (game theory); Relation (database); Capacity building; Psychology; Political science; Mathematics education; Sociology; Medical education; Pedagogy; Economics; History; Computer science; Medicine; Law; Archaeology","score_opus":0.5869895881998264,"score_gpt":0.5568682661750065,"score_spread":0.030121322024819874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W347468065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98850214,0.00031368886,0.0007815619,0.0053696265,0.0010902137,0.003144827,0.000007287293,0.000009685716,0.0007809813],"genre_scores_gemma":[0.99642354,0.0000021329024,0.0025875238,0.00047289464,0.0003371447,0.00011960386,0.0000037475404,0.000007735796,0.00004567788],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99135005,0.0018910256,0.0013092175,0.00032731565,0.004753226,0.00036914702],"domain_scores_gemma":[0.99117595,0.00044652776,0.00078840513,0.00059697183,0.0062591396,0.0007330246],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.045115404,0.00017224195,0.00026433222,0.00058607315,0.0008591939,0.0012347567,0.00069905503,0.00007258916,0.00064018136],"category_scores_gemma":[0.0081747845,0.00011215395,0.00013835568,0.0011963639,0.00005828659,0.00069230126,0.0000141847995,0.00028404006,0.00008419783],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020954245,0.00009706214,0.011682958,2.245599e-7,0.00003056772,0.00004572726,0.004168433,0.0035854003,0.000047063026,0.000116899646,0.0016548397,0.9785499],"study_design_scores_gemma":[0.003692471,0.0044816053,0.5596265,0.00005526825,0.0005900239,0.0007032326,0.046759654,0.31195873,0.0001238653,0.039043974,0.03250885,0.00045578805],"about_ca_topic_score_codex":0.009889596,"about_ca_topic_score_gemma":0.16983685,"teacher_disagreement_score":0.9780941,"about_ca_system_score_codex":0.0008702355,"about_ca_system_score_gemma":0.004507436,"threshold_uncertainty_score":0.99980205},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6740282,0.019420017,0.0068898723,0.25047967,0.017956803,0.0087127,0.000014932305,0.00010631784,0.022391489],"genre_scores_gemma":[0.9826619,0.00007211175,0.003992935,0.0014620465,0.01129269,0.00028710996,0.00013610932,0.000029109835,0.00006596032],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984859,0.000059511556,0.0004364898,0.00018365314,0.00059165264,0.00024279562],"domain_scores_gemma":[0.9889184,0.00006637236,0.000467623,0.000121880104,0.010384328,0.000041381725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036734561,0.00011265714,0.0001644481,0.00026139794,0.00032680828,0.00044608823,0.000114715374,0.000053957756,0.00045863286],"category_scores_gemma":[0.0056559453,0.00010741382,0.00009452229,0.00079533964,0.000044341596,0.0022470579,0.000007049236,0.00010433868,0.000012704155],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004372001,0.00008115277,0.0026045989,0.00010455056,0.00010761295,0.000009497651,0.00025852048,0.0033896025,0.00010859547,0.003455519,0.011197351,0.9786393],"study_design_scores_gemma":[0.0014439204,0.0000767799,0.006514446,0.000102345504,0.0012064835,0.00007179975,0.0030347563,0.008482785,0.00018521823,0.0037649646,0.97490835,0.00020817415],"about_ca_topic_score_codex":0.0006697169,"about_ca_topic_score_gemma":0.008401206,"teacher_disagreement_score":0.9784311,"about_ca_system_score_codex":0.0002033404,"about_ca_system_score_gemma":0.0014478585,"threshold_uncertainty_score":0.6771103},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13064277,0.2443947,0.00075603026,0.025300723,0.0071314885,0.00068272545,0.0001890354,0.000018712188,0.5908838],"genre_scores_gemma":[0.9854279,0.0005861974,0.0019141036,0.00028791415,0.0051831715,0.0000105215295,0.000037359077,0.00002323766,0.006529599],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981881,0.00056876714,0.0004217033,0.00011363414,0.00037850405,0.00032930585],"domain_scores_gemma":[0.996414,0.00012440288,0.00030932852,0.00013541541,0.002448489,0.0005683833],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024284315,0.00012122046,0.00020434165,0.00023681615,0.0003923096,0.0009389626,0.00012851729,0.00010996852,0.010759417],"category_scores_gemma":[0.0014329602,0.00012525555,0.00022974797,0.00014874463,0.00025061436,0.00014786649,0.000006256969,0.0002893187,0.000032700642],"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":[0.0000057247053,0.00021156625,0.0012888411,0.000050572853,0.0005072359,0.0008566306,0.006481401,0.00081884005,0.000008920461,0.4092085,0.010475079,0.57008666],"study_design_scores_gemma":[0.0005057712,0.00014695109,0.001392827,0.00014552151,0.0018981938,0.00018864087,0.002898057,0.008309436,0.00006777037,0.030566128,0.953722,0.0001587208],"about_ca_topic_score_codex":0.012958672,"about_ca_topic_score_gemma":0.042966418,"teacher_disagreement_score":0.9432469,"about_ca_system_score_codex":0.00048036038,"about_ca_system_score_gemma":0.008020966,"threshold_uncertainty_score":0.99760264},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2427235,0.03313073,0.04650247,0.044887356,0.07192716,0.0072100097,0.00010064889,0.00030448,0.55321366],"genre_scores_gemma":[0.95899093,0.00006180923,0.027008427,0.0011222598,0.009821691,0.0004989012,0.00006280922,0.000048840076,0.0023843555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990897,0.00014247374,0.00027407572,0.000109886656,0.00020466358,0.00017920148],"domain_scores_gemma":[0.9984921,0.000023158793,0.00017664729,0.00022248735,0.0008186093,0.000266987],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00089620246,0.000062963125,0.00009821958,0.00012559214,0.00007638419,0.000056464803,0.00013146704,0.000091245514,0.0051804306],"category_scores_gemma":[0.00006928101,0.0000626228,0.000082126346,0.00026564137,0.000037759266,0.00006497725,0.000001712045,0.00016708576,0.000036851325],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005561407,0.000064885906,0.0008792077,0.0000018243312,0.000046468405,0.000022314214,0.0004181671,0.0000035504813,0.0002169252,0.003783578,0.30561963,0.6889379],"study_design_scores_gemma":[0.0004367062,0.00015028774,0.01329559,0.00002645287,0.000050570612,0.00016886443,0.0002613816,0.000089384186,0.00015460695,0.006672406,0.9786101,0.00008364537],"about_ca_topic_score_codex":0.00031524088,"about_ca_topic_score_gemma":0.003975999,"teacher_disagreement_score":0.7162674,"about_ca_system_score_codex":0.00013499382,"about_ca_system_score_gemma":0.0012181766,"threshold_uncertainty_score":0.99572897},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97875303,0.009388031,0.000031629486,0.0037071689,0.0019690623,0.00041641833,0.000010992721,0.000006777272,0.0057168677],"genre_scores_gemma":[0.9953772,0.00012322054,0.0029503903,0.00049238536,0.00029073225,0.000106045445,0.000022813012,0.000012061623,0.0006251681],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983066,0.00046524132,0.0004893287,0.00019123158,0.0002670414,0.00028057286],"domain_scores_gemma":[0.9984036,0.00013342762,0.00022902731,0.00015959032,0.0007298696,0.00034447003],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017152593,0.00013108073,0.00024293752,0.00023295276,0.000105999075,0.00007093426,0.0000989294,0.000088261164,0.0017474446],"category_scores_gemma":[0.00020360335,0.00011506137,0.000057254016,0.00056393445,0.00011646025,0.00014932608,0.00001217032,0.00029987315,0.000011918618],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035001067,0.00071692374,0.23500492,0.00004761535,0.00047966032,0.007039694,0.009036464,0.000053206786,0.0001316394,0.0040311925,0.010236938,0.7331867],"study_design_scores_gemma":[0.005501757,0.0016117886,0.813431,0.00025291689,0.0004526147,0.026571237,0.045932848,0.00023518916,0.000034055247,0.019392535,0.085996404,0.00058763684],"about_ca_topic_score_codex":0.0006325103,"about_ca_topic_score_gemma":0.0076867957,"teacher_disagreement_score":0.7325991,"about_ca_system_score_codex":0.00025839478,"about_ca_system_score_gemma":0.0011867913,"threshold_uncertainty_score":0.9991651},"labels":[],"label_agreement":null},{"id":"W4213063025","doi":"10.3138/cjpe.72865.en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Sociology; Psychology; Political science; Medicine; Biology; Ecology","score_opus":0.27978764456850475,"score_gpt":0.5262429699080209,"score_spread":0.24645532533951614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213063025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9775889,0.0049584657,0.0005268059,0.00791092,0.00075792253,0.0012292688,0.0000029296978,0.0000061849614,0.0070186025],"genre_scores_gemma":[0.99665123,0.000034791974,0.0026925178,0.00019480259,0.00017146727,0.00006495977,0.000027922924,0.0000081587,0.00015417121],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99406713,0.001324287,0.0012636663,0.00025026992,0.0028433716,0.00025129583],"domain_scores_gemma":[0.99346375,0.0004549975,0.0007303446,0.00024212802,0.00477355,0.0003352137],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030536922,0.00011555905,0.00026597249,0.000920401,0.00024222917,0.0002678779,0.00019931329,0.00009770841,0.0034133026],"category_scores_gemma":[0.0102188885,0.000094504896,0.00005048755,0.0014287628,0.00008354196,0.0007792089,0.000012797006,0.0002675326,0.000027757325],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004596401,0.000027510516,0.16425598,0.0000034150412,0.000013107188,0.0000115716575,0.0041026645,0.003866218,0.00009962884,0.00034405905,0.0004991876,0.82677203],"study_design_scores_gemma":[0.0024406686,0.0004332862,0.80741656,0.00019082477,0.00013511017,0.00015084111,0.005734523,0.13922137,0.000085221596,0.03364631,0.010378179,0.0001671233],"about_ca_topic_score_codex":0.0007310564,"about_ca_topic_score_gemma":0.10389733,"teacher_disagreement_score":0.82660496,"about_ca_system_score_codex":0.0006167421,"about_ca_system_score_gemma":0.009383112,"threshold_uncertainty_score":0.9982663},"labels":[],"label_agreement":null},{"id":"W4220680129","doi":"10.3138/cjpe.73686","title":"Michael D. Fetters. (2020). <i>The Mixed Methods Research Workbook: Activities for Designing Implementing, and Publishing Projects</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workbook; Publishing; Management; Library science; Sociology; Political science; Computer science; Economics; Law","score_opus":0.573506722105812,"score_gpt":0.60678165072158,"score_spread":0.033274928615767974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220680129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84028107,0.005984673,0.066250406,0.06938068,0.0041076136,0.0106238155,0.00005264958,0.000033973014,0.0032851023],"genre_scores_gemma":[0.9118855,0.000011441339,0.08522473,0.0007527543,0.00039021703,0.0012044457,0.000018951623,0.000021319624,0.0004906172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9900618,0.005093637,0.00085937354,0.00028974723,0.0031101035,0.00058533787],"domain_scores_gemma":[0.9934396,0.0029455947,0.0007360206,0.0002731183,0.0023309493,0.0002747095],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16884273,0.00011134995,0.0002117425,0.0008732485,0.0023335847,0.0031283698,0.00077130744,0.000043724864,0.0007253903],"category_scores_gemma":[0.008394346,0.00008190744,0.0001076912,0.001239718,0.00014671055,0.0013990839,0.00011551182,0.000637818,0.0000013380611],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028577331,0.000014752091,0.0046784254,0.000005976339,0.000032189175,0.0000018435725,0.0054357247,0.00042153828,0.00029882928,0.00034231803,0.0677884,0.9209514],"study_design_scores_gemma":[0.0013920309,0.00095944933,0.006645488,0.00003407059,0.00010500895,0.00010486658,0.068605624,0.07160179,0.00051362213,0.021219734,0.82861745,0.00020083808],"about_ca_topic_score_codex":0.0005210855,"about_ca_topic_score_gemma":0.006009505,"teacher_disagreement_score":0.92075056,"about_ca_system_score_codex":0.0005567383,"about_ca_system_score_gemma":0.005559565,"threshold_uncertainty_score":0.9999584},"labels":[],"label_agreement":null},{"id":"W4220683166","doi":"10.3138/cjpe.73683","title":"Why a Focus on Integration and Complex Mixed Methods Evaluation Designs?: Introducing this Special Issue of the <i>Canadian Journal of Program Evaluation</i>","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Focus (optics); Management science; Engineering ethics; Program evaluation; Sociology; Computer science; Political science; Engineering; Public administration","score_opus":0.4085758629978245,"score_gpt":0.5421811162476561,"score_spread":0.13360525324983158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220683166","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79589653,0.0051997695,0.016436744,0.08448081,0.03682384,0.036404587,0.00017549474,0.00004451118,0.024537738],"genre_scores_gemma":[0.97180945,0.000008659741,0.025691837,0.00060308736,0.0013913565,0.0003725316,0.00003321671,0.000026032987,0.00006385353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97909874,0.010128319,0.002414211,0.00039599813,0.0075135953,0.00044915406],"domain_scores_gemma":[0.98266774,0.0008112181,0.003427791,0.0005819848,0.011878119,0.0006331444],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10336724,0.00027775473,0.00058952166,0.0019217015,0.0013357421,0.0007384312,0.0010435405,0.00013439982,0.016071681],"category_scores_gemma":[0.014582077,0.00020392684,0.000321758,0.0022574884,0.00033865197,0.00081803265,0.00004709744,0.000810898,0.000008801129],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069669324,0.0000993053,0.0022828926,0.00000603386,0.000073385454,0.000001677159,0.0043871533,0.016620424,0.0002623894,0.00036849704,0.042504225,0.93332434],"study_design_scores_gemma":[0.0050961007,0.005383277,0.08609597,0.00020757245,0.0014145292,0.0003092722,0.0098429695,0.5588755,0.0020779336,0.044207502,0.28597587,0.00051347364],"about_ca_topic_score_codex":0.00547071,"about_ca_topic_score_gemma":0.20998779,"teacher_disagreement_score":0.9328109,"about_ca_system_score_codex":0.0024790128,"about_ca_system_score_gemma":0.022517025,"threshold_uncertainty_score":0.99996436},"labels":[],"label_agreement":null},{"id":"W4220735178","doi":"10.3138/cjpe.71488","title":"A Framework to Combine Mixed Methods Integration and Developmental Evaluation to Study Complex Systems","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Stakeholder; Context (archaeology); Scale (ratio); Work (physics); Key (lock); Computer science; Literacy; Data collection; Process management; Management science; Knowledge management; Data science; Sociology; Business; Political science; Public relations; Engineering; Social science; Geography","score_opus":0.5638809926219458,"score_gpt":0.6081958073315192,"score_spread":0.044314814709573436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220735178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93464243,0.00019710288,0.05408008,0.0026382841,0.002013852,0.005999939,0.000013580102,0.000011703282,0.00040302597],"genre_scores_gemma":[0.9119889,6.8321015e-7,0.08641133,0.00039641577,0.00008653526,0.001035029,0.000024159675,0.000012532265,0.000044382024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98843443,0.005070539,0.0013445165,0.00036736293,0.004465838,0.0003173208],"domain_scores_gemma":[0.9943734,0.0005944391,0.00057859597,0.0002728222,0.0034770488,0.0007037071],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07062779,0.00016697777,0.00035012775,0.001375372,0.0008135756,0.00068316195,0.00050996814,0.00004526079,0.0033401647],"category_scores_gemma":[0.008052069,0.00014377138,0.000062325504,0.0019545332,0.000029747913,0.0004438978,0.00008999078,0.00030420715,0.000042564032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000435071,0.00012757885,0.008710627,0.0000016324119,0.00004262944,0.0000024686753,0.011100038,0.015608054,0.0001495409,0.00037556796,0.0025470646,0.9612913],"study_design_scores_gemma":[0.0023496614,0.004977043,0.481616,0.000056666882,0.00026869366,0.00014246278,0.13413844,0.33010417,0.000077126104,0.008142937,0.03772621,0.00040062153],"about_ca_topic_score_codex":0.0007284707,"about_ca_topic_score_gemma":0.006962473,"teacher_disagreement_score":0.96089065,"about_ca_system_score_codex":0.0017027915,"about_ca_system_score_gemma":0.0039430014,"threshold_uncertainty_score":0.99757093},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.886904,0.00017202049,0.0910389,0.011756903,0.0011609558,0.0021642118,0.0000072583007,0.00014946239,0.006646275],"genre_scores_gemma":[0.71987057,0.0000010672836,0.27863643,0.0009860565,0.000069569905,0.00035741585,0.00001828934,0.000020759073,0.000039862287],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919927,0.005482102,0.0005483525,0.0002102572,0.0012025853,0.00056402053],"domain_scores_gemma":[0.996643,0.0005214425,0.00053694117,0.0002526467,0.0014490102,0.0005969488],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.018544681,0.00016556993,0.00026780574,0.00053906353,0.003029129,0.00032306396,0.0007558895,0.00004804773,0.0005015209],"category_scores_gemma":[0.0015117918,0.00018643426,0.00011923805,0.0017233873,0.00006063855,0.00025983018,0.00004364023,0.0010416543,0.000002936628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021549018,0.00006340132,0.0038003353,0.0000137202405,0.000017758322,0.000006945384,0.030757949,0.64633226,0.00015299683,0.0010233659,0.00008980192,0.3177199],"study_design_scores_gemma":[0.0006084769,0.00040973877,0.0022377076,0.00015380433,0.00010667384,0.0000019623897,0.13167842,0.8359178,0.000072384595,0.00066538743,0.027872546,0.00027514933],"about_ca_topic_score_codex":0.04775806,"about_ca_topic_score_gemma":0.43083122,"teacher_disagreement_score":0.38307315,"about_ca_system_score_codex":0.0019881122,"about_ca_system_score_gemma":0.015834201,"threshold_uncertainty_score":0.9982688},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23240685,0.17883481,0.00041303673,0.029163903,0.011937056,0.0017622086,0.0006044765,0.000031166288,0.5448465],"genre_scores_gemma":[0.99198186,0.000116485775,0.00051726965,0.00025459746,0.0029654778,0.000041169154,0.00003144104,0.000021482136,0.0040702117],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777865,0.00082651374,0.0004103282,0.00010442784,0.0005462844,0.00033380627],"domain_scores_gemma":[0.9980745,0.000109003675,0.000403248,0.000119432625,0.00083081,0.00046304477],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004357631,0.000114878836,0.00018010597,0.00041493113,0.0010842774,0.00054916745,0.0002235641,0.000049994353,0.023343585],"category_scores_gemma":[0.00053948665,0.00012417213,0.00021093557,0.00015824617,0.00022835354,0.00011666381,0.000013833664,0.00043627742,0.000014500047],"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":[0.000016043996,0.00028181035,0.0013144792,0.000030416524,0.00045060687,0.00035549692,0.013078188,0.007863948,0.0000029526568,0.42928192,0.02256234,0.5247618],"study_design_scores_gemma":[0.00047131488,0.00040744862,0.00068037806,0.000027297723,0.0012950425,0.00012758936,0.004975552,0.016806114,0.0000042180955,0.024642214,0.9504219,0.00014090425],"about_ca_topic_score_codex":0.028426161,"about_ca_topic_score_gemma":0.0151615245,"teacher_disagreement_score":0.9278596,"about_ca_system_score_codex":0.0010015641,"about_ca_system_score_gemma":0.0050789863,"threshold_uncertainty_score":0.9780436},"labels":[],"label_agreement":null},{"id":"W4220870230","doi":"10.3138/cjpe.36.3.ann-en","title":"Announcement from Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Political science; Social science; Sociology; History; Medicine; Biology; Ecology","score_opus":0.26152087117811373,"score_gpt":0.5024621923116173,"score_spread":0.24094132113350353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220870230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98627293,0.0031238855,0.00031726825,0.00507677,0.0009232503,0.0019230961,0.000019841656,0.000006114595,0.0023368637],"genre_scores_gemma":[0.99776775,0.00001365655,0.0013553223,0.00024376185,0.00015927294,0.00028231787,0.00009574481,0.000008481438,0.00007371128],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9919996,0.0017562232,0.0013287263,0.00027491915,0.0043841545,0.00025634136],"domain_scores_gemma":[0.9962669,0.00043104016,0.0009900079,0.00024312014,0.0017933408,0.0002756093],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03738723,0.00012238139,0.0002557585,0.0011332657,0.0005618665,0.0001771652,0.00033432277,0.000050140796,0.0073728603],"category_scores_gemma":[0.0029252872,0.00010461313,0.000046111738,0.0012092221,0.00007160386,0.0006185558,0.000030077377,0.00036049302,0.0000123215805],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001625537,0.00004786269,0.19577709,0.0000014426024,0.000019786385,0.000005546967,0.009968947,0.02714721,0.00007649368,0.00016561271,0.0011621304,0.76561165],"study_design_scores_gemma":[0.003105009,0.0012198332,0.6409743,0.00006532271,0.00014295707,0.000035669636,0.013397944,0.27466822,0.000011452702,0.036801275,0.029387163,0.00019088664],"about_ca_topic_score_codex":0.0057122204,"about_ca_topic_score_gemma":0.07802388,"teacher_disagreement_score":0.76542073,"about_ca_system_score_codex":0.0014927584,"about_ca_system_score_gemma":0.005845272,"threshold_uncertainty_score":0.99979067},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17478326,0.0055578267,0.0013777405,0.7860597,0.007351994,0.005794429,0.00023711183,0.000099616416,0.018738367],"genre_scores_gemma":[0.9537909,0.00001231026,0.0019296666,0.042044003,0.001788586,0.00014006256,0.0002632119,0.00001903066,0.000012226892],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974412,0.000296655,0.0007580246,0.00024034688,0.00061622413,0.00064759067],"domain_scores_gemma":[0.9979728,0.000034234152,0.00070230017,0.00034210586,0.0006924071,0.00025619208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014272078,0.00013371024,0.00031083054,0.00034802288,0.00068427174,0.0002050452,0.00077455374,0.000036395675,0.0005427882],"category_scores_gemma":[0.0022897671,0.00012537815,0.00006315365,0.0008694072,0.000034217454,0.0006235269,0.00018505391,0.00028750495,0.000032954835],"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":[0.000018981056,0.00004026224,0.0015838618,0.000040893377,0.00002731306,0.000007485967,0.00015030119,0.004583496,3.25435e-7,0.007727979,0.4282441,0.557575],"study_design_scores_gemma":[0.0005451341,0.0002493423,0.004213307,0.000028966248,0.00004238377,0.000032920212,0.00093282945,0.070028886,8.849194e-9,0.004905289,0.918915,0.000105966836],"about_ca_topic_score_codex":0.08914146,"about_ca_topic_score_gemma":0.13115256,"teacher_disagreement_score":0.7790076,"about_ca_system_score_codex":0.0011011141,"about_ca_system_score_gemma":0.0036220022,"threshold_uncertainty_score":0.916924},"labels":[],"label_agreement":null},{"id":"W4220996640","doi":"10.3138/cjpe.71288","title":"Leveraging Mixed Methods Designs for Promoting Evaluation and Evaluation Capacity Building","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Capacity building; Evaluation methods; Resource (disambiguation); Business; Process management; Knowledge management; Computer science; Political science; Engineering","score_opus":0.6983590582177419,"score_gpt":0.594212927107646,"score_spread":0.10414613111009596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220996640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92208487,0.0010280391,0.06676176,0.0020502456,0.0020429434,0.005638423,0.000013182241,0.000014840622,0.00036569542],"genre_scores_gemma":[0.8861568,0.00000260828,0.11216054,0.00012556487,0.00019156777,0.0012927306,0.00003186388,0.00001920994,0.000019140536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9847623,0.0072128996,0.0015105555,0.00048203484,0.005572919,0.0004592539],"domain_scores_gemma":[0.9887518,0.001224149,0.001550136,0.0003257847,0.007720808,0.00042730046],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.204169,0.00019615721,0.00035724815,0.0011978461,0.0014123038,0.0006211166,0.00047780978,0.000073190946,0.0020316292],"category_scores_gemma":[0.016707383,0.00018159367,0.00017027595,0.0010999553,0.000083951614,0.000942092,0.00004565711,0.00035696858,0.0000028118807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002187818,0.000035477537,0.0031329608,0.000008968258,0.000041266834,4.5444423e-7,0.004275049,0.031520776,0.0011835329,0.00024893647,0.0005804665,0.9589502],"study_design_scores_gemma":[0.0020065506,0.0006487898,0.019206963,0.000032115164,0.00042960266,0.00007173287,0.004397142,0.91157866,0.0007913764,0.049641743,0.010990237,0.00020508876],"about_ca_topic_score_codex":0.00026492972,"about_ca_topic_score_gemma":0.0015348003,"teacher_disagreement_score":0.9587451,"about_ca_system_score_codex":0.0020270643,"about_ca_system_score_gemma":0.007978697,"threshold_uncertainty_score":0.9998877},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75831234,0.115362845,0.0020798002,0.111247964,0.0068174643,0.0042883726,0.00042137495,0.00001429549,0.0014555289],"genre_scores_gemma":[0.91966265,0.0031030949,0.011351836,0.0013214888,0.0011707636,0.00077538687,0.00023722547,0.000111462796,0.0622661],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98776907,0.0047364193,0.0020638846,0.00083999475,0.0033499983,0.0012406476],"domain_scores_gemma":[0.99063486,0.0007459861,0.0011852355,0.00044462338,0.0056248996,0.0013644128],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059782594,0.00045539744,0.00086273387,0.0016039256,0.0011832408,0.0029672768,0.0019946224,0.0003605307,0.004684648],"category_scores_gemma":[0.032878492,0.0004730403,0.00031785114,0.0023382779,0.0005559999,0.0046526077,0.00022810911,0.0015845869,0.000045770004],"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":[0.00008161101,0.00009468968,0.068034835,0.00010200096,0.00005727726,0.00015474587,0.0064240918,0.0005574132,0.000007829795,0.00014704891,0.18376407,0.74057436],"study_design_scores_gemma":[0.002006391,0.0008555872,0.21241173,0.00070305314,0.00036845132,0.0006432516,0.014523231,0.027157428,0.00001177997,0.017793844,0.72295517,0.0005700636],"about_ca_topic_score_codex":0.01578532,"about_ca_topic_score_gemma":0.048963927,"teacher_disagreement_score":0.7400043,"about_ca_system_score_codex":0.0023130078,"about_ca_system_score_gemma":0.0046812664,"threshold_uncertainty_score":0.99977213},"labels":[],"label_agreement":null},{"id":"W4224228919","doi":"10.3138/cjpe.69932","title":"Examining the Process and Effects of Engaging Patients and Family in Health Service Evaluation: Results from a One-Year Prospective Intervention Study","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Home and Community Care Support Services","funders":"","keywords":"General partnership; Intervention (counseling); Context (archaeology); Nursing; Service (business); Health care; Psychology; Process (computing); Medical education; Medicine; Business; Political science; Computer science","score_opus":0.2617535692198355,"score_gpt":0.49518366530346136,"score_spread":0.23343009608362586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224228919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99445254,0.00069173175,0.00003063506,0.0008822214,0.00028243396,0.003552684,0.000015314072,0.0000026970472,0.0000897705],"genre_scores_gemma":[0.99928415,0.000005383863,0.00021787148,0.0001439644,0.000030943076,0.00028907415,0.000018182725,0.0000064410215,0.000003975974],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99239933,0.0033049802,0.0011490788,0.00027396783,0.0027074818,0.00016513713],"domain_scores_gemma":[0.9956456,0.00066088623,0.0012547498,0.00018126809,0.002111856,0.0001456788],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.036571376,0.00009655486,0.00024166735,0.00049219915,0.00037566878,0.0001705958,0.00025393572,0.000022142647,0.000082565566],"category_scores_gemma":[0.0034407561,0.00007484436,0.000027339294,0.00096642366,0.000042068674,0.00042991716,0.000044682445,0.00029776673,7.6378666e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105756466,0.00023934415,0.46997124,0.000020386877,0.000032942746,7.0745057e-7,0.046871915,0.0027069713,0.0000058066507,0.000010596619,0.000041090734,0.47999325],"study_design_scores_gemma":[0.0053138365,0.001981611,0.8923333,0.0001302105,0.000061140105,0.0000013093293,0.0524016,0.045342512,0.000008967092,0.0022981707,0.00006249444,0.0000648227],"about_ca_topic_score_codex":0.0039070807,"about_ca_topic_score_gemma":0.024902534,"teacher_disagreement_score":0.47992843,"about_ca_system_score_codex":0.0004923886,"about_ca_system_score_gemma":0.0020517977,"threshold_uncertainty_score":0.9928905},"labels":[],"label_agreement":null},{"id":"W4224229215","doi":"10.3138/cjpe.71300","title":"Professionalism in Program Evaluators: A Comparison of American and Canadian Evaluators","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Professionalization; Credentialing; Autonomy; Exploratory research; Field (mathematics); Perception; Psychology; Sociology; Medical education; Pedagogy; Social science; Political science; Medicine; Law","score_opus":0.4228532574958362,"score_gpt":0.5923266515598159,"score_spread":0.1694733940639797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224229215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99133605,0.001190618,0.000014311889,0.0031515174,0.00079277554,0.0025113435,0.00003121654,0.000008251818,0.00096394075],"genre_scores_gemma":[0.99682474,0.000005841843,0.002283016,0.00020223059,0.00006000406,0.0005197826,0.000028889555,0.00001705814,0.000058410744],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99037725,0.0024641391,0.001822781,0.00035214456,0.004455364,0.00052831165],"domain_scores_gemma":[0.994511,0.00034728946,0.0015646169,0.00036720213,0.0023931018,0.00081676623],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029424105,0.00019516137,0.0005863548,0.0025550565,0.00046306013,0.00019641986,0.000696274,0.000065761276,0.0028699643],"category_scores_gemma":[0.002731338,0.00016964122,0.00013328835,0.0026633488,0.00029614393,0.00043859318,0.000050420884,0.00056933204,0.000009508004],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002628317,0.00014806949,0.2960329,0.0000054353054,0.000022035203,0.000005689003,0.003719577,0.003297336,0.000011304321,0.00021641518,0.0014082752,0.6951067],"study_design_scores_gemma":[0.002243588,0.003247332,0.6424399,0.000090129215,0.0001443454,0.000065859,0.026992213,0.22021309,0.00004146445,0.0062336475,0.09793392,0.00035448972],"about_ca_topic_score_codex":0.074025266,"about_ca_topic_score_gemma":0.62354314,"teacher_disagreement_score":0.6947522,"about_ca_system_score_codex":0.0015047486,"about_ca_system_score_gemma":0.020823931,"threshold_uncertainty_score":0.9994121},"labels":[],"label_agreement":null},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97720814,0.0020872273,0.000003555186,0.001962991,0.0008960457,0.0150611745,0.00001581831,0.00000506128,0.0027599824],"genre_scores_gemma":[0.9918198,0.0000066704124,0.0002482128,0.00045363815,0.00012313543,0.0072165797,0.00011050699,0.000010711317,0.000010729246],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97524107,0.019053446,0.0011014208,0.00014971817,0.0038498603,0.0006045141],"domain_scores_gemma":[0.99610585,0.00063692534,0.00073484104,0.00028905374,0.0020239835,0.00020933988],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.07408545,0.000094244824,0.00015464898,0.00047098025,0.0021089346,0.000023391252,0.000451445,0.00005064794,0.0007704948],"category_scores_gemma":[0.0007370484,0.000060040235,0.00006323357,0.0009775027,0.00008194592,0.00008780226,0.000056334444,0.001530699,0.0000056538274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007949526,0.00034188596,0.079699256,0.00016296143,0.000025493153,0.0000062813037,0.11724077,0.0050414964,0.0000038178373,0.00042706722,0.004658254,0.7923132],"study_design_scores_gemma":[0.0040962803,0.009659629,0.15579078,0.0010948005,0.00025102677,0.00001361776,0.4982466,0.032040842,0.000019104438,0.00585052,0.29271996,0.00021684426],"about_ca_topic_score_codex":0.0035766277,"about_ca_topic_score_gemma":0.009952009,"teacher_disagreement_score":0.7920964,"about_ca_system_score_codex":0.0025231042,"about_ca_system_score_gemma":0.008070708,"threshold_uncertainty_score":0.9991902},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9007081,0.008226238,0.0005424509,0.011816512,0.00974967,0.043546036,0.0005162545,0.00033265087,0.024562089],"genre_scores_gemma":[0.99164695,0.00007037257,0.0020368749,0.00016952411,0.0017610409,0.0021011506,0.00084355613,0.00006182835,0.0013087332],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912418,0.0017149594,0.0009978063,0.0007088171,0.004002876,0.0013337204],"domain_scores_gemma":[0.99501246,0.000048113798,0.001173653,0.0008130154,0.0017745555,0.0011782149],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016325017,0.00037850803,0.00043561385,0.0006634352,0.0018727332,0.0013452696,0.0021100722,0.00016364262,0.003202709],"category_scores_gemma":[0.0009924173,0.0003618226,0.00027643124,0.0016948666,0.00040728113,0.0018215111,0.00022541854,0.00074524054,0.00003744545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045122713,0.00033356136,0.012990517,0.000026947122,0.00015623715,0.000025056499,0.006885474,0.0006448811,0.00004413809,0.00018959453,0.008686619,0.96997184],"study_design_scores_gemma":[0.003594429,0.003933763,0.02568283,0.00012028035,0.0016499421,0.000059346767,0.058785018,0.088824615,0.000018244828,0.004460097,0.81173295,0.0011384775],"about_ca_topic_score_codex":0.01180251,"about_ca_topic_score_gemma":0.029173775,"teacher_disagreement_score":0.9688334,"about_ca_system_score_codex":0.0022046492,"about_ca_system_score_gemma":0.012131394,"threshold_uncertainty_score":0.99988335},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9756994,0.0007537008,0.000180263,0.019085694,0.00039539277,0.0026944554,0.00006630035,0.0000105122845,0.001114272],"genre_scores_gemma":[0.97980326,0.000004432247,0.00066598476,0.018993104,0.000051282383,0.00018602745,0.0002802501,0.000010075356,0.0000055651108],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9860585,0.0111381,0.0012490677,0.00009247908,0.0009933681,0.00046852394],"domain_scores_gemma":[0.99616605,0.0006144309,0.0015477971,0.0003932758,0.0009830788,0.00029539602],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.03126671,0.00010838409,0.00045128146,0.0009955872,0.0020091918,0.000042313433,0.00060979475,0.00006849383,0.00042111814],"category_scores_gemma":[0.00019485396,0.000084596395,0.00017682878,0.0017556533,0.000042199463,0.00029768838,0.00006378029,0.0015712221,0.0000013464139],"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":[0.00011150219,0.0004430845,0.39296463,0.0020229702,0.00018099343,0.000017436114,0.06565005,0.003387004,0.000024067242,0.00018274678,0.0019589213,0.53305656],"study_design_scores_gemma":[0.0015392214,0.0011984215,0.89575905,0.00021408503,0.00041029695,0.000006542795,0.081500895,0.006577589,0.0000011335493,0.0005994895,0.012081579,0.000111694935],"about_ca_topic_score_codex":0.102373704,"about_ca_topic_score_gemma":0.4268726,"teacher_disagreement_score":0.53294486,"about_ca_system_score_codex":0.0035329545,"about_ca_system_score_gemma":0.034184605,"threshold_uncertainty_score":0.99929005},"labels":[],"label_agreement":null},{"id":"W4224793496","doi":"10.3138/cjpe.71430","title":"Redesigning a University-Based Evaluator Education Program for Scholarship and Practice","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Premise; Curriculum; Process (computing); Medical education; Pedagogy; Engineering ethics; Sociology; Psychology; Computer science; Engineering; Political science; Medicine","score_opus":0.4058180102937288,"score_gpt":0.5556122397401135,"score_spread":0.1497942294463847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224793496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86500365,0.0043757926,0.019413607,0.063412815,0.0058701863,0.029931305,0.00010053187,0.000114536786,0.011777588],"genre_scores_gemma":[0.9176187,0.000003963729,0.08085257,0.0006656414,0.00012840435,0.0004388801,0.000035350822,0.000012895265,0.00024358481],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946605,0.0021486953,0.0005596971,0.00024883947,0.0021431514,0.00023911038],"domain_scores_gemma":[0.9927693,0.0010787058,0.0009061515,0.00022177838,0.0046043317,0.00041975337],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038800385,0.000104850624,0.00017209293,0.00093587616,0.00089211616,0.00047103254,0.00040324382,0.000047119796,0.00076417596],"category_scores_gemma":[0.011037154,0.00010188124,0.00010017399,0.0009899825,0.00007004551,0.0010407228,0.000018726087,0.00026973087,0.0000057412567],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001444301,0.00014689457,0.0039155036,0.0000064880905,0.00002175848,0.0000024125943,0.0006358425,0.0029872563,0.000043330878,0.0007894672,0.0030108031,0.9882958],"study_design_scores_gemma":[0.0019944499,0.0024796545,0.012248867,0.000034527045,0.00028563727,0.00010354818,0.010995443,0.09396074,0.00003148239,0.0056486595,0.8720331,0.00018389404],"about_ca_topic_score_codex":0.00013479794,"about_ca_topic_score_gemma":0.0009968302,"teacher_disagreement_score":0.9881119,"about_ca_system_score_codex":0.0009327774,"about_ca_system_score_gemma":0.022411311,"threshold_uncertainty_score":0.9972933},"labels":[],"label_agreement":null},{"id":"W4224862209","doi":"10.3138/cjpe.71349","title":"Collaborative Evaluation Frameworks for Indigenous-Led Community Health Interventions: A Narrative Review","year":2022,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Indigenous; Psychological intervention; Narrative; Context (archaeology); Participatory action research; Equity (law); Sociology; Traditional knowledge; Citizen journalism; Community-based participatory research; Health equity; Community development; Narrative review; Engineering ethics; Medicine; Political science; Psychology; Geography; Nursing; Public health; Anthropology; Ecology; Engineering; Psychotherapist","score_opus":0.5641203596982542,"score_gpt":0.6521167436229571,"score_spread":0.08799638392470288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224862209","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018648412,0.9716064,0.0011055615,0.0012266896,0.001914396,0.023443364,0.00027039347,0.000013441567,0.00040114947],"genre_scores_gemma":[0.00007744555,0.9854752,0.0032064226,0.00072578917,0.00023611511,0.008655813,0.001456665,0.00004791403,0.00011865154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96473634,0.023889469,0.0050941124,0.00048772924,0.0052088844,0.00058349007],"domain_scores_gemma":[0.97402924,0.0031318523,0.00952573,0.0009932254,0.011579936,0.0007400369],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15306132,0.0004981181,0.0027414828,0.0019449613,0.002148797,0.00066333864,0.0016783815,0.00039921456,0.009285927],"category_scores_gemma":[0.03052667,0.00039325465,0.0015732993,0.0037977744,0.00015119837,0.00076376216,0.00006316171,0.0026781058,0.000037935984],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000007909904,0.00013900633,0.0000075786465,0.00472326,0.00025017918,8.524135e-7,0.0070718415,0.00011375913,2.782553e-9,0.00005635244,0.016779749,0.9708495],"study_design_scores_gemma":[0.00071886624,0.00202479,0.000034884633,0.033846363,0.0019653577,0.000046403624,0.0077513917,0.001114353,2.9090868e-8,0.0040387386,0.94814545,0.00031335646],"about_ca_topic_score_codex":0.00061512354,"about_ca_topic_score_gemma":0.04463242,"teacher_disagreement_score":0.9705362,"about_ca_system_score_codex":0.0062409635,"about_ca_system_score_gemma":0.08534402,"threshold_uncertainty_score":0.99985194},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4224866913","doi":"10.3138/cjpe.72386","title":"Evaluation Utility Metrics (EUMs) in Reflective Practice","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences","keywords":"Quality (philosophy); Negotiation; Computer science; Evaluation methods; Management science; Process management; Risk analysis (engineering); Psychology; Medicine; Business; Reliability engineering; Sociology; Engineering","score_opus":0.5800774051525978,"score_gpt":0.6115541890215195,"score_spread":0.03147678386892172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224866913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8902088,0.004783796,0.002588208,0.017193928,0.0056158523,0.0073326873,0.000043129956,0.00002570776,0.0722079],"genre_scores_gemma":[0.9960427,0.0000097633265,0.0030074792,0.00042313602,0.00009734366,0.0003248661,0.000017786637,0.000009402238,0.000067512585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98045856,0.007188049,0.0014725018,0.00034716068,0.010176695,0.00035703293],"domain_scores_gemma":[0.98698246,0.0010863034,0.0013428361,0.0003801053,0.009865666,0.00034260374],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15872046,0.00012719163,0.00026250578,0.0022371481,0.00045851356,0.0003251662,0.00062254636,0.000060126073,0.0093865935],"category_scores_gemma":[0.044602763,0.00011532523,0.00012324768,0.0043587075,0.0000629419,0.0013443884,0.000039046063,0.0005886337,0.00004069535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054261505,0.00014062457,0.01552068,0.0000012838668,0.000028328084,0.000009048811,0.0024340576,0.020213649,0.000009387164,0.00027501964,0.002833664,0.95848],"study_design_scores_gemma":[0.0023902107,0.0012535456,0.13926625,0.000014663539,0.0002986005,0.00012648824,0.015243135,0.5985043,0.00003697706,0.036958177,0.20568629,0.00022132428],"about_ca_topic_score_codex":0.0014772441,"about_ca_topic_score_gemma":0.025800275,"teacher_disagreement_score":0.9582587,"about_ca_system_score_codex":0.0034589607,"about_ca_system_score_gemma":0.018219441,"threshold_uncertainty_score":0.9919763},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9664773,0.0010264349,0.028149264,0.0017350782,0.00015612545,0.0005849141,0.000021322325,0.000021902488,0.0018276945],"genre_scores_gemma":[0.9889453,0.00036817734,0.00987983,0.00011613534,0.00018833531,0.00024573877,0.000012795719,0.000015230337,0.00022843726],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99315804,0.0048212693,0.00042121785,0.00018572665,0.00082434167,0.00058942474],"domain_scores_gemma":[0.99825263,0.00037744417,0.00046982712,0.00009053628,0.00037345913,0.0004360963],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.018207977,0.00013032326,0.00016242515,0.00014668032,0.0019071762,0.00030574805,0.00039302753,0.00014178621,0.0003601282],"category_scores_gemma":[0.0020817372,0.00014739663,0.00020628422,0.0007023214,0.0007339275,0.00043271444,0.000019809495,0.00033728208,0.0000018857278],"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":[0.000051502393,0.0002196374,0.0425887,0.000042861713,0.000056358997,0.000032634973,0.35048786,0.0102884,0.0007354393,0.0014985997,0.0011592779,0.5928387],"study_design_scores_gemma":[0.0018925694,0.001095843,0.6095002,0.0007905101,0.0004951874,0.0001788054,0.22425362,0.04593957,0.00046343313,0.08626755,0.028607592,0.0005150827],"about_ca_topic_score_codex":0.090976655,"about_ca_topic_score_gemma":0.265018,"teacher_disagreement_score":0.59232366,"about_ca_system_score_codex":0.0042761634,"about_ca_system_score_gemma":0.01136606,"threshold_uncertainty_score":0.99954623},"labels":[],"label_agreement":null},{"id":"W4224940934","doi":"10.3138/cjpe.71050","title":"Realistic Evaluation and the Process-Tracing Method: A Combined Approach to Scrutinizing Causal Mechanisms","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Scrutiny; Framing (construction); Process tracing; Tracing; Causal model; Computer science; Process (computing); Causal inference; Psychology; Management science; Process management; Epistemology; Econometrics; Political science; Engineering; Economics; Mathematics","score_opus":0.34706621608805643,"score_gpt":0.5365759557097144,"score_spread":0.18950973962165796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224940934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46707392,0.0017537336,0.4430212,0.03189943,0.0043597133,0.022231419,0.00006643769,0.000067937704,0.029526202],"genre_scores_gemma":[0.9762182,0.0000015924514,0.022103008,0.00065051444,0.00009488537,0.0008250916,0.000023099665,0.0000137908,0.00006979393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892115,0.0039417804,0.0010928137,0.00033586074,0.0050938553,0.00032420122],"domain_scores_gemma":[0.9943823,0.0006849616,0.0008861811,0.00032025226,0.0032989206,0.00042735366],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.099355064,0.00014896314,0.0003242643,0.00078012823,0.0011147292,0.00059123803,0.00058255624,0.000044201795,0.00091238006],"category_scores_gemma":[0.007989855,0.000102877675,0.000097201635,0.0014950973,0.00008662509,0.0004048615,0.00004770486,0.00037915458,0.0000074089667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020193701,0.000071838964,0.000735709,0.000010826412,0.00005785547,0.0000023162413,0.013235679,0.19538611,0.0000419639,0.016998004,0.0012746181,0.77198315],"study_design_scores_gemma":[0.0028691941,0.0005664865,0.0046903347,0.000020929707,0.00027164535,0.00013230421,0.013569495,0.8680088,0.000031097705,0.107864596,0.0018221673,0.00015293976],"about_ca_topic_score_codex":0.0006551677,"about_ca_topic_score_gemma":0.0022824667,"teacher_disagreement_score":0.7718302,"about_ca_system_score_codex":0.0005991992,"about_ca_system_score_gemma":0.0052622,"threshold_uncertainty_score":0.9989922},"labels":[],"label_agreement":null},{"id":"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38609836,0.019396707,0.020511186,0.044127163,0.10625002,0.017102921,0.00029969087,0.0004422422,0.40577173],"genre_scores_gemma":[0.99031377,0.0000061390274,0.0038112404,0.00057049363,0.003123364,0.0012915129,0.000030200516,0.00002613489,0.0008271748],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989323,0.00021463768,0.0002658982,0.00010012797,0.0003052501,0.00018178944],"domain_scores_gemma":[0.9990868,0.000019993351,0.0002357374,0.00019351029,0.00025084737,0.00021313953],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016991018,0.00005937241,0.000085647756,0.0002317584,0.00023246116,0.000031499974,0.00024057778,0.000038554197,0.012090714],"category_scores_gemma":[0.000023674203,0.00006202511,0.00007483218,0.00028398522,0.000034074357,0.000050039485,0.0000040752284,0.00026160365,0.00001510552],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013648735,0.00007084126,0.0007152871,8.3479284e-7,0.000032590804,0.00000679686,0.0007212163,0.000033865155,0.000051748335,0.0030625323,0.46070194,0.5345887],"study_design_scores_gemma":[0.00039282825,0.00044534678,0.0059144823,0.0000041779076,0.000032326698,0.00010703597,0.00046295972,0.00018948648,0.000007236017,0.00505492,0.9873178,0.00007141658],"about_ca_topic_score_codex":0.0007603403,"about_ca_topic_score_gemma":0.001237728,"teacher_disagreement_score":0.6042154,"about_ca_system_score_codex":0.0003006601,"about_ca_system_score_gemma":0.0007367085,"threshold_uncertainty_score":0.9888124},"labels":[],"label_agreement":null},{"id":"W4225929430","doi":"10.3138/cjpe.73685","title":"Pat Bazeley. (2018). <i>Integrating Analyses in Mixed Methods Research</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.8220107669184188,"score_gpt":0.7166431773534617,"score_spread":0.10536758956495706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225929430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9570402,0.0046429294,0.006473159,0.008726217,0.0041374452,0.002710508,0.000024809531,0.00002049064,0.016224226],"genre_scores_gemma":[0.96736175,0.000009195239,0.031866755,0.00016836995,0.0001261142,0.00020943217,0.000011876238,0.000011761334,0.00023477565],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9822384,0.010452636,0.0014809713,0.00030874758,0.0050109373,0.0005083145],"domain_scores_gemma":[0.9938296,0.0014670225,0.0006999278,0.00038554013,0.003174828,0.0004430865],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12263103,0.000120778925,0.000319694,0.0025238064,0.0006889202,0.00048204264,0.0008754666,0.000052672098,0.006716306],"category_scores_gemma":[0.012044523,0.000096336305,0.0001573749,0.003645101,0.000114350696,0.00058145146,0.000061581915,0.0008595508,0.000034915392],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017320855,0.000051989897,0.009515124,0.0000019483527,0.000016609016,0.000014205456,0.0019421295,0.0102701355,0.0005349439,0.00036752227,0.0075713247,0.96969676],"study_design_scores_gemma":[0.0019366257,0.0018050815,0.10324251,0.000063924985,0.00008318242,0.000121648765,0.05411251,0.31792912,0.0006787907,0.05150673,0.46817395,0.00034592944],"about_ca_topic_score_codex":0.002718627,"about_ca_topic_score_gemma":0.05086131,"teacher_disagreement_score":0.9693508,"about_ca_system_score_codex":0.0014490895,"about_ca_system_score_gemma":0.00869532,"threshold_uncertainty_score":0.99692446},"labels":[],"label_agreement":null},{"id":"W4225936008","doi":"10.3138/cjpe.73771","title":"Jill Anne Chouinard &amp; Fiona Cram. (2020). <i>Culturally responsive approaches to evaluation: Empirical implications for theory and practice.</i>","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Empirical research; Psychology; Epistemology; Philosophy","score_opus":0.7071106155438179,"score_gpt":0.5753760736915132,"score_spread":0.1317345418523047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225936008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5060367,0.0060410625,0.021340916,0.44062787,0.0023757338,0.01632479,0.00038607832,0.00005139955,0.006815434],"genre_scores_gemma":[0.9617542,0.000015947624,0.030119184,0.004114132,0.00037274632,0.00271793,0.00016036142,0.000025097806,0.0007204204],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907859,0.004449929,0.0011197997,0.0004703424,0.0027999515,0.00037409316],"domain_scores_gemma":[0.9885985,0.0032805107,0.000914698,0.0004644979,0.0060470896,0.0006946658],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07074684,0.00018227457,0.00029847934,0.00063841464,0.0011357114,0.0005540988,0.000587256,0.00007224571,0.0017557654],"category_scores_gemma":[0.03436423,0.00014987742,0.00015915137,0.0013226497,0.00011117148,0.0008784526,0.00006290584,0.00030459723,0.000028969536],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069913984,0.00015615475,0.003853935,0.0000063374623,0.0000961167,0.0000019573586,0.008495332,0.021609884,0.00009279296,0.006244892,0.09708923,0.8616542],"study_design_scores_gemma":[0.001649292,0.0014866173,0.08011646,0.00001593824,0.00037869727,0.00043134368,0.010157078,0.010784401,0.0000093510325,0.07308408,0.8216011,0.00028564673],"about_ca_topic_score_codex":0.000046908215,"about_ca_topic_score_gemma":0.0023777473,"teacher_disagreement_score":0.8613686,"about_ca_system_score_codex":0.00092848646,"about_ca_system_score_gemma":0.007500404,"threshold_uncertainty_score":0.9991568},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7720447,0.07578208,0.0014724316,0.04032968,0.02369236,0.004544022,0.0001445253,0.00009471885,0.08189546],"genre_scores_gemma":[0.9927052,0.0004630239,0.0014986669,0.0003493249,0.0019963565,0.00023260996,0.000029129065,0.00002347325,0.0027022138],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99282676,0.004609394,0.000558306,0.00020467411,0.0012439742,0.0005569204],"domain_scores_gemma":[0.9974898,0.00034736586,0.0006368176,0.00011110626,0.00092369044,0.0004912278],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013184382,0.00017703573,0.00028551277,0.00030872918,0.0021125246,0.0002544004,0.0002612978,0.0001756673,0.0015041343],"category_scores_gemma":[0.0018400919,0.00021073269,0.00020890094,0.0011081262,0.00053889176,0.000507975,0.00002564065,0.00074473734,0.000009808675],"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":[0.000025531446,0.00029244897,0.008210838,0.00003550993,0.00021995939,0.000049890044,0.12767449,0.018994596,0.00005102975,0.024313157,0.041560914,0.77857167],"study_design_scores_gemma":[0.00114547,0.00114892,0.095740855,0.00012428987,0.0006071983,0.00009971659,0.02034219,0.014363422,0.000008136371,0.016966548,0.8490846,0.00036861905],"about_ca_topic_score_codex":0.10680057,"about_ca_topic_score_gemma":0.20127794,"teacher_disagreement_score":0.8075237,"about_ca_system_score_codex":0.0049983603,"about_ca_system_score_gemma":0.009169526,"threshold_uncertainty_score":0.9994086},"labels":[],"label_agreement":null},{"id":"W4226083882","doi":"10.3138/cjpe.71482","title":"Learning and Leading: Integrating Mixed Methods in a Collaborative Approach to Educational Evaluation","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta; Western University; Queen's University","funders":"","keywords":"Multimethodology; Perspective (graphical); Context (archaeology); Mental health; Value (mathematics); Collaborative learning; Qualitative property; Qualitative research; Phenomenon; Psychology; Knowledge management; Sociology; Pedagogy; Computer science; Epistemology; Social science","score_opus":0.35869882773020634,"score_gpt":0.6077636009537061,"score_spread":0.24906477322349974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226083882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9466424,0.0016668849,0.012277377,0.009850387,0.0019123277,0.004741582,0.000012018095,0.000011979069,0.022885025],"genre_scores_gemma":[0.90167415,0.0000026729763,0.09713544,0.00013616045,0.00008737962,0.00070283207,0.000028665905,0.00000972229,0.00022294925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9901146,0.0054877214,0.0010266878,0.00031624877,0.0027922834,0.0002624041],"domain_scores_gemma":[0.9946153,0.00078640116,0.0007156785,0.0001400929,0.0033787957,0.00036369226],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06729252,0.00012702683,0.0002722126,0.0016385359,0.00053902727,0.0004054779,0.00032011748,0.00004366824,0.0017554337],"category_scores_gemma":[0.014144973,0.00011381951,0.000057280373,0.0026404806,0.000054341308,0.0004964794,0.000040233972,0.00048046774,0.000009236074],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019981397,0.00006424526,0.02464444,0.0000026862797,0.00001522867,4.9353355e-7,0.01302375,0.058438268,0.00015088395,0.0011670854,0.0011853895,0.90128756],"study_design_scores_gemma":[0.0015180736,0.0011846572,0.09079633,0.000038701368,0.00008923199,0.00007134486,0.07677867,0.7643225,0.000066533714,0.019073633,0.04579341,0.00026686542],"about_ca_topic_score_codex":0.0002520109,"about_ca_topic_score_gemma":0.005059473,"teacher_disagreement_score":0.9010207,"about_ca_system_score_codex":0.0014106336,"about_ca_system_score_gemma":0.010012442,"threshold_uncertainty_score":0.9991571},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41199163,0.0018613231,0.5689761,0.012199257,0.002235151,0.0022501447,0.000026755088,0.0000454089,0.00041423546],"genre_scores_gemma":[0.73136604,9.353092e-7,0.26827538,0.00019454454,0.00006490754,0.0000631041,0.000014517992,0.0000074117697,0.000013181658],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961169,0.0018115421,0.0005780997,0.00017581152,0.0010396697,0.00027799833],"domain_scores_gemma":[0.9960435,0.00019579504,0.00054183794,0.00021408334,0.0027372835,0.00026749942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006253013,0.00011293645,0.00027636994,0.00062960165,0.00032220205,0.00012125003,0.0006093982,0.00003134146,0.00009789992],"category_scores_gemma":[0.0008526048,0.00011860416,0.000102190104,0.00081793265,0.000056001714,0.00025558163,0.000084275875,0.00026012186,0.0000021691699],"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":[0.000010961806,0.000031127096,0.00019771513,0.000016077585,0.00007352298,0.000006343297,0.0038879903,0.051115062,0.00019652011,0.012902967,0.000587711,0.930974],"study_design_scores_gemma":[0.0013723801,0.0013620023,0.012364585,0.00012298745,0.00017355214,0.00013641758,0.0063669626,0.9362705,0.00036479856,0.019441439,0.021741481,0.00028290926],"about_ca_topic_score_codex":0.0007267755,"about_ca_topic_score_gemma":0.0017284672,"teacher_disagreement_score":0.93069106,"about_ca_system_score_codex":0.0006769754,"about_ca_system_score_gemma":0.005090814,"threshold_uncertainty_score":0.90308857},"labels":[],"label_agreement":null},{"id":"W4226119644","doi":"10.3138/cjpe.73687","title":"The Contributions of Innovations in Integration in Complex Mixed Methods Evaluation Designs in This Issue and Beyond","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Closing (real estate); Management science; Psychology; Computer science; Epistemology; Business; Economics; Philosophy","score_opus":0.4642771256930222,"score_gpt":0.5952877465304317,"score_spread":0.1310106208374095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226119644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674415,0.0016760043,0.0073604872,0.015766026,0.0010864225,0.004132914,0.00004688915,0.0000051447087,0.0024846098],"genre_scores_gemma":[0.99247915,0.00001991287,0.006857106,0.000117931915,0.000027564993,0.00040050125,0.000058074827,0.000005631019,0.000034154404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9900854,0.0055554505,0.0018329646,0.00020694235,0.002060021,0.00025921976],"domain_scores_gemma":[0.99462575,0.0012725759,0.00089801487,0.00022750236,0.002865571,0.0001106075],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08397856,0.000103665916,0.000270798,0.0018621017,0.00033714526,0.00016962668,0.0003566378,0.000057079673,0.0018563524],"category_scores_gemma":[0.010179714,0.00008166485,0.00005053264,0.003430356,0.00012933159,0.00048997055,0.000029215196,0.00041304788,0.0000026754399],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030701638,0.000075623706,0.0180719,0.0000017499293,0.000007896983,0.0000011460884,0.0035213062,0.013755363,0.00079491484,0.0033333334,0.0014104799,0.9589956],"study_design_scores_gemma":[0.0020420197,0.0004048086,0.3564094,0.000027594246,0.00003646163,0.000014915558,0.012982923,0.57049894,0.00031232895,0.0446928,0.012466846,0.00011095369],"about_ca_topic_score_codex":0.0017843962,"about_ca_topic_score_gemma":0.112096526,"teacher_disagreement_score":0.95888466,"about_ca_system_score_codex":0.0013100732,"about_ca_system_score_gemma":0.004570174,"threshold_uncertainty_score":0.9990561},"labels":[],"label_agreement":null},{"id":"W4226263038","doi":"10.3138/cjpe.70920","title":"Responding to the Evaluation Capacity Needs of the Early Childhood Field: Insights from a Mixed Methods Community-based Participatory Design","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Capacity building; Interdependence; Citizen journalism; Knowledge management; Participatory action research; Multimethodology; Resource (disambiguation); Capacity development; Qualitative property; Sociology; Management science; Psychology; Pedagogy; Environmental resource management; Computer science; Engineering; Political science; Social science","score_opus":0.6312424150244843,"score_gpt":0.5375796860218353,"score_spread":0.09366272900264905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226263038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97525793,0.00019934951,0.016248865,0.0045371014,0.0014181489,0.002047593,0.000018397053,0.0000054615166,0.00026713524],"genre_scores_gemma":[0.99034745,4.2253006e-7,0.007882344,0.0012647393,0.00008409564,0.00038315807,0.000008993519,0.00000998869,0.000018808818],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.964317,0.030285915,0.001126366,0.00014163823,0.0038800451,0.000249027],"domain_scores_gemma":[0.99221605,0.0032588262,0.0010675233,0.00078183477,0.0024019198,0.00027382452],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07678471,0.00013186522,0.00025483532,0.0012386293,0.0014639152,0.00024161258,0.0013441718,0.000059463084,0.0014318884],"category_scores_gemma":[0.009859901,0.000081099344,0.00017254068,0.00319335,0.00009153005,0.00029335002,0.000058317524,0.0007130683,0.000009622618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009259405,0.00013509169,0.006684137,0.0000022340114,0.00007334371,4.6349032e-7,0.062428515,0.17161919,0.0008193095,0.00035109738,0.0028635748,0.75493044],"study_design_scores_gemma":[0.0025219105,0.0028659035,0.60953856,0.00010296314,0.0006713112,0.000010358133,0.03752649,0.25954756,0.008729595,0.036440346,0.041713458,0.0003315238],"about_ca_topic_score_codex":0.0022831848,"about_ca_topic_score_gemma":0.009209466,"teacher_disagreement_score":0.7545989,"about_ca_system_score_codex":0.00064800127,"about_ca_system_score_gemma":0.007165092,"threshold_uncertainty_score":0.999836},"labels":[],"label_agreement":null},{"id":"W4226406422","doi":"10.3138/cjpe.73684","title":"Donna Mertens. (2018). <i>Mixed Methods Design in Evaluation</i> .","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.5744650939781201,"score_gpt":0.5931184524350988,"score_spread":0.018653358456978686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226406422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6328445,0.018954078,0.22771825,0.03977698,0.0308152,0.024798818,0.000088029716,0.00010616772,0.024897983],"genre_scores_gemma":[0.9392788,0.000013575241,0.059052866,0.00059929624,0.0001459638,0.00070382754,0.000021886353,0.000018817595,0.00016500583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9797209,0.01155475,0.0017973672,0.0003850233,0.006067562,0.00047443452],"domain_scores_gemma":[0.99343276,0.0010013585,0.0011295377,0.00049008563,0.0034659598,0.00048030727],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15702192,0.00017400524,0.00038497325,0.001777161,0.0005115673,0.00035908382,0.00090943597,0.000069959584,0.014228218],"category_scores_gemma":[0.0086573,0.0001505796,0.00017105868,0.0023807867,0.00008642388,0.0007179695,0.000045790188,0.0005003411,0.00006001056],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002959452,0.00006438093,0.0036163884,0.0000013708957,0.000021806942,0.000007370621,0.0012731252,0.08718261,0.00008483916,0.00017630334,0.012299714,0.8952425],"study_design_scores_gemma":[0.0026946242,0.0010111505,0.050942827,0.00002180349,0.00018183235,0.00013295682,0.00518071,0.72025615,0.00020099706,0.040345423,0.1787395,0.0002919997],"about_ca_topic_score_codex":0.00062963174,"about_ca_topic_score_gemma":0.008715989,"teacher_disagreement_score":0.8949505,"about_ca_system_score_codex":0.0018131185,"about_ca_system_score_gemma":0.014502859,"threshold_uncertainty_score":0.9996932},"labels":[],"label_agreement":null},{"id":"W4226507667","doi":"10.3138/cjpe.71237","title":"A Multi-Stage Approach to Qualitative Sampling within a Mixed Methods Evaluation: Some Reflections on Purpose and Process","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Economic and Social Research Council","keywords":"Randomized controlled trial; Scale (ratio); Sampling (signal processing); Process (computing); Qualitative property; Sample (material); Computer science; Intervention (counseling); Multimethodology; Psychology; Process management; Mathematics education; Business; Machine learning; Geography; Medicine","score_opus":0.8290454090139003,"score_gpt":0.7062106398700911,"score_spread":0.1228347691438092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226507667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86651117,0.0010273425,0.11089235,0.005355739,0.0033931676,0.008705301,0.000093784685,0.000043281412,0.003977875],"genre_scores_gemma":[0.7894692,0.0000014441454,0.20825164,0.00053348404,0.00011338916,0.0013662952,0.000027228918,0.000017660877,0.00021968859],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98765457,0.006291381,0.0012445372,0.00047143968,0.004008813,0.00032926432],"domain_scores_gemma":[0.9937488,0.00068908784,0.0009844693,0.00033854874,0.0035927226,0.0006463855],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08511748,0.00018854608,0.00034196852,0.0015539991,0.0010871474,0.000502952,0.00048910326,0.000060535946,0.00085399015],"category_scores_gemma":[0.009353917,0.00016038692,0.00011017275,0.001948444,0.000088480876,0.00070013636,0.000031863732,0.0004965261,0.000013822558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009777286,0.0002622263,0.00031130263,0.000012901575,0.00006935516,0.0000016590076,0.11846542,0.3269271,0.00023025683,0.002318587,0.00044865286,0.55085474],"study_design_scores_gemma":[0.0024447453,0.0021235577,0.007996258,0.00004255494,0.00020788994,0.000076120275,0.24189028,0.7107358,0.00014459442,0.01700569,0.0169559,0.0003766208],"about_ca_topic_score_codex":0.00023274841,"about_ca_topic_score_gemma":0.0033456713,"teacher_disagreement_score":0.55047816,"about_ca_system_score_codex":0.001091506,"about_ca_system_score_gemma":0.0067000124,"threshold_uncertainty_score":0.9989907},"labels":[],"label_agreement":null},{"id":"W4230488502","doi":"10.3138/cjpe.230","title":"Useful Theory of Change Models","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":213,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Causality (physics); Theory of change; Development theory; Intervention (counseling); Epistemology; Computer science; Psychological intervention; Management science; Psychology; Sociology; Economics; Philosophy; Physics","score_opus":0.8815743086593234,"score_gpt":0.5830366120430426,"score_spread":0.2985376966162808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230488502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95964456,0.002650479,0.00972136,0.0034881167,0.002291091,0.0019165735,0.00001772277,0.000012306121,0.020257823],"genre_scores_gemma":[0.9969894,0.000007206828,0.0024429155,0.00017880819,0.00018884783,0.00003806376,0.0000045625,0.0000066679577,0.00014349655],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995709,0.000712624,0.00080876506,0.00012122727,0.0024613836,0.00018701832],"domain_scores_gemma":[0.9930302,0.0001720576,0.00075566175,0.00026301024,0.005218913,0.0005601838],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029516792,0.00008291962,0.00021489646,0.00064535695,0.00006086782,0.00013213043,0.00043061728,0.00006207573,0.0009688999],"category_scores_gemma":[0.0025231948,0.00006067476,0.0001000823,0.0006161088,0.00008981459,0.0010544589,0.000010740537,0.00011993154,0.000047256257],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030111445,0.0000372332,0.014560733,0.0000027214232,0.000021238911,0.000002753057,0.0053672697,0.004864279,0.0000065628965,0.0056105354,0.002937779,0.96655875],"study_design_scores_gemma":[0.0024415264,0.0015677082,0.060294893,0.000098611206,0.00016923127,0.0000638531,0.008755816,0.28167215,0.0002045228,0.59057784,0.053905766,0.0002480593],"about_ca_topic_score_codex":0.00031486075,"about_ca_topic_score_gemma":0.005280161,"teacher_disagreement_score":0.96631074,"about_ca_system_score_codex":0.00024369179,"about_ca_system_score_gemma":0.005279141,"threshold_uncertainty_score":0.9999443},"labels":[],"label_agreement":null},{"id":"W4234160001","doi":"10.3138/cjpe.34.3.v","title":"Editor’s Remarks","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.3130698758640696,"score_gpt":0.5203254987844013,"score_spread":0.20725562292033167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234160001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52900785,0.0040491326,0.027930891,0.27963135,0.053766813,0.0069849757,0.00004936131,0.000109825014,0.09846981],"genre_scores_gemma":[0.99058664,0.0000053420094,0.0038575812,0.0013054257,0.0041178796,0.000018446484,0.00000620796,0.0000075254093,0.00009497755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958979,0.00040524476,0.00080519787,0.00016036778,0.0025289329,0.00020235057],"domain_scores_gemma":[0.9951727,0.000161213,0.00056355965,0.00017884086,0.0030918855,0.0008318189],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010229976,0.00008598123,0.00018712904,0.0002938923,0.00013863586,0.00038374503,0.0004830046,0.0000647104,0.0061310297],"category_scores_gemma":[0.0065565505,0.000064959335,0.00011773652,0.0007403048,0.000056413235,0.00059451355,0.000009513816,0.00020880539,0.00028931972],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013141119,0.000012106104,0.0115501555,0.0000022819681,0.000014669857,0.000005402182,0.0012205056,0.0013830048,0.000036111567,0.00020052133,0.20221043,0.78335166],"study_design_scores_gemma":[0.00076907175,0.000649044,0.028208481,0.000020196903,0.00005483759,0.000017999322,0.0011803188,0.087478034,0.00007881379,0.004332372,0.877088,0.00012279728],"about_ca_topic_score_codex":0.00010812263,"about_ca_topic_score_gemma":0.0030603046,"teacher_disagreement_score":0.7832289,"about_ca_system_score_codex":0.00018679582,"about_ca_system_score_gemma":0.0055253017,"threshold_uncertainty_score":0.9947775},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6713685,0.015585941,0.0003694747,0.27095422,0.021709451,0.003906344,0.000046964553,0.000019014278,0.016040072],"genre_scores_gemma":[0.9839782,0.00091037183,0.003122397,0.003424584,0.006404361,0.00006242193,0.000019096404,0.00004423596,0.0020343375],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941366,0.0027637915,0.0011493625,0.0002032873,0.0007884106,0.0009585923],"domain_scores_gemma":[0.9920711,0.0003370347,0.0017582837,0.00058858347,0.0028589172,0.0023860915],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018560447,0.00020699005,0.00045362685,0.00019402256,0.0032326374,0.00018495573,0.0005722081,0.0010115838,0.0042536613],"category_scores_gemma":[0.011732701,0.00019694408,0.00022333748,0.00014765978,0.00039888461,0.0006711735,0.000022666001,0.002796996,0.00026988055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011625796,0.0000720254,0.037357166,0.00023400233,0.000089357025,0.000105462364,0.019209987,0.0000107118185,0.000003189555,0.0014111117,0.059665225,0.88183016],"study_design_scores_gemma":[0.0023753645,0.00072888855,0.28777066,0.0012326312,0.0004319996,0.000087096436,0.0060055065,0.0032924826,0.000003941018,0.0027191155,0.69517344,0.0001788689],"about_ca_topic_score_codex":0.031516593,"about_ca_topic_score_gemma":0.095848374,"teacher_disagreement_score":0.8816513,"about_ca_system_score_codex":0.0015343548,"about_ca_system_score_gemma":0.031096883,"threshold_uncertainty_score":0.9995036},"labels":[],"label_agreement":null},{"id":"W4234946968","doi":"10.3138/cjpe.30.3.04","title":"Lessons on Decolonizing Evaluation from Kaupapa Māori Evaluation","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Indigenous; Sociology; Traditional knowledge; Equity (law); Christian ministry; Community development; Cultural competence; Pedagogy; Public relations; Political science; Gender studies","score_opus":0.6218029580620157,"score_gpt":0.5966281862836175,"score_spread":0.02517477177839822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234946968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9594777,0.0008938044,0.0029264065,0.01931495,0.0040838,0.0036810867,0.000055407672,0.000027335254,0.0095395],"genre_scores_gemma":[0.99641144,0.000022851691,0.001998685,0.00034696082,0.00064630306,0.00033308365,0.00004879966,0.000024254758,0.00016760209],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9858571,0.002900598,0.0016683901,0.0005500306,0.008518367,0.0005054679],"domain_scores_gemma":[0.9845241,0.0013719837,0.001603414,0.00071467593,0.0110867,0.0006991334],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.058124952,0.00026448964,0.00040006728,0.0012778983,0.0004523172,0.0005933336,0.00077739725,0.00019679208,0.019662144],"category_scores_gemma":[0.019394701,0.00017384806,0.00024294358,0.001030944,0.00013277824,0.0014127949,0.000020870215,0.00026287622,0.0009154424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043138112,0.00006247364,0.011369663,0.0000011128104,0.000052071373,0.0000023579335,0.0006137678,0.002794091,0.0003966936,0.0004391378,0.005214055,0.9790114],"study_design_scores_gemma":[0.008954713,0.0018509018,0.46356136,0.000508078,0.0010589805,0.00003315095,0.0018462199,0.29799646,0.0018805807,0.13820444,0.083402075,0.00070303655],"about_ca_topic_score_codex":0.0005779843,"about_ca_topic_score_gemma":0.02840033,"teacher_disagreement_score":0.9783084,"about_ca_system_score_codex":0.002719115,"about_ca_system_score_gemma":0.013221617,"threshold_uncertainty_score":0.99986243},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18407509,0.05766507,0.00091787736,0.013249926,0.008174929,0.00096703274,0.00012961736,0.000022289581,0.7347982],"genre_scores_gemma":[0.9839501,0.00014234566,0.0013413194,0.00021424955,0.011154443,0.000008770935,0.000011095383,0.000020275304,0.0031573947],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833846,0.00040993496,0.00041554426,0.00010650192,0.00036559207,0.00036395065],"domain_scores_gemma":[0.9964736,0.00009209455,0.00036816543,0.00013175055,0.0023525443,0.0005818561],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032152543,0.00012805813,0.00018466116,0.00035476443,0.00054757914,0.00077843474,0.00018284908,0.00011264752,0.010411143],"category_scores_gemma":[0.0009870362,0.0001236415,0.00017524936,0.00012789616,0.00070286077,0.00016770093,0.0000054687966,0.0002342628,0.00008651209],"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":[0.000012649467,0.00014624327,0.0012901517,0.000028046608,0.0003915749,0.00010786413,0.010578297,0.00010595668,0.0000047419835,0.3364197,0.018083297,0.63283145],"study_design_scores_gemma":[0.0004648803,0.000546443,0.0015459652,0.00011986147,0.0014936975,0.000067431385,0.0015366926,0.011952746,0.00003524284,0.030893652,0.9511872,0.00015618553],"about_ca_topic_score_codex":0.025262361,"about_ca_topic_score_gemma":0.052095737,"teacher_disagreement_score":0.9331039,"about_ca_system_score_codex":0.00046038712,"about_ca_system_score_gemma":0.004001158,"threshold_uncertainty_score":0.9904935},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58033943,0.0179087,0.001913398,0.37513658,0.01540679,0.0037697786,0.000066031214,0.000028828314,0.005430471],"genre_scores_gemma":[0.9814541,0.0014364216,0.0030635798,0.0050234925,0.005829187,0.00008222191,0.000011560803,0.00005225977,0.0030472118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926546,0.0040739593,0.0012707216,0.00020430688,0.0007912063,0.0010052015],"domain_scores_gemma":[0.992776,0.0008175139,0.0008856408,0.00027805733,0.0028152291,0.0024276073],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016365433,0.00020374294,0.0004108166,0.00026463138,0.0007044998,0.000035334604,0.00026914407,0.00094393065,0.0088431975],"category_scores_gemma":[0.0072988425,0.00014673066,0.00020835553,0.00041823374,0.00026731525,0.00045542183,0.000011460501,0.0015408145,0.0004749879],"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":[0.000012777212,0.000063139,0.016555069,0.00014090403,0.00007340191,0.00005602853,0.0120403385,0.0000027875947,0.000019478653,0.0014972641,0.07230386,0.897235],"study_design_scores_gemma":[0.0032873582,0.001066367,0.079395294,0.0021569494,0.00037312106,0.00010984545,0.004911565,0.0005322766,0.000011859062,0.0036607487,0.9042971,0.00019749875],"about_ca_topic_score_codex":0.007577257,"about_ca_topic_score_gemma":0.037281413,"teacher_disagreement_score":0.89703745,"about_ca_system_score_codex":0.002323768,"about_ca_system_score_gemma":0.030892022,"threshold_uncertainty_score":0.99903136},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59015524,0.0045218603,0.005723127,0.008169647,0.038998034,0.008027191,0.000029979268,0.00014420456,0.34423074],"genre_scores_gemma":[0.9909198,0.000008985267,0.0044220015,0.00031599053,0.0028276376,0.00019990753,0.000013081237,0.000022411741,0.0012701853],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913853,0.00009288225,0.00026483418,0.000105424515,0.00021117886,0.00018714246],"domain_scores_gemma":[0.9988997,0.00002183916,0.00021670833,0.00023353877,0.00039762454,0.00023057818],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011063268,0.00006724679,0.00010344004,0.0001896501,0.000045092635,0.00004217769,0.00018552248,0.00009442917,0.007229418],"category_scores_gemma":[0.000022652235,0.00006246527,0.000074762516,0.00018950894,0.00002964725,0.00008169749,0.0000013845249,0.00016732901,0.0001982932],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015639813,0.000058774807,0.0059841834,0.0000031995896,0.00005089969,0.000002926577,0.0005721819,0.000008817004,0.00021277781,0.0047480427,0.2686139,0.71972865],"study_design_scores_gemma":[0.0005987153,0.0004106286,0.02736122,0.000029413188,0.000034587214,0.000047570986,0.00018637505,0.00021215963,0.000030733747,0.0043008565,0.9666912,0.00009656008],"about_ca_topic_score_codex":0.00052838423,"about_ca_topic_score_gemma":0.0013256163,"teacher_disagreement_score":0.7196321,"about_ca_system_score_codex":0.00013932769,"about_ca_system_score_gemma":0.0005402496,"threshold_uncertainty_score":0.9936781},"labels":[],"label_agreement":null},{"id":"W4235919605","doi":"10.3138/cjpe.30.3.03","title":"Getting to the Roots of Evaluation Capacity Building in the Global South: Multiple Streams Model to Frame the Agenda Status of Evaluation in Turkey","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Frame (networking); Capacity building; Window of opportunity; Political science; Business; Public administration; Public economics; Economic growth; Economics; Computer science","score_opus":0.44681448485405895,"score_gpt":0.5082014368718829,"score_spread":0.06138695201782396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235919605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98243314,0.00020869853,0.0060419403,0.006817719,0.0003837045,0.0037731922,0.00006107345,0.0000028607196,0.0002776901],"genre_scores_gemma":[0.99620944,0.0000044726426,0.003099974,0.00030361715,0.000094753246,0.00026801927,0.0000059421554,0.000008625499,0.000005175448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9876095,0.0034578103,0.0018030375,0.00033355088,0.006255284,0.0005408326],"domain_scores_gemma":[0.9920117,0.0012796427,0.0011870342,0.00062178937,0.0046397373,0.0002600443],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07228505,0.00017997876,0.00031062085,0.00061694544,0.00020702148,0.00020357239,0.0007944043,0.00009809897,0.0002511758],"category_scores_gemma":[0.028655706,0.000085318265,0.0001389793,0.0020474277,0.00011297868,0.00054213183,0.00003868932,0.00024312745,0.000012647535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003677378,0.000037620048,0.0730728,0.0000029686526,0.000013283315,3.8105506e-7,0.009824901,0.40213165,0.00036663038,0.00018539066,0.00020874341,0.51411885],"study_design_scores_gemma":[0.001158377,0.0002333254,0.32945964,0.00014437789,0.000081665436,0.000005361129,0.0047680256,0.65497637,0.00016496185,0.008420636,0.00048924825,0.000097999895],"about_ca_topic_score_codex":0.005316777,"about_ca_topic_score_gemma":0.12935029,"teacher_disagreement_score":0.51402086,"about_ca_system_score_codex":0.0017013742,"about_ca_system_score_gemma":0.006016409,"threshold_uncertainty_score":0.99961853},"labels":[],"label_agreement":null},{"id":"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23604794,0.016634332,0.04535694,0.029341467,0.07786545,0.010820499,0.00006267356,0.0003703516,0.5835003],"genre_scores_gemma":[0.9753451,0.000009542056,0.014681339,0.00046682137,0.008231892,0.00040698418,0.000021474947,0.00003335291,0.0008035416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990764,0.00012423398,0.0002678869,0.00009149735,0.0002576919,0.00018224666],"domain_scores_gemma":[0.99830085,0.000015419024,0.00020827037,0.00019559836,0.0007673357,0.0005125032],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017722502,0.00006620762,0.0000951053,0.00018704076,0.0000486614,0.000047553167,0.00018227157,0.00009096148,0.00092113664],"category_scores_gemma":[0.00007760923,0.0000612259,0.00005723914,0.00021276154,0.000048142934,0.000086789274,0.0000014824033,0.00015232264,0.00005567514],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000118027165,0.00004186888,0.0009707293,7.1695376e-7,0.000025830002,0.000004384925,0.0007338043,0.0000066166294,0.000016238877,0.0019535976,0.5215928,0.4746416],"study_design_scores_gemma":[0.0006506717,0.00041292523,0.0052480474,0.000016034817,0.000038963502,0.00007245528,0.00036102172,0.00017662866,0.000016599139,0.010280763,0.9826441,0.000081783866],"about_ca_topic_score_codex":0.0008875339,"about_ca_topic_score_gemma":0.002538721,"teacher_disagreement_score":0.7392971,"about_ca_system_score_codex":0.00020721725,"about_ca_system_score_gemma":0.0010830013,"threshold_uncertainty_score":0.99999213},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6826276,0.04216174,0.0009252586,0.22933474,0.02527649,0.0049401005,0.000045263492,0.000035933994,0.014652839],"genre_scores_gemma":[0.97595525,0.0005192736,0.006513008,0.0072096605,0.007639823,0.000083847684,0.000045959496,0.000059617494,0.0019735906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918583,0.0047219293,0.001264366,0.00018680583,0.0010274132,0.0009411819],"domain_scores_gemma":[0.98963857,0.00036498564,0.00086393533,0.000261881,0.0046629324,0.004207722],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024825655,0.00020416657,0.00043992265,0.0002718579,0.000559854,0.000056705456,0.00027155568,0.0009763066,0.0023058027],"category_scores_gemma":[0.009200823,0.00019303817,0.0001725541,0.0005740642,0.00021131635,0.00043251383,0.000012781666,0.0026224023,0.00036820731],"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":[0.000017756218,0.00009529789,0.01571199,0.00016647886,0.000077148434,0.00009421809,0.050828017,0.00006642691,0.0000013172577,0.0011330922,0.1963771,0.73543113],"study_design_scores_gemma":[0.0033368345,0.0014308102,0.02707491,0.00082065153,0.00043229453,0.00015383218,0.026613247,0.005708466,0.0000026449713,0.0038289393,0.9304041,0.00019324261],"about_ca_topic_score_codex":0.020325191,"about_ca_topic_score_gemma":0.05077063,"teacher_disagreement_score":0.7352379,"about_ca_system_score_codex":0.002790051,"about_ca_system_score_gemma":0.060077798,"threshold_uncertainty_score":0.9996786},"labels":[],"label_agreement":null},{"id":"W4237364742","doi":"10.3138/cjpe.154","title":"Implementation and Evaluation of an Evidence-Based Treatment of Disruptive Behaviour within a Children's Mental Health Program","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Multidisciplinary approach; Mental health; Context (archaeology); Psychology; Program evaluation; Medical education; Applied psychology; Process management; Multidisciplinary team; Knowledge management; Nursing; Medicine; Computer science; Business; Psychiatry; Sociology; Political science","score_opus":0.5674638354909648,"score_gpt":0.6170743887808582,"score_spread":0.04961055328989339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237364742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923357,0.0012886592,0.00012184878,0.0013942185,0.00030870186,0.0044598975,0.0000497427,0.000006765586,0.000034507935],"genre_scores_gemma":[0.9921294,0.000021892916,0.007380417,0.000038531707,0.00006620069,0.00021784168,0.000130409,0.000010345554,0.0000049863256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9919169,0.0019357316,0.0015396744,0.0002711555,0.00409398,0.00024256881],"domain_scores_gemma":[0.99105614,0.00010899973,0.0022419703,0.00028590445,0.005616305,0.0006906735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027095268,0.00016831183,0.00039324988,0.0007491126,0.00014485502,0.00016918281,0.0002264356,0.000061764564,0.000294417],"category_scores_gemma":[0.0007972223,0.00012849522,0.000108406624,0.0006583208,0.00015506132,0.001149057,0.000007856394,0.00007882837,0.0000022557492],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007248083,0.00028610876,0.20690893,0.0000040403634,0.000036104822,3.4906284e-7,0.007043483,0.00234511,0.00001995764,0.00004048167,0.00013632538,0.7831066],"study_design_scores_gemma":[0.0075395717,0.020984633,0.77777886,0.00019121502,0.00046379783,0.000038168673,0.01805647,0.17158726,0.0013959057,0.0015371059,0.00022785568,0.00019915939],"about_ca_topic_score_codex":0.0051614507,"about_ca_topic_score_gemma":0.04635285,"teacher_disagreement_score":0.7829075,"about_ca_system_score_codex":0.0013593439,"about_ca_system_score_gemma":0.01675551,"threshold_uncertainty_score":0.9888186},"labels":[],"label_agreement":null},{"id":"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23780048,0.0052692755,0.015249424,0.034747723,0.06062846,0.00790564,0.000062753206,0.0001737966,0.63816243],"genre_scores_gemma":[0.98909414,0.000013143265,0.0049765315,0.00016074997,0.004830672,0.0002261087,0.0000063377274,0.000018232673,0.0006740783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992064,0.000068948546,0.000244358,0.00010023258,0.00019420059,0.00018585697],"domain_scores_gemma":[0.9983335,0.000013781063,0.00045239404,0.00047191652,0.0004521915,0.00027618994],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012980276,0.000067253466,0.00009844051,0.0001299089,0.0003270829,0.00016991935,0.0004103299,0.00009462506,0.0019903718],"category_scores_gemma":[0.000102910875,0.00006261352,0.00007562828,0.00004787068,0.000095331816,0.00013905646,0.0000027783205,0.00016380209,0.000040820174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008327528,0.000034782803,0.002870369,0.0000011905563,0.000033329932,0.000005376202,0.00028841884,9.562965e-7,0.00004878527,0.0029748892,0.22063214,0.77310145],"study_design_scores_gemma":[0.00055450824,0.00024147119,0.10567143,0.000030733136,0.00004780394,0.000047695856,0.00008834566,0.000119070704,0.000031305673,0.008605012,0.88446975,0.00009290366],"about_ca_topic_score_codex":0.001506263,"about_ca_topic_score_gemma":0.005835251,"teacher_disagreement_score":0.7730085,"about_ca_system_score_codex":0.00011185041,"about_ca_system_score_gemma":0.0005263032,"threshold_uncertainty_score":0.99892193},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32802257,0.010508888,0.16094324,0.092540264,0.07318775,0.013059129,0.00015377176,0.00047230654,0.32111207],"genre_scores_gemma":[0.98731,0.000024954983,0.0056203636,0.0002721259,0.005295664,0.00034530906,0.0000041811845,0.00002510632,0.0011023321],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913466,0.00010567461,0.00026909096,0.000100759244,0.00019434809,0.00019543752],"domain_scores_gemma":[0.9988177,0.00003691904,0.00021325031,0.00020825876,0.00044386982,0.00027999017],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011216193,0.00006606734,0.000088372835,0.0001816262,0.00006230171,0.000028376206,0.000180547,0.00008774043,0.003968188],"category_scores_gemma":[0.00006044537,0.000045448392,0.00007008234,0.00015162685,0.00006223523,0.00009179858,0.0000013171076,0.00008526373,0.00007228435],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000079713745,0.000025969268,0.001009522,5.8040945e-7,0.00002373559,0.0000024160768,0.00014334303,2.0568687e-7,0.0002981803,0.0025383201,0.21378082,0.7821689],"study_design_scores_gemma":[0.0006476132,0.00030454624,0.017995642,0.000046242258,0.000033786375,0.000051050316,0.000057186593,0.000013569701,0.00008598221,0.009941733,0.97073764,0.00008498881],"about_ca_topic_score_codex":0.00029808327,"about_ca_topic_score_gemma":0.0018135837,"teacher_disagreement_score":0.7820839,"about_ca_system_score_codex":0.00017019546,"about_ca_system_score_gemma":0.0005056381,"threshold_uncertainty_score":0.99694234},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27921957,0.0052973866,0.045495447,0.017890278,0.06624108,0.008371442,0.0000530952,0.00029201596,0.5771397],"genre_scores_gemma":[0.9761888,0.0000073246356,0.010009542,0.00044883855,0.012493505,0.00022723414,0.000009317756,0.00002317847,0.00059226406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913025,0.00010010605,0.00027004117,0.00010266206,0.00019746929,0.00019948868],"domain_scores_gemma":[0.99850494,0.000016781754,0.00021192925,0.0002147504,0.0007786144,0.00027297914],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012138597,0.00006681583,0.00008802599,0.00019629569,0.00010998356,0.000046299447,0.00019276854,0.00009308907,0.005059352],"category_scores_gemma":[0.000046160363,0.00006182393,0.000061383485,0.00022976684,0.00011532527,0.00007396709,0.000001488243,0.0001336708,0.00010443284],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010746576,0.000035152145,0.0007144624,7.858516e-7,0.0000287551,0.0000019531913,0.00058826944,3.202788e-7,0.00008858956,0.0023687016,0.37943134,0.6167309],"study_design_scores_gemma":[0.00039311234,0.0006231209,0.014686065,0.000021409563,0.000038720435,0.000054270335,0.00013381675,0.00013507993,0.00007511134,0.0066086925,0.97714907,0.00008152399],"about_ca_topic_score_codex":0.0006619898,"about_ca_topic_score_gemma":0.0049793874,"teacher_disagreement_score":0.6969693,"about_ca_system_score_codex":0.00012922895,"about_ca_system_score_gemma":0.0005705281,"threshold_uncertainty_score":0.99585015},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8586387,0.07284038,0.00016481419,0.058069523,0.0024587368,0.0027576543,0.00009841505,0.000014300502,0.0049574575],"genre_scores_gemma":[0.93184096,0.009340095,0.0030420723,0.0004016589,0.00091476005,0.00018588686,0.000026980242,0.000049432165,0.054198176],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957143,0.0010429963,0.00087626063,0.00037855166,0.0008856458,0.0011022212],"domain_scores_gemma":[0.9946011,0.00018150994,0.00082373334,0.000311217,0.003017799,0.0010646896],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.012218705,0.00037124543,0.0006155261,0.00039461633,0.0018189233,0.0010707021,0.00056487415,0.0002853356,0.00018011151],"category_scores_gemma":[0.009174997,0.0003645123,0.00023729946,0.0002523356,0.0019432217,0.002380319,0.000049244387,0.00035383392,0.00005083224],"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":[0.000037050115,0.00008740319,0.15279132,0.00027425186,0.000107700864,0.00005529312,0.029947413,0.000008762209,0.00000807107,0.00017803305,0.11587772,0.70062697],"study_design_scores_gemma":[0.001766878,0.00079479563,0.64615357,0.0019235924,0.0004753278,0.00005476105,0.009458853,0.00048211755,0.000007345681,0.007750707,0.3307136,0.00041843287],"about_ca_topic_score_codex":0.046724066,"about_ca_topic_score_gemma":0.34579322,"teacher_disagreement_score":0.70020854,"about_ca_system_score_codex":0.000963594,"about_ca_system_score_gemma":0.003166199,"threshold_uncertainty_score":0.99996626},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6826276,0.04216174,0.0009252586,0.22933474,0.02527649,0.0049401005,0.000045263492,0.000035933994,0.014652839],"genre_scores_gemma":[0.97595525,0.0005192736,0.006513008,0.0072096605,0.007639823,0.000083847684,0.000045959496,0.000059617494,0.0019735906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918583,0.0047219293,0.001264366,0.00018680583,0.0010274132,0.0009411819],"domain_scores_gemma":[0.98963857,0.00036498564,0.00086393533,0.000261881,0.0046629324,0.004207722],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024825655,0.00020416657,0.00043992265,0.0002718579,0.000559854,0.000056705456,0.00027155568,0.0009763066,0.0023058027],"category_scores_gemma":[0.009200823,0.00019303817,0.0001725541,0.0005740642,0.00021131635,0.00043251383,0.000012781666,0.0026224023,0.00036820731],"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":[0.000017756218,0.00009529789,0.01571199,0.00016647886,0.000077148434,0.00009421809,0.050828017,0.00006642691,0.0000013172577,0.0011330922,0.1963771,0.73543113],"study_design_scores_gemma":[0.0033368345,0.0014308102,0.02707491,0.00082065153,0.00043229453,0.00015383218,0.026613247,0.005708466,0.0000026449713,0.0038289393,0.9304041,0.00019324261],"about_ca_topic_score_codex":0.020325191,"about_ca_topic_score_gemma":0.05077063,"teacher_disagreement_score":0.7352379,"about_ca_system_score_codex":0.002790051,"about_ca_system_score_gemma":0.060077798,"threshold_uncertainty_score":0.9996786},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7309378,0.0006566908,0.0024988297,0.16503407,0.021996463,0.0029884602,0.0000059747726,0.00006603465,0.07581568],"genre_scores_gemma":[0.99038583,0.000015526975,0.005996345,0.00007413615,0.0024713618,0.00008113725,0.000015510512,0.000007824962,0.0009523491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99756306,0.00027281372,0.00041780487,0.00013082752,0.0013775066,0.00023797757],"domain_scores_gemma":[0.9958107,0.00005246777,0.00031444847,0.000062438274,0.003502304,0.000257658],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070765032,0.00007836236,0.000088036286,0.00040148775,0.00037866252,0.0001541876,0.00027336896,0.00006807453,0.0060888752],"category_scores_gemma":[0.002278068,0.000062870255,0.000052507123,0.00020877804,0.000103726576,0.00066295214,0.0000074422164,0.00007566344,0.00009943143],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000990992,0.000021284473,0.01008346,0.0000010869117,0.000060697133,0.0000029224889,0.003084509,0.000024806397,0.0000627614,0.0062891375,0.007208378,0.973151],"study_design_scores_gemma":[0.00081227795,0.00005173919,0.036992673,0.000072805684,0.000045779638,0.000012969777,0.00071339775,0.00023798832,0.00038873736,0.0047359546,0.955794,0.00014171113],"about_ca_topic_score_codex":0.0002679235,"about_ca_topic_score_gemma":0.02987834,"teacher_disagreement_score":0.97300935,"about_ca_system_score_codex":0.002562859,"about_ca_system_score_gemma":0.0089006005,"threshold_uncertainty_score":0.996718},"labels":[],"label_agreement":null},{"id":"W4244221056","doi":"10.3138/cjpe.202","title":"Inspiring Future Program Evaluators through Innovative Curriculum for Undergraduates","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Curriculum; Credentialing; Program evaluation; Medical education; Professionalization; Logic model; Psychology; Computer science; Engineering management; Pedagogy; Engineering; Medicine; Sociology; Political science","score_opus":0.4974043274798436,"score_gpt":0.5733680132125911,"score_spread":0.07596368573274753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244221056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93151635,0.0028570078,0.010774877,0.026494253,0.008836536,0.010770401,0.00003628002,0.00009978197,0.008614518],"genre_scores_gemma":[0.9504496,0.000011805941,0.047331497,0.00035919913,0.0010754473,0.0005793992,0.000048770515,0.000024627678,0.0001196882],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99390525,0.00060759246,0.0013745597,0.00033123253,0.0033000908,0.00048130407],"domain_scores_gemma":[0.98041534,0.00021424437,0.001241984,0.00034335937,0.017138261,0.0006468028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020619873,0.00022681864,0.00038743732,0.0007256227,0.0003033746,0.0007027501,0.000651505,0.00014358062,0.00028139577],"category_scores_gemma":[0.006663735,0.00016745298,0.000179361,0.0025073763,0.00014051022,0.0015494947,0.000021103911,0.00029855114,0.000054112807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027047232,0.0001313676,0.028404288,0.0000081981525,0.00006431305,0.0000028816476,0.002909922,0.0019697635,0.000006038011,0.0038274887,0.02586515,0.93678355],"study_design_scores_gemma":[0.004209193,0.0037514963,0.0164901,0.00010849855,0.00019833779,0.00006345313,0.019649377,0.107108496,0.00019213038,0.11740778,0.73035944,0.00046169708],"about_ca_topic_score_codex":0.00034558238,"about_ca_topic_score_gemma":0.008295364,"teacher_disagreement_score":0.93632185,"about_ca_system_score_codex":0.0008664044,"about_ca_system_score_gemma":0.012532327,"threshold_uncertainty_score":0.9930657},"labels":[],"label_agreement":null},{"id":"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27921957,0.0052973866,0.045495447,0.017890278,0.06624108,0.008371442,0.0000530952,0.00029201596,0.5771397],"genre_scores_gemma":[0.9761888,0.0000073246356,0.010009542,0.00044883855,0.012493505,0.00022723414,0.000009317756,0.00002317847,0.00059226406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913025,0.00010010605,0.00027004117,0.00010266206,0.00019746929,0.00019948868],"domain_scores_gemma":[0.99850494,0.000016781754,0.00021192925,0.0002147504,0.0007786144,0.00027297914],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012138597,0.00006681583,0.00008802599,0.00019629569,0.00010998356,0.000046299447,0.00019276854,0.00009308907,0.005059352],"category_scores_gemma":[0.000046160363,0.00006182393,0.000061383485,0.00022976684,0.00011532527,0.00007396709,0.000001488243,0.0001336708,0.00010443284],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010746576,0.000035152145,0.0007144624,7.858516e-7,0.0000287551,0.0000019531913,0.00058826944,3.202788e-7,0.00008858956,0.0023687016,0.37943134,0.6167309],"study_design_scores_gemma":[0.00039311234,0.0006231209,0.014686065,0.000021409563,0.000038720435,0.000054270335,0.00013381675,0.00013507993,0.00007511134,0.0066086925,0.97714907,0.00008152399],"about_ca_topic_score_codex":0.0006619898,"about_ca_topic_score_gemma":0.0049793874,"teacher_disagreement_score":0.6969693,"about_ca_system_score_codex":0.00012922895,"about_ca_system_score_gemma":0.0005705281,"threshold_uncertainty_score":0.99585015},"labels":[],"label_agreement":null},{"id":"W4245842532","doi":"10.3138/cjpe.30.3.08","title":"A Transcultural Global Systems Perspective: In Search of <i>Blue Marble</i> Evaluators","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Framing (construction); Reflexivity; Indigenous; Sociology; Praxis; Perspective (graphical); Public relations; Engineering ethics; Political science; Social science; Epistemology; Computer science; Engineering","score_opus":0.3034525345500509,"score_gpt":0.5381338373521743,"score_spread":0.23468130280212346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245842532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895033,0.001084313,0.0010714792,0.0029653443,0.00092225504,0.0012585329,0.00003176112,0.000005270749,0.0031577423],"genre_scores_gemma":[0.9992104,0.00001933992,0.00046433308,0.000027122891,0.00010560466,0.000043655466,0.0000017107968,0.0000062947715,0.00012150802],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934442,0.001328877,0.0012310187,0.00023966898,0.0034121785,0.0003440669],"domain_scores_gemma":[0.9928841,0.00022894093,0.00053915445,0.00026649877,0.005665247,0.00041607226],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021669034,0.00013341775,0.0003450386,0.0005770284,0.00008263691,0.00017941523,0.0005443365,0.000105307045,0.0011324905],"category_scores_gemma":[0.0022781051,0.00007855566,0.00016895655,0.0013102457,0.00016283458,0.00073584676,0.000009456638,0.00015148972,0.000038835977],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107371074,0.00011579585,0.31125364,0.000015179192,0.000069373455,0.000013019382,0.004839717,0.006116169,0.00046101835,0.0059821396,0.0015271413,0.66949946],"study_design_scores_gemma":[0.008229752,0.0022228246,0.87778026,0.00068087876,0.00019982636,0.00028182013,0.03315467,0.051679976,0.000494658,0.013501898,0.011278725,0.00049473543],"about_ca_topic_score_codex":0.0036338128,"about_ca_topic_score_gemma":0.041297916,"teacher_disagreement_score":0.66900474,"about_ca_system_score_codex":0.0017485966,"about_ca_system_score_gemma":0.0073787197,"threshold_uncertainty_score":0.9997806},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6713685,0.015585941,0.0003694747,0.27095422,0.021709451,0.003906344,0.000046964553,0.000019014278,0.016040072],"genre_scores_gemma":[0.9839782,0.00091037183,0.003122397,0.003424584,0.006404361,0.00006242193,0.000019096404,0.00004423596,0.0020343375],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941366,0.0027637915,0.0011493625,0.0002032873,0.0007884106,0.0009585923],"domain_scores_gemma":[0.9920711,0.0003370347,0.0017582837,0.00058858347,0.0028589172,0.0023860915],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018560447,0.00020699005,0.00045362685,0.00019402256,0.0032326374,0.00018495573,0.0005722081,0.0010115838,0.0042536613],"category_scores_gemma":[0.011732701,0.00019694408,0.00022333748,0.00014765978,0.00039888461,0.0006711735,0.000022666001,0.002796996,0.00026988055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011625796,0.0000720254,0.037357166,0.00023400233,0.000089357025,0.000105462364,0.019209987,0.0000107118185,0.000003189555,0.0014111117,0.059665225,0.88183016],"study_design_scores_gemma":[0.0023753645,0.00072888855,0.28777066,0.0012326312,0.0004319996,0.000087096436,0.0060055065,0.0032924826,0.000003941018,0.0027191155,0.69517344,0.0001788689],"about_ca_topic_score_codex":0.031516593,"about_ca_topic_score_gemma":0.095848374,"teacher_disagreement_score":0.8816513,"about_ca_system_score_codex":0.0015343548,"about_ca_system_score_gemma":0.031096883,"threshold_uncertainty_score":0.9995036},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13064277,0.2443947,0.00075603026,0.025300723,0.0071314885,0.00068272545,0.0001890354,0.000018712188,0.5908838],"genre_scores_gemma":[0.9854279,0.0005861974,0.0019141036,0.00028791415,0.0051831715,0.0000105215295,0.000037359077,0.00002323766,0.006529599],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981881,0.00056876714,0.0004217033,0.00011363414,0.00037850405,0.00032930585],"domain_scores_gemma":[0.996414,0.00012440288,0.00030932852,0.00013541541,0.002448489,0.0005683833],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024284315,0.00012122046,0.00020434165,0.00023681615,0.0003923096,0.0009389626,0.00012851729,0.00010996852,0.010759417],"category_scores_gemma":[0.0014329602,0.00012525555,0.00022974797,0.00014874463,0.00025061436,0.00014786649,0.000006256969,0.0002893187,0.000032700642],"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":[0.0000057247053,0.00021156625,0.0012888411,0.000050572853,0.0005072359,0.0008566306,0.006481401,0.00081884005,0.000008920461,0.4092085,0.010475079,0.57008666],"study_design_scores_gemma":[0.0005057712,0.00014695109,0.001392827,0.00014552151,0.0018981938,0.00018864087,0.002898057,0.008309436,0.00006777037,0.030566128,0.953722,0.0001587208],"about_ca_topic_score_codex":0.012958672,"about_ca_topic_score_gemma":0.042966418,"teacher_disagreement_score":0.9432469,"about_ca_system_score_codex":0.00048036038,"about_ca_system_score_gemma":0.008020966,"threshold_uncertainty_score":0.99760264},"labels":[],"label_agreement":null},{"id":"W4248910069","doi":"10.3138/cjpe.223","title":"Meeting at the Crossroads: Interactivity, Technology, and Evaluation Utilization","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Interactivity; Relevance (law); Creativity; Scholarship; Negotiation; Knowledge management; Computer science; Citizen journalism; Sociology; Psychology; Multimedia; Political science; Social psychology; World Wide Web; Social science","score_opus":0.6056598746697802,"score_gpt":0.5861427794867573,"score_spread":0.019517095183022914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248910069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805477,0.002237303,0.0005592415,0.009485436,0.0009263626,0.0012784818,0.0000033034105,0.00001138831,0.004950753],"genre_scores_gemma":[0.9986797,0.000011783869,0.0007501861,0.00013864657,0.0001241553,0.0000823844,0.000011306314,0.00000824444,0.00019360946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99494237,0.00097572175,0.0007771944,0.00021759333,0.002859743,0.00022737168],"domain_scores_gemma":[0.99160045,0.0002975314,0.000884451,0.00030742618,0.0065774745,0.00033266307],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04159735,0.00011604843,0.00017926242,0.0009271357,0.0004126967,0.0005898573,0.00036985334,0.00009946297,0.000707305],"category_scores_gemma":[0.012620152,0.00007514428,0.000057271413,0.0013269507,0.00023889996,0.0008793022,0.000049046677,0.00021284884,0.000057809713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016027649,0.000021528136,0.0545489,0.0000014095791,0.00001641485,0.0000010574089,0.0015166182,0.003271767,0.00004577472,0.00027886173,0.003734655,0.936547],"study_design_scores_gemma":[0.0028282413,0.00085761957,0.100062706,0.00011892411,0.00030015619,0.00027640662,0.011883047,0.6374953,0.00093628507,0.06259459,0.18236184,0.00028487793],"about_ca_topic_score_codex":0.00027856225,"about_ca_topic_score_gemma":0.029745437,"teacher_disagreement_score":0.93626213,"about_ca_system_score_codex":0.00087029306,"about_ca_system_score_gemma":0.0044872016,"threshold_uncertainty_score":0.99569696},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832269,0.00046894734,0.0025887701,0.0030837606,0.0004885568,0.0004124012,0.0000049044143,0.000018215263,0.009707574],"genre_scores_gemma":[0.99655557,0.00004692096,0.0024783364,0.00017051454,0.00023506912,0.000030595977,0.000008074006,0.000010546836,0.00046436352],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99339104,0.0052799825,0.00029769522,0.0001080419,0.00059116486,0.00033207994],"domain_scores_gemma":[0.9981979,0.000377289,0.00034524602,0.0000970083,0.00047521127,0.00050733046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023412494,0.00008956898,0.00013569563,0.00007613333,0.0003690791,0.00026988346,0.00032904066,0.00017495868,0.000066834735],"category_scores_gemma":[0.0036357355,0.0000917242,0.00009544009,0.00045832258,0.00028815828,0.00035046475,0.000012851352,0.0002749,0.0000035114026],"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":[0.00008809656,0.00023701525,0.114268705,0.000012680153,0.00007333695,0.000029054187,0.5550982,0.007764387,0.00025861178,0.0087382225,0.011875147,0.30155656],"study_design_scores_gemma":[0.003998686,0.001074284,0.35739717,0.00040015983,0.00027656794,0.00008219398,0.38603562,0.022263024,0.0002781101,0.05267264,0.17499864,0.00052292197],"about_ca_topic_score_codex":0.37030065,"about_ca_topic_score_gemma":0.4520364,"teacher_disagreement_score":0.30103365,"about_ca_system_score_codex":0.0016110587,"about_ca_system_score_gemma":0.00910319,"threshold_uncertainty_score":0.99651426},"labels":[],"label_agreement":null},{"id":"W4249543881","doi":"10.3138/cjpe.69771","title":"Reflective Practice: Moving Intention into Action","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reflective practice; Leverage (statistics); Pillar; Action (physics); Reflection (computer programming); Psychology; Embodied cognition; Engineering ethics; Knowledge management; Pedagogy; Computer science; Artificial intelligence; Engineering","score_opus":0.5098205725321647,"score_gpt":0.6235932080024176,"score_spread":0.11377263547025285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249543881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.858048,0.0029471102,0.043435615,0.0379169,0.008876205,0.0020937643,0.000005813994,0.000043591514,0.046632968],"genre_scores_gemma":[0.9776795,0.000032594606,0.02118932,0.0004386728,0.00023815031,0.000035247347,0.000014660671,0.000008710247,0.00036317486],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99517524,0.001210189,0.00086611457,0.00022301517,0.0023178898,0.00020753415],"domain_scores_gemma":[0.98600626,0.00038160352,0.0009453619,0.0002573033,0.0120614115,0.00034806898],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016461248,0.00009914036,0.00018391569,0.00060372846,0.00030576135,0.00065793254,0.00023803691,0.00008680361,0.0024139816],"category_scores_gemma":[0.02066719,0.00008422106,0.00013548815,0.0012143794,0.000053934138,0.0019951377,0.000014471141,0.00029145804,0.00011901576],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023355049,0.000049014878,0.0037412047,0.000003378782,0.00003845484,0.000017516506,0.0017686889,0.0009949646,0.0006885534,0.00062101864,0.0021628896,0.98989093],"study_design_scores_gemma":[0.002963071,0.0015998356,0.13563521,0.00024248453,0.0005764498,0.0009904518,0.058454666,0.12028977,0.0057984437,0.12203936,0.550877,0.0005332483],"about_ca_topic_score_codex":0.0005946538,"about_ca_topic_score_gemma":0.03466982,"teacher_disagreement_score":0.9893577,"about_ca_system_score_codex":0.0010191383,"about_ca_system_score_gemma":0.008718637,"threshold_uncertainty_score":0.99849796},"labels":[],"label_agreement":null},{"id":"W4250786345","doi":"10.3138/cjpe.30.3.06","title":"A Cross-cultural Evaluation Conversation in India: Benefits, Challenges, and Lessons Learned","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Conversation; Cross-cultural; Work (physics); Bridging (networking); Sociology; Principal (computer security); Public relations; Political science; Medical education; Psychology; Medicine; Engineering; Computer science","score_opus":0.5494404661293435,"score_gpt":0.5595244125498549,"score_spread":0.010083946420511358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250786345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.973059,0.0050137946,0.00006168285,0.018076546,0.00060410006,0.0011369643,0.000010086629,0.000007657344,0.0020301577],"genre_scores_gemma":[0.99850947,0.0007079664,0.0003946696,0.00008094495,0.00012724916,0.00009711146,0.000010397466,0.000008545968,0.000063646505],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950272,0.00091152586,0.0009553628,0.0003077742,0.0025011771,0.0002969867],"domain_scores_gemma":[0.99377984,0.00037510603,0.00072996825,0.00023686662,0.004516769,0.00036147237],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027055254,0.00013924639,0.00023970848,0.00086799153,0.000142776,0.00040673622,0.00028370434,0.00013650632,0.0014605323],"category_scores_gemma":[0.006925618,0.00008966424,0.00007317548,0.00045198976,0.00017043266,0.0019196545,0.000015205644,0.00016410294,0.00005350037],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021217293,0.000020436719,0.03744981,0.0000028842508,0.000012194109,0.000001676243,0.002248701,0.0003410813,0.0000537307,0.0018979488,0.00008735935,0.957863],"study_design_scores_gemma":[0.0030984376,0.00032132646,0.95409214,0.00011907395,0.000053431584,0.000029989984,0.0019524719,0.014114902,0.00007980914,0.018248389,0.007740063,0.00014997146],"about_ca_topic_score_codex":0.00022566979,"about_ca_topic_score_gemma":0.01719881,"teacher_disagreement_score":0.957713,"about_ca_system_score_codex":0.00078422576,"about_ca_system_score_gemma":0.0033905292,"threshold_uncertainty_score":0.9994523},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9345692,0.0074588223,0.001233443,0.013593338,0.004136737,0.0354305,0.00017681356,0.0000761831,0.003324958],"genre_scores_gemma":[0.9777739,0.000009558115,0.019200277,0.000215291,0.00048780788,0.0014719628,0.00077526056,0.00002843114,0.000037503956],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931016,0.0027935626,0.0015831193,0.00031126366,0.0013910495,0.0008193899],"domain_scores_gemma":[0.98721266,0.00031722826,0.0012375298,0.0007276027,0.008972407,0.00153258],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036734965,0.00020901684,0.0003636377,0.00037358567,0.0011631342,0.00006386754,0.0007368373,0.00025239462,0.00023190366],"category_scores_gemma":[0.00987526,0.00016905331,0.00006899363,0.00067606586,0.00017237455,0.00050280005,0.00003729667,0.00046693787,0.000016767719],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094118936,0.00006631517,0.09954758,0.00015240209,0.000058023583,0.0000017161685,0.0055639558,0.00012317937,9.609049e-7,0.00017524976,0.018592766,0.8756237],"study_design_scores_gemma":[0.0037229494,0.0007866077,0.29362908,0.0021526362,0.0006652873,0.00004967992,0.011159689,0.17550361,0.000016207277,0.0055605737,0.5063643,0.00038942104],"about_ca_topic_score_codex":0.2282159,"about_ca_topic_score_gemma":0.911987,"teacher_disagreement_score":0.8752343,"about_ca_system_score_codex":0.0030965356,"about_ca_system_score_gemma":0.06563334,"threshold_uncertainty_score":0.998465},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40052813,0.057557777,0.00015986328,0.0075129494,0.0058204965,0.0010762279,0.00008936279,0.000013498595,0.5272417],"genre_scores_gemma":[0.9892085,0.0001814398,0.0006632937,0.00016386701,0.0030319782,0.000008178652,0.000016040693,0.000020737094,0.0067059346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983675,0.00038311066,0.00040818818,0.000109092405,0.0003887324,0.0003433718],"domain_scores_gemma":[0.99759,0.000117662494,0.00037596334,0.00014239002,0.0012757749,0.00049817894],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029530702,0.000128816,0.00021412961,0.00034441042,0.00024224436,0.0007150358,0.00017667456,0.00011414802,0.014160823],"category_scores_gemma":[0.0005158273,0.00012481783,0.00020999036,0.00010726789,0.00020230428,0.00018354793,0.0000051194834,0.0002885928,0.00015555207],"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":[0.0000136520175,0.00017829773,0.0069220625,0.00007706481,0.00050379086,0.00011916766,0.007910335,0.0016948306,0.000008093631,0.47532684,0.007997751,0.49924812],"study_design_scores_gemma":[0.0006722757,0.00036583448,0.0027224277,0.00015708164,0.0013271376,0.00005872224,0.0020477201,0.017758623,0.000015335747,0.020517865,0.9541776,0.00017937303],"about_ca_topic_score_codex":0.020664338,"about_ca_topic_score_gemma":0.015971983,"teacher_disagreement_score":0.94617987,"about_ca_system_score_codex":0.0004919072,"about_ca_system_score_gemma":0.0038176544,"threshold_uncertainty_score":0.98674035},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1357311,0.16651362,0.0019575278,0.13829799,0.005630152,0.001806561,0.0003147792,0.000045834226,0.5497024],"genre_scores_gemma":[0.9907136,0.00022618534,0.0010681461,0.00076637993,0.0064468132,0.000008411161,0.000016339975,0.000021084143,0.0007330587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840045,0.00039777716,0.00042064543,0.0001093611,0.0003654922,0.00030628938],"domain_scores_gemma":[0.99740046,0.00009143806,0.00034619728,0.00008291472,0.001147942,0.0009310533],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017762363,0.00012718134,0.00020719366,0.00018038102,0.0003259082,0.00073079974,0.00018076105,0.000097010714,0.00680096],"category_scores_gemma":[0.0013455988,0.00012614288,0.00020524887,0.00013383917,0.0002621826,0.00015613681,0.0000056592385,0.00030832196,0.0000516633],"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":[0.000019155654,0.00013144487,0.0014889578,0.00008212406,0.00053841836,0.000325566,0.022094257,0.0018129573,0.0000073227448,0.32254454,0.023805546,0.6271497],"study_design_scores_gemma":[0.0005319347,0.00039925455,0.0006975265,0.000077771365,0.0016578132,0.000032935364,0.0023493282,0.034848098,0.000018031336,0.010400374,0.94882995,0.00015700684],"about_ca_topic_score_codex":0.011858761,"about_ca_topic_score_gemma":0.009236932,"teacher_disagreement_score":0.9250244,"about_ca_system_score_codex":0.0003045457,"about_ca_system_score_gemma":0.0037287355,"threshold_uncertainty_score":0.99472135},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23780048,0.0052692755,0.015249424,0.034747723,0.06062846,0.00790564,0.000062753206,0.0001737966,0.63816243],"genre_scores_gemma":[0.98909414,0.000013143265,0.0049765315,0.00016074997,0.004830672,0.0002261087,0.0000063377274,0.000018232673,0.0006740783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992064,0.000068948546,0.000244358,0.00010023258,0.00019420059,0.00018585697],"domain_scores_gemma":[0.9983335,0.000013781063,0.00045239404,0.00047191652,0.0004521915,0.00027618994],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012980276,0.000067253466,0.00009844051,0.0001299089,0.0003270829,0.00016991935,0.0004103299,0.00009462506,0.0019903718],"category_scores_gemma":[0.000102910875,0.00006261352,0.00007562828,0.00004787068,0.000095331816,0.00013905646,0.0000027783205,0.00016380209,0.000040820174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008327528,0.000034782803,0.002870369,0.0000011905563,0.000033329932,0.000005376202,0.00028841884,9.562965e-7,0.00004878527,0.0029748892,0.22063214,0.77310145],"study_design_scores_gemma":[0.00055450824,0.00024147119,0.10567143,0.000030733136,0.00004780394,0.000047695856,0.00008834566,0.000119070704,0.000031305673,0.008605012,0.88446975,0.00009290366],"about_ca_topic_score_codex":0.001506263,"about_ca_topic_score_gemma":0.005835251,"teacher_disagreement_score":0.7730085,"about_ca_system_score_codex":0.00011185041,"about_ca_system_score_gemma":0.0005263032,"threshold_uncertainty_score":0.99892193},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27921957,0.0052973866,0.045495447,0.017890278,0.06624108,0.008371442,0.0000530952,0.00029201596,0.5771397],"genre_scores_gemma":[0.9761888,0.0000073246356,0.010009542,0.00044883855,0.012493505,0.00022723414,0.000009317756,0.00002317847,0.00059226406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913025,0.00010010605,0.00027004117,0.00010266206,0.00019746929,0.00019948868],"domain_scores_gemma":[0.99850494,0.000016781754,0.00021192925,0.0002147504,0.0007786144,0.00027297914],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012138597,0.00006681583,0.00008802599,0.00019629569,0.00010998356,0.000046299447,0.00019276854,0.00009308907,0.005059352],"category_scores_gemma":[0.000046160363,0.00006182393,0.000061383485,0.00022976684,0.00011532527,0.00007396709,0.000001488243,0.0001336708,0.00010443284],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010746576,0.000035152145,0.0007144624,7.858516e-7,0.0000287551,0.0000019531913,0.00058826944,3.202788e-7,0.00008858956,0.0023687016,0.37943134,0.6167309],"study_design_scores_gemma":[0.00039311234,0.0006231209,0.014686065,0.000021409563,0.000038720435,0.000054270335,0.00013381675,0.00013507993,0.00007511134,0.0066086925,0.97714907,0.00008152399],"about_ca_topic_score_codex":0.0006619898,"about_ca_topic_score_gemma":0.0049793874,"teacher_disagreement_score":0.6969693,"about_ca_system_score_codex":0.00012922895,"about_ca_system_score_gemma":0.0005705281,"threshold_uncertainty_score":0.99585015},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58033943,0.0179087,0.001913398,0.37513658,0.01540679,0.0037697786,0.000066031214,0.000028828314,0.005430471],"genre_scores_gemma":[0.9814541,0.0014364216,0.0030635798,0.0050234925,0.005829187,0.00008222191,0.000011560803,0.00005225977,0.0030472118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926546,0.0040739593,0.0012707216,0.00020430688,0.0007912063,0.0010052015],"domain_scores_gemma":[0.992776,0.0008175139,0.0008856408,0.00027805733,0.0028152291,0.0024276073],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016365433,0.00020374294,0.0004108166,0.00026463138,0.0007044998,0.000035334604,0.00026914407,0.00094393065,0.0088431975],"category_scores_gemma":[0.0072988425,0.00014673066,0.00020835553,0.00041823374,0.00026731525,0.00045542183,0.000011460501,0.0015408145,0.0004749879],"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":[0.000012777212,0.000063139,0.016555069,0.00014090403,0.00007340191,0.00005602853,0.0120403385,0.0000027875947,0.000019478653,0.0014972641,0.07230386,0.897235],"study_design_scores_gemma":[0.0032873582,0.001066367,0.079395294,0.0021569494,0.00037312106,0.00010984545,0.004911565,0.0005322766,0.000011859062,0.0036607487,0.9042971,0.00019749875],"about_ca_topic_score_codex":0.007577257,"about_ca_topic_score_gemma":0.037281413,"teacher_disagreement_score":0.89703745,"about_ca_system_score_codex":0.002323768,"about_ca_system_score_gemma":0.030892022,"threshold_uncertainty_score":0.99903136},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23780048,0.0052692755,0.015249424,0.034747723,0.06062846,0.00790564,0.000062753206,0.0001737966,0.63816243],"genre_scores_gemma":[0.98909414,0.000013143265,0.0049765315,0.00016074997,0.004830672,0.0002261087,0.0000063377274,0.000018232673,0.0006740783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992064,0.000068948546,0.000244358,0.00010023258,0.00019420059,0.00018585697],"domain_scores_gemma":[0.9983335,0.000013781063,0.00045239404,0.00047191652,0.0004521915,0.00027618994],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012980276,0.000067253466,0.00009844051,0.0001299089,0.0003270829,0.00016991935,0.0004103299,0.00009462506,0.0019903718],"category_scores_gemma":[0.000102910875,0.00006261352,0.00007562828,0.00004787068,0.000095331816,0.00013905646,0.0000027783205,0.00016380209,0.000040820174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008327528,0.000034782803,0.002870369,0.0000011905563,0.000033329932,0.000005376202,0.00028841884,9.562965e-7,0.00004878527,0.0029748892,0.22063214,0.77310145],"study_design_scores_gemma":[0.00055450824,0.00024147119,0.10567143,0.000030733136,0.00004780394,0.000047695856,0.00008834566,0.000119070704,0.000031305673,0.008605012,0.88446975,0.00009290366],"about_ca_topic_score_codex":0.001506263,"about_ca_topic_score_gemma":0.005835251,"teacher_disagreement_score":0.7730085,"about_ca_system_score_codex":0.00011185041,"about_ca_system_score_gemma":0.0005263032,"threshold_uncertainty_score":0.99892193},"labels":[],"label_agreement":null},{"id":"W4255004666","doi":"10.3138/cjpe.30.3.05","title":"Decolonizing and Indigenizing Evaluation Practice in Africa: Toward African Relational Evaluation Approaches","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenization; Decolonization; Sociology; African culture; Metaphor; Epistemology; African philosophy; Political science; Gender studies; Anthropology; Linguistics; Philosophy","score_opus":0.6556148384806202,"score_gpt":0.5116189627666728,"score_spread":0.14399587571394734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255004666","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93572444,0.0052598123,0.004710685,0.02307783,0.0013497263,0.0057212277,0.000014383914,0.000021335934,0.024120536],"genre_scores_gemma":[0.9902479,0.000035872625,0.00904714,0.000078095865,0.00018292668,0.00032753038,0.000013662335,0.000015786844,0.00005107632],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9886178,0.0031119587,0.0015523541,0.0004511544,0.0058074305,0.00045933024],"domain_scores_gemma":[0.98957413,0.0019039495,0.0014756396,0.00030762915,0.0062951283,0.00044354345],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08925153,0.00019977007,0.0003175055,0.0016175024,0.0002873926,0.0004182764,0.0003562937,0.00016368974,0.0016030824],"category_scores_gemma":[0.03800416,0.0001420932,0.00009661925,0.0014030725,0.00014891039,0.002789038,0.000027711762,0.00026754424,0.00004579013],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004277796,0.00005646494,0.028917048,0.0000031277514,0.000033734024,0.0000028044396,0.007473428,0.0028450645,0.000048929254,0.0008893684,0.00033735912,0.9593499],"study_design_scores_gemma":[0.00613897,0.0008221081,0.5347691,0.0002531704,0.0006291003,0.00016237008,0.016303267,0.3467783,0.00010468415,0.05241629,0.041109595,0.0005130569],"about_ca_topic_score_codex":0.00022380236,"about_ca_topic_score_gemma":0.010278481,"teacher_disagreement_score":0.95883685,"about_ca_system_score_codex":0.0020036304,"about_ca_system_score_gemma":0.01060369,"threshold_uncertainty_score":0.9993096},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18407509,0.05766507,0.00091787736,0.013249926,0.008174929,0.00096703274,0.00012961736,0.000022289581,0.7347982],"genre_scores_gemma":[0.9839501,0.00014234566,0.0013413194,0.00021424955,0.011154443,0.000008770935,0.000011095383,0.000020275304,0.0031573947],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833846,0.00040993496,0.00041554426,0.00010650192,0.00036559207,0.00036395065],"domain_scores_gemma":[0.9964736,0.00009209455,0.00036816543,0.00013175055,0.0023525443,0.0005818561],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032152543,0.00012805813,0.00018466116,0.00035476443,0.00054757914,0.00077843474,0.00018284908,0.00011264752,0.010411143],"category_scores_gemma":[0.0009870362,0.0001236415,0.00017524936,0.00012789616,0.00070286077,0.00016770093,0.0000054687966,0.0002342628,0.00008651209],"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":[0.000012649467,0.00014624327,0.0012901517,0.000028046608,0.0003915749,0.00010786413,0.010578297,0.00010595668,0.0000047419835,0.3364197,0.018083297,0.63283145],"study_design_scores_gemma":[0.0004648803,0.000546443,0.0015459652,0.00011986147,0.0014936975,0.000067431385,0.0015366926,0.011952746,0.00003524284,0.030893652,0.9511872,0.00015618553],"about_ca_topic_score_codex":0.025262361,"about_ca_topic_score_gemma":0.052095737,"teacher_disagreement_score":0.9331039,"about_ca_system_score_codex":0.00046038712,"about_ca_system_score_gemma":0.004001158,"threshold_uncertainty_score":0.9904935},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8629527,0.010495019,0.00040894825,0.10155855,0.0015790022,0.012172159,0.000016651878,0.000031370626,0.010785618],"genre_scores_gemma":[0.9951974,0.000088334826,0.0039619636,0.00015580769,0.00011918342,0.00040567806,0.0000087204735,0.000012937704,0.0000499312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99145585,0.0029953301,0.0015087139,0.00035483498,0.003118108,0.00056717184],"domain_scores_gemma":[0.9956593,0.00021155394,0.0009145286,0.00032169404,0.0023502104,0.00054275093],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.102147155,0.00014993292,0.00042313055,0.0018888247,0.00011677633,0.00027000296,0.0004554402,0.00010681361,0.00018750553],"category_scores_gemma":[0.011050231,0.00012314577,0.00008145295,0.0016752005,0.00004332843,0.0007417122,0.000021801403,0.00047533086,0.000039591785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005686246,0.00011448285,0.031236788,0.000011408477,0.0000066597268,0.0000091347965,0.013885094,0.0013850031,0.0000021054884,0.0007432563,0.00034016697,0.95220906],"study_design_scores_gemma":[0.009585535,0.0068768105,0.33799526,0.0006801749,0.000038603335,0.0000956289,0.054638043,0.46027577,0.000011350511,0.059133846,0.07019137,0.00047763073],"about_ca_topic_score_codex":0.0023467657,"about_ca_topic_score_gemma":0.3681619,"teacher_disagreement_score":0.9517314,"about_ca_system_score_codex":0.0015112992,"about_ca_system_score_gemma":0.031832885,"threshold_uncertainty_score":0.9972801},"labels":[],"label_agreement":null},{"id":"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31834242,0.010443769,0.15474188,0.08974779,0.07106683,0.012988068,0.00015525357,0.00046722023,0.3420468],"genre_scores_gemma":[0.98757374,0.000024795592,0.005589275,0.00027730406,0.0049679447,0.00034900534,0.0000042267425,0.000024987792,0.001188729],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991306,0.00010545762,0.000272226,0.00010087941,0.0001951254,0.00019572386],"domain_scores_gemma":[0.99881613,0.000036181627,0.00021408653,0.0002085298,0.00044388117,0.00028117723],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011304364,0.00006611352,0.00008847461,0.00018245698,0.000061967636,0.00002794287,0.00018055292,0.00008782416,0.004336032],"category_scores_gemma":[0.00006142888,0.000045478948,0.000070155234,0.0001488304,0.00006159168,0.000090928785,0.0000013153089,0.00008545189,0.00007452376],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007925805,0.000025868034,0.0010058355,5.9015383e-7,0.00002311629,0.0000023473406,0.0001492486,1.9309878e-7,0.00030404856,0.0026855764,0.22313058,0.77266467],"study_design_scores_gemma":[0.00065371656,0.00030367175,0.018071312,0.000046736106,0.00003390084,0.000051521143,0.00005847506,0.000013607333,0.00008650438,0.009796332,0.9707984,0.00008582964],"about_ca_topic_score_codex":0.0003083922,"about_ca_topic_score_gemma":0.001965771,"teacher_disagreement_score":0.77257884,"about_ca_system_score_codex":0.00017556464,"about_ca_system_score_gemma":0.0005213951,"threshold_uncertainty_score":0.99657416},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20294718,0.016925748,0.10504445,0.2291862,0.044127226,0.01662544,0.00013922562,0.00063749636,0.38436702],"genre_scores_gemma":[0.9811972,0.000013390003,0.008734486,0.0019954871,0.0076445057,0.00023959493,0.000015514783,0.000026876938,0.00013299633],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916214,0.00009661992,0.00027323692,0.000105353334,0.00019696566,0.00016569032],"domain_scores_gemma":[0.9988379,0.000016541822,0.00019965965,0.00013009101,0.000357986,0.00045782968],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00063940266,0.00006635384,0.00009977342,0.00009339505,0.00006232997,0.000043065636,0.0001908392,0.00007962011,0.0031737657],"category_scores_gemma":[0.00006471582,0.00006309934,0.00007266033,0.0002366378,0.000039679802,0.00006909887,0.0000015334616,0.00017897207,0.000060261278],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000142779145,0.00002655506,0.00070841564,0.0000021332935,0.000034148048,0.000005304436,0.0011114924,0.000005871098,0.0001202258,0.0017764885,0.43602738,0.56016773],"study_design_scores_gemma":[0.00046973533,0.00045631654,0.0063764295,0.000013680887,0.000044359276,0.000025363925,0.00021458704,0.00044801287,0.0000368394,0.0020280217,0.98980236,0.000084280284],"about_ca_topic_score_codex":0.00028724602,"about_ca_topic_score_gemma":0.0007153057,"teacher_disagreement_score":0.77825,"about_ca_system_score_codex":0.00008184413,"about_ca_system_score_gemma":0.00052410923,"threshold_uncertainty_score":0.99773747},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23604794,0.016634332,0.04535694,0.029341467,0.07786545,0.010820499,0.00006267356,0.0003703516,0.5835003],"genre_scores_gemma":[0.9753451,0.000009542056,0.014681339,0.00046682137,0.008231892,0.00040698418,0.000021474947,0.00003335291,0.0008035416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990764,0.00012423398,0.0002678869,0.00009149735,0.0002576919,0.00018224666],"domain_scores_gemma":[0.99830085,0.000015419024,0.00020827037,0.00019559836,0.0007673357,0.0005125032],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017722502,0.00006620762,0.0000951053,0.00018704076,0.0000486614,0.000047553167,0.00018227157,0.00009096148,0.00092113664],"category_scores_gemma":[0.00007760923,0.0000612259,0.00005723914,0.00021276154,0.000048142934,0.000086789274,0.0000014824033,0.00015232264,0.00005567514],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000118027165,0.00004186888,0.0009707293,7.1695376e-7,0.000025830002,0.000004384925,0.0007338043,0.0000066166294,0.000016238877,0.0019535976,0.5215928,0.4746416],"study_design_scores_gemma":[0.0006506717,0.00041292523,0.0052480474,0.000016034817,0.000038963502,0.00007245528,0.00036102172,0.00017662866,0.000016599139,0.010280763,0.9826441,0.000081783866],"about_ca_topic_score_codex":0.0008875339,"about_ca_topic_score_gemma":0.002538721,"teacher_disagreement_score":0.7392971,"about_ca_system_score_codex":0.00020721725,"about_ca_system_score_gemma":0.0010830013,"threshold_uncertainty_score":0.99999213},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2427235,0.03313073,0.04650247,0.044887356,0.07192716,0.0072100097,0.00010064889,0.00030448,0.55321366],"genre_scores_gemma":[0.95899093,0.00006180923,0.027008427,0.0011222598,0.009821691,0.0004989012,0.00006280922,0.000048840076,0.0023843555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990897,0.00014247374,0.00027407572,0.000109886656,0.00020466358,0.00017920148],"domain_scores_gemma":[0.9984921,0.000023158793,0.00017664729,0.00022248735,0.0008186093,0.000266987],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00089620246,0.000062963125,0.00009821958,0.00012559214,0.00007638419,0.000056464803,0.00013146704,0.000091245514,0.0051804306],"category_scores_gemma":[0.00006928101,0.0000626228,0.000082126346,0.00026564137,0.000037759266,0.00006497725,0.000001712045,0.00016708576,0.000036851325],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005561407,0.000064885906,0.0008792077,0.0000018243312,0.000046468405,0.000022314214,0.0004181671,0.0000035504813,0.0002169252,0.003783578,0.30561963,0.6889379],"study_design_scores_gemma":[0.0004367062,0.00015028774,0.01329559,0.00002645287,0.000050570612,0.00016886443,0.0002613816,0.000089384186,0.00015460695,0.006672406,0.9786101,0.00008364537],"about_ca_topic_score_codex":0.00031524088,"about_ca_topic_score_gemma":0.003975999,"teacher_disagreement_score":0.7162674,"about_ca_system_score_codex":0.00013499382,"about_ca_system_score_gemma":0.0012181766,"threshold_uncertainty_score":0.99572897},"labels":[],"label_agreement":null},{"id":"W4317356924","doi":"10.3138/cjpe.74693","title":"Listening with the Heart: A Reflection on Relationality and Ceremony","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Ceremony; Active listening; Reflection (computer programming); Sociology; Process (computing); Psychology; History; Computer science; Communication; Archaeology; Ecology","score_opus":0.4173002021624416,"score_gpt":0.531349183556716,"score_spread":0.11404898139427438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317356924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95948625,0.00024404131,0.0003611167,0.032678872,0.00040914933,0.00080929586,0.000004976629,0.000006581483,0.005999711],"genre_scores_gemma":[0.99800456,0.0000011049946,0.0008118231,0.00070407265,0.00008462736,0.00006724385,0.000004667255,0.0000049205487,0.00031697846],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962193,0.0009213158,0.0003729689,0.0001394106,0.0022172886,0.00012972702],"domain_scores_gemma":[0.99795693,0.00031651816,0.0004172306,0.00016851469,0.0009788102,0.00016197472],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016023112,0.00006504151,0.00010449167,0.00031044212,0.0009058045,0.00026729118,0.00018291842,0.000019974274,0.0013156261],"category_scores_gemma":[0.0006854555,0.000038974675,0.000044296172,0.00066255435,0.000074799376,0.00027716873,0.0000116998135,0.00029549928,0.0000083938385],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018477428,0.00006091594,0.08500864,0.000002873303,0.00004642622,0.0000060613306,0.0051773586,0.0664101,0.0000531813,0.0042711087,0.01678733,0.8219912],"study_design_scores_gemma":[0.0012278024,0.002603944,0.5099091,0.000022248083,0.00008555178,0.0003240172,0.00538108,0.07941684,0.000025452377,0.013846726,0.3870061,0.00015112798],"about_ca_topic_score_codex":0.00026467448,"about_ca_topic_score_gemma":0.0073011694,"teacher_disagreement_score":0.8218401,"about_ca_system_score_codex":0.00037685345,"about_ca_system_score_gemma":0.002180333,"threshold_uncertainty_score":0.9995973},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9584281,0.0021526893,0.0001409241,0.008411847,0.0019279139,0.0050878967,0.00005293831,0.000060942646,0.023736738],"genre_scores_gemma":[0.9936098,0.000034854067,0.0031175278,0.0017337671,0.00021905583,0.0010327334,0.0002024342,0.000024301744,0.000025551055],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9779393,0.01926369,0.0009884943,0.00012135153,0.001083029,0.00060414046],"domain_scores_gemma":[0.9949095,0.0008260315,0.0009799621,0.00040319728,0.0019997482,0.0008815215],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037096616,0.00014475132,0.00028803953,0.00052130566,0.0059571136,0.00003271288,0.0005203683,0.00010058861,0.0020565933],"category_scores_gemma":[0.0025181447,0.00015404898,0.00006769016,0.0003759612,0.000065623106,0.00037710555,0.00014932116,0.0027404956,0.00001914579],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009508553,0.00018898842,0.0031885856,0.00013065164,0.00003404518,0.000006531392,0.075588614,0.00025620928,0.000011047075,0.0011615113,0.0012510731,0.91808766],"study_design_scores_gemma":[0.008956666,0.010490984,0.3502,0.0007035179,0.0003170859,0.0000976784,0.4390984,0.01369588,0.000011152132,0.06425813,0.11144372,0.00072680233],"about_ca_topic_score_codex":0.009091249,"about_ca_topic_score_gemma":0.17121705,"teacher_disagreement_score":0.91736084,"about_ca_system_score_codex":0.0033269827,"about_ca_system_score_gemma":0.019298805,"threshold_uncertainty_score":0.99956024},"labels":[],"label_agreement":null},{"id":"W4317381160","doi":"10.3138/cjpe.66908","title":"Making Relationships Count: Measuring Trust in Relationships Between a Catholic Development Agency and Māori Communities","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aotearoa; Indigenous; Centrality; Agency (philosophy); Foundation (evidence); Sociology; Affect (linguistics); Cultural values; Public relations; Social psychology; Psychology; Political science; Social science; Gender studies","score_opus":0.7823290008155973,"score_gpt":0.5171308822180672,"score_spread":0.26519811859753006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9952139,0.00075840513,0.00038646787,0.0010170788,0.0002736776,0.0007206733,0.0000079981255,0.000008054678,0.0016137481],"genre_scores_gemma":[0.9957646,0.000006425411,0.0038553963,0.000042344374,0.000062928804,0.00015962585,0.000027402695,0.000010714169,0.00007054156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99323225,0.0028843684,0.0012364949,0.00015404478,0.00222854,0.00026430076],"domain_scores_gemma":[0.9971275,0.0007463592,0.0007139652,0.00024152298,0.00093271985,0.00023795906],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.044799767,0.00012062852,0.00023413336,0.001499301,0.0017448092,0.0003421432,0.0004220697,0.00006029647,0.00077270524],"category_scores_gemma":[0.0023554473,0.0001171158,0.000049950486,0.0011390907,0.000077127945,0.0006554511,0.000048039667,0.00092116604,0.000013072799],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057569255,0.000017424603,0.74354804,0.000003948924,0.000012269778,0.0000032594014,0.044378024,0.005727601,0.0000012040476,0.00034538514,0.000064344196,0.20589276],"study_design_scores_gemma":[0.0005619199,0.00010248851,0.9291764,0.000053566197,0.000038651462,0.0000421003,0.023980796,0.0146553125,0.0000029831197,0.006044241,0.025204787,0.00013676641],"about_ca_topic_score_codex":0.00057776074,"about_ca_topic_score_gemma":0.05893753,"teacher_disagreement_score":0.20575598,"about_ca_system_score_codex":0.0012358942,"about_ca_system_score_gemma":0.004931012,"threshold_uncertainty_score":0.9995548},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6129679,0.024422906,0.0008316984,0.16069382,0.08500686,0.0031279828,0.000084034145,0.0001427275,0.11272205],"genre_scores_gemma":[0.98418605,0.000540241,0.0008099115,0.00021111235,0.012324654,0.000023627501,0.000010118793,0.000024365283,0.0018698946],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99629503,0.0017567195,0.00035489642,0.0001340462,0.0008836012,0.0005756903],"domain_scores_gemma":[0.9973063,0.0004771489,0.0003929626,0.000112829584,0.00089902035,0.00081172975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016263494,0.00011990892,0.00017027314,0.0003339168,0.0006494706,0.00040040992,0.00031830088,0.00036094655,0.00067331316],"category_scores_gemma":[0.002379345,0.00013007752,0.00014321104,0.0010533192,0.00055544724,0.00039673896,0.000009102885,0.00069881807,0.00008942503],"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":[0.0000057453644,0.00005762137,0.0008731104,0.000020951991,0.00008181499,0.00012880299,0.014984212,0.00023474757,0.000036924805,0.017487098,0.06634791,0.89974105],"study_design_scores_gemma":[0.00041014585,0.00024978447,0.013898912,0.00017890755,0.00021100191,0.000044240587,0.002348228,0.0053880904,0.000027960969,0.072061576,0.9050092,0.00017194008],"about_ca_topic_score_codex":0.016683703,"about_ca_topic_score_gemma":0.028257124,"teacher_disagreement_score":0.8995691,"about_ca_system_score_codex":0.001313153,"about_ca_system_score_gemma":0.010676706,"threshold_uncertainty_score":0.9949318},"labels":[],"label_agreement":null},{"id":"W4317381171","doi":"10.3138/cjpe.74487","title":"New Insights for Tracking and Reporting Milestones","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tracking (education); Reflection (computer programming); Process (computing); Metric (unit); Developmental Milestone; Key (lock); Critical reflection; Psychology; Computer science; Operations management; Pedagogy; Engineering; Computer security; Developmental psychology","score_opus":0.6188240831545975,"score_gpt":0.573439920067952,"score_spread":0.0453841630866455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98512375,0.0015906617,0.0060144383,0.0036401341,0.0014010302,0.0013319968,0.000004348239,0.000007735525,0.0008859148],"genre_scores_gemma":[0.9890606,0.0000034436152,0.010234126,0.00016169205,0.0001870245,0.00007516749,0.000006886398,0.0000067955743,0.00026431005],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99659663,0.00027211083,0.0013221313,0.00015631493,0.0014895478,0.00016324432],"domain_scores_gemma":[0.99580663,0.000245248,0.0021182583,0.00013816828,0.0013595377,0.00033216222],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01736877,0.00006892241,0.00018665439,0.0005065588,0.0005494458,0.00030625574,0.00021564303,0.000024439334,0.0011172834],"category_scores_gemma":[0.0054823407,0.00005648795,0.00008680702,0.00044394174,0.00002491884,0.00042919288,0.00001382826,0.00014062907,0.0000022249312],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000108548975,0.000008527662,0.013615856,0.0000021277515,0.000010343813,0.0000041460653,0.0022364974,0.0027937633,0.000055163015,0.00046923666,0.0038537902,0.9769397],"study_design_scores_gemma":[0.0021703304,0.0015421249,0.16668889,0.000039281837,0.00015444435,0.00042203668,0.010231323,0.10609517,0.00021004336,0.07818985,0.63398755,0.00026896296],"about_ca_topic_score_codex":0.000294796,"about_ca_topic_score_gemma":0.0057733557,"teacher_disagreement_score":0.97667074,"about_ca_system_score_codex":0.00024104008,"about_ca_system_score_gemma":0.005292828,"threshold_uncertainty_score":0.99979585},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9806438,0.0019938692,0.0020554801,0.0064264797,0.0020986176,0.004850914,0.000101385434,0.000033178723,0.0017962562],"genre_scores_gemma":[0.9954532,0.00011378306,0.0014452012,0.00016264005,0.0010206545,0.0007738942,0.00004602626,0.000035044337,0.0009495657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930534,0.0037843965,0.0006256687,0.00032625694,0.0014741487,0.00073617825],"domain_scores_gemma":[0.9971951,0.0007706486,0.00049568666,0.0001145884,0.00074257725,0.0006813875],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.016838146,0.00016105449,0.00030985515,0.0006227665,0.0019478629,0.00034600665,0.00028304392,0.00012884555,0.0008545889],"category_scores_gemma":[0.0059091346,0.00018753622,0.00012411314,0.0010787672,0.0003252279,0.00062529295,0.00004002445,0.0005388756,0.000004223077],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003046591,0.00024122879,0.006813015,0.000079250276,0.000081499995,0.00006380461,0.019961236,0.001304111,0.0019609279,0.00040046457,0.014314442,0.95447534],"study_design_scores_gemma":[0.0066033993,0.0022997758,0.054925308,0.00012806321,0.0009342318,0.000047451576,0.07343199,0.046859577,0.0009312771,0.0047882767,0.80813587,0.00091479515],"about_ca_topic_score_codex":0.008394545,"about_ca_topic_score_gemma":0.11723729,"teacher_disagreement_score":0.9535606,"about_ca_system_score_codex":0.0016141146,"about_ca_system_score_gemma":0.004924238,"threshold_uncertainty_score":0.99935144},"labels":[],"label_agreement":null},{"id":"W4317381207","doi":"10.3138/cjpe.73987","title":"Involving Youth in Empowerment Evaluation: Evaluators’ Perspectives","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Winnipeg","funders":"","keywords":"Youth empowerment; Empowerment; Positive Youth Development; Psychology; Applied psychology; Developmental psychology; Political science","score_opus":0.41873982061622445,"score_gpt":0.5321663351437933,"score_spread":0.11342651452756886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842958,0.004111406,0.000089654044,0.0027998267,0.0017849274,0.0024301722,0.000019791063,0.000010367381,0.004458076],"genre_scores_gemma":[0.9983367,0.0000140487155,0.00074121845,0.00019464582,0.00018451465,0.0003856089,0.000030152325,0.00001562993,0.000097484975],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98578304,0.0035318807,0.0015375402,0.00041308257,0.008299016,0.00043543387],"domain_scores_gemma":[0.9932643,0.00025622666,0.0010525582,0.0004485754,0.0045397384,0.00043859737],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.07362724,0.000182141,0.00033710332,0.0020013321,0.0005890861,0.00041340565,0.0008202611,0.000057942507,0.020896576],"category_scores_gemma":[0.005051852,0.00016368182,0.00018980446,0.0021420347,0.000100073295,0.0008150669,0.000059121234,0.0005182731,0.000043045402],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000071259004,0.00030363674,0.12749267,0.000004935279,0.00006015881,0.000018042956,0.07497705,0.0919096,0.000034901743,0.0011623055,0.0031523886,0.70081306],"study_design_scores_gemma":[0.0050701774,0.0018784199,0.22326659,0.00006741191,0.00036305285,0.000070195085,0.37197798,0.3507553,0.000033792574,0.026017688,0.020003272,0.00049610995],"about_ca_topic_score_codex":0.00076630997,"about_ca_topic_score_gemma":0.017636098,"teacher_disagreement_score":0.7003169,"about_ca_system_score_codex":0.0039842674,"about_ca_system_score_gemma":0.016126284,"threshold_uncertainty_score":0.99983925},"labels":[],"label_agreement":null},{"id":"W4317381228","doi":"10.3138/cjpe.72343","title":"The Evaluation Marketplace in Canada: What Qualifications Do Employers Demand?","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Business; Profit (economics); Public relations; Marketing; Private sector; Political science; Economics; Economic growth","score_opus":0.37366454585497816,"score_gpt":0.5216791308618242,"score_spread":0.148014585006846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9573012,0.007336563,0.00020942886,0.025296593,0.004341485,0.0032915156,0.000020017873,0.0000068625045,0.0021963338],"genre_scores_gemma":[0.99857986,0.000084168816,0.00020917789,0.00031579475,0.00007670581,0.00057685946,0.000021485575,0.0000104379205,0.00012549765],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9873052,0.0041801594,0.0014342013,0.00026187248,0.006427395,0.00039117207],"domain_scores_gemma":[0.9941158,0.0011285718,0.0010018803,0.0004720586,0.002933291,0.0003483982],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06987932,0.00012549282,0.00020392815,0.0006033633,0.00110766,0.00092057127,0.00090976874,0.000032323205,0.00522633],"category_scores_gemma":[0.0047617164,0.000093721974,0.00009300272,0.0016163555,0.00006908027,0.0009642404,0.00003100021,0.00039440306,0.000016284506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000028055136,0.000023087905,0.041128088,0.0000011290252,0.000019858782,0.0000038862377,0.0013977461,0.0696343,0.0000041275753,0.00038731625,0.0155045,0.8718679],"study_design_scores_gemma":[0.0016597398,0.00028084515,0.35904816,0.000037239955,0.00011225466,0.00006837895,0.0826673,0.3267503,0.000011708983,0.01241859,0.21670029,0.00024519555],"about_ca_topic_score_codex":0.25882727,"about_ca_topic_score_gemma":0.9875174,"teacher_disagreement_score":0.8716227,"about_ca_system_score_codex":0.006138984,"about_ca_system_score_gemma":0.05846519,"threshold_uncertainty_score":0.99767625},"labels":[],"label_agreement":null},{"id":"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18949826,0.11311208,0.1823405,0.4111006,0.006608202,0.058487978,0.0047386363,0.0002390059,0.03387475],"genre_scores_gemma":[0.94402575,0.0059606014,0.027259825,0.0010898546,0.005059746,0.0068661263,0.0002121507,0.00014674253,0.009379224],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882205,0.008092281,0.00064041925,0.0003482474,0.0019159308,0.0007825816],"domain_scores_gemma":[0.99252844,0.0038880273,0.00051179645,0.00025146926,0.0019397414,0.00088055164],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.038452946,0.0001839401,0.00029327162,0.00030430427,0.0039663096,0.0005608642,0.00061469036,0.00009972781,0.0021630707],"category_scores_gemma":[0.0061124125,0.00015502836,0.00019700768,0.00077859045,0.0012826946,0.00038165398,0.000063928695,0.000734486,0.000009449642],"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":[0.0001644792,0.00028293437,0.00014225222,0.000073233874,0.00032453306,0.000026345708,0.11296501,0.00035058186,0.00029807436,0.012783186,0.1864527,0.68613666],"study_design_scores_gemma":[0.0013314902,0.0007849035,0.00094290683,0.00007159866,0.00018832005,0.000012360069,0.1296923,0.0016667753,0.000121050005,0.048517797,0.81639075,0.00027974817],"about_ca_topic_score_codex":0.011059283,"about_ca_topic_score_gemma":0.04569508,"teacher_disagreement_score":0.75452745,"about_ca_system_score_codex":0.00076485606,"about_ca_system_score_gemma":0.006160548,"threshold_uncertainty_score":0.9994736},"labels":[],"label_agreement":null},{"id":"W4317381695","doi":"10.3138/cjpe.74582","title":"Fostering an Evaluative Culture by Addressing a Breakdown in the Policy Development Cycle","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Accountability; Corporate governance; Function (biology); Process (computing); Citizen journalism; Participatory evaluation; Process management; Political science; Public relations; Public administration; Business; Management; Economics; Computer science; Law","score_opus":0.4732297645571751,"score_gpt":0.5733556647379928,"score_spread":0.10012590018081774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9809259,0.0011005427,0.00048122418,0.007594812,0.0005778534,0.002876265,0.000025113346,0.000010312747,0.006407946],"genre_scores_gemma":[0.996736,0.00000442471,0.0016685083,0.0008939194,0.00012359314,0.00043934453,0.000039510047,0.000008626414,0.00008607125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925865,0.0023436619,0.0008942783,0.00022225104,0.0036318272,0.0003215132],"domain_scores_gemma":[0.99763674,0.00015344755,0.00063515594,0.00026476034,0.0010461869,0.00026373673],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030251922,0.00012488168,0.00018710598,0.00074203825,0.00078292825,0.0005820196,0.0008868488,0.00003978303,0.0015953489],"category_scores_gemma":[0.0013352222,0.00008517215,0.00006813429,0.0014649624,0.000057348552,0.00075344177,0.00006572332,0.0003822946,0.000013486996],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016259033,0.00007198569,0.0026774597,0.000001984707,0.000010931433,0.0000056932017,0.039834894,0.00911664,0.00007942525,0.00009043364,0.0032441535,0.94485015],"study_design_scores_gemma":[0.0041908096,0.0023975987,0.13778444,0.00012275341,0.0001044531,0.000426786,0.10204167,0.18852764,0.00023091331,0.026370855,0.537186,0.0006160518],"about_ca_topic_score_codex":0.0008079827,"about_ca_topic_score_gemma":0.019134898,"teacher_disagreement_score":0.9442341,"about_ca_system_score_codex":0.0012473877,"about_ca_system_score_gemma":0.009316388,"threshold_uncertainty_score":0.99931735},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4317381706","doi":"10.3138/cjpe.73451","title":"Validation du questionnaire sur la capacité évaluative des organisations et ses déterminants (QCEOD)","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Internal consistency; Confirmatory factor analysis; Psychology; Reliability (semiconductor); Applied psychology; Consistency (knowledge bases); Social psychology; Structural equation modeling; Psychometrics; Statistics; Clinical psychology; Computer science; Mathematics","score_opus":0.3059432813083428,"score_gpt":0.5062255374256022,"score_spread":0.20028225611725936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317381706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877031,0.00026729767,0.0030060702,0.004014036,0.00093893404,0.0010178614,0.00003790226,0.000021188896,0.0029936444],"genre_scores_gemma":[0.9968752,0.00001794547,0.0021838841,0.0002586028,0.00012800776,0.00020666345,0.000045778932,0.000017602495,0.00026628672],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9922253,0.00303823,0.0010194884,0.00025920436,0.0031784733,0.00027932794],"domain_scores_gemma":[0.9936284,0.0006153193,0.00073785987,0.0002862803,0.004366316,0.00036583922],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029391808,0.00016045225,0.0002486382,0.0009042191,0.0010659859,0.0005735658,0.0005226761,0.000060336286,0.005671295],"category_scores_gemma":[0.007942067,0.0001407003,0.00013619904,0.0012605718,0.0001850489,0.0014526506,0.00003711379,0.00035026405,0.000050939463],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003682178,0.00023352171,0.15777284,0.000009587097,0.00007279469,0.000026698339,0.023834134,0.05839053,0.0002722692,0.0025054566,0.011286219,0.7455591],"study_design_scores_gemma":[0.0030201867,0.0018194038,0.68994516,0.00014270506,0.00034601951,0.00077924354,0.014395236,0.1311972,0.0007795685,0.06422792,0.09276739,0.0005799692],"about_ca_topic_score_codex":0.0013156909,"about_ca_topic_score_gemma":0.011454686,"teacher_disagreement_score":0.74497914,"about_ca_system_score_codex":0.0011309515,"about_ca_system_score_gemma":0.010821815,"threshold_uncertainty_score":0.9994454},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017187491,0.031001545,0.00030428008,0.004683407,0.07435184,0.016615111,0.0032679893,0.00018342785,0.8524049],"genre_scores_gemma":[0.05293044,0.0001879609,0.0066132187,0.0010422253,0.016178098,0.0018426507,0.0076665245,0.0022870088,0.91125184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99548167,0.0006928806,0.0011590264,0.00032845986,0.0015400158,0.0007979648],"domain_scores_gemma":[0.9936965,0.00006143685,0.0016493603,0.00043803657,0.0028915156,0.0012631381],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0045776074,0.00041988716,0.00066309504,0.0021580502,0.00018443413,0.00048634678,0.0006534424,0.0005202369,0.14199565],"category_scores_gemma":[0.00049831247,0.00041179432,0.00039233762,0.0005948923,0.00014458063,0.0003036016,0.000015871077,0.0010544006,0.6648571],"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":[0.000013504697,0.000019478422,0.00018601558,0.000055131484,0.00023644566,0.000058241934,0.00030968586,0.0009859111,0.000011615826,0.0000018916844,0.9316999,0.06642223],"study_design_scores_gemma":[0.00077667175,0.00029923406,0.0041214563,0.00065183145,0.00071828836,0.00015413256,0.00012497851,0.00095905043,0.000018098644,0.0002527038,0.9914801,0.0004434275],"about_ca_topic_score_codex":0.0073901447,"about_ca_topic_score_gemma":0.08879282,"teacher_disagreement_score":0.5228614,"about_ca_system_score_codex":0.0033192758,"about_ca_system_score_gemma":0.016652994,"threshold_uncertainty_score":0.9998334},"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":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007955466,0.009509932,0.00008557867,0.0028656693,0.032779574,0.008692726,0.0015395856,0.000039362523,0.9365321],"genre_scores_gemma":[0.013039291,0.00010942273,0.0036847184,0.00064132194,0.00798829,0.0006096243,0.0044373753,0.0013132663,0.96817666],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956811,0.0006999279,0.0011610773,0.00032935312,0.0013179497,0.0008105805],"domain_scores_gemma":[0.99372494,0.000061901395,0.0016354222,0.000442236,0.0028558508,0.0012796607],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038546696,0.0004240505,0.00064298935,0.0020829628,0.00015899797,0.0005160386,0.0006636663,0.0005332252,0.28846347],"category_scores_gemma":[0.00029072535,0.00042079086,0.00039118118,0.0010817577,0.00016083437,0.0003271038,0.000016142512,0.0009912371,0.8410531],"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":[0.000012462232,0.000018641302,0.00019764305,0.00007880921,0.00021850261,0.000025187883,0.00020484814,0.0007546923,0.0000147759,0.0000023782695,0.96622753,0.032244522],"study_design_scores_gemma":[0.00081987947,0.0002815643,0.0020677594,0.00068250904,0.00054492947,0.0001823897,0.00008638211,0.0006985588,0.000019417424,0.00010652026,0.9940816,0.0004284656],"about_ca_topic_score_codex":0.0043839104,"about_ca_topic_score_gemma":0.041076414,"teacher_disagreement_score":0.55258965,"about_ca_system_score_codex":0.0026309805,"about_ca_system_score_gemma":0.014854807,"threshold_uncertainty_score":0.9998244},"labels":[],"label_agreement":null},{"id":"W4353055378","doi":"10.3138/cjpe.75448","title":"John Mayne and Rules of Thumb for Contribution Analysis: A Comparison With Two Related Approaches","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rule of thumb; Manifesto; Thumb; Epistemology; Work (physics); Sociology; Computer science; Political science; Law; Philosophy; Medicine; Engineering; Algorithm; Surgery","score_opus":0.4678585488688824,"score_gpt":0.5302059008889366,"score_spread":0.0623473520200542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99035895,0.0005304466,0.0058180713,0.001656896,0.00013179917,0.0011529941,0.000045889305,0.000010331382,0.0002946065],"genre_scores_gemma":[0.99602515,0.000009009951,0.0036314763,0.000014725181,0.00003654241,0.00005028772,0.00017807905,0.000005853359,0.000048880887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99700975,0.00036602197,0.00092343974,0.00020477318,0.0012955364,0.00020045589],"domain_scores_gemma":[0.99580115,0.0003965314,0.0010033937,0.00028240096,0.0022937944,0.00022274218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0187302,0.0000923242,0.00037395238,0.0011364669,0.00016077656,0.00018897708,0.00031049026,0.000056267894,0.00013645954],"category_scores_gemma":[0.0016503269,0.000063698244,0.00009178544,0.001681784,0.00011764126,0.00041321918,0.0000131788265,0.00010047608,0.0000073023402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001272462,0.00006576826,0.2647713,0.000014208235,0.00073690945,0.0000019680201,0.0025042712,0.039624188,0.000040242136,0.002901427,0.0013184445,0.687894],"study_design_scores_gemma":[0.0016194995,0.0005151323,0.21675566,0.000031299573,0.0008841282,0.000007642675,0.0018659047,0.7692501,0.00005472162,0.006607699,0.002325412,0.00008282906],"about_ca_topic_score_codex":0.00021491873,"about_ca_topic_score_gemma":0.01351109,"teacher_disagreement_score":0.7296259,"about_ca_system_score_codex":0.000103028,"about_ca_system_score_gemma":0.0016509243,"threshold_uncertainty_score":0.75395054},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3573177,0.07480315,0.0003454156,0.0352124,0.011113903,0.001631526,0.00032378762,0.000089680056,0.5191625],"genre_scores_gemma":[0.9872375,0.000505272,0.0004190274,0.00013599951,0.004957391,0.000018873508,0.00004141492,0.000026813515,0.00665772],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982658,0.00040621354,0.00041159362,0.000103784725,0.00041028342,0.00040229675],"domain_scores_gemma":[0.9976857,0.00015578754,0.00030650396,0.00011930481,0.0011802155,0.0005525144],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004051792,0.00012308868,0.00018874853,0.0005902698,0.00045259195,0.0007468748,0.00017269659,0.000107535074,0.00450268],"category_scores_gemma":[0.0011512612,0.00012193488,0.00020565704,0.00027817787,0.00028206132,0.00014810302,0.000006509233,0.00026238823,0.00014889376],"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":[0.0000074607487,0.00009704818,0.0015545229,0.000053797627,0.00042384048,0.0003941915,0.009659845,0.0022309374,0.0000039883857,0.31046063,0.03802626,0.63708746],"study_design_scores_gemma":[0.00044688198,0.0002108264,0.00323924,0.000120965895,0.0012980227,0.000043873588,0.0027639773,0.0317155,0.000010549721,0.037427913,0.922566,0.00015623908],"about_ca_topic_score_codex":0.019542458,"about_ca_topic_score_gemma":0.024132023,"teacher_disagreement_score":0.8845397,"about_ca_system_score_codex":0.0004104469,"about_ca_system_score_gemma":0.0036099183,"threshold_uncertainty_score":0.99640733},"labels":[],"label_agreement":null},{"id":"W4353055384","doi":"10.3138/cjpe.75515","title":"Remembering John Mayne—A Practical Thinker and a Thinking Practitioner","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Stroke Network","funders":"","keywords":"Psychoanalysis; Psychology; Epistemology; Philosophy","score_opus":0.4904664904135886,"score_gpt":0.5735784858630458,"score_spread":0.08311199544945724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055384","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9210034,0.0004307254,0.0028486904,0.050624818,0.0026487224,0.0017682888,0.0000074069703,0.000078055156,0.02058988],"genre_scores_gemma":[0.98850065,0.00003965697,0.010276212,0.00041870723,0.0002712975,0.000042654032,0.000010487821,0.000012429974,0.0004278936],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956469,0.00052894844,0.00074895006,0.00020637907,0.0025869526,0.00028189356],"domain_scores_gemma":[0.99616265,0.0005689892,0.00061932486,0.00021886104,0.001997458,0.00043272108],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025636477,0.00010372759,0.0001852663,0.00082684174,0.0003828657,0.0008589659,0.00021514164,0.000084299856,0.0018438477],"category_scores_gemma":[0.00843999,0.00007973721,0.00007516478,0.001090363,0.000078110905,0.0014794471,0.000025112053,0.00029213383,0.0002328866],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003308573,0.00004379826,0.02980915,0.000012172598,0.00007092299,0.00008755224,0.005841572,0.003266818,0.00018245095,0.0059483354,0.046809334,0.9078948],"study_design_scores_gemma":[0.0015817065,0.00058218325,0.27750462,0.0001508337,0.00019847623,0.00062139216,0.0078944145,0.21895744,0.000090458125,0.077694535,0.41438448,0.0003394599],"about_ca_topic_score_codex":0.00019027307,"about_ca_topic_score_gemma":0.0059579005,"teacher_disagreement_score":0.90755534,"about_ca_system_score_codex":0.00021658152,"about_ca_system_score_gemma":0.003544823,"threshold_uncertainty_score":0.9999123},"labels":[],"label_agreement":null},{"id":"W4353055391","doi":"10.3138/cjpe.75444","title":"Using Evaluative Information Sensibly: The Enduring Contributions of John Mayne","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Stroke Network","funders":"MetroWest Health Foundation; Hartford Foundation for Public Giving","keywords":"Causation; Audit; Accountability; Discipline; Bridge (graph theory); Work (physics); Knowledge management; Sociology; Engineering ethics; Epistemology; Computer science; Political science; Social science; Accounting; Engineering; Medicine; Business; Law","score_opus":0.47197470653963447,"score_gpt":0.5711621102531929,"score_spread":0.09918740371355839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055391","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9846249,0.00021139582,0.00478111,0.004298168,0.001349868,0.0017431269,0.000063457876,0.000018486196,0.002909494],"genre_scores_gemma":[0.99846494,0.000012776565,0.0011888852,0.00009841069,0.00012767344,0.000030733776,0.000028623917,0.0000055865466,0.000042343807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945276,0.00088651007,0.0013176386,0.0001094071,0.0028665264,0.00029231168],"domain_scores_gemma":[0.9897987,0.0005650801,0.0013217032,0.00029889448,0.00777217,0.00024344811],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028679764,0.000109641136,0.00023939906,0.0012211953,0.0004174108,0.00031186786,0.00040432898,0.000073932686,0.00089069013],"category_scores_gemma":[0.008966826,0.00007256842,0.0001517296,0.0024235395,0.00015097213,0.0013623735,0.000023308712,0.00020989684,0.00012445672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038679576,0.00003666825,0.0122142695,0.000013716735,0.00012639065,0.000004306047,0.008158214,0.14734825,0.0009713076,0.0029570877,0.008098386,0.8200327],"study_design_scores_gemma":[0.0014882,0.0003884603,0.11509988,0.00010560851,0.00022808556,0.00006030012,0.010879092,0.83022666,0.0014596437,0.012949068,0.026944742,0.0001702811],"about_ca_topic_score_codex":0.00041972546,"about_ca_topic_score_gemma":0.002198187,"teacher_disagreement_score":0.8198624,"about_ca_system_score_codex":0.00039102402,"about_ca_system_score_gemma":0.0064977994,"threshold_uncertainty_score":0.99938107},"labels":[],"label_agreement":null},{"id":"W4353055426","doi":"10.3138/cjpe.75451","title":"John Mayne and the Origins of Evaluation in the Public Sector in Canada: A Shaping of Both Evaluation and the Evaluator","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Test (biology); Public sector; Public administration; Political science; Sociology; Management; Public relations; Economics; Law; Philosophy; Geology","score_opus":0.37158747526533276,"score_gpt":0.48774464836179726,"score_spread":0.1161571730964645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055426","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9766919,0.0022472444,0.00003675037,0.01615367,0.0004294204,0.004004699,0.000010685831,0.0000022987317,0.00042332086],"genre_scores_gemma":[0.99906635,0.00011857902,0.00008904139,0.0002485306,0.00007252637,0.00037641398,0.00001288551,0.000008947046,0.000006730184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9825772,0.007646695,0.0019724176,0.00029496488,0.0071237376,0.00038495375],"domain_scores_gemma":[0.99206847,0.0026368261,0.0013310511,0.00042186156,0.0033922496,0.00014951854],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16078137,0.00015832736,0.0004487634,0.0009772494,0.0002192174,0.0002598263,0.0005597079,0.000067415596,0.0004702977],"category_scores_gemma":[0.014689999,0.00008004488,0.00009145456,0.0026743417,0.00043820674,0.00053726096,0.000032075364,0.00030841999,0.0000025203442],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002686929,0.00004608861,0.10597804,0.000032548287,0.00008728667,0.0000037874581,0.016573137,0.0120452745,0.000045212983,0.0100857355,0.0012814454,0.85355276],"study_design_scores_gemma":[0.0060614487,0.00009820517,0.36397165,0.00007485624,0.00015949293,0.00002113067,0.007833255,0.6106292,0.000009118127,0.009844811,0.0012230133,0.00007380592],"about_ca_topic_score_codex":0.2899152,"about_ca_topic_score_gemma":0.96185267,"teacher_disagreement_score":0.85347897,"about_ca_system_score_codex":0.0015257866,"about_ca_system_score_gemma":0.02524637,"threshold_uncertainty_score":0.99360967},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6367845,0.00093435467,0.026862862,0.24783604,0.011577381,0.017111385,0.00004878734,0.0015714638,0.05727321],"genre_scores_gemma":[0.9932001,0.0000024334777,0.00136292,0.0036739027,0.0011390664,0.00007747773,0.00025979354,0.000033918688,0.0002503807],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976353,0.00004277126,0.0005830265,0.00024207089,0.0010060873,0.00049071596],"domain_scores_gemma":[0.9975577,0.000039946914,0.00047537943,0.0002090278,0.0016198882,0.000098071214],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004707546,0.00017403084,0.00018399929,0.0016795701,0.00039451843,0.0011174132,0.00039758725,0.00007068153,0.00016774434],"category_scores_gemma":[0.0012628724,0.00017294743,0.000097614866,0.0023940937,0.00003716433,0.0009889696,0.00003902827,0.00014946758,0.0007091832],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003570782,0.00022795124,0.024780022,0.0005330606,0.00039099372,0.00034910464,0.00049130217,0.072105944,0.00006233884,0.09553752,0.33928037,0.4658843],"study_design_scores_gemma":[0.0037966508,0.00013864777,0.13081147,0.0006340547,0.0005585209,0.000005798155,0.0019093221,0.04054759,0.000037054957,0.008300678,0.8127362,0.0005239727],"about_ca_topic_score_codex":0.0007226263,"about_ca_topic_score_gemma":0.0030070487,"teacher_disagreement_score":0.47345588,"about_ca_system_score_codex":0.00041023805,"about_ca_system_score_gemma":0.00037048923,"threshold_uncertainty_score":0.99991953},"labels":[],"label_agreement":null},{"id":"W4353055441","doi":"10.3138/cjpe.37.3.ed-en","title":"Editor’s Remarks","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.3016607384097375,"score_gpt":0.5419447489581198,"score_spread":0.24028401054838233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055441","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83711743,0.00097156427,0.002445411,0.03685035,0.06468003,0.0036134229,0.000029206036,0.00013233752,0.05416026],"genre_scores_gemma":[0.9940449,0.000013220605,0.0014438768,0.00020563856,0.0031648087,0.000045330296,0.00001773646,0.000009942429,0.0010545491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955053,0.000415694,0.0007865304,0.00015167915,0.002868767,0.0002720561],"domain_scores_gemma":[0.9953159,0.00028554566,0.0004931246,0.0002655536,0.0031687526,0.0004710908],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.024627816,0.000083011575,0.00016917981,0.0010701319,0.00019822734,0.0003929544,0.0004595897,0.00007228107,0.0038903803],"category_scores_gemma":[0.005499139,0.00006263263,0.00011801692,0.0016472327,0.00006102372,0.0005616982,0.000011080702,0.00017529621,0.00091196224],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004549832,0.000008382617,0.0116367815,0.000001386721,0.000010852067,0.0000064418723,0.00047632185,0.0016546788,0.000018128467,0.00019120304,0.28842306,0.69756824],"study_design_scores_gemma":[0.0006104685,0.0003107812,0.13341339,0.00003110775,0.000040280895,0.000023838049,0.0013397733,0.07667341,0.000042513147,0.016967505,0.7704299,0.00011702141],"about_ca_topic_score_codex":0.0001839598,"about_ca_topic_score_gemma":0.008594621,"teacher_disagreement_score":0.6974512,"about_ca_system_score_codex":0.00025826498,"about_ca_system_score_gemma":0.0053484077,"threshold_uncertainty_score":0.99986595},"labels":[],"label_agreement":null},{"id":"W4353055504","doi":"10.3138/cjpe.75430","title":"Causality and Complexity in Evaluating Equity Interventions: Conceptual Issues That Need to Be Addressed in Theory-Driven Evaluation Approaches","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Causality (physics); Variety (cybernetics); Psychological intervention; Equity (law); Management science; Causal model; Conceptual framework; Risk analysis (engineering); Positive economics; Psychology; Computer science; Sociology; Economics; Political science; Business; Medicine; Social science","score_opus":0.921309918994153,"score_gpt":0.6511159997897381,"score_spread":0.27019391920441493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866945,0.00061955536,0.00044118156,0.007808607,0.00045970856,0.0030938115,0.000025385658,0.000017992475,0.0008392673],"genre_scores_gemma":[0.99669397,0.000013904525,0.0024813092,0.00019321575,0.00008304773,0.0003709172,0.00007556356,0.000013161999,0.000074930445],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98853093,0.0048682257,0.0016825474,0.00046148914,0.0039542895,0.00050249],"domain_scores_gemma":[0.9956864,0.0008232879,0.00077206426,0.00035920864,0.0019115558,0.0004475013],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09844063,0.00019984314,0.00046809332,0.0019735503,0.00021952525,0.00052699697,0.0005483606,0.00012333576,0.0017816039],"category_scores_gemma":[0.014224714,0.00017474595,0.00014034042,0.0023267458,0.00027780602,0.0009436707,0.000100698206,0.0003474602,0.000040607723],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000947511,0.000114589035,0.14119618,0.000030088577,0.000036644546,0.0000067873334,0.019164206,0.03206704,0.00007355578,0.0043197433,0.0013146211,0.8015818],"study_design_scores_gemma":[0.001892026,0.00049186643,0.5385117,0.00024054127,0.000071401984,0.0000068193835,0.025557417,0.38283092,0.000043343756,0.04963478,0.0005388537,0.00018035003],"about_ca_topic_score_codex":0.0016824801,"about_ca_topic_score_gemma":0.16618764,"teacher_disagreement_score":0.80140144,"about_ca_system_score_codex":0.00095736614,"about_ca_system_score_gemma":0.003084084,"threshold_uncertainty_score":0.9991309},"labels":[],"label_agreement":null},{"id":"W4353055508","doi":"10.3138/cjpe.75467","title":"John Mayne’s Contribution to Performance Audit","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Audit; Government (linguistics); Service (business); Public service; Business; Accounting; Public administration; Political science; Philosophy; Marketing","score_opus":0.3441610320995043,"score_gpt":0.528996299099539,"score_spread":0.18483526700003472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98598784,0.00008504031,0.0006832591,0.007916707,0.0017978908,0.0011509322,0.0000109819575,0.000028262077,0.0023390802],"genre_scores_gemma":[0.9978024,0.00001598916,0.00069295155,0.0003779117,0.00029200115,0.00009361082,0.000026284393,0.000009384194,0.00068951986],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954164,0.00035389408,0.00092094846,0.00020857553,0.0026944932,0.00040568202],"domain_scores_gemma":[0.9939035,0.00020025743,0.0004899483,0.00029670438,0.0044148252,0.0006947373],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02122548,0.00011672165,0.00022702584,0.0014030781,0.00031010757,0.00041319587,0.0005087196,0.000075720665,0.0025384875],"category_scores_gemma":[0.004966496,0.00009275142,0.00011064636,0.0025010402,0.000048945243,0.0007051433,0.000018641202,0.00017142645,0.0022771521],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021681868,0.0000155456,0.03882633,0.0000030317708,0.000018145449,0.00000653601,0.00059652154,0.011763633,0.0001555637,0.00043551796,0.03864247,0.909515],"study_design_scores_gemma":[0.0008127224,0.0007137563,0.50682807,0.000055414625,0.00004474881,0.00002936009,0.00047201457,0.095139466,0.00031420344,0.0023064103,0.39312485,0.00015896978],"about_ca_topic_score_codex":0.0001198295,"about_ca_topic_score_gemma":0.005362593,"teacher_disagreement_score":0.90935606,"about_ca_system_score_codex":0.00053728133,"about_ca_system_score_gemma":0.0044759014,"threshold_uncertainty_score":0.9984997},"labels":[],"label_agreement":null},{"id":"W4353055537","doi":"10.3138/cjpe.75431","title":"Building Evaluation Culture—The Missing Link","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Sociology; Knowledge management; Psychology; Epistemology; Computer science; Philosophy","score_opus":0.5208539717794183,"score_gpt":0.5865932421472865,"score_spread":0.0657392703678682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8144254,0.004027716,0.011062529,0.1356717,0.010375078,0.007065487,0.000018014936,0.00012802676,0.01722601],"genre_scores_gemma":[0.9940717,0.000017431012,0.0043542664,0.0004222477,0.00070020405,0.00009730976,0.000018147057,0.000013142458,0.0003055332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99242246,0.0012359023,0.0010439067,0.00022761324,0.0047103143,0.0003598027],"domain_scores_gemma":[0.99254125,0.00041509993,0.00082254503,0.00038251976,0.005448218,0.00039036118],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05735271,0.0001314581,0.00020116502,0.0008599142,0.0006382905,0.0009247136,0.000674629,0.000094607865,0.0018211184],"category_scores_gemma":[0.010421291,0.000082493236,0.0001671914,0.0023532289,0.000101280006,0.0007337571,0.000018313582,0.00029571741,0.00030338805],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046499877,0.000006583839,0.0026067628,0.0000019037814,0.000019111727,0.0000026601108,0.0014186067,0.010633542,0.00014020059,0.0005200926,0.013712593,0.9709333],"study_design_scores_gemma":[0.0008529485,0.00023776163,0.06726978,0.000068410125,0.00016998181,0.00004499004,0.0014202937,0.6034538,0.00017267934,0.07539648,0.25075975,0.00015311589],"about_ca_topic_score_codex":0.00017751264,"about_ca_topic_score_gemma":0.003225833,"teacher_disagreement_score":0.9707802,"about_ca_system_score_codex":0.00053978106,"about_ca_system_score_gemma":0.006295008,"threshold_uncertainty_score":0.9993384},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79622644,0.15074362,0.00025721957,0.043851353,0.0023696714,0.005794198,0.00022368948,0.00003201678,0.00050179334],"genre_scores_gemma":[0.85852355,0.04307473,0.0048860093,0.0008194571,0.0016992269,0.0016241925,0.0013046818,0.0002089642,0.08785922],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9930852,0.001661174,0.0010845,0.00050136604,0.0020553735,0.0016123928],"domain_scores_gemma":[0.9931399,0.00039803828,0.00033228926,0.0002918712,0.0030228882,0.0028150019],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017096663,0.00040564014,0.0007493483,0.0009593839,0.00036516567,0.00024701373,0.00031400443,0.00032234724,0.0017624438],"category_scores_gemma":[0.024551691,0.0003953912,0.00024665223,0.0013432339,0.00071835006,0.00063453015,0.000047244823,0.0008572323,0.00015542173],"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":[0.00013432404,0.0002031684,0.11489229,0.001194998,0.0002527084,0.0015184972,0.0021556125,0.000015801568,0.00004298675,0.000059526585,0.10747363,0.77205646],"study_design_scores_gemma":[0.008173309,0.0044535757,0.69544786,0.0045798826,0.0012001068,0.0006209648,0.0031242282,0.019411745,0.00004949336,0.0062952023,0.2561886,0.0004550107],"about_ca_topic_score_codex":0.0065161665,"about_ca_topic_score_gemma":0.052005056,"teacher_disagreement_score":0.77160144,"about_ca_system_score_codex":0.0022409642,"about_ca_system_score_gemma":0.0039444915,"threshold_uncertainty_score":0.9998498},"labels":[],"label_agreement":null},{"id":"W4353055566","doi":"10.3138/cjpe.75441","title":"Mapping the Contributions of John Mayne: Bridging the Gaps Between Evaluation, Auditing, and Performance Monitoring","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Citation; Bridging (networking); Field (mathematics); Library science; Data science; Computer science; Accounting; Business","score_opus":0.36971123944452877,"score_gpt":0.5041761856590817,"score_spread":0.13446494621455296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055566","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887963,0.0009021795,0.00044641295,0.0074141547,0.0007014889,0.0011337185,0.000015619964,0.000011130092,0.0005789776],"genre_scores_gemma":[0.99892324,0.00007905726,0.0001992012,0.000042715714,0.0005675952,0.00009639588,0.000013816036,0.000008270334,0.00006968634],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99457127,0.0009383209,0.0010786209,0.00017669427,0.0029090678,0.00032603266],"domain_scores_gemma":[0.99265146,0.00097549555,0.0010910012,0.0003311767,0.00473712,0.00021373932],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.049873527,0.00011858243,0.00022822041,0.0006429794,0.0009363149,0.00040039976,0.00053983997,0.000058834583,0.0002986035],"category_scores_gemma":[0.00681114,0.000070114365,0.00009837245,0.0019264793,0.00021169221,0.00055016385,0.00003438331,0.0002835635,0.000031692394],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003049859,0.0000042486768,0.30430388,0.000006122753,0.00003749699,4.7462888e-7,0.002107484,0.0043916656,0.00006161742,0.00006233117,0.002015983,0.68700564],"study_design_scores_gemma":[0.00052256905,0.000121068406,0.8387907,0.0001222366,0.000119306664,0.00001616207,0.0050122985,0.14499968,0.000374473,0.001655146,0.008183329,0.00008304469],"about_ca_topic_score_codex":0.00019068459,"about_ca_topic_score_gemma":0.00047351595,"teacher_disagreement_score":0.6869226,"about_ca_system_score_codex":0.00025552648,"about_ca_system_score_gemma":0.003226933,"threshold_uncertainty_score":0.97835517},"labels":[],"label_agreement":null},{"id":"W4353055592","doi":"10.3138/cjpe.37.3.addendum-fr","title":"Addendum","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Addendum; Philosophy; Linguistics","score_opus":0.642089777734816,"score_gpt":0.5990496877794452,"score_spread":0.043040089955370786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9540916,0.00043606546,0.0006610809,0.012670758,0.0046380693,0.0013814108,0.000013304841,0.000052672887,0.026055051],"genre_scores_gemma":[0.99746716,0.000008909568,0.0008860703,0.00017324988,0.00034030667,0.000035940233,0.000012235989,0.000007058447,0.0010690439],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99615,0.0003575139,0.0007025887,0.00013286926,0.0024045184,0.00025249607],"domain_scores_gemma":[0.996134,0.00020753607,0.00042654618,0.00023272597,0.002569188,0.00043000194],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019818896,0.00007338626,0.00015013629,0.0010854412,0.00017640422,0.00035183533,0.00043078838,0.000053238673,0.0057088393],"category_scores_gemma":[0.0039079995,0.000055008473,0.000108579545,0.0017535926,0.00005347931,0.0005079353,0.000009701136,0.00014022966,0.0013377728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035498335,0.000008186101,0.015335971,0.0000010713674,0.000011100746,0.000008956075,0.00058021606,0.0017007942,0.000023370401,0.00047397587,0.07176863,0.9100842],"study_design_scores_gemma":[0.00088556076,0.00044394648,0.25132003,0.000032330274,0.000056172234,0.000037142803,0.0023367624,0.11563147,0.00010049322,0.031403188,0.5975973,0.00015560775],"about_ca_topic_score_codex":0.0001781861,"about_ca_topic_score_gemma":0.009452958,"teacher_disagreement_score":0.90992856,"about_ca_system_score_codex":0.00019560097,"about_ca_system_score_gemma":0.004715324,"threshold_uncertainty_score":0.9994398},"labels":[],"label_agreement":null},{"id":"W4353055595","doi":"10.3138/cjpe.37.3.addendum-en","title":"Addendum","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Addendum; Philosophy; Linguistics","score_opus":0.642089777734816,"score_gpt":0.5990496877794452,"score_spread":0.043040089955370786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9540916,0.00043606546,0.0006610809,0.012670758,0.0046380693,0.0013814108,0.000013304841,0.000052672887,0.026055051],"genre_scores_gemma":[0.99746716,0.000008909568,0.0008860703,0.00017324988,0.00034030667,0.000035940233,0.000012235989,0.000007058447,0.0010690439],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99615,0.0003575139,0.0007025887,0.00013286926,0.0024045184,0.00025249607],"domain_scores_gemma":[0.996134,0.00020753607,0.00042654618,0.00023272597,0.002569188,0.00043000194],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019818896,0.00007338626,0.00015013629,0.0010854412,0.00017640422,0.00035183533,0.00043078838,0.000053238673,0.0057088393],"category_scores_gemma":[0.0039079995,0.000055008473,0.000108579545,0.0017535926,0.00005347931,0.0005079353,0.000009701136,0.00014022966,0.0013377728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035498335,0.000008186101,0.015335971,0.0000010713674,0.000011100746,0.000008956075,0.00058021606,0.0017007942,0.000023370401,0.00047397587,0.07176863,0.9100842],"study_design_scores_gemma":[0.00088556076,0.00044394648,0.25132003,0.000032330274,0.000056172234,0.000037142803,0.0023367624,0.11563147,0.00010049322,0.031403188,0.5975973,0.00015560775],"about_ca_topic_score_codex":0.0001781861,"about_ca_topic_score_gemma":0.009452958,"teacher_disagreement_score":0.90992856,"about_ca_system_score_codex":0.00019560097,"about_ca_system_score_gemma":0.004715324,"threshold_uncertainty_score":0.9994398},"labels":[],"label_agreement":null},{"id":"W4353055654","doi":"10.3138/cjpe.75428","title":"Causal Claims in Contribution Analysis","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Counterfactual thinking; Causality (physics); Causation; Relevance (law); Epistemology; Causal analysis; Counterfactual conditional; Generative grammar; Probabilistic logic; Computer science; Positive economics; Psychology; Sociology; Econometrics; Philosophy; Artificial intelligence; Economics; Political science; Law","score_opus":0.4173134303158473,"score_gpt":0.5774615920977317,"score_spread":0.16014816178188446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99369323,0.00012365221,0.0010822137,0.003255388,0.00063187175,0.000596357,0.000008983438,0.0000121522235,0.00059615343],"genre_scores_gemma":[0.9992996,0.000010986737,0.0002776369,0.00008889131,0.00009570678,0.000042555483,0.000054344837,0.0000043555006,0.00012591996],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9958046,0.00062353734,0.0009811239,0.0001716958,0.0021209598,0.0002980918],"domain_scores_gemma":[0.9961322,0.00027665118,0.0004912705,0.00021873532,0.0025483463,0.00033278693],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026240636,0.00008046794,0.00026938439,0.0032622819,0.00012252547,0.00029069558,0.00031517533,0.00007741166,0.0016899792],"category_scores_gemma":[0.002684498,0.0000669835,0.00016813693,0.0067898184,0.000050014627,0.0005031266,0.000008600842,0.00017585952,0.00024824962],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014157892,0.000024405,0.40862143,0.0000012078931,0.00009387408,0.000021289767,0.0007356543,0.044790983,0.000030735642,0.00093538093,0.0032190424,0.54151183],"study_design_scores_gemma":[0.0006366847,0.00014150837,0.6970087,0.000010099759,0.00015748403,0.000005241214,0.0005071957,0.27787903,0.000024009234,0.0118117295,0.011745176,0.00007311533],"about_ca_topic_score_codex":0.0007143109,"about_ca_topic_score_gemma":0.12745304,"teacher_disagreement_score":0.54143876,"about_ca_system_score_codex":0.00050000014,"about_ca_system_score_gemma":0.0032608567,"threshold_uncertainty_score":0.99922264},"labels":[],"label_agreement":null},{"id":"W4353055688","doi":"10.3138/cjpe.75457","title":"Bridging Evaluation Theory and Practice: The Contributions of John Mayne to Canadian Federal Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bridging (networking); Thematic analysis; Function (biology); Government (linguistics); Conceptual framework; Sociology; Qualitative research; Computer science; Social science; Philosophy","score_opus":0.3228660608706075,"score_gpt":0.5747000820470364,"score_spread":0.2518340211764289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87996596,0.0019778193,0.003365531,0.09280909,0.0025876372,0.008613405,0.00012582056,0.000028886183,0.010525852],"genre_scores_gemma":[0.99781984,0.000025171103,0.0005740177,0.0008621635,0.00024161045,0.00027934747,0.000070474525,0.000014286463,0.00011311616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9868277,0.005697487,0.0013462972,0.00032646616,0.0052808058,0.0005212678],"domain_scores_gemma":[0.97947073,0.0020775006,0.0009793128,0.00044086904,0.016184555,0.0008470409],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16893819,0.00017143167,0.00029573176,0.0017312695,0.00084787083,0.00067647535,0.00048194148,0.0001130932,0.0019278515],"category_scores_gemma":[0.07724181,0.0001257896,0.000121177254,0.0024590986,0.00016215212,0.0010140538,0.000026656066,0.00026779991,0.00011875319],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060651288,0.000020962736,0.0027572077,0.0000039839415,0.000073058975,0.0000030462813,0.0034749617,0.02000812,0.00021261157,0.002833807,0.016165065,0.95438653],"study_design_scores_gemma":[0.0027390907,0.000775858,0.27729595,0.00014959893,0.000908626,0.00016873398,0.016695004,0.6002636,0.00028990788,0.04142255,0.058935553,0.00035554077],"about_ca_topic_score_codex":0.016771773,"about_ca_topic_score_gemma":0.29755536,"teacher_disagreement_score":0.954031,"about_ca_system_score_codex":0.0013372877,"about_ca_system_score_gemma":0.02151677,"threshold_uncertainty_score":0.9989845},"labels":[],"label_agreement":null},{"id":"W4353055711","doi":"10.3138/cjpe.75429","title":"Enduring Themes in John Mayne’s Work: Implications for Evaluation Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Sophistication; Checklist; Work (physics); Elaboration; Accountability; Field (mathematics); Causality (physics); Sociology; Psychology; Engineering ethics; Political science; Social science; Engineering; Cognitive psychology","score_opus":0.5854453128611484,"score_gpt":0.6102911840352087,"score_spread":0.02484587117406023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353055711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88561356,0.001573196,0.0032382314,0.083452865,0.0029347253,0.009873807,0.000040279447,0.00006606989,0.013207276],"genre_scores_gemma":[0.9942446,0.000030256719,0.0041701095,0.00023024288,0.0002179809,0.00084547733,0.00005180038,0.000015223684,0.00019432868],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952069,0.0008258319,0.0011972279,0.00027650656,0.0020934085,0.00040013422],"domain_scores_gemma":[0.9911466,0.0014283418,0.0008885919,0.00036293326,0.005868492,0.00030500357],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044765096,0.00012662027,0.00022409689,0.001628307,0.0002815622,0.00045052226,0.0004895403,0.000093550945,0.00068472145],"category_scores_gemma":[0.021236487,0.00010741412,0.00013405657,0.0027659356,0.000052232037,0.0012248317,0.000015985763,0.00018878185,0.00011503267],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031113592,0.000040542698,0.028187193,0.00000414862,0.000022843426,0.0000011725665,0.0015609208,0.016917948,0.00004756416,0.0011210503,0.00817898,0.9438865],"study_design_scores_gemma":[0.0026729566,0.0003038603,0.6936453,0.00009154642,0.00018870943,0.000027426824,0.0046955124,0.10970281,0.00006152578,0.039484233,0.14890315,0.00022294786],"about_ca_topic_score_codex":0.00018476204,"about_ca_topic_score_gemma":0.009194592,"teacher_disagreement_score":0.9436636,"about_ca_system_score_codex":0.0007706328,"about_ca_system_score_gemma":0.0061575915,"threshold_uncertainty_score":0.99947655},"labels":[],"label_agreement":null},{"id":"W4362681378","doi":"10.3138/cjpe.18.001","title":"Evaluation and Research: Differences and Similarities","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Generalization; Similarity (geometry); Relevance (law); Causality (physics); Psychology; Management science; Computer science; Knowledge management; Epistemology; Artificial intelligence; Political science","score_opus":0.7713106731453503,"score_gpt":0.617815743068949,"score_spread":0.15349493007640125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362681378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9844016,0.00381466,0.00014528737,0.0020574243,0.00042547498,0.0010164215,0.0000030095123,0.0000038579474,0.008132269],"genre_scores_gemma":[0.99806005,0.00008386681,0.0015337277,0.00007177858,0.00006955137,0.000060993905,0.0000016297314,0.000005473414,0.00011294165],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9910994,0.0030733766,0.0006434766,0.0002176959,0.004689834,0.0002762164],"domain_scores_gemma":[0.9909535,0.00068525743,0.00030426294,0.00018408304,0.007424066,0.00044883115],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08505214,0.0000954722,0.00018930787,0.0009065759,0.00043490867,0.0008093224,0.00019029075,0.00007599516,0.0016136573],"category_scores_gemma":[0.017424863,0.00007102668,0.00003748609,0.0006272737,0.00029546625,0.00068457256,0.000010928867,0.00024829633,0.0000116165675],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053831495,0.000018394889,0.07548368,0.0000039467272,0.000019205441,0.0000015763649,0.0021206224,0.00008591494,0.00001783085,0.0035500245,0.0010547277,0.9176387],"study_design_scores_gemma":[0.0016731175,0.0010282922,0.57746077,0.00008341578,0.00017597666,0.00011013792,0.012340396,0.071233734,0.000094366194,0.28318226,0.052406553,0.00021099592],"about_ca_topic_score_codex":0.00025552302,"about_ca_topic_score_gemma":0.011736539,"teacher_disagreement_score":0.9174277,"about_ca_system_score_codex":0.00023385437,"about_ca_system_score_gemma":0.0052477377,"threshold_uncertainty_score":0.999299},"labels":[],"label_agreement":null},{"id":"W4362683297","doi":"10.3138/cjpe.18.006","title":"Creating Logic Models Using Grounded Theory: A Case Example Demonstrating a Unique Approach to Logic Model Development","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Saskatchewan Health; University of Regina; York University","funders":"","keywords":"Grounded theory; Logic model; Parallels; Computer science; Process (computing); Context (archaeology); Theory; Management science; Sociology; Qualitative research; Engineering; Programming language","score_opus":0.7082610594770602,"score_gpt":0.5253019207443822,"score_spread":0.182959138732678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30181333,0.00011602683,0.6816635,0.00008456192,0.00012226493,0.0011809538,0.0000025206975,0.000011317328,0.015005538],"genre_scores_gemma":[0.62965894,6.562184e-7,0.3699659,0.00021267709,0.000027787566,0.00006851188,0.0000041377953,0.000010630881,0.000050750394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945899,0.0014632939,0.00131956,0.0003645955,0.0017879684,0.00047468176],"domain_scores_gemma":[0.99522233,0.00031470222,0.0007872159,0.000308201,0.0026359165,0.0007316361],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032538123,0.00021330996,0.000332524,0.0007966804,0.00076130405,0.00068918,0.00036075845,0.00011414633,0.000226161],"category_scores_gemma":[0.003184243,0.00016814722,0.000108490676,0.0010712212,0.00006584022,0.00088217686,0.000017745893,0.00026690259,0.0000082747265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011039259,0.000065883105,0.00061164494,0.0000058819624,0.000027640706,0.00003148451,0.0060218954,0.75925046,0.000047336584,0.06421748,0.000036135716,0.16967314],"study_design_scores_gemma":[0.00042494407,0.00012811202,0.00015276916,0.000038643215,0.00005301087,0.0008545106,0.0058831605,0.8255775,0.00006713719,0.16645424,0.00018153041,0.0001844195],"about_ca_topic_score_codex":0.000646872,"about_ca_topic_score_gemma":0.00750663,"teacher_disagreement_score":0.3278456,"about_ca_system_score_codex":0.0010024618,"about_ca_system_score_gemma":0.0111301085,"threshold_uncertainty_score":0.99620557},"labels":[],"label_agreement":null},{"id":"W4362683298","doi":"10.3138/cjpe.18.005","title":"Theory-Driven Approach for Facilitation of Planning Health Promotion or Other Programs","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Theory of change; Promotion (chess); Computer science; Process management; Management science; Chen; Development theory; Facilitation; Program Design Language; Program evaluation; Knowledge management; Business; Political science; Software engineering; Management; Engineering; Economic growth; Economics","score_opus":0.6171863065840855,"score_gpt":0.5681104673795182,"score_spread":0.04907583920456726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2739828,0.00093733193,0.7072621,0.0015223895,0.0010555977,0.010287403,0.00004612441,0.00002667373,0.0048795748],"genre_scores_gemma":[0.9244789,0.0000021980588,0.07481214,0.00007280456,0.00006228559,0.00024997938,0.00003701311,0.000012316959,0.00027236465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955315,0.0012374566,0.0011805331,0.00021195936,0.0015475574,0.00029097765],"domain_scores_gemma":[0.99514776,0.00026377055,0.0013065953,0.00021795776,0.0027465175,0.00031736938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026848048,0.00012178065,0.00030138882,0.0005609995,0.00020615573,0.00018011787,0.00026375864,0.000076729964,0.00051602634],"category_scores_gemma":[0.003919819,0.00008395931,0.00013801038,0.00069534546,0.0000956927,0.00049093796,0.000003270157,0.00012121721,0.0000050695667],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007747474,0.00020237862,0.013548168,0.00004203663,0.000042346946,3.379833e-7,0.0054621943,0.013586673,0.000023324137,0.0058019822,0.00061728247,0.9605958],"study_design_scores_gemma":[0.009235308,0.020836566,0.02638343,0.0005898032,0.0003240769,0.00013893595,0.037180733,0.6533473,0.00065769104,0.11861812,0.13191381,0.0007742297],"about_ca_topic_score_codex":0.00007410995,"about_ca_topic_score_gemma":0.0012749764,"teacher_disagreement_score":0.9598216,"about_ca_system_score_codex":0.00031816805,"about_ca_system_score_gemma":0.0059718234,"threshold_uncertainty_score":0.9996634},"labels":[],"label_agreement":null},{"id":"W4362683301","doi":"10.3138/cjpe.18.002","title":"The Language of Evaluation Theory: Insights Gained from an Empirical Study of Evaluation Theory and Practice","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Terminology; Ambiguity; Confusion; Epistemology; Field (mathematics); Vernacular; Empirical research; Psychology; Linguistics; Sociology; Computer science; Philosophy","score_opus":0.28713025319252194,"score_gpt":0.573348207363572,"score_spread":0.28621795417105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99082917,0.002529248,0.0006522984,0.00064329896,0.00050752814,0.0027933298,0.0000063550738,0.000004693772,0.002034072],"genre_scores_gemma":[0.99867654,0.000018277988,0.000896304,0.00012345577,0.00010621905,0.000116894225,0.000019598985,0.000012766227,0.000029933095],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96107405,0.029510027,0.0019053805,0.0003949662,0.006831573,0.0002839711],"domain_scores_gemma":[0.9824272,0.0054181195,0.0020024588,0.00060945103,0.009228049,0.0003147326],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14912175,0.00017197564,0.00034845047,0.0005437812,0.0003601666,0.0002875756,0.00034234495,0.000105205385,0.0011111647],"category_scores_gemma":[0.058101732,0.00010999613,0.000088328656,0.00088903145,0.00020951922,0.001153712,0.000015920818,0.00023668857,0.0000067504807],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004898968,0.0005716317,0.014977594,0.0000042381134,0.00021140769,0.0000038678136,0.06494115,0.0036191726,0.00034135638,0.0035388607,0.00032152343,0.9109793],"study_design_scores_gemma":[0.007901782,0.0051505384,0.2847515,0.00008693657,0.0023592599,0.00006159814,0.31856167,0.14750025,0.00068157626,0.22762607,0.004966112,0.0003527231],"about_ca_topic_score_codex":0.0005401118,"about_ca_topic_score_gemma":0.015662538,"teacher_disagreement_score":0.9106266,"about_ca_system_score_codex":0.0003327773,"about_ca_system_score_gemma":0.0058983997,"threshold_uncertainty_score":0.99980193},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98971146,0.00089225045,0.004442549,0.0002856838,0.00031287727,0.0017583409,0.000011537859,0.0000254371,0.002559841],"genre_scores_gemma":[0.98016983,0.000022129205,0.01890344,0.00026562446,0.00007222538,0.00037120678,0.00008825262,0.00002924781,0.00007803384],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99481297,0.0026282715,0.0006465243,0.00028267002,0.0006849041,0.00094467297],"domain_scores_gemma":[0.99721307,0.00032761507,0.00023784424,0.00024482724,0.0012111453,0.0007654915],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012080121,0.00022220728,0.0002549877,0.00044659225,0.0003669904,0.00018575878,0.00022003996,0.00022212685,0.0011146623],"category_scores_gemma":[0.0034221832,0.00020961501,0.00014992528,0.00039183357,0.00035773002,0.0002921734,0.00000969288,0.0003935033,0.00004081359],"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":[0.00021248103,0.00036835702,0.36477903,0.00005599491,0.00018276589,0.000070470815,0.042599343,0.000813033,0.00052537554,0.0006844535,0.0004898542,0.58921885],"study_design_scores_gemma":[0.0049616797,0.0019435446,0.92528284,0.00018851139,0.00038301662,0.0010525935,0.033304457,0.0033468853,0.003015428,0.023691438,0.0023925172,0.00043708787],"about_ca_topic_score_codex":0.0043055895,"about_ca_topic_score_gemma":0.020127628,"teacher_disagreement_score":0.5887818,"about_ca_system_score_codex":0.0011869752,"about_ca_system_score_gemma":0.0031716959,"threshold_uncertainty_score":0.9997985},"labels":[],"label_agreement":null},{"id":"W4362683309","doi":"10.3138/cjpe.18.004","title":"User-Friendly Evaluation in Community-Based Projects","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); User Friendly; Evaluation methods; Program evaluation; Process management; User group; Computer science; Psychology; Knowledge management; Management science; Business; Political science; Multimedia; Engineering","score_opus":0.4381303297538949,"score_gpt":0.5384420399654519,"score_spread":0.10031171021155705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362683309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795924,0.0004311537,0.0017802537,0.0012256767,0.001111118,0.002829241,0.0000052464497,0.000010656135,0.013014254],"genre_scores_gemma":[0.9932124,0.0000023417424,0.006118928,0.00031352916,0.000049832037,0.00018431534,0.000023800623,0.000012030699,0.000082811755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9876653,0.006523764,0.0013058477,0.00020187613,0.0039306204,0.00037259702],"domain_scores_gemma":[0.9926142,0.00056501303,0.0008216046,0.0005032487,0.0051001883,0.00039575036],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.080191724,0.000156272,0.00028376767,0.0015911781,0.000338777,0.00043058998,0.00055975735,0.0001143518,0.0025135258],"category_scores_gemma":[0.012645561,0.00012914008,0.0001235947,0.0018361423,0.000098672346,0.0008162135,0.000007129977,0.00053990004,0.00007816242],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041374737,0.00034127824,0.18425815,0.000018455381,0.000027384816,0.000009138679,0.003447199,0.045194414,0.000083566694,0.001726729,0.0063309846,0.7585213],"study_design_scores_gemma":[0.009504683,0.0029088908,0.29900858,0.00029958625,0.00026144358,0.00007841825,0.01220201,0.31170353,0.001010256,0.026072847,0.3363188,0.0006309707],"about_ca_topic_score_codex":0.001030756,"about_ca_topic_score_gemma":0.07812917,"teacher_disagreement_score":0.75789034,"about_ca_system_score_codex":0.001077034,"about_ca_system_score_gemma":0.017883226,"threshold_uncertainty_score":0.9983983},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99042344,0.0011702352,0.004152922,0.00089283305,0.00015360952,0.0009583646,0.000001749466,0.000013208529,0.0022336422],"genre_scores_gemma":[0.9104214,0.00011060764,0.089066006,0.000108110486,0.000083276485,0.0001049705,0.000011772567,0.00001740927,0.00007648504],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99781317,0.00085189415,0.00042130332,0.00012869308,0.00046264482,0.0003222987],"domain_scores_gemma":[0.99821043,0.00016218553,0.00024331179,0.000089872185,0.00075975974,0.0005344265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038718043,0.00012710929,0.00016674412,0.00032551074,0.00018114482,0.00011371387,0.00005823744,0.00010407958,0.00034096645],"category_scores_gemma":[0.0012318962,0.000105045554,0.00012680363,0.00020538452,0.0001857174,0.00017443344,0.000003378349,0.00020890635,0.000006270294],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000773661,0.00022641041,0.38055757,0.00007980436,0.00011064735,0.000049493196,0.003990812,0.00036428942,0.002050857,0.0003789913,0.00075905584,0.6113547],"study_design_scores_gemma":[0.007332285,0.0017346875,0.9357884,0.0012198441,0.0005018391,0.0011351533,0.00519301,0.0027606403,0.0074813166,0.011491019,0.025125377,0.00023640759],"about_ca_topic_score_codex":0.00019953493,"about_ca_topic_score_gemma":0.0011208679,"teacher_disagreement_score":0.6111183,"about_ca_system_score_codex":0.0013637536,"about_ca_system_score_gemma":0.003546012,"threshold_uncertainty_score":0.62904733},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6987752,0.007844245,0.00021860267,0.2794642,0.0010179067,0.00890539,0.0001719,0.000036965423,0.0035656171],"genre_scores_gemma":[0.97030616,0.0010470863,0.013722337,0.008278737,0.002643024,0.0018664505,0.0008553978,0.00007866257,0.0012021343],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934873,0.003302644,0.0009078562,0.00028495927,0.0011903472,0.0008269105],"domain_scores_gemma":[0.99306333,0.0013380222,0.00046826174,0.00024161907,0.0038674155,0.0010213767],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030343976,0.00013151586,0.0003545157,0.00053006806,0.002126364,0.00010885625,0.00022635997,0.00023173662,0.0015909821],"category_scores_gemma":[0.0022056962,0.00012571563,0.00007178009,0.00049130456,0.000120782206,0.00049822876,0.000013200609,0.0011026481,0.00002139998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012523253,0.000033225253,0.008390511,0.000081259175,0.000029805435,0.0000016682156,0.0047289925,0.000025740346,0.000003473952,0.0008652686,0.044330694,0.94138414],"study_design_scores_gemma":[0.0044381456,0.0013169571,0.13184556,0.000501283,0.00013575362,0.000010402385,0.0048283464,0.008199142,0.000001473055,0.13836181,0.7101584,0.00020270441],"about_ca_topic_score_codex":0.040169198,"about_ca_topic_score_gemma":0.16701347,"teacher_disagreement_score":0.9411814,"about_ca_system_score_codex":0.0027542394,"about_ca_system_score_gemma":0.047759604,"threshold_uncertainty_score":0.9993217},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.906102,0.0025357064,0.006609394,0.02818028,0.0011475924,0.0055377213,0.000008982188,0.00002108655,0.049857225],"genre_scores_gemma":[0.9968178,0.000030855164,0.0014897139,0.00087939616,0.00021766034,0.00024814764,0.0000116185665,0.000010404752,0.0002943481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927259,0.0019036739,0.001070485,0.00023899598,0.0037383107,0.0003226342],"domain_scores_gemma":[0.9963578,0.00029864506,0.00047141113,0.0004943398,0.002158007,0.00021978957],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.055985577,0.00014307412,0.00019689578,0.00036936963,0.00043829705,0.00061008986,0.0007941889,0.00008256025,0.0028639208],"category_scores_gemma":[0.0017450028,0.00007757838,0.000116386705,0.0012524283,0.00015370749,0.00077631744,0.000009864898,0.00039245005,0.00006454406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010162721,0.000025899697,0.0033982128,0.0000012228181,0.000008603717,7.460006e-7,0.0018037264,0.33691776,0.0000062827453,0.0004205022,0.0026007437,0.65480614],"study_design_scores_gemma":[0.00067431823,0.00010631445,0.038360965,0.000028688277,0.00007482855,0.000036540525,0.0011534067,0.9199799,0.000011081626,0.012149879,0.027322758,0.0001013732],"about_ca_topic_score_codex":0.0008463787,"about_ca_topic_score_gemma":0.028681673,"teacher_disagreement_score":0.65470475,"about_ca_system_score_codex":0.0005451822,"about_ca_system_score_gemma":0.0051731127,"threshold_uncertainty_score":0.9980476},"labels":[],"label_agreement":null},{"id":"W4362688961","doi":"10.3138/cjpe.015.002","title":"Towards Sustainability of Human Services: Assessing Community Self-Determination and Self-Reliance","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sustainability; Negotiation; Dependency (UML); Process (computing); Accountability; Process management; Relevance (law); Knowledge management; Human resources; Environmental resource management; Business; Psychology; Computer science; Political science; Ecology; Economics","score_opus":0.21373330538929033,"score_gpt":0.5275247607142796,"score_spread":0.3137914553249892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362688961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955047,0.00018897082,0.00009034753,0.00064046605,0.00013342645,0.0007077557,0.0000037996895,0.00002146449,0.0027090719],"genre_scores_gemma":[0.9947963,0.000019205252,0.004966537,0.00007627901,0.000057295016,0.00002248732,0.000009205914,0.000007662326,0.00004506275],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99528587,0.0016323125,0.0010582114,0.00016017698,0.0016352248,0.00022819801],"domain_scores_gemma":[0.993378,0.00022100205,0.00080801186,0.00037687164,0.004901634,0.00031451715],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021769814,0.0001270793,0.00028134466,0.00045447185,0.000532294,0.0004734396,0.00047158342,0.00009518245,0.0010439781],"category_scores_gemma":[0.0007016078,0.00010610817,0.00008533845,0.0007080653,0.00011327541,0.0013891844,0.000015868452,0.00030555,0.000006088695],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069345615,0.00017228718,0.04694076,0.00007873279,0.000019895817,0.0000018541263,0.007855395,0.0005829181,0.0000252687,0.0000747511,0.00006976557,0.9441714],"study_design_scores_gemma":[0.0012197276,0.0009657405,0.77202207,0.00014702736,0.00016472409,0.000038212496,0.008438433,0.18621986,0.00014238062,0.022892667,0.0075490237,0.00020014787],"about_ca_topic_score_codex":0.002617416,"about_ca_topic_score_gemma":0.014656929,"teacher_disagreement_score":0.9439713,"about_ca_system_score_codex":0.00060681056,"about_ca_system_score_gemma":0.004048246,"threshold_uncertainty_score":0.9998692},"labels":[],"label_agreement":null},{"id":"W4362689123","doi":"10.3138/cjpe.015.005","title":"The Redesign of Advanced Patrol Training for Police Constables in Ontario: Making Use of Evaluation to Maximize Organizational Effectiveness and Efficiency","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Nipissing University","funders":"","keywords":"Training (meteorology); Curriculum; Operations management; Business; Medical education; Engineering management; Psychology; Engineering; Medicine; Pedagogy","score_opus":0.31680565738729644,"score_gpt":0.48073747035389924,"score_spread":0.1639318129666028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99300396,0.00012520044,0.0037145182,0.00027753168,0.00017102533,0.0024288425,0.000011003679,0.0000019185125,0.00026602065],"genre_scores_gemma":[0.99198645,0.000005172301,0.0077991593,0.00003988863,0.000019298292,0.000114979244,0.0000059578188,0.000007468163,0.000021612987],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99628586,0.0008294433,0.00097507157,0.00017601116,0.0015035659,0.00023006475],"domain_scores_gemma":[0.99387634,0.0017704676,0.00060130196,0.00016621906,0.0034543118,0.00013138301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022331176,0.000098894765,0.00026175077,0.00046052574,0.0002064184,0.00016540936,0.000196065,0.000051594256,0.0004931854],"category_scores_gemma":[0.004553163,0.00007318303,0.000057383626,0.000783266,0.00010143036,0.00054651557,0.000006838059,0.000096938435,0.0000011045432],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022216265,0.000029199276,0.03297231,0.0000072066055,0.000016783972,2.2229499e-7,0.0057278415,0.090294905,0.0003624554,0.00040312335,0.000026886923,0.8699369],"study_design_scores_gemma":[0.00394412,0.0012573169,0.80906373,0.00037126942,0.00014499672,0.000021049356,0.004784106,0.16701293,0.000534329,0.009233293,0.0034422132,0.00019067236],"about_ca_topic_score_codex":0.005986917,"about_ca_topic_score_gemma":0.33350575,"teacher_disagreement_score":0.8697462,"about_ca_system_score_codex":0.00048066917,"about_ca_system_score_gemma":0.0068638874,"threshold_uncertainty_score":0.99876624},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98759186,0.0015515649,0.0039308565,0.00057210756,0.0011986016,0.0021343513,0.0000034044308,0.000052111594,0.0029651318],"genre_scores_gemma":[0.99411756,0.000021302762,0.0047540856,0.00004375757,0.0007649296,0.00013990181,0.000022805982,0.000025687896,0.00010995022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722713,0.00081812637,0.00072304206,0.00014005868,0.00045956136,0.0006320727],"domain_scores_gemma":[0.99698895,0.0001904974,0.0005677513,0.00017663909,0.0014544675,0.0006217072],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0046925624,0.00014386796,0.00025374026,0.0003916575,0.00062461285,0.00007676782,0.00014423807,0.00015869603,0.0010477221],"category_scores_gemma":[0.0005134159,0.00011667722,0.00017739141,0.00054007745,0.00005557312,0.00031245698,0.000006831543,0.0005116026,0.0000349986],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007827843,0.000070554466,0.05436247,0.000032643686,0.000077142206,0.00003270012,0.0055985204,0.026094973,0.0000123077525,0.00022038222,0.0016273458,0.9117927],"study_design_scores_gemma":[0.006299471,0.0041837324,0.15167509,0.0019306963,0.0015802052,0.00038884053,0.025106717,0.7016858,0.000025857174,0.042732745,0.06332676,0.0010641217],"about_ca_topic_score_codex":0.0053628627,"about_ca_topic_score_gemma":0.0064497585,"teacher_disagreement_score":0.9107286,"about_ca_system_score_codex":0.0008460808,"about_ca_system_score_gemma":0.0041212523,"threshold_uncertainty_score":0.9998655},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9272921,0.056222815,0.000066697605,0.0018455317,0.0033611995,0.0027155585,0.0000023795965,0.000028756698,0.008464937],"genre_scores_gemma":[0.9874509,0.00059328455,0.010178061,0.00029580534,0.0006329473,0.0007754588,0.000015432002,0.00002313017,0.000034997287],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99609494,0.0014574644,0.00091593387,0.00032156415,0.0005742399,0.0006358423],"domain_scores_gemma":[0.9979267,0.00015576767,0.00054475095,0.0002598284,0.0005304636,0.0005824571],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0090885805,0.00018436974,0.00036843948,0.00077096064,0.000121324825,0.00005516914,0.000305823,0.00022067993,0.0010962903],"category_scores_gemma":[0.00006587427,0.00016483855,0.00016672479,0.0009507188,0.000041617302,0.00018162312,0.000009211035,0.00040893958,0.000048062982],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010251826,0.00027724984,0.0155909,0.000037821515,0.0000360779,0.000050269882,0.007708329,0.000051904277,0.000002302996,0.0002582777,0.00047303754,0.9754113],"study_design_scores_gemma":[0.014495781,0.029128341,0.43852118,0.0005514355,0.0011330523,0.0035172517,0.27103126,0.0036577228,0.00001073043,0.02944952,0.20698753,0.001516203],"about_ca_topic_score_codex":0.009369401,"about_ca_topic_score_gemma":0.11205541,"teacher_disagreement_score":0.97389513,"about_ca_system_score_codex":0.00044142987,"about_ca_system_score_gemma":0.0011245443,"threshold_uncertainty_score":0.99981683},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95541114,0.0011349735,0.000031263622,0.0061855675,0.0019340793,0.0013466394,0.000004162493,0.00002532768,0.03392684],"genre_scores_gemma":[0.99762404,0.00008775828,0.00017701344,0.00067069806,0.00078151317,0.000112633104,0.000008599795,0.00001754087,0.0005201919],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99803174,0.00042686847,0.00052574766,0.000119996694,0.0004426674,0.0004529761],"domain_scores_gemma":[0.9982584,0.00012128125,0.00041408866,0.00013508374,0.00074827066,0.00032288823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020733734,0.00011505039,0.00019994669,0.0002754666,0.0008475321,0.000025062745,0.00014992201,0.00010754735,0.0006986527],"category_scores_gemma":[0.00035420948,0.0000978333,0.00007172176,0.00031703588,0.00004849497,0.00014344536,0.000008206395,0.00048667873,0.00010881935],"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":[0.00003488461,0.000023054135,0.6374558,0.000010660924,0.000032912543,0.000019197752,0.0015017291,0.00004155115,0.0000044444578,0.00033493768,0.00986618,0.35067463],"study_design_scores_gemma":[0.0012094234,0.00039496188,0.6589914,0.00063258986,0.00005090684,0.0000090421,0.0010256516,0.00016274807,0.0000036206404,0.0018081343,0.3355814,0.00013015121],"about_ca_topic_score_codex":0.0009971253,"about_ca_topic_score_gemma":0.04563102,"teacher_disagreement_score":0.35054448,"about_ca_system_score_codex":0.00051462906,"about_ca_system_score_gemma":0.0013204607,"threshold_uncertainty_score":0.9717837},"labels":[],"label_agreement":null},{"id":"W4362689223","doi":"10.3138/cjpe.015.008","title":"Focusing on Inputs, Outputs, and Outcomes: Are International Approaches to Performance Management Really so Different?","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Logic model; Process (computing); Service (business); Focus (optics); Key (lock); Performance measurement; Process management; Performance management; Business; Public relations; Knowledge management; Computer science; Political science; Public administration; Marketing; Computer security","score_opus":0.45225536612016,"score_gpt":0.4616739906963755,"score_spread":0.009418624576215506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9738167,0.000079568184,0.00044482815,0.013404128,0.0006354857,0.000942429,0.000007574315,0.0000104063865,0.01065886],"genre_scores_gemma":[0.9952449,0.000043310127,0.0024801618,0.00095521315,0.00015077698,0.000062080544,0.000010306852,0.000011201316,0.0010420338],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961743,0.00022621163,0.0007882351,0.00028594548,0.002253811,0.0002715188],"domain_scores_gemma":[0.99813396,0.000095475785,0.00040248453,0.00027931502,0.00061419606,0.00047459124],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005137632,0.00017081505,0.00025816515,0.00085177185,0.0002836425,0.00084743684,0.0004923974,0.000059467297,0.001605435],"category_scores_gemma":[0.0003240404,0.00012288042,0.000086238484,0.00038001256,0.0000689055,0.00057471247,0.000021484235,0.00018052352,0.00011408843],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034892808,0.000049524628,0.09814749,0.0000052499317,0.00004415366,0.0000043637683,0.00079351617,0.0022722369,0.0000017309324,0.00039764386,0.0007631455,0.89748603],"study_design_scores_gemma":[0.0010714835,0.00046925203,0.9030715,0.00014581757,0.000062072686,0.000020528758,0.0006967255,0.02006915,0.00004521054,0.0015044288,0.07265265,0.00019112925],"about_ca_topic_score_codex":0.00005889707,"about_ca_topic_score_gemma":0.002872105,"teacher_disagreement_score":0.89729494,"about_ca_system_score_codex":0.00040058402,"about_ca_system_score_gemma":0.00048797447,"threshold_uncertainty_score":0.9993072},"labels":[],"label_agreement":null},{"id":"W4362689327","doi":"10.3138/cjpe.16.001","title":"Using the Right Tools to Answer the Right Questions: The Importance of Evaluative Research Techniques for Health Services Evaluation Research in the 21st Century","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Rubric; Causal inference; Affect (linguistics); Accountability; Health care; Psychology; Causal model; Inference; Health policy; Health services research; Applied psychology; Public relations; Social psychology; Management science; Political science; Computer science; Medicine; Economics; Mathematics education; Econometrics","score_opus":0.6435564373162587,"score_gpt":0.6614983899363868,"score_spread":0.0179419526201281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6673424,0.014679478,0.0016839638,0.2576538,0.0018850473,0.04564247,0.00008708846,0.000020246403,0.011005496],"genre_scores_gemma":[0.9934181,0.00023138867,0.0021387085,0.0017882604,0.00052093837,0.0018239459,0.00001858901,0.000015935875,0.000044126446],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9695797,0.017033111,0.0018994437,0.00038677393,0.010301925,0.00079907366],"domain_scores_gemma":[0.97614807,0.004652134,0.0010318585,0.0010433125,0.016884169,0.00024043408],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.2995536,0.0001744248,0.00030055482,0.0011506716,0.0021329995,0.0010351166,0.002263509,0.00010440617,0.000532556],"category_scores_gemma":[0.006347903,0.00007342146,0.00015309884,0.0047508557,0.0005245109,0.00085591816,0.000057253812,0.0008740616,0.000011352426],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120367265,0.00016515511,0.008165993,0.00002636781,0.00003808595,0.000001594023,0.027062943,0.0033206597,0.000048245114,0.010918362,0.00568143,0.9444508],"study_design_scores_gemma":[0.0012017466,0.002169,0.09937133,0.00092176395,0.00016365583,0.00011224467,0.14931108,0.1386855,0.00018859802,0.16225943,0.4453416,0.00027406687],"about_ca_topic_score_codex":0.0025920072,"about_ca_topic_score_gemma":0.12625095,"teacher_disagreement_score":0.94417673,"about_ca_system_score_codex":0.0014834844,"about_ca_system_score_gemma":0.016393794,"threshold_uncertainty_score":0.9991661},"labels":[],"label_agreement":null},{"id":"W4362689335","doi":"10.3138/cjpe.16.004","title":"Accountability, Rationality, and New Structures of Governance: Making Room for Political Rationality","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Accountability; Rationality; Agency (philosophy); Politics; Bureaucracy; Law and economics; Corporate governance; Technocracy; Parliament; Mandate; Political science; Sociology; Economics; Public relations; Public administration; Positive economics; Law; Social science; Finance","score_opus":0.518764035540208,"score_gpt":0.5838040393902938,"score_spread":0.06504000385008579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9587135,0.00075046043,0.017425885,0.018275108,0.0008805572,0.0018801435,0.000075839016,0.00000711474,0.001991415],"genre_scores_gemma":[0.99005574,0.0000061068536,0.009176132,0.00029610493,0.00033884545,0.000023163393,0.000017431232,0.0000057841676,0.000080692414],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99622977,0.00029233968,0.0010486916,0.00019855537,0.0019860158,0.00024465693],"domain_scores_gemma":[0.99484307,0.00051295763,0.0007537269,0.00020709138,0.0033144292,0.00036874964],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009857579,0.000105565596,0.00024902902,0.00019730497,0.00016745194,0.00029628226,0.00028831873,0.00007965692,0.0014891978],"category_scores_gemma":[0.0051947,0.00008441537,0.00011163592,0.0003666541,0.00009871594,0.00070448144,0.00001528975,0.00011485701,0.0000026391867],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098642566,0.000048626145,0.290163,0.00001837983,0.000042580617,9.494343e-7,0.00061955,0.001679335,0.000059460916,0.14609443,0.0046635508,0.5565115],"study_design_scores_gemma":[0.0010180863,0.00023773861,0.59559566,0.000028350856,0.000060504022,0.00004140383,0.0005493758,0.018194448,0.00007139096,0.36096105,0.023145935,0.00009605137],"about_ca_topic_score_codex":0.0008202045,"about_ca_topic_score_gemma":0.020923853,"teacher_disagreement_score":0.55641544,"about_ca_system_score_codex":0.00035210367,"about_ca_system_score_gemma":0.0064886487,"threshold_uncertainty_score":0.99942356},"labels":[],"label_agreement":null},{"id":"W4362689338","doi":"10.3138/cjpe.015.006","title":"Contributions of Evaluation Research to the Development of Community Policing in a Canadian City","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Windsor; Service (business); Community service; Population; Sociology; Political science; Business; Demography; Public relations; Marketing","score_opus":0.6536296981549493,"score_gpt":0.636219151212957,"score_spread":0.01741054694199229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362689338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988159,0.00010697722,0.00010066715,0.005388503,0.00014564348,0.001745166,0.000023157094,0.000001445147,0.0043294528],"genre_scores_gemma":[0.99864787,0.000002943628,0.0010105851,0.00011459867,0.000048698195,0.00010490252,0.000016963759,0.0000049387218,0.00004849549],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.989585,0.0044071106,0.0015901558,0.000118819,0.0038173643,0.00048156016],"domain_scores_gemma":[0.9885776,0.00068961625,0.0004167686,0.0004337726,0.009257699,0.0006245098],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1334795,0.00009090618,0.0002555288,0.0018229575,0.000640917,0.00012314023,0.00068127975,0.000079326346,0.0033177678],"category_scores_gemma":[0.009964478,0.00006673517,0.00007037597,0.0026962669,0.00014311478,0.00029361848,0.000016536,0.0005015467,0.00003748664],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002111918,0.000061865285,0.033197436,0.0000037597504,0.000018401422,4.2022145e-7,0.02147956,0.012250973,0.00007444043,0.00019558136,0.0011731385,0.9315233],"study_design_scores_gemma":[0.0010089594,0.00039111316,0.9188525,0.00014264627,0.00003966269,0.000009025708,0.0074231825,0.031827457,0.00080336374,0.0051801926,0.03421356,0.000108327324],"about_ca_topic_score_codex":0.44661522,"about_ca_topic_score_gemma":0.9896937,"teacher_disagreement_score":0.93141496,"about_ca_system_score_codex":0.002256378,"about_ca_system_score_gemma":0.035862356,"threshold_uncertainty_score":0.998375},"labels":[],"label_agreement":null},{"id":"W4366382532","doi":"10.3138/cjpe.31132","title":"Moving Beyond the Buzzword: A Framework for Teaching Culturally Responsive Approaches to Evaluation","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conceptual framework; Competence (human resources); Cultural competence; Sociology; Domain (mathematical analysis); Knowledge management; Computer science; Engineering ethics; Psychology; Pedagogy; Social psychology; Social science; Engineering","score_opus":0.6407724104552023,"score_gpt":0.5597165071488638,"score_spread":0.0810559033063385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366382532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7964171,0.0006996965,0.06172205,0.11679335,0.0039230823,0.010497101,0.000029389254,0.00001937502,0.009898834],"genre_scores_gemma":[0.9442305,0.0000020867046,0.053669736,0.0006807805,0.00062992965,0.0005111801,0.000010829728,0.000014514366,0.00025042123],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99375,0.0012998708,0.0009640276,0.00032071312,0.0032831854,0.00038220125],"domain_scores_gemma":[0.9916731,0.001200062,0.0015481611,0.00085052446,0.0042589023,0.0004692256],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06413532,0.00017211442,0.00027153068,0.00047589108,0.0025056505,0.002436947,0.0014618158,0.000120825745,0.00044665832],"category_scores_gemma":[0.05975384,0.00010669613,0.00021011101,0.00027187346,0.00015377066,0.0012010831,0.000033656175,0.00042033644,0.000043056185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063470805,0.000021310096,0.0030200302,0.0000031741024,0.00004120647,8.601991e-7,0.0076990915,0.0064308494,0.000034300905,0.012181978,0.0043913624,0.9661124],"study_design_scores_gemma":[0.0017336969,0.001117979,0.1500711,0.0002102308,0.0004454044,0.000045278404,0.01645248,0.3153688,0.00016640026,0.42197177,0.092011586,0.00040529348],"about_ca_topic_score_codex":0.00029378763,"about_ca_topic_score_gemma":0.012848757,"teacher_disagreement_score":0.96570706,"about_ca_system_score_codex":0.00061139866,"about_ca_system_score_gemma":0.005132222,"threshold_uncertainty_score":0.99879295},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920569,0.001638828,0.000049802813,0.00033289424,0.0004485065,0.0006552109,7.828184e-7,0.000013519744,0.0048035416],"genre_scores_gemma":[0.9913177,0.000011176713,0.0076431097,0.00012342827,0.00032289381,0.000094492745,0.00001675565,0.000013624069,0.00045681163],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99830866,0.00015649799,0.0005286598,0.00013991987,0.0005501577,0.00031610514],"domain_scores_gemma":[0.9985724,0.000028993923,0.00028504035,0.00011465236,0.0006643915,0.00033453837],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036050284,0.00013277578,0.0001626475,0.00041855295,0.00027262917,0.0000884753,0.00014901727,0.00008272701,0.003302505],"category_scores_gemma":[0.00008429301,0.00012150942,0.000035297522,0.0001771197,0.00008810236,0.00028827385,0.0000072657413,0.00018022647,0.00019890505],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022207447,0.000024265159,0.05446751,0.000009417151,0.000049363538,0.0000018339072,0.010535739,0.00013487869,0.00001062258,0.0000918673,0.0010967823,0.9335555],"study_design_scores_gemma":[0.001174473,0.00035330077,0.7398441,0.00006487069,0.00007650415,0.00010007215,0.0007563294,0.008319708,0.00009655191,0.000040400115,0.248984,0.00018971825],"about_ca_topic_score_codex":0.0000529835,"about_ca_topic_score_gemma":0.0029176825,"teacher_disagreement_score":0.9333658,"about_ca_system_score_codex":0.00035433733,"about_ca_system_score_gemma":0.001870627,"threshold_uncertainty_score":0.9976086},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50284755,0.0030113126,0.0008881862,0.3570749,0.052848622,0.0030927253,0.000009124288,0.00009523615,0.080132365],"genre_scores_gemma":[0.95836884,0.000014604697,0.001042798,0.00010391779,0.040220365,0.000009347612,0.0000027577335,0.0000049820883,0.00023238566],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888134,0.00020692477,0.00017436515,0.00006280708,0.0004903344,0.00018422092],"domain_scores_gemma":[0.9986177,0.00002244585,0.00016798885,0.000059321923,0.000840993,0.00029155082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040215007,0.00004160837,0.00006428521,0.0001453124,0.00038664506,0.00015187844,0.00012284996,0.00007188845,0.0007021888],"category_scores_gemma":[0.0007569632,0.000041028587,0.00004484815,0.00014332954,0.0001312814,0.00039981218,0.0000016390192,0.00018684533,0.000025786521],"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":[0.0000027981703,0.000023802022,0.00025085735,0.0000011729697,0.000012261485,0.0000013104534,0.0065888762,0.00009813819,0.0000358243,0.011582469,0.05436964,0.9270328],"study_design_scores_gemma":[0.00013720867,0.00007153009,0.0010898088,0.0000074835375,0.000025392894,0.000004025781,0.00077398785,0.00022660205,0.00003878163,0.0039247675,0.99365115,0.00004925917],"about_ca_topic_score_codex":0.003574546,"about_ca_topic_score_gemma":0.14998132,"teacher_disagreement_score":0.9392815,"about_ca_system_score_codex":0.0005817081,"about_ca_system_score_gemma":0.0033549475,"threshold_uncertainty_score":0.8655293},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9016391,0.0014307873,0.002162075,0.050581753,0.0015848686,0.001220378,0.00000988321,0.00004850238,0.04132268],"genre_scores_gemma":[0.9931814,0.000060647937,0.005387547,0.00016733696,0.0008833431,0.000029259667,0.0000035014812,0.0000046384616,0.0002823378],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981368,0.00031288975,0.0003107133,0.00011304857,0.00076815696,0.00035834368],"domain_scores_gemma":[0.99823713,0.00005514564,0.000302952,0.00007782953,0.0008924066,0.0004345448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003851661,0.00007655429,0.00011390478,0.00013262089,0.0011536367,0.00020580506,0.00026992103,0.00009694066,0.0005765573],"category_scores_gemma":[0.0016322038,0.00007170142,0.000089082714,0.0007239261,0.0006395305,0.0008805754,0.0000048808797,0.00013327795,0.000037043268],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004667985,0.00003451109,0.006394693,0.000001809833,0.000012860403,0.0000035397,0.018730497,0.0015353992,0.000019873618,0.04000868,0.0018957882,0.9313577],"study_design_scores_gemma":[0.0012866724,0.00056356983,0.40797183,0.00017384668,0.0002654885,0.00002664239,0.024973402,0.007356085,0.00009276958,0.17102027,0.38577792,0.0004915046],"about_ca_topic_score_codex":0.096510574,"about_ca_topic_score_gemma":0.7209419,"teacher_disagreement_score":0.9308662,"about_ca_system_score_codex":0.0011297668,"about_ca_system_score_gemma":0.00838475,"threshold_uncertainty_score":0.9972368},"labels":[],"label_agreement":null},{"id":"W4366383480","doi":"10.3138/cjpe.20.008","title":"Certification, Credentialing, Licensure, Competencies, and the Like: Issues Confronting the Field of Evaluation","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credentialing; Accreditation; Licensure; Certification; Competence (human resources); Engineering ethics; Medical education; Professional certification (computer technology); Framing (construction); Certification and Accreditation; Professional association; Psychology; Political science; Medicine; Public relations; Engineering; Law; Social psychology","score_opus":0.2723915791832564,"score_gpt":0.5250140899096121,"score_spread":0.25262251072635566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383480","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8244046,0.021209618,0.0029290023,0.13813572,0.0021279568,0.004691288,0.000009240871,0.000015408616,0.006477189],"genre_scores_gemma":[0.9967683,0.000082372215,0.001855139,0.000705869,0.00030977477,0.00005960799,0.000006462632,0.000005838889,0.00020661255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994516,0.0013542504,0.001154233,0.00016055521,0.0026330575,0.00018186166],"domain_scores_gemma":[0.99185896,0.0010577325,0.0012241112,0.00036020926,0.005356948,0.00014206761],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03997838,0.00010218194,0.00022630607,0.0002618588,0.00042943726,0.00047157385,0.0004467758,0.00006298137,0.0015731286],"category_scores_gemma":[0.0076117963,0.00005508857,0.00010463037,0.00049164117,0.0002844933,0.00047590444,0.0000173508,0.00019388313,0.000015672573],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039603885,0.000022825463,0.007507359,0.0000039874835,0.000048282353,2.1112133e-7,0.0058557703,0.0037924263,0.000053966734,0.0019443509,0.016343147,0.9643881],"study_design_scores_gemma":[0.0024821816,0.0002587298,0.07593752,0.00007048294,0.00040191546,0.00003739935,0.0061757355,0.57144344,0.0005000144,0.008750696,0.33379665,0.000145262],"about_ca_topic_score_codex":0.0014878527,"about_ca_topic_score_gemma":0.024798421,"teacher_disagreement_score":0.9642428,"about_ca_system_score_codex":0.00012728287,"about_ca_system_score_gemma":0.0022657458,"threshold_uncertainty_score":0.9993396},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9616924,0.0023000522,0.0008823932,0.022295294,0.00036669304,0.0007583276,0.000016286349,0.000049357204,0.011639204],"genre_scores_gemma":[0.99248785,0.00017157172,0.005959692,0.000273877,0.00071793084,0.000049249848,0.00004405874,0.000015656067,0.00028012332],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9975366,0.0010566284,0.0003271834,0.00013700435,0.0005182043,0.00042439898],"domain_scores_gemma":[0.9978032,0.00018875096,0.00024517256,0.00010357742,0.0011335482,0.00052574824],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005082565,0.00011166439,0.00016149333,0.00024496604,0.0014337037,0.00020421617,0.00023168986,0.00018485515,0.00013637941],"category_scores_gemma":[0.0025592756,0.00011900965,0.000110010864,0.00033125823,0.00029670005,0.00028733606,0.000005051049,0.00041281804,0.0000045867273],"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":[0.00006306941,0.0007335959,0.25975585,0.000098210265,0.00016913524,0.00012003679,0.385184,0.003469649,0.0010643877,0.050571512,0.044266045,0.25450453],"study_design_scores_gemma":[0.0063846274,0.00092030375,0.49168053,0.0019169317,0.0008891421,0.0013686169,0.18808763,0.008616906,0.0017194982,0.060609877,0.23632386,0.0014820776],"about_ca_topic_score_codex":0.022428883,"about_ca_topic_score_gemma":0.1133516,"teacher_disagreement_score":0.25302246,"about_ca_system_score_codex":0.00045606997,"about_ca_system_score_gemma":0.014489037,"threshold_uncertainty_score":0.9998663},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.595125,0.001953396,0.37301245,0.017843772,0.0012405079,0.0066452385,0.00008539317,0.000028931863,0.0040653134],"genre_scores_gemma":[0.97413033,0.0000048866254,0.025012542,0.00008629546,0.00035209768,0.00019727477,0.00006055218,0.000010510193,0.00014548791],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99396026,0.0006707037,0.001454308,0.00032847858,0.0032087944,0.00037746882],"domain_scores_gemma":[0.9891877,0.0009181516,0.0012800301,0.0003837719,0.007969437,0.0002608749],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03017244,0.00014714901,0.00044843956,0.0018927362,0.0003641576,0.00078385085,0.00037691678,0.0001283591,0.0013833622],"category_scores_gemma":[0.011750337,0.00011890066,0.0006841536,0.003034598,0.000076416436,0.0007579318,0.000008990465,0.00016940109,0.00003168434],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004678128,0.00004921321,0.022381304,0.0000016455007,0.00029902335,0.0000057014977,0.00015303183,0.09042046,0.000010131666,0.0015495571,0.0034420528,0.8816411],"study_design_scores_gemma":[0.0011981662,0.00020705948,0.111472644,0.000014933579,0.005222896,0.00002847915,0.00042401126,0.73064756,0.000024174758,0.11676051,0.033812772,0.00018677425],"about_ca_topic_score_codex":0.0011134084,"about_ca_topic_score_gemma":0.08802898,"teacher_disagreement_score":0.88145435,"about_ca_system_score_codex":0.00068627513,"about_ca_system_score_gemma":0.0032016924,"threshold_uncertainty_score":0.9995295},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61384934,0.010692255,0.024846807,0.01314568,0.03622142,0.007922642,0.000048733793,0.00028134324,0.29299176],"genre_scores_gemma":[0.9857288,0.00003809588,0.0083767045,0.000318607,0.0044672103,0.0002871578,0.000012905542,0.00002308127,0.0007474208],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990948,0.00009969183,0.00028779716,0.00009839196,0.00022620153,0.00019312729],"domain_scores_gemma":[0.99881285,0.000020041547,0.00021079948,0.00019886864,0.00046659578,0.00029083726],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008145393,0.00007005995,0.0001013675,0.00020153163,0.00013573247,0.00002016004,0.00017621566,0.000092803595,0.0025132005],"category_scores_gemma":[0.000039343944,0.00006597102,0.00007836028,0.00021674529,0.00008099614,0.000078127276,0.0000012079823,0.00017007707,0.00004929161],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012307582,0.00007217121,0.0030324426,0.0000012692099,0.000041573,0.000018433526,0.0010501556,0.000004825593,0.00007148409,0.001588481,0.5490004,0.44510648],"study_design_scores_gemma":[0.0005486493,0.00034216244,0.044187576,0.000017596032,0.00003388938,0.00035939625,0.00011600798,0.00011313893,0.00003514404,0.0028005322,0.9513445,0.0001014425],"about_ca_topic_score_codex":0.0007355751,"about_ca_topic_score_gemma":0.0016076542,"teacher_disagreement_score":0.44500503,"about_ca_system_score_codex":0.00013786921,"about_ca_system_score_gemma":0.0007602046,"threshold_uncertainty_score":0.99839866},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9073221,0.016516905,0.012199761,0.015848521,0.0018371653,0.042763498,0.00024144702,0.000030381947,0.0032402314],"genre_scores_gemma":[0.9648609,0.000020677617,0.025016326,0.007462824,0.00019722884,0.0020720044,0.0002844714,0.000047977454,0.000037554357],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99075663,0.0044165473,0.0021679625,0.00028098223,0.0016187612,0.0007591269],"domain_scores_gemma":[0.9912828,0.0018012656,0.0017677275,0.000555601,0.004287545,0.000305067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019359535,0.0002481388,0.0008028258,0.00059493224,0.0010579602,0.00001805457,0.0005410512,0.00023895659,0.000089043315],"category_scores_gemma":[0.0015467318,0.00016676773,0.00024652298,0.0006481147,0.00014260708,0.00022735784,0.000034627188,0.0011741716,0.0000015224118],"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":[0.0013048317,0.00014816887,0.10613336,0.0025369367,0.00012797958,0.0000026546988,0.3497515,0.026325217,0.000020086261,0.0024201581,0.0053255023,0.5059036],"study_design_scores_gemma":[0.016695905,0.010365794,0.74593365,0.005252667,0.0015580067,0.000016721175,0.12178222,0.022081535,0.00018137129,0.021790767,0.053255495,0.0010858647],"about_ca_topic_score_codex":0.06724242,"about_ca_topic_score_gemma":0.6038181,"teacher_disagreement_score":0.6398003,"about_ca_system_score_codex":0.012649068,"about_ca_system_score_gemma":0.15874173,"threshold_uncertainty_score":0.9911412},"labels":[],"label_agreement":null},{"id":"W4366383880","doi":"10.3138/cjpe.026.005","title":"Evaluation-Capacity Building: The Three Sides of the Coin","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Gautama Buddha; Metaphor; Context (archaeology); Field (mathematics); Intervention (counseling); Process (computing); Computer science; Psychology; Linguistics; Mathematics; History; Philosophy; Buddhism; Archaeology","score_opus":0.6801887921330342,"score_gpt":0.5042779477622058,"score_spread":0.17591084437082838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366383880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98361266,0.00050078414,0.0012146707,0.0027541795,0.001448625,0.0018623952,0.0000071673626,0.0000047655426,0.00859474],"genre_scores_gemma":[0.9969236,0.0000035731566,0.0026648482,0.00016913988,0.00012386947,0.00006805711,9.645311e-7,0.0000076008537,0.000038322887],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99191195,0.0015387897,0.0011193379,0.00017313682,0.005012187,0.00024461903],"domain_scores_gemma":[0.98971075,0.00040139828,0.0013879434,0.0006073003,0.0076686232,0.00022399498],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052748356,0.00012366741,0.00021537775,0.00031581274,0.00039260933,0.00018192171,0.0011853719,0.00007413497,0.0043214606],"category_scores_gemma":[0.009290858,0.00006218052,0.00022315515,0.0010248885,0.00034287278,0.00049777026,0.000027412529,0.00026774805,0.000029466826],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014671591,0.000060486756,0.108337305,0.0000033427202,0.00007606901,5.210546e-7,0.0040113735,0.0020295605,0.00014072249,0.004089684,0.002350601,0.8788857],"study_design_scores_gemma":[0.00078568404,0.0003252918,0.73602027,0.00006129213,0.0003721656,0.000033124954,0.0014848546,0.090533406,0.0013248635,0.16018963,0.008746546,0.00012289232],"about_ca_topic_score_codex":0.0015430005,"about_ca_topic_score_gemma":0.06333101,"teacher_disagreement_score":0.8787628,"about_ca_system_score_codex":0.00033430333,"about_ca_system_score_gemma":0.007134706,"threshold_uncertainty_score":0.9990543},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863861,0.00043309186,0.0001307586,0.0032661473,0.00035073556,0.0011171758,0.0000069233283,0.0000056056906,0.008303456],"genre_scores_gemma":[0.99842656,0.00000453455,0.000923226,0.00032745075,0.00019019948,0.000058927606,0.0000021388103,0.000008490061,0.000058456528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973706,0.0006837848,0.00044596838,0.00012417743,0.00077256764,0.00060292054],"domain_scores_gemma":[0.99763656,0.00007385884,0.00017752522,0.00010397788,0.0010216876,0.0009863739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007299644,0.000079047066,0.00016837884,0.00019405998,0.00026390323,0.00007778414,0.00018454001,0.00008483973,0.0005272962],"category_scores_gemma":[0.001845941,0.00008258827,0.000058584843,0.0004322617,0.00008625669,0.00032774755,0.0000050234657,0.00015540038,0.00000779],"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":[0.000050394377,0.000067248526,0.528498,0.000020144791,0.000034595643,0.000014265929,0.020158067,0.0008053372,0.0001523378,0.00667472,0.0021263915,0.44139853],"study_design_scores_gemma":[0.0010456474,0.00037239498,0.96181124,0.0002729239,0.00005510877,0.000007106756,0.0031887935,0.007352499,0.00024438524,0.0038863216,0.021584567,0.00017902676],"about_ca_topic_score_codex":0.9361812,"about_ca_topic_score_gemma":0.990752,"teacher_disagreement_score":0.4412195,"about_ca_system_score_codex":0.002642865,"about_ca_system_score_gemma":0.008521262,"threshold_uncertainty_score":0.9970995},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935269,0.00006830118,0.0020621151,0.002152025,0.001119057,0.0008107621,0.0000059215977,0.000011788576,0.00024313206],"genre_scores_gemma":[0.9839249,0.0000011233257,0.01584872,0.000017727638,0.00015801332,0.000022964829,0.000002704773,0.000008282856,0.000015536296],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99879104,0.0001448215,0.0004952665,0.000061786515,0.00036507676,0.0001420324],"domain_scores_gemma":[0.9975889,0.00014968794,0.0006292315,0.00010841827,0.001394071,0.00012973868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022337777,0.000082109174,0.00017014366,0.0001579463,0.00013884065,0.000050689745,0.00012753661,0.00007100997,0.0001726711],"category_scores_gemma":[0.0022017183,0.00005642654,0.0000859882,0.00018997659,0.00015336901,0.00017120547,0.0000018939304,0.00023689623,0.0000015764459],"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":[0.000020690213,0.000049387527,0.832442,0.000021356804,0.000117506046,0.0000018782422,0.0010228311,0.0010011637,0.002763961,0.019227656,0.00030845802,0.14302312],"study_design_scores_gemma":[0.0023108353,0.0004525016,0.7341966,0.0001695022,0.00056457164,0.00017241504,0.00088165054,0.023808282,0.005517295,0.22869264,0.0029634605,0.0002702605],"about_ca_topic_score_codex":0.00094262295,"about_ca_topic_score_gemma":0.008114636,"teacher_disagreement_score":0.20946497,"about_ca_system_score_codex":0.0001049979,"about_ca_system_score_gemma":0.00094690366,"threshold_uncertainty_score":0.45281577},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.812539,0.0016374371,0.0003074823,0.06169615,0.08072918,0.0021356693,0.000007832793,0.000070269205,0.040876992],"genre_scores_gemma":[0.9605483,0.000038757327,0.000377229,0.000056783265,0.038730167,0.000010338472,0.0000045346205,0.0000057564257,0.0002281549],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987281,0.00024559262,0.0001853691,0.00007219356,0.00057248777,0.00019628645],"domain_scores_gemma":[0.9983472,0.000026656577,0.00018716021,0.000068612615,0.001047178,0.00032318052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029834434,0.000047797697,0.00007859067,0.00015630072,0.0007186986,0.00008043061,0.0001323417,0.000080434475,0.00032328043],"category_scores_gemma":[0.0009804516,0.00004725304,0.000050310926,0.00018314898,0.0002660709,0.00033747093,0.0000019598597,0.00020740072,0.00001961518],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019501116,0.00015260837,0.007248496,0.000008533842,0.00007818487,0.00006707207,0.05462694,0.000103568666,0.00019302056,0.024247339,0.47835526,0.43489948],"study_design_scores_gemma":[0.00016765684,0.00012385572,0.0045510354,0.000009183705,0.000024241699,0.000027097107,0.0008056655,0.000055365756,0.0000407661,0.002641037,0.99148935,0.00006475037],"about_ca_topic_score_codex":0.007998101,"about_ca_topic_score_gemma":0.06824559,"teacher_disagreement_score":0.5131341,"about_ca_system_score_codex":0.00043205108,"about_ca_system_score_gemma":0.004683284,"threshold_uncertainty_score":0.99860775},"labels":[],"label_agreement":null},{"id":"W4366384040","doi":"10.3138/cjpe.0024.004","title":"Utilité de l’évaluation de l’évaluabilité des politiques gouvernementales de lutte contre le tabagisme : l’expérience québécoise des centres d’abandon du tabagisme","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Government (linguistics); Welfare economics; Political science; Humanities; Psychology; Economics; Philosophy; Accounting","score_opus":0.14670026669426978,"score_gpt":0.4436251216368626,"score_spread":0.2969248549425928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902577,0.0005518048,0.002287714,0.0024249828,0.000499632,0.0010445545,0.000025286694,0.000034729645,0.0028736363],"genre_scores_gemma":[0.9855101,0.00009501058,0.013290312,0.00039868263,0.00036784462,0.00013631348,0.000020581729,0.000025710195,0.0001554338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99360067,0.0015742475,0.0013032123,0.00040221133,0.0021850131,0.00093464134],"domain_scores_gemma":[0.9929193,0.00066159037,0.0008758289,0.00045501452,0.003918949,0.0011692663],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027978051,0.0002868877,0.0003894897,0.0006319111,0.0008831175,0.00078793016,0.00079787895,0.00019679221,0.0019185279],"category_scores_gemma":[0.010647361,0.00024536406,0.00026743178,0.0007134197,0.00081000815,0.0015011964,0.0000332779,0.0004929825,0.00002813773],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049985072,0.00014801866,0.4964407,0.000016098349,0.000037310747,0.000015336962,0.019264705,0.0011475626,0.0026411356,0.0023023395,0.00086853374,0.47706828],"study_design_scores_gemma":[0.0019440652,0.00049349695,0.778329,0.00011773545,0.0001652065,0.00033950093,0.014158482,0.09807688,0.0032947222,0.09102852,0.011718732,0.00033360964],"about_ca_topic_score_codex":0.0397154,"about_ca_topic_score_gemma":0.41797534,"teacher_disagreement_score":0.47673467,"about_ca_system_score_codex":0.001485949,"about_ca_system_score_gemma":0.018263398,"threshold_uncertainty_score":0.9999999},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5134099,0.055658873,0.0048392615,0.2287649,0.025768336,0.003804578,0.000049910057,0.00004990459,0.16765432],"genre_scores_gemma":[0.9898412,0.0005554146,0.003870098,0.0015525976,0.0015330603,0.000017092529,0.00000857718,0.00001535334,0.002606555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995855,0.00092481106,0.00069565704,0.00019264438,0.0016229769,0.00070892216],"domain_scores_gemma":[0.9963489,0.00018027521,0.00086281245,0.00012193794,0.0015297852,0.00095625053],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023173543,0.0001550898,0.00021572706,0.00020825748,0.0006094778,0.00030096824,0.00035833937,0.00022164854,0.0013532001],"category_scores_gemma":[0.0013905634,0.0001623674,0.00019732748,0.0012084725,0.0007024543,0.0010942423,0.000008331496,0.0003293765,0.000052225678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011033085,0.00008422427,0.0059587453,0.000008235781,0.000036297355,0.000020587577,0.030428085,0.00018388749,0.000020785334,0.069942,0.013101473,0.8802047],"study_design_scores_gemma":[0.00071911915,0.00072663964,0.081324585,0.00030304267,0.00027875282,0.000027378435,0.013887247,0.00084290095,0.000054501517,0.0607501,0.84076226,0.00032345744],"about_ca_topic_score_codex":0.17738727,"about_ca_topic_score_gemma":0.79149973,"teacher_disagreement_score":0.8798812,"about_ca_system_score_codex":0.0016611508,"about_ca_system_score_gemma":0.0145881465,"threshold_uncertainty_score":0.9995597},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979835,0.0020016036,0.0007580833,0.003504372,0.0003919104,0.0008779623,0.0000067811334,0.000023220922,0.012601068],"genre_scores_gemma":[0.99491745,0.00009803324,0.00381458,0.00016288499,0.00044486893,0.000037995233,0.000003337072,0.000012978797,0.0005078794],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99717706,0.0003407396,0.0004757268,0.00019509441,0.0011807343,0.00063064304],"domain_scores_gemma":[0.99620545,0.0002132114,0.0006133539,0.000090376125,0.0022032433,0.00067436066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010619814,0.00014066775,0.00020413099,0.00016607642,0.0012997867,0.0002951192,0.00035696622,0.00014725415,0.000523495],"category_scores_gemma":[0.0047934046,0.0001357063,0.00011298835,0.0011858733,0.00063798414,0.0005708081,0.0000075996127,0.00022026176,0.000007383679],"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":[0.00001750083,0.00005473276,0.065510854,0.000006846672,0.00003132886,0.000017638462,0.07346584,0.000040248196,0.00009330721,0.00035956816,0.0008398829,0.8595623],"study_design_scores_gemma":[0.0018571767,0.0005495817,0.8492736,0.00023229161,0.0002900886,0.000048912374,0.05988812,0.0005135676,0.0012662162,0.03959865,0.04598171,0.0005000793],"about_ca_topic_score_codex":0.3741279,"about_ca_topic_score_gemma":0.9634284,"teacher_disagreement_score":0.8590622,"about_ca_system_score_codex":0.0016047842,"about_ca_system_score_gemma":0.016601125,"threshold_uncertainty_score":0.99970406},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95586395,0.00057503325,0.0012595793,0.015341775,0.0015534626,0.00072168506,0.00000315469,0.000018820509,0.024662547],"genre_scores_gemma":[0.99673676,0.00002823377,0.0016464272,0.00025742952,0.000887461,0.000010943746,0.0000016873572,0.000008129473,0.00042294108],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974054,0.00036292485,0.0003766915,0.00013223718,0.0010563134,0.00066642504],"domain_scores_gemma":[0.9973694,0.00010915764,0.0004291939,0.00009516337,0.00101134,0.0009857245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016018495,0.00008820621,0.00014369324,0.00017608404,0.00063142687,0.00023631062,0.00034363696,0.00013530247,0.00018405495],"category_scores_gemma":[0.0024975769,0.00008471659,0.0001087339,0.00091900624,0.00036832923,0.00045323698,0.0000047866224,0.0002009576,0.00000904176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022437313,0.000038068945,0.12816052,0.000004183445,0.000023449427,0.000046405574,0.044041708,0.00012189669,0.000046022215,0.007939161,0.012452975,0.80710316],"study_design_scores_gemma":[0.0010089974,0.0005568206,0.32563314,0.000104702536,0.00011680398,0.000032014344,0.031805143,0.0004014148,0.00014703514,0.030129377,0.609718,0.00034654594],"about_ca_topic_score_codex":0.37928247,"about_ca_topic_score_gemma":0.9158388,"teacher_disagreement_score":0.8067566,"about_ca_system_score_codex":0.0018815482,"about_ca_system_score_gemma":0.015816387,"threshold_uncertainty_score":0.989763},"labels":[],"label_agreement":null},{"id":"W4366384054","doi":"10.3138/cjpe.0021.005","title":"Evaluation Can Cross the Boundaries: The Case of Transport Canada","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Transport Canada","funders":"","keywords":"Champion; Coaching; Unit (ring theory); Work (physics); Service (business); Function (biology); Resource (disambiguation); Government (linguistics); Independence (probability theory); Computer science; Process management; Operations management; Business; Public relations; Psychology; Political science; Management; Marketing; Engineering; Economics; Mathematics education","score_opus":0.29431312733175025,"score_gpt":0.5310447804049384,"score_spread":0.23673165307318816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98612195,0.0006557619,0.0007478885,0.006722981,0.0017190161,0.0015562251,0.000028939303,0.0000029826892,0.0024442498],"genre_scores_gemma":[0.9989744,0.0000029813698,0.00021028102,0.00045130786,0.00020478539,0.000037861933,0.000010079322,0.000008537822,0.00009977701],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99225247,0.00092489034,0.0015096385,0.00018040322,0.0047735,0.00035909784],"domain_scores_gemma":[0.9873845,0.0007944243,0.0011779527,0.0004897701,0.009855563,0.00029778725],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.09317276,0.00013438164,0.00021794591,0.0002767006,0.0010045595,0.00045070806,0.0006905874,0.00006769253,0.0015958486],"category_scores_gemma":[0.0051573324,0.000071977556,0.0001337288,0.0010593954,0.00048202256,0.00034176465,0.000007717608,0.00028958,0.000003632746],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028258097,0.000023077451,0.030321103,0.000004259544,0.00007093389,0.00008051695,0.0053213225,0.008177948,0.000012481866,0.00065141334,0.0043482236,0.95096046],"study_design_scores_gemma":[0.0026153661,0.0006748299,0.5667385,0.000068480236,0.0008968642,0.001996605,0.028129306,0.09082799,0.0006009841,0.01429833,0.29279155,0.00036125272],"about_ca_topic_score_codex":0.604967,"about_ca_topic_score_gemma":0.9982539,"teacher_disagreement_score":0.9505992,"about_ca_system_score_codex":0.0011463522,"about_ca_system_score_gemma":0.054257307,"threshold_uncertainty_score":0.9993168},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8967909,0.07383012,0.00033692428,0.021290215,0.0015917636,0.005432458,0.00022320363,0.00001831519,0.00048607835],"genre_scores_gemma":[0.9969913,0.0002136258,0.0013539696,0.00054014917,0.00027360246,0.00020351745,0.00037896185,0.00003614332,0.00000872791],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9923661,0.0023376732,0.0038631018,0.00030269107,0.00043444172,0.0006959995],"domain_scores_gemma":[0.9872266,0.00073528045,0.0070962505,0.0003317945,0.0035805032,0.0010295808],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09005611,0.00019074911,0.00063057285,0.0020212189,0.00022825747,0.00014100615,0.00031957534,0.00017361467,0.0002951342],"category_scores_gemma":[0.08424596,0.00024568106,0.000053811546,0.0019358606,0.00007164943,0.001731055,0.000010387071,0.00030909455,0.00006333948],"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":[0.000010613055,0.000093251045,0.9678968,0.00059122615,0.00005244918,4.9118836e-7,0.009067315,0.0017047651,0.0000010222846,0.00223372,0.0019928166,0.01635553],"study_design_scores_gemma":[0.0011557085,0.00017433795,0.94503856,0.0006344399,0.00008586762,0.000022020035,0.0041921935,0.02024206,0.0000085331,0.001957136,0.026097806,0.00039132737],"about_ca_topic_score_codex":0.67824274,"about_ca_topic_score_gemma":0.95806044,"teacher_disagreement_score":0.27981773,"about_ca_system_score_codex":0.00493767,"about_ca_system_score_gemma":0.01816089,"threshold_uncertainty_score":0.9999995},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86349916,0.014501328,0.00065879605,0.06939352,0.031937342,0.001645591,0.000040134455,0.00002719927,0.018296937],"genre_scores_gemma":[0.96612984,0.0002730038,0.0029125656,0.00008405455,0.028143566,0.000036782814,0.000012329487,0.000018894516,0.0023889812],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994543,0.002305816,0.0006138299,0.00020381481,0.0014084259,0.0009251132],"domain_scores_gemma":[0.99643296,0.0002685959,0.0006486547,0.00014193244,0.0012906672,0.0012171882],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013281984,0.00019134558,0.00027760142,0.00018630292,0.0014207786,0.0002680839,0.00037534165,0.00028056407,0.0047820704],"category_scores_gemma":[0.0035263998,0.00018558222,0.00021498931,0.0012215462,0.0013237216,0.0018359668,0.000015827834,0.00039428804,0.00009318054],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010673128,0.0001881094,0.05980041,0.000018588422,0.00005088033,0.0000031772192,0.072847664,0.00041557493,0.000026926324,0.022139557,0.049137175,0.7953613],"study_design_scores_gemma":[0.0004671503,0.00022634164,0.30637908,0.00012336922,0.00023640155,0.00004627793,0.01467466,0.0014413246,0.000014582274,0.013029613,0.6631144,0.00024676244],"about_ca_topic_score_codex":0.1800012,"about_ca_topic_score_gemma":0.4929386,"teacher_disagreement_score":0.7951145,"about_ca_system_score_codex":0.0029578074,"about_ca_system_score_gemma":0.011283904,"threshold_uncertainty_score":0.99987924},"labels":[],"label_agreement":null},{"id":"W4366384066","doi":"10.3138/cjpe.022.004","title":"Conceptualizing Research Impact: The Case of Education Research","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Social Sciences and Humanities Research Council; University of Ottawa","funders":"","keywords":"Interdependence; Educational research; Conceptual framework; Task (project management); Field (mathematics); Subject (documents); Sociology; Process (computing); Qualitative research; Grounded theory; Research methodology; Management science; Psychology; Epistemology; Computer science; Pedagogy; Social science; Management","score_opus":0.8198728471732565,"score_gpt":0.7382456792202653,"score_spread":0.08162716795299119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98511773,0.0013001775,0.0003527487,0.0020263293,0.0007065446,0.0012539653,0.0000035797495,0.000002511769,0.009236391],"genre_scores_gemma":[0.99848205,0.000009572531,0.0008480491,0.000049526985,0.00034386868,0.000033507553,0.000003724175,0.000007830843,0.00022188184],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99062663,0.0030850773,0.0012159203,0.0001921264,0.0043466394,0.00053360773],"domain_scores_gemma":[0.97355336,0.0026942817,0.00055441645,0.00046931228,0.022199819,0.00052881544],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22608447,0.00008099514,0.0001756403,0.0019005467,0.0007034097,0.00040644102,0.0006827635,0.00008640378,0.002035838],"category_scores_gemma":[0.01661185,0.00004871923,0.000120365774,0.0031792196,0.00056793157,0.0005338523,0.000025396817,0.0006578428,0.000057304802],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023462053,0.00005650416,0.0092983395,0.0000034509492,0.00001558454,0.000027843656,0.006868469,0.0003807237,0.00010694053,0.0034972236,0.010969504,0.96875197],"study_design_scores_gemma":[0.0021994659,0.0044011963,0.24227458,0.0003637121,0.00012586062,0.0034067368,0.36882576,0.042484377,0.0022028112,0.16799235,0.16532993,0.00039322476],"about_ca_topic_score_codex":0.007916379,"about_ca_topic_score_gemma":0.07659635,"teacher_disagreement_score":0.96835876,"about_ca_system_score_codex":0.0009653412,"about_ca_system_score_gemma":0.021847008,"threshold_uncertainty_score":0.99887645},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95752454,0.00044081672,0.00061843765,0.033149105,0.00051185396,0.00055534235,0.000008003789,0.000025847306,0.007166066],"genre_scores_gemma":[0.99760795,0.000083843646,0.00062125793,0.00058783987,0.00092672143,0.000030878087,0.0000026897033,0.000010728291,0.00012809747],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975894,0.00057530694,0.00041989877,0.00014856628,0.0007345738,0.0005322182],"domain_scores_gemma":[0.9974054,0.0003081071,0.00045743084,0.00008663604,0.0010588135,0.00068360195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007373413,0.000113296825,0.0001791905,0.00012683653,0.0011267135,0.00027850113,0.00028587368,0.0001367632,0.00029490274],"category_scores_gemma":[0.0029793067,0.00011119517,0.00012402315,0.0006943365,0.00037553028,0.00046322923,0.00000715045,0.00017638449,0.000006409998],"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":[0.00003299011,0.00013631616,0.66834885,0.0000065610197,0.000044788627,0.000062465355,0.08905222,0.00033223728,0.00006365497,0.011380779,0.012118538,0.21842062],"study_design_scores_gemma":[0.0010317992,0.00039416764,0.7655276,0.00007911751,0.00018100305,0.000033355802,0.01763689,0.0020409517,0.00021126837,0.009021084,0.20351765,0.00032513152],"about_ca_topic_score_codex":0.62982935,"about_ca_topic_score_gemma":0.9807724,"teacher_disagreement_score":0.35094303,"about_ca_system_score_codex":0.0014379349,"about_ca_system_score_gemma":0.013217258,"threshold_uncertainty_score":0.99237686},"labels":[],"label_agreement":null},{"id":"W4366384075","doi":"10.3138/cjpe.021.005","title":"Discours qui résistent à l’objectivation : que peut-on en tirer pour l’évaluation?","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Meaning (existential); Sympathy; Politics; Political science; Context (archaeology); Sociology; Welfare economics; Social psychology; Psychology; Public relations; Epistemology; Philosophy; Law; Economics; Geography","score_opus":0.2866063764522911,"score_gpt":0.5192156027950292,"score_spread":0.23260922634273812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9466943,0.00024304763,0.0031946276,0.025243111,0.0017304268,0.0018296684,0.000013637995,0.00002549816,0.021025691],"genre_scores_gemma":[0.9956453,0.000005895136,0.002195191,0.00028498887,0.00071530277,0.00010717243,0.00004522849,0.000019140329,0.0009817807],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99287075,0.0012149231,0.0013554929,0.0003261841,0.0038610718,0.00037158967],"domain_scores_gemma":[0.9940565,0.00051680184,0.0010551844,0.00039677363,0.0036274611,0.00034727165],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019056115,0.00020596995,0.00029762494,0.0011532848,0.0003787196,0.00059217785,0.0004897079,0.00012946222,0.002460211],"category_scores_gemma":[0.002786931,0.0001584345,0.00022436562,0.0009615048,0.000080969956,0.0008344098,0.000012113687,0.00029451208,0.00027675246],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051116986,0.00023020562,0.069561385,0.0000060646266,0.000049768023,0.000008506884,0.0014879936,0.05363563,0.00028271254,0.009592043,0.021754535,0.84334004],"study_design_scores_gemma":[0.0023662604,0.0010968017,0.7351185,0.00012342601,0.00020474412,0.000062895364,0.0042682006,0.11926798,0.0005942376,0.09480292,0.04168377,0.000410251],"about_ca_topic_score_codex":0.0016943304,"about_ca_topic_score_gemma":0.024113974,"teacher_disagreement_score":0.8429298,"about_ca_system_score_codex":0.0010399222,"about_ca_system_score_gemma":0.0076495185,"threshold_uncertainty_score":0.99845165},"labels":[],"label_agreement":null},{"id":"W4366384079","doi":"10.3138/cjpe.021.007","title":"Participatory Needs Assessment","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Credibility; Participatory evaluation; Citizen journalism; Needs assessment; Relevance (law); Quality (philosophy); Process (computing); Process management; Business; Program evaluation; Knowledge management; Computer science; Sociology; Political science","score_opus":0.497564820203374,"score_gpt":0.5742346745312081,"score_spread":0.07666985432783413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9536883,0.00052039506,0.0035838818,0.0039182967,0.0016764601,0.0009392741,0.000005634104,0.000014981336,0.035652727],"genre_scores_gemma":[0.99521124,0.0000021097803,0.0037150558,0.00018265964,0.00035379393,0.000059661266,0.000009638691,0.000008153902,0.00045767843],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99516284,0.0005896442,0.0010844563,0.00013577884,0.002722702,0.0003045683],"domain_scores_gemma":[0.9955565,0.00018570366,0.0006986608,0.0002773539,0.0028868255,0.0003949583],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018478857,0.0001077817,0.00020975975,0.0009498888,0.00021317584,0.000474227,0.0003944825,0.00006622345,0.0044497056],"category_scores_gemma":[0.00081469194,0.00008233226,0.00013396009,0.0009882016,0.0000888572,0.00061351963,0.0000085317015,0.00018649049,0.00012332946],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067378874,0.00008196205,0.21806926,0.000002511991,0.00002056998,0.000008406315,0.00045413597,0.008901226,0.00008793112,0.0057178424,0.022609858,0.74403954],"study_design_scores_gemma":[0.0010712304,0.00047400832,0.62328565,0.00002677739,0.00010506735,0.000034747292,0.0014084314,0.07748473,0.00012522878,0.032309126,0.2634955,0.00017949371],"about_ca_topic_score_codex":0.00080841297,"about_ca_topic_score_gemma":0.016559925,"teacher_disagreement_score":0.74386007,"about_ca_system_score_codex":0.00051100005,"about_ca_system_score_gemma":0.007290182,"threshold_uncertainty_score":0.99833757},"labels":[],"label_agreement":null},{"id":"W4366384147","doi":"10.3138/cjpe.26.005","title":"Using Evaluation to Shape and Direct Comprehensive Community Initiatives: Evaluation, Reflective Practice, and Interventions Dealing with Complexity","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Regional Municipality of Waterloo; Wilfrid Laurier University; Centre for Community Based Research","funders":"","keywords":"Citizen journalism; Participatory action research; Experiential learning; Experiential knowledge; Psychological intervention; Value (mathematics); Reflective practice; Action (physics); Sociology; Engineering ethics; Knowledge management; Psychology; Computer science; Pedagogy; Epistemology; Engineering","score_opus":0.8567416364459937,"score_gpt":0.631227536497771,"score_spread":0.2255140999482227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98096496,0.0009874278,0.0040801866,0.0006598071,0.0002515844,0.0032517947,0.000017696222,0.000011255449,0.009775275],"genre_scores_gemma":[0.9567327,0.000016432494,0.042772334,0.00027950987,0.000048803075,0.00011544071,0.000017258388,0.000013823665,0.0000037247064],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990506,0.0051858686,0.0010440155,0.00029283966,0.0026876342,0.00028362297],"domain_scores_gemma":[0.9802481,0.0008291129,0.001219279,0.0003194292,0.016851624,0.0005324716],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039546747,0.00019577795,0.0003567759,0.0009809297,0.0009649922,0.00041285378,0.0002711274,0.00007464553,0.0011407239],"category_scores_gemma":[0.008975552,0.00015906307,0.00007966048,0.0009079338,0.00029899544,0.0022041244,0.00004790155,0.00039085172,0.00000779551],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030263668,0.00024827983,0.02544828,0.00003259796,0.0003170501,0.0000048227844,0.04249009,0.004703097,0.0001405039,0.0016393267,0.00011706374,0.92455626],"study_design_scores_gemma":[0.002506036,0.0024560916,0.58566487,0.00046461055,0.0012269558,0.00018327532,0.036746547,0.3491762,0.00009176386,0.02031888,0.0008452677,0.00031952988],"about_ca_topic_score_codex":0.0023677659,"about_ca_topic_score_gemma":0.03642814,"teacher_disagreement_score":0.9242367,"about_ca_system_score_codex":0.0006575838,"about_ca_system_score_gemma":0.0032631832,"threshold_uncertainty_score":0.99977237},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92003435,0.000052191324,0.00018432143,0.06935906,0.0037687575,0.004052512,0.000041547057,0.00003087964,0.0024764093],"genre_scores_gemma":[0.98410606,0.0000028048385,0.002348322,0.012008251,0.00092205266,0.0004151699,0.00001394947,0.000023861016,0.00015954518],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99455297,0.0017944569,0.0013530833,0.00020320452,0.0011246849,0.00097161264],"domain_scores_gemma":[0.9926398,0.00078888616,0.0010867859,0.00033607922,0.0033875005,0.001760951],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016721202,0.00015826708,0.0002920286,0.00055178476,0.0009646104,0.00006853731,0.00042625377,0.00020526563,0.0053655813],"category_scores_gemma":[0.009913799,0.00014303531,0.00008816183,0.00087449845,0.00015800999,0.00032142422,0.000011190123,0.0012384196,0.00014024493],"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":[0.000050796443,0.00003315867,0.4088325,0.000038315644,0.00004918291,0.000015154797,0.017531708,0.00011986408,0.00031898596,0.00071489054,0.059519812,0.51277566],"study_design_scores_gemma":[0.0060541704,0.0005397894,0.44504884,0.00018401862,0.00020937246,0.00003591642,0.0041673095,0.001341855,0.00003036522,0.002088757,0.5399624,0.00033718577],"about_ca_topic_score_codex":0.008638887,"about_ca_topic_score_gemma":0.2205,"teacher_disagreement_score":0.5124385,"about_ca_system_score_codex":0.00085566303,"about_ca_system_score_gemma":0.036256146,"threshold_uncertainty_score":0.99842614},"labels":[],"label_agreement":null},{"id":"W4366384160","doi":"10.3138/cjpe.22.004","title":"Using Public Databases to Study Relative Program Impact","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Impact assessment; Database; Computer science; Control (management); Impact evaluation; Statistics; Political science; Artificial intelligence; Mathematics","score_opus":0.7796421792303019,"score_gpt":0.6674537745782021,"score_spread":0.11218840465209978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98172134,0.00015459246,0.011932047,0.0006884004,0.00063914363,0.0034238196,0.00001044089,0.000016728234,0.0014134716],"genre_scores_gemma":[0.9676183,7.942863e-7,0.031952973,0.000109580295,0.00021254295,0.00004775395,0.0000113491915,0.000013240179,0.000033469525],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99373335,0.00077419804,0.0013200481,0.0002912941,0.0033513035,0.00052978884],"domain_scores_gemma":[0.99206424,0.0003718588,0.0008163736,0.00042765733,0.005060794,0.0012591004],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.042586878,0.0001707963,0.00029235793,0.0017038023,0.00037592082,0.00070283655,0.00054330676,0.000051337283,0.0022812593],"category_scores_gemma":[0.0073068673,0.00012324264,0.00015568218,0.0024167167,0.000066767505,0.0017328428,0.000028219685,0.00026673943,0.00008255824],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020761561,0.00023568062,0.22376633,7.137686e-7,0.0000580831,0.00001677117,0.0017987413,0.0010605259,0.000021591466,0.00014771438,0.0004263151,0.77244675],"study_design_scores_gemma":[0.0017647748,0.003935724,0.9071324,0.000046402984,0.00020648612,0.00011096797,0.011237666,0.034835365,0.0000737013,0.0021189204,0.038220257,0.00031733024],"about_ca_topic_score_codex":0.001525843,"about_ca_topic_score_gemma":0.049713615,"teacher_disagreement_score":0.7721294,"about_ca_system_score_codex":0.0010121913,"about_ca_system_score_gemma":0.008199334,"threshold_uncertainty_score":0.99863076},"labels":[],"label_agreement":null},{"id":"W4366384164","doi":"10.3138/cjpe.027.008","title":"DeMars, C. (2010). <i>Item Response Theory.</i> Oxford, UK: Oxford University Press. 137 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Item response theory; Media studies; Political science; Economic history; Library science; Economics; Sociology; Computer science; Law","score_opus":0.29078747149008427,"score_gpt":0.43684040231959376,"score_spread":0.1460529308295095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.961349,0.002761361,0.0047892695,0.004362343,0.0034769576,0.0019183956,0.00004053598,0.000033330743,0.021268792],"genre_scores_gemma":[0.9934893,0.00011995051,0.002633894,0.00030986848,0.0002777804,0.000012039394,0.000012800299,0.000014477944,0.0031298527],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933485,0.0026377747,0.00083812024,0.00022489885,0.0023786523,0.00057207677],"domain_scores_gemma":[0.99408484,0.0011431535,0.00088525703,0.00047178185,0.0023421582,0.0010728285],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04634388,0.00018158955,0.00029039296,0.0007254572,0.0003924487,0.00033633306,0.0007499513,0.00014462057,0.0031836147],"category_scores_gemma":[0.0057933154,0.0001471977,0.00019834936,0.0007961469,0.00015340392,0.001478871,0.000034225777,0.000330295,0.0000428782],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000605115,0.00010717055,0.09931136,0.0000060334205,0.00008295233,0.000016746135,0.002116507,0.0008315641,0.000057616056,0.003974797,0.045773517,0.84711665],"study_design_scores_gemma":[0.0010386518,0.00035557878,0.18604569,0.000030730407,0.00011430205,0.00005992337,0.001947274,0.0040247696,0.00010430245,0.001919418,0.8041753,0.00018405702],"about_ca_topic_score_codex":0.0001485702,"about_ca_topic_score_gemma":0.002137612,"teacher_disagreement_score":0.8469326,"about_ca_system_score_codex":0.0007189188,"about_ca_system_score_gemma":0.0043380046,"threshold_uncertainty_score":0.99772763},"labels":[],"label_agreement":null},{"id":"W4366384165","doi":"10.3138/cjpe.21.001","title":"Suggestions d’améliorations d’un cadre conceptuel de l’évaluation participative","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Participatory evaluation; Empowerment; Stakeholder; Citizen journalism; Relevance (law); Valuation (finance); Sociology; Knowledge management; Management science; Process management; Business; Political science; Computer science; Public relations; Social science; Engineering; Accounting","score_opus":0.3522063354619847,"score_gpt":0.5249077562850959,"score_spread":0.17270142082311118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9610089,0.0005563038,0.019721702,0.006071924,0.0008718071,0.001475194,0.000030262925,0.000025886782,0.010237997],"genre_scores_gemma":[0.98992616,0.0000057995467,0.0089163445,0.0001772879,0.00035348174,0.00018245871,0.000052972915,0.000012038005,0.0003734587],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945997,0.001228601,0.0012423052,0.0002236655,0.002317746,0.0003879626],"domain_scores_gemma":[0.99258685,0.00043091763,0.0009025907,0.00029675558,0.0053524603,0.00043043157],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01660161,0.000148748,0.0002432948,0.00074208935,0.00053383136,0.0005301964,0.0003798437,0.000113418035,0.00446357],"category_scores_gemma":[0.003993693,0.00012541348,0.00015252939,0.00126438,0.00017576334,0.0008772354,0.000009483308,0.00024893376,0.0001461224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018953036,0.00017421169,0.10015462,0.0000033201036,0.000047724985,0.000011362216,0.004176653,0.08557067,0.00044010472,0.010497415,0.016817708,0.78208727],"study_design_scores_gemma":[0.0017191214,0.0006039254,0.6223053,0.00005045508,0.00029629437,0.000076090946,0.0035984549,0.21812914,0.0009140578,0.1075364,0.04447358,0.00029720244],"about_ca_topic_score_codex":0.00188833,"about_ca_topic_score_gemma":0.03895649,"teacher_disagreement_score":0.78179,"about_ca_system_score_codex":0.0006453629,"about_ca_system_score_gemma":0.008704844,"threshold_uncertainty_score":0.99691486},"labels":[],"label_agreement":null},{"id":"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008607877,0.009676406,0.9656688,0.008389756,0.0032673082,0.002308388,0.00002861856,0.00006137043,0.0019914503],"genre_scores_gemma":[0.8938132,0.00013351231,0.09412054,0.0013658426,0.0035803805,0.00031705413,0.000047733738,0.00006833135,0.006553422],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731445,0.00034586203,0.00075491716,0.00026294956,0.0005983884,0.000723432],"domain_scores_gemma":[0.99680215,0.00015616413,0.00061988935,0.00043588236,0.0015333806,0.0004525181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005704527,0.00024050329,0.0002724292,0.0002216011,0.0005221158,0.0007104914,0.0007121586,0.00012977839,0.00003761894],"category_scores_gemma":[0.00042171802,0.00017279937,0.00018331406,0.00020776594,0.00008959171,0.0011097785,0.000030505458,0.00034301225,0.000034294066],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004637525,0.0000853122,0.00097086054,0.000077738354,0.00021598622,0.000014532859,0.008406478,0.071127325,0.00028221795,0.036491368,0.2378656,0.6444162],"study_design_scores_gemma":[0.00064529345,0.0002301855,0.00050829275,0.0001795767,0.00010946186,0.00011451504,0.00026950976,0.080457546,0.000074973876,0.0064880047,0.91061455,0.00030809495],"about_ca_topic_score_codex":0.0010861785,"about_ca_topic_score_gemma":0.0060617076,"teacher_disagreement_score":0.8852053,"about_ca_system_score_codex":0.00035712746,"about_ca_system_score_gemma":0.0016480613,"threshold_uncertainty_score":0.70465535},"labels":[],"label_agreement":null},{"id":"W4366384172","doi":"10.3138/cjpe.0024.005","title":"Rigour and Feasibility in Tobacco Control Evaluation: Toward a Successful Reconciliation","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Communications and Information Technology Ontario; Heart and Stroke Foundation; University of Waterloo; Public Health Ontario; University of Toronto","funders":"","keywords":"Rigour; Stakeholder; Relevance (law); Context (archaeology); Tobacco control; Control (management); Plan (archaeology); Management science; Program evaluation; Process management; Political science; Engineering ethics; Public relations; Computer science; Business; Public administration; Engineering; Medicine; Public health; Epistemology; Nursing; Law; Geography","score_opus":0.37313234694188385,"score_gpt":0.5320879190308285,"score_spread":0.15895557208894467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891412,0.00028643722,0.00030339696,0.005145354,0.0013281248,0.002073204,0.0000088797715,0.0000065427803,0.0017068554],"genre_scores_gemma":[0.9978325,0.000006655799,0.0015518485,0.00021967375,0.00022016437,0.00012203827,0.000009854979,0.0000075204457,0.000029788976],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934024,0.0017805285,0.0013331604,0.0003279183,0.00285614,0.00029981267],"domain_scores_gemma":[0.99232656,0.00060288055,0.00084140495,0.000349631,0.0053927344,0.00048677818],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07160067,0.00014694757,0.0003180493,0.0008249185,0.0002218369,0.0005462925,0.0003851185,0.00015045279,0.0042349803],"category_scores_gemma":[0.016914625,0.00011910437,0.000095614494,0.0008217563,0.00012246043,0.0012192744,0.000010256778,0.00063199794,0.000042938125],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023974068,0.00002849496,0.4936072,0.0000020551763,0.000007763319,0.0000015455843,0.0008486235,0.00052015873,0.000059895807,0.00012834684,0.0002606644,0.5045113],"study_design_scores_gemma":[0.003238206,0.00025778174,0.84857404,0.000024111161,0.00007724069,0.000038437778,0.0013563512,0.1252883,0.000039765488,0.0157944,0.0051650214,0.00014634946],"about_ca_topic_score_codex":0.0009988707,"about_ca_topic_score_gemma":0.18166767,"teacher_disagreement_score":0.5043649,"about_ca_system_score_codex":0.00054977246,"about_ca_system_score_gemma":0.0075788377,"threshold_uncertainty_score":0.9980473},"labels":[],"label_agreement":null},{"id":"W4366384175","doi":"10.3138/cjpe.23.017","title":"R. Pawson. (2006). <i>Evidence-based Policy: A Realist Perspective.</i> Thousand Oaks, CA: Sage. 209 pages.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); SAGE; Sociology; Philosophy; Political science; Epistemology; Regional science; Art; Physics; Visual arts; Quantum mechanics","score_opus":0.3443396687424581,"score_gpt":0.4951481816256015,"score_spread":0.1508085128831434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.657566,0.038133673,0.020112224,0.23198123,0.00660885,0.009093144,0.00025409032,0.00016441953,0.03608637],"genre_scores_gemma":[0.99257696,0.00041400248,0.003310403,0.0016256184,0.0007424489,0.00008012181,0.000014813794,0.00002226518,0.001213373],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99298465,0.0011460591,0.001209685,0.00038450622,0.003743501,0.0005315986],"domain_scores_gemma":[0.9914111,0.00057269196,0.0010416192,0.00053932285,0.0054948735,0.00094042206],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014876123,0.00023353346,0.0004106598,0.0013266002,0.0006600296,0.00050374336,0.00071636995,0.00013406284,0.002781709],"category_scores_gemma":[0.009568143,0.00018276717,0.0002644656,0.0018777762,0.00032007493,0.0012394843,0.000015717595,0.00037827773,0.00016492215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001412407,0.00019736914,0.066849336,0.000013800783,0.000089478846,0.00016527531,0.004356773,0.012546573,0.00013699959,0.0013756211,0.1977672,0.71636033],"study_design_scores_gemma":[0.0048979656,0.002264339,0.39768738,0.0005847221,0.0003246415,0.0007129553,0.005303364,0.068970114,0.00054142834,0.019385034,0.49843794,0.0008901233],"about_ca_topic_score_codex":0.009111389,"about_ca_topic_score_gemma":0.052051786,"teacher_disagreement_score":0.7154702,"about_ca_system_score_codex":0.0017363442,"about_ca_system_score_gemma":0.027101418,"threshold_uncertainty_score":0.9987747},"labels":[],"label_agreement":null},{"id":"W4366384176","doi":"10.3138/cjpe.21.002","title":"Challenges of Participatory Evaluation within a Community-Based Health Promotion Partnership: Mujer Sana, Comunidad Sana—Healthy Women, Healthy Communities","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"General partnership; Citizen journalism; Participatory action research; Community-based participatory research; Participatory evaluation; Promotion (chess); Sociology; Public relations; Nursing; Medicine; Political science; Social science","score_opus":0.7114160732550165,"score_gpt":0.5663836151296869,"score_spread":0.1450324581253296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97991896,0.0027511003,0.000413304,0.011962513,0.00066617155,0.002683601,0.000020454416,0.00002574266,0.001558182],"genre_scores_gemma":[0.996739,0.000047713103,0.001341658,0.0010419842,0.00015654867,0.00046172185,0.00016417925,0.000027041102,0.000020187183],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97514385,0.015917672,0.0030896803,0.0002281717,0.0048535126,0.00076711795],"domain_scores_gemma":[0.98741335,0.00093803636,0.0035650202,0.0009650173,0.0062890626,0.00082951586],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.10788584,0.0002906319,0.0007475109,0.0015210053,0.0010504451,0.00027008157,0.0008495457,0.00017556807,0.0008559491],"category_scores_gemma":[0.0014232639,0.00025516681,0.00018464803,0.0011213582,0.0003980392,0.00079379126,0.000020735146,0.0008481647,0.000025752475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044139213,0.002059455,0.081304796,0.00043415537,0.0001135617,0.0000023082337,0.06531169,0.060067613,0.000024421839,0.004443939,0.004694976,0.7811017],"study_design_scores_gemma":[0.01022975,0.021342123,0.38107774,0.0010616679,0.00031636423,0.000041838957,0.1646568,0.35505587,0.00017635436,0.047900848,0.017302146,0.0008384845],"about_ca_topic_score_codex":0.012303684,"about_ca_topic_score_gemma":0.36469564,"teacher_disagreement_score":0.7802632,"about_ca_system_score_codex":0.0024872217,"about_ca_system_score_gemma":0.020535868,"threshold_uncertainty_score":0.99999005},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91934645,0.050912138,0.010972239,0.01117125,0.001920327,0.0019434938,0.000063600804,0.00011173079,0.003558773],"genre_scores_gemma":[0.94307244,0.0037698385,0.04892698,0.00034414843,0.0013767139,0.00020334721,0.00010298252,0.000106402644,0.0020971552],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98538125,0.009531713,0.001149671,0.00055087666,0.0016085756,0.0017779204],"domain_scores_gemma":[0.994511,0.0008281111,0.000970031,0.0004251775,0.0010979581,0.002167729],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.018398184,0.0005104422,0.0006215106,0.00054038706,0.0023934385,0.00043582392,0.00077621016,0.00071183755,0.0012700015],"category_scores_gemma":[0.0052947644,0.0005417716,0.00044551076,0.0011827897,0.002829829,0.0009044671,0.000043666078,0.0013332994,0.00006447092],"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":[0.000030956166,0.00074239686,0.21104266,0.00012474299,0.00026980098,0.0014934704,0.15268278,0.0013602123,0.0003506869,0.00016174234,0.022640234,0.60910034],"study_design_scores_gemma":[0.0028355634,0.0008330865,0.49853787,0.0013806594,0.0008788363,0.0026582477,0.013279202,0.0018242847,0.00035992844,0.0019628408,0.47452965,0.0009198372],"about_ca_topic_score_codex":0.32387328,"about_ca_topic_score_gemma":0.70870626,"teacher_disagreement_score":0.60818046,"about_ca_system_score_codex":0.004069832,"about_ca_system_score_gemma":0.032691155,"threshold_uncertainty_score":0.9998839},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9177632,0.0039485325,0.0005548778,0.0505575,0.0027301318,0.0015053834,8.56035e-7,0.000070518974,0.022869026],"genre_scores_gemma":[0.9949288,0.0000065537474,0.00047229792,0.0011939482,0.0032547635,0.000013558193,0.000010816125,0.0000142085955,0.00010507188],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989497,0.000017358449,0.00033865907,0.00008491638,0.00041576746,0.00019360219],"domain_scores_gemma":[0.9980117,0.000026404372,0.00040904686,0.00010490313,0.001431045,0.000016897087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019441899,0.00009070274,0.00010289613,0.0002499122,0.00044763339,0.00040774758,0.00020810624,0.000029047556,0.00011759675],"category_scores_gemma":[0.00041451532,0.0000637191,0.000046846446,0.0005148038,0.000068789144,0.0006951944,0.000015562915,0.00010952195,0.000056756042],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008469852,0.000033852742,0.111667514,0.00013019683,0.00009018805,0.000010634097,0.00011597421,0.009450811,0.000016889067,0.006424366,0.055110086,0.816941],"study_design_scores_gemma":[0.0007348996,0.00004338045,0.26179534,0.00022328814,0.00045666215,0.00001788133,0.00072584406,0.069830425,0.000017551292,0.014391632,0.65151256,0.0002505285],"about_ca_topic_score_codex":0.0009510287,"about_ca_topic_score_gemma":0.0027098262,"teacher_disagreement_score":0.8166905,"about_ca_system_score_codex":0.00016140063,"about_ca_system_score_gemma":0.00028988416,"threshold_uncertainty_score":0.39319193},"labels":[],"label_agreement":null},{"id":"W4366384241","doi":"10.3138/cjpe.21.006","title":"Development of a Framework for Comprehensive Evaluation of Client Outcomes in Community Mental Health Services","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Western University; Riverview Hospital; University of British Columbia","funders":"","keywords":"Operationalization; Assertive community treatment; Mental health; Conceptualization; Stakeholder; Psychology; Inclusion (mineral); Mental illness; Applied psychology; Process management; Psychiatry; Public relations; Social psychology; Business; Computer science","score_opus":0.46199264417842795,"score_gpt":0.5765774015422332,"score_spread":0.1145847573638053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99425006,0.0004643644,0.0015066881,0.0008527099,0.00042074372,0.0023291581,0.000028480938,0.0000033146866,0.00014449607],"genre_scores_gemma":[0.9446337,0.0000036731954,0.0550537,0.00010381031,0.000027062737,0.00009877094,0.000067575456,0.000006863718,0.0000048456186],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9929539,0.0014380341,0.0021346842,0.0001364799,0.0030929307,0.00024395683],"domain_scores_gemma":[0.99185306,0.0005008559,0.0021119711,0.00027264078,0.005092013,0.00016946663],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.031386834,0.00012654076,0.00046183425,0.0008131309,0.0002479021,0.00007161492,0.00042356676,0.00007705681,0.00019554223],"category_scores_gemma":[0.0006480303,0.00010295472,0.00012670887,0.0006226366,0.000076569784,0.00031450365,0.000018418412,0.00020178701,0.0000029463797],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006422149,0.00047543747,0.16545223,0.000097909,0.000058718528,1.3956345e-7,0.02006756,0.013671346,0.000104721876,0.0010657794,0.0002842805,0.79865766],"study_design_scores_gemma":[0.0027183315,0.00061975024,0.8813681,0.0004080878,0.000060495153,0.0000031971056,0.017552538,0.06406259,0.00039729464,0.02910006,0.0035798533,0.00012970928],"about_ca_topic_score_codex":0.0026180723,"about_ca_topic_score_gemma":0.12973092,"teacher_disagreement_score":0.79852796,"about_ca_system_score_codex":0.0008860047,"about_ca_system_score_gemma":0.0076221703,"threshold_uncertainty_score":0.99800366},"labels":[],"label_agreement":null},{"id":"W4366384242","doi":"10.3138/cjpe.0023.008","title":"Insights into Evaluation Capacity Building: Motivations, Strategies, Outcomes, and Lessons Learned","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Capacity building; Accountability; Face (sociological concept); Public relations; Business; Psychology; Process management; Knowledge management; Political science; Sociology; Computer science","score_opus":0.536890060585536,"score_gpt":0.5401212105282374,"score_spread":0.00323114994270135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97717315,0.00083537295,0.0036009275,0.0142057305,0.00052734156,0.0012199333,0.0000027607134,0.000015393829,0.0024193688],"genre_scores_gemma":[0.99173206,0.000026702288,0.0076521295,0.00035116615,0.000116593976,0.000041648458,0.00001762846,0.000008058163,0.000054027165],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9938912,0.0010419987,0.0011347256,0.0003255178,0.003329569,0.00027701736],"domain_scores_gemma":[0.99318695,0.0002812643,0.0008867626,0.00036000082,0.0047391346,0.0005458742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015174372,0.00018985014,0.00033268647,0.0010538633,0.0004900606,0.0009908496,0.00041137775,0.00013256073,0.0005911456],"category_scores_gemma":[0.005554219,0.00014624203,0.00011164167,0.0009687603,0.000120594465,0.0018059745,0.000010829596,0.00031365402,0.000020536068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009682146,0.000059652062,0.014953587,0.0000027618826,0.000028330682,0.0000018001508,0.0022115756,0.0044333255,0.00036345056,0.015815735,0.00075832586,0.96136177],"study_design_scores_gemma":[0.0013085816,0.00045035264,0.5793656,0.00004037739,0.00013104484,0.000012014356,0.001792088,0.0814666,0.000096767864,0.3186343,0.016510535,0.00019174427],"about_ca_topic_score_codex":0.00073628547,"about_ca_topic_score_gemma":0.016562002,"teacher_disagreement_score":0.96117,"about_ca_system_score_codex":0.0006728097,"about_ca_system_score_gemma":0.0071945894,"threshold_uncertainty_score":0.9984337},"labels":[],"label_agreement":null},{"id":"W4366384248","doi":"10.3138/cjpe.026.006","title":"J. Fitzpatrick, C. Christie, &amp; M. M. Mark. (2009). <i>Evaluation in Action: Interviews with Expert Evaluators</i> . Thousand Oaks, CA: Sage. xiv + 456 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Action (physics); Psychology; Sociology; Physics","score_opus":0.3641684196792167,"score_gpt":0.47772110415375324,"score_spread":0.11355268447453654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9293127,0.017051077,0.009984993,0.004627008,0.0064280387,0.009063288,0.000051749725,0.00006718653,0.023413982],"genre_scores_gemma":[0.9891888,0.0004303301,0.007911993,0.00051946,0.000446215,0.0004934626,0.000061421975,0.000041949505,0.00090636057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9890019,0.002568539,0.0021007776,0.00058487704,0.0051065255,0.00063736126],"domain_scores_gemma":[0.9917103,0.00028594985,0.0016357206,0.000763234,0.004844266,0.0007605417],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.040738348,0.00037557798,0.0006054776,0.0017447225,0.00031737724,0.0004899637,0.00082718243,0.00021785246,0.017610447],"category_scores_gemma":[0.0029169626,0.0002791596,0.00021927232,0.0021811333,0.00018305639,0.0016413591,0.00003248651,0.00056222046,0.00032639134],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016510944,0.00018267483,0.028036604,0.000012579505,0.00006066099,0.000018283672,0.0052371756,0.0012780866,0.000033098946,0.000031608102,0.039513167,0.92543095],"study_design_scores_gemma":[0.00807724,0.0018241998,0.27006137,0.0006187036,0.0005913967,0.0003633595,0.006529498,0.07318255,0.0003379863,0.0062306914,0.63111156,0.0010714221],"about_ca_topic_score_codex":0.0019076646,"about_ca_topic_score_gemma":0.18559937,"teacher_disagreement_score":0.92435956,"about_ca_system_score_codex":0.0013857904,"about_ca_system_score_gemma":0.008647293,"threshold_uncertainty_score":0.9999661},"labels":[],"label_agreement":null},{"id":"W4366384250","doi":"10.3138/cjpe.27.005","title":"The Key Functions of Collaborative Logic Modelling: Insights from the British Columbia Early Childhood Dental Programs","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Documentation; General partnership; Key (lock); Logic model; Government (linguistics); Knowledge management; Computer science; Process management; Public relations; Political science; Psychology; Business; Public administration","score_opus":0.21203274369979694,"score_gpt":0.40990725897507363,"score_spread":0.1978745152752767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897834,0.0038878303,0.0013870632,0.00080021436,0.0012972075,0.0015499736,0.000030446381,0.0000070074216,0.0012568553],"genre_scores_gemma":[0.99786836,0.000041580468,0.0012293317,0.00009579834,0.0003524162,0.00011065983,0.000028681538,0.000009536059,0.0002636531],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954444,0.0009125912,0.0009520268,0.00015717126,0.0022211988,0.00031256635],"domain_scores_gemma":[0.9941746,0.0005433342,0.00096807315,0.00031507493,0.0036104969,0.00038842185],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006398575,0.00010042607,0.0002112036,0.00008179085,0.001472804,0.0029386224,0.0005196907,0.00008304356,0.0005159218],"category_scores_gemma":[0.0010991032,0.00007259355,0.00014543752,0.0010818916,0.00027391553,0.0008607192,0.000018968887,0.0002707753,0.000041712377],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013536142,0.00019071369,0.21848427,9.153167e-7,0.000120307945,0.0000018742664,0.009175833,0.002685331,0.000007270763,0.00026526226,0.006990548,0.76206416],"study_design_scores_gemma":[0.00116329,0.0008284012,0.8450762,0.00008966461,0.0002427623,0.000045665645,0.018333683,0.025069753,0.000014835202,0.018070757,0.09086806,0.00019694761],"about_ca_topic_score_codex":0.020511515,"about_ca_topic_score_gemma":0.60070926,"teacher_disagreement_score":0.76186717,"about_ca_system_score_codex":0.0002182644,"about_ca_system_score_gemma":0.002934671,"threshold_uncertainty_score":0.99982715},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98880315,0.0008932195,0.00031416214,0.00018501727,0.0007386187,0.008619242,0.00011317325,0.00002281513,0.00031061773],"genre_scores_gemma":[0.9699357,0.0000012763263,0.025961902,0.0003823735,0.0005354018,0.0011607188,0.001983985,0.00002842269,0.000010180098],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99275017,0.004569587,0.00093912997,0.00012856627,0.0007278693,0.00088466407],"domain_scores_gemma":[0.99452776,0.00026409735,0.00047349295,0.0002708959,0.0036602984,0.0008034511],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.011144179,0.00012368744,0.00020272973,0.00045921246,0.0026640967,0.000040709205,0.00024050142,0.00015327547,0.000105725696],"category_scores_gemma":[0.00015044278,0.000117445175,0.00007682666,0.00033222107,0.00011417028,0.00017760757,0.000011633757,0.0008991639,0.0000056959566],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031202033,0.001988976,0.4173466,0.0035366386,0.00007056286,0.000006644711,0.012123666,0.0028781295,0.0001498501,0.0004231722,0.0040395805,0.55712414],"study_design_scores_gemma":[0.01847414,0.03393001,0.11603978,0.0059085255,0.0012177544,0.0000067511096,0.10332038,0.19467033,0.00047102929,0.00810168,0.51687574,0.0009838631],"about_ca_topic_score_codex":0.03548895,"about_ca_topic_score_gemma":0.40609324,"teacher_disagreement_score":0.5561403,"about_ca_system_score_codex":0.0016604014,"about_ca_system_score_gemma":0.0100103365,"threshold_uncertainty_score":0.9986343},"labels":[],"label_agreement":null},{"id":"W4366384275","doi":"10.3138/cjpe.027.006","title":"Ryan, K. E., &amp; Cousins, J. B. (Eds.). (2009). <i>The Sage International Handbook of Educational Evaluation.</i> Thousand Oaks, CA: Sage. 608 Pages.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Sociology; Psychology; Gerontology; Library science; Medicine; Computer science; Physics","score_opus":0.17755472847929304,"score_gpt":0.4727750580837578,"score_spread":0.29522032960446476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62938523,0.16491692,0.01734778,0.08940604,0.039802715,0.0130556105,0.000595395,0.000055965575,0.04543436],"genre_scores_gemma":[0.9898535,0.0005569011,0.004204648,0.0007224767,0.0014862027,0.00020912205,0.0001740039,0.000026443244,0.0027666795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906725,0.0012724423,0.0017014944,0.00027376553,0.0055801054,0.0004996918],"domain_scores_gemma":[0.99031264,0.0009117057,0.0017220034,0.0005662253,0.0058605084,0.00062693394],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032235708,0.00023668852,0.0003586858,0.00079966563,0.0004426348,0.0004390875,0.0009801697,0.00013677921,0.022426955],"category_scores_gemma":[0.006382394,0.00016852183,0.00024355699,0.00091021485,0.00028765277,0.0013730157,0.00003787424,0.00036316417,0.00029243354],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036386697,0.000222272,0.062126674,0.000007914618,0.00012523515,6.5905135e-7,0.0022452148,0.003505039,0.0001950994,0.00031964516,0.107829735,0.82338613],"study_design_scores_gemma":[0.002003869,0.00019087736,0.1399945,0.00021354543,0.00040913545,0.00012448945,0.0008521978,0.019607043,0.00026276388,0.0067654047,0.8292551,0.00032107273],"about_ca_topic_score_codex":0.00045531002,"about_ca_topic_score_gemma":0.015040838,"teacher_disagreement_score":0.82306504,"about_ca_system_score_codex":0.00074975024,"about_ca_system_score_gemma":0.009834842,"threshold_uncertainty_score":0.996517},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8692618,0.021074284,0.0014262529,0.018536866,0.002962642,0.0031204226,0.000025328316,0.00009560584,0.08349681],"genre_scores_gemma":[0.99306184,0.00021494809,0.005555823,0.00035284902,0.0004901101,0.000015663429,0.0000049838945,0.000015314125,0.00028847152],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801856,0.00043355327,0.00036469114,0.0001876174,0.00049457396,0.00050098024],"domain_scores_gemma":[0.9978282,0.00013096828,0.0002105662,0.000112757036,0.0004364765,0.001281018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003497582,0.00012484557,0.00021950572,0.00015578544,0.0004243559,0.00018524984,0.00022560888,0.00021671368,0.0008180198],"category_scores_gemma":[0.0011036894,0.00012207891,0.000058297734,0.00012246652,0.0008024914,0.00029456333,0.000012856985,0.0003094093,0.000011583211],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012506152,0.000026797672,0.009642337,0.000011138823,0.000039034574,0.000034341803,0.06135993,0.0000012396783,0.000016121316,0.024329955,0.011451502,0.8930751],"study_design_scores_gemma":[0.0036391942,0.0019178194,0.14034417,0.00023117053,0.0008532784,0.00025070793,0.074517734,0.00032625024,0.000064993925,0.37865013,0.39825553,0.0009490503],"about_ca_topic_score_codex":0.04280722,"about_ca_topic_score_gemma":0.19310084,"teacher_disagreement_score":0.892126,"about_ca_system_score_codex":0.0002743173,"about_ca_system_score_gemma":0.0029861894,"threshold_uncertainty_score":0.9635668},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28165522,0.01197116,0.038979128,0.016591545,0.036288742,0.0084724715,0.00006814401,0.00030448387,0.6056691],"genre_scores_gemma":[0.9823563,0.0000060565803,0.008621924,0.00019665757,0.0075135543,0.0003043907,0.00002738656,0.000024330464,0.00094937603],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991015,0.000090840644,0.0003100653,0.0000966774,0.00020590876,0.00019497957],"domain_scores_gemma":[0.9989849,0.000018485114,0.00022807125,0.00017935196,0.00041825225,0.00017098032],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009764653,0.00006954133,0.00009213593,0.00019903475,0.00008087765,0.000050024937,0.00015798054,0.00009226691,0.0021345017],"category_scores_gemma":[0.00001882138,0.00006575653,0.00007384243,0.0002073346,0.000049164206,0.000069942325,0.000001026648,0.00014257198,0.000036147572],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007770363,0.00006903987,0.0019523639,0.0000013107567,0.00002052688,0.0000050040644,0.00013642687,0.000011699194,0.00011807642,0.0074447645,0.553448,0.43678498],"study_design_scores_gemma":[0.00046721692,0.00021183223,0.040643558,0.00001776121,0.00004179726,0.000057672656,0.00007028138,0.0001381636,0.000042403877,0.016144847,0.94207335,0.00009112403],"about_ca_topic_score_codex":0.0028897782,"about_ca_topic_score_gemma":0.008170205,"teacher_disagreement_score":0.7007011,"about_ca_system_score_codex":0.00015041165,"about_ca_system_score_gemma":0.0004609098,"threshold_uncertainty_score":0.9987777},"labels":[],"label_agreement":null},{"id":"W4366384291","doi":"10.3138/cjpe.0027.008","title":"Meta-evaluation: Evaluating the Evaluation of the Paris Declaration","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Evaluation methods; Meta-analysis; Strengths and weaknesses; Quality (philosophy); Psychology; Computer science; Management science; Political science; Medicine; Engineering; Social psychology; Law; Reliability engineering","score_opus":0.7957816232407139,"score_gpt":0.5870236538267359,"score_spread":0.20875796941397795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96098644,0.004065051,0.0007365009,0.016335307,0.002346641,0.009341846,0.000009715868,0.000010815894,0.0061676796],"genre_scores_gemma":[0.99622387,0.0000124762555,0.0016438719,0.00036576472,0.00027523696,0.0012547144,0.00001518066,0.00001707606,0.00019178685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9732264,0.008540806,0.0024578976,0.0003717549,0.014992796,0.0004103212],"domain_scores_gemma":[0.9641123,0.0010375741,0.003087276,0.00107267,0.030381324,0.0003088746],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14050691,0.0002561096,0.0004972088,0.000548324,0.00078080606,0.0007824051,0.0013134441,0.00015122445,0.020378957],"category_scores_gemma":[0.016130183,0.00012968751,0.0005753705,0.0019734094,0.00028431488,0.0014929724,0.00004636222,0.00042079517,0.00014415798],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010064508,0.00005282935,0.008378584,0.000004432981,0.0004205836,1.05890216e-7,0.0019893844,0.06408812,0.00025197296,0.0003605446,0.0068642166,0.9175792],"study_design_scores_gemma":[0.0013521746,0.00043032708,0.18385406,0.000036939076,0.00564792,0.000024897552,0.0020164358,0.76085836,0.0004697795,0.04103515,0.004106369,0.00016759669],"about_ca_topic_score_codex":0.0014933308,"about_ca_topic_score_gemma":0.011145987,"teacher_disagreement_score":0.91741157,"about_ca_system_score_codex":0.0008810804,"about_ca_system_score_gemma":0.015448592,"threshold_uncertainty_score":0.9921574},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04443792,0.00090066274,0.93619144,0.014819206,0.0009882854,0.0019218915,0.00005190467,0.00006403614,0.00062463107],"genre_scores_gemma":[0.22730222,0.00002233869,0.771634,0.00058105757,0.00020295432,0.00008091376,0.000085142485,0.000018192419,0.000073166164],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826527,0.00009290948,0.00041675518,0.000323036,0.00052522536,0.0003768166],"domain_scores_gemma":[0.99712217,0.000049558323,0.0002457025,0.00096384453,0.00079071824,0.0008279824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017593966,0.00012874085,0.0001561263,0.00039535036,0.0002454417,0.00088137825,0.0017779698,0.00005283711,0.000118117205],"category_scores_gemma":[0.00023597969,0.00012027032,0.00004739075,0.0008575527,0.000048253045,0.001579823,0.00009447854,0.00017451923,0.000142299],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.30898e-7,0.000028107446,0.00016294967,0.000003870064,0.000025562293,0.0000025595104,0.00049043173,0.0002895247,0.0001036092,0.0042349314,0.09539804,0.89925987],"study_design_scores_gemma":[0.0009900547,0.00047265922,0.008961978,0.0002009346,0.00014193571,0.00023789296,0.0005332585,0.2712922,0.000110215304,0.044094767,0.67228466,0.00067942357],"about_ca_topic_score_codex":0.005209203,"about_ca_topic_score_gemma":0.014111141,"teacher_disagreement_score":0.89858043,"about_ca_system_score_codex":0.00021063547,"about_ca_system_score_gemma":0.0013048614,"threshold_uncertainty_score":0.8499151},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8678862,0.007207902,0.10866088,0.002893196,0.0008314611,0.010557861,0.00009997245,0.000014243676,0.0018482934],"genre_scores_gemma":[0.9820397,5.130287e-7,0.017453477,0.000027880236,0.00030204523,0.00013511175,0.000009559859,0.000010468393,0.000021224614],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935378,0.0025542793,0.0018887793,0.00017616522,0.0015017529,0.00034126177],"domain_scores_gemma":[0.98920697,0.0062690577,0.0022603013,0.00037382884,0.0016010803,0.00028877254],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049262866,0.00014432224,0.000559362,0.00027555396,0.0007715018,0.00047000873,0.0006299733,0.00005506223,0.00012456076],"category_scores_gemma":[0.019925669,0.00007271074,0.00037724987,0.0005294801,0.0007663256,0.00037021047,0.0000482829,0.00018642437,0.000002750537],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098330944,0.00007743525,0.055777356,0.000100115016,0.00021854513,3.858082e-7,0.018995779,0.0007198229,0.000025325347,0.08786621,0.0012375896,0.8348831],"study_design_scores_gemma":[0.0051436727,0.0007855222,0.34552968,0.000556929,0.0007606987,0.000105173756,0.015459596,0.33232158,0.000016506983,0.29495943,0.00410659,0.00025461693],"about_ca_topic_score_codex":0.0006797148,"about_ca_topic_score_gemma":0.0037144134,"teacher_disagreement_score":0.83462846,"about_ca_system_score_codex":0.00011092867,"about_ca_system_score_gemma":0.0006680056,"threshold_uncertainty_score":0.9883299},"labels":[],"label_agreement":null},{"id":"W4366384338","doi":"10.3138/cjpe.0025.011","title":"Je me souviens … de t’avoir trop longtemps cherché","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Logic program; Set (abstract data type); Computer science; Process (computing); Expression (computer science); Epistemology; Artificial intelligence; Programming language; Philosophy; Logic programming","score_opus":0.6896710628632848,"score_gpt":0.5555406698966722,"score_spread":0.13413039296661267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9661593,0.0004970395,0.0032816306,0.002097455,0.001167533,0.0009854111,0.0000071256527,0.00001858179,0.025785968],"genre_scores_gemma":[0.9876087,0.000012501293,0.011457461,0.00028843293,0.00021852218,0.000042645115,0.0000045327934,0.000012635259,0.0003546225],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956443,0.0007981136,0.0009626057,0.00020495965,0.0019801299,0.0004098969],"domain_scores_gemma":[0.99505013,0.00018979122,0.00066948484,0.00034651498,0.0029587753,0.0007853063],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021191187,0.00013527718,0.00024552934,0.00067528826,0.00022069407,0.00028123366,0.00063310127,0.00011082458,0.008359505],"category_scores_gemma":[0.003850304,0.000103799524,0.00017149642,0.0007334507,0.00011802802,0.000692828,0.000012340149,0.00028421474,0.0003065675],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026813841,0.000073106174,0.08025526,0.000003941398,0.000040795116,0.000017984941,0.0069417763,0.0004001202,0.00009499033,0.0010337849,0.004892967,0.90621847],"study_design_scores_gemma":[0.0027924255,0.002663075,0.6696998,0.00011933875,0.00033478966,0.0003306539,0.008012687,0.07386107,0.0013239667,0.083013356,0.15728307,0.00056578673],"about_ca_topic_score_codex":0.00070376426,"about_ca_topic_score_gemma":0.020627595,"teacher_disagreement_score":0.9056527,"about_ca_system_score_codex":0.0006121915,"about_ca_system_score_gemma":0.007694202,"threshold_uncertainty_score":0.99793124},"labels":[],"label_agreement":null},{"id":"W4366384352","doi":"10.3138/cjpe.024.008","title":"Valéry Ridde &amp; Christian Dagenais (Éds.). (2009). <i>Approches et pratiques en évaluation de programme.</i> Montréal : Les Presses de l’Université de Montréal. 358 pages.","year":2009,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Art; Sociology","score_opus":0.14445123495851397,"score_gpt":0.4024079413428465,"score_spread":0.25795670638433255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66751605,0.18622242,0.038846083,0.09326714,0.0014490763,0.005497358,0.0001390927,0.0001352743,0.006927518],"genre_scores_gemma":[0.8774948,0.016257878,0.1004861,0.0015814318,0.0009815079,0.00019360674,0.00027661698,0.00006931189,0.002658724],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98950875,0.0042522037,0.0015659729,0.000559724,0.002797572,0.0013158015],"domain_scores_gemma":[0.99223834,0.00067474536,0.0015743439,0.00056887657,0.003310523,0.001633148],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.031810906,0.00049825263,0.0006010933,0.0008986872,0.00094816973,0.0011652162,0.0009168722,0.00053610926,0.0034790959],"category_scores_gemma":[0.0058931503,0.00048224707,0.00037364455,0.0010423097,0.00027499162,0.0016324748,0.000048655627,0.00085082726,0.00010704198],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00012274248,0.00030660923,0.014432008,0.00004411143,0.00012468577,0.000062506035,0.021587636,0.01630046,0.0005416778,0.00028850898,0.08764335,0.8585457],"study_design_scores_gemma":[0.0024785988,0.0019274977,0.26970285,0.00054800574,0.0010221179,0.0006553725,0.008527149,0.09847045,0.0011796652,0.012027348,0.60276586,0.00069506106],"about_ca_topic_score_codex":0.033725668,"about_ca_topic_score_gemma":0.3491635,"teacher_disagreement_score":0.8578507,"about_ca_system_score_codex":0.0043890355,"about_ca_system_score_gemma":0.02066079,"threshold_uncertainty_score":0.9998717},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917448,0.0022197182,0.0007825127,0.0014084745,0.00049220497,0.003298307,0.000010165267,0.00001353825,0.000030256038],"genre_scores_gemma":[0.9815475,0.00003909398,0.017882146,0.00008379646,0.00023101972,0.00017088985,0.000030310617,0.0000143017105,9.960845e-7],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99760383,0.00039902216,0.00096046575,0.0001073275,0.00060264487,0.00032669996],"domain_scores_gemma":[0.9964796,0.000052331256,0.00075199583,0.00020615724,0.0023055202,0.00020444387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037144506,0.00015254322,0.00034024921,0.00029379697,0.00073902454,0.000033723027,0.00015870135,0.000055225937,0.00007384402],"category_scores_gemma":[0.00044336694,0.000119295895,0.00026193119,0.0006325964,0.000039719678,0.00017893894,0.000009069175,0.00026504273,2.3560801e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001388293,0.00028867257,0.028887013,0.00015665231,0.00027409664,0.0000012438891,0.07576282,0.00055375363,0.0042738374,0.00006657951,0.00092655193,0.88866997],"study_design_scores_gemma":[0.008131171,0.023948824,0.6463411,0.00055648334,0.0050782394,0.00015631797,0.25890762,0.049344238,0.0028834278,0.0033782083,0.00065100356,0.00062340614],"about_ca_topic_score_codex":0.00703608,"about_ca_topic_score_gemma":0.010978371,"teacher_disagreement_score":0.88804656,"about_ca_system_score_codex":0.00028859318,"about_ca_system_score_gemma":0.0011409442,"threshold_uncertainty_score":0.99957615},"labels":[],"label_agreement":null},{"id":"W4366384398","doi":"10.3138/cjpe.0025.004","title":"L’influence de l’évaluation sur les suites des projets d’expérimentation : l’exemple des projets d’informatisation au Québec","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université Laval","funders":"","keywords":"Formative assessment; Valuation (finance); Political science; Action plan; Knowledge management; Business; Sociology; Pedagogy; Management; Computer science; Economics; Accounting","score_opus":0.3539878063192124,"score_gpt":0.47094040675696225,"score_spread":0.11695260043774985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927232,0.00036539562,0.0022793151,0.00026757742,0.0001703708,0.0015717234,0.0000072101566,0.000027066342,0.0025880886],"genre_scores_gemma":[0.9844763,0.00004275402,0.01491718,0.00008907969,0.000106331005,0.0002205346,0.000030083835,0.000018200893,0.00009948126],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99431187,0.00091980695,0.001523277,0.00026344167,0.0024509141,0.00053071696],"domain_scores_gemma":[0.99081844,0.00038965407,0.0013599376,0.0003196925,0.0065915594,0.00052071066],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016868737,0.0002280652,0.00028563463,0.0010090168,0.0009833279,0.00036842696,0.0005439035,0.00013485475,0.000954941],"category_scores_gemma":[0.008411306,0.00018860404,0.00014885807,0.000998452,0.00040415506,0.003561389,0.000019783665,0.00022604647,0.00008897913],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029247976,0.000057615587,0.38320822,0.000016019294,0.00002468795,0.0000026959258,0.06335707,0.0020132235,0.00022040778,0.000100684156,0.00029419168,0.5506759],"study_design_scores_gemma":[0.000979164,0.0007229464,0.95150065,0.00011954698,0.0001026165,0.00012081856,0.0053761993,0.030204805,0.002090236,0.0063047605,0.0022512854,0.00022694173],"about_ca_topic_score_codex":0.15701804,"about_ca_topic_score_gemma":0.5986734,"teacher_disagreement_score":0.5682925,"about_ca_system_score_codex":0.0024974572,"about_ca_system_score_gemma":0.022152748,"threshold_uncertainty_score":0.99995834},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W4366384407","doi":"10.3138/cjpe.0025.015","title":"Réflexions autour des 25 ans de la <i>Revue canadienne d’évaluation de programme</i> : l’évaluation au passé, au présent, et au futur","year":2011,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Economics; Humanities; Philosophy","score_opus":0.3511264130259222,"score_gpt":0.4670286099850321,"score_spread":0.11590219695910992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93144196,0.001262691,0.018643826,0.0195165,0.005306934,0.0035193102,0.00008155064,0.00005522534,0.020172024],"genre_scores_gemma":[0.9371318,0.00020472295,0.058691736,0.0006395547,0.0015292097,0.000479144,0.00010444517,0.00007312847,0.0011462233],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9843196,0.007984751,0.0023804798,0.0006951127,0.0022890575,0.002330984],"domain_scores_gemma":[0.9879731,0.0009823996,0.0020175693,0.00071159087,0.00537217,0.0029431614],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08701528,0.00057745527,0.0006823147,0.0015702151,0.0013880274,0.00093939295,0.0010233207,0.00062722625,0.0043994067],"category_scores_gemma":[0.00918734,0.00057259016,0.0004979591,0.0021649476,0.0009685875,0.0023947386,0.00004865199,0.0010308612,0.00014818305],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000053945798,0.00036733825,0.17766392,0.00007392025,0.0001463509,0.00004565362,0.11106018,0.005224754,0.00008282027,0.0058604493,0.0011797799,0.6982409],"study_design_scores_gemma":[0.0026349942,0.0021138757,0.6431869,0.00085175555,0.001259248,0.0008824984,0.017745117,0.18897116,0.00019940201,0.09370403,0.047738932,0.00071208127],"about_ca_topic_score_codex":0.30575317,"about_ca_topic_score_gemma":0.9079721,"teacher_disagreement_score":0.6975288,"about_ca_system_score_codex":0.014018771,"about_ca_system_score_gemma":0.12133292,"threshold_uncertainty_score":0.999912},"labels":[],"label_agreement":null},{"id":"W4366384488","doi":"10.3138/cjpe.0025.006","title":"Chronique d’une évaluation ratée","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Charter; Confusion; Transparency (behavior); Pluralism (philosophy); Valuation (finance); Management science; Engineering ethics; Political science; Arbitration; Public relations; Sociology; Law and economics; Epistemology; Business; Psychology; Law; Accounting; Economics; Engineering","score_opus":0.6502887605764812,"score_gpt":0.5430176093994878,"score_spread":0.10727115117699337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8935444,0.00084652175,0.013067436,0.0051350184,0.0033299832,0.0027886585,0.000008347454,0.000034925033,0.08124476],"genre_scores_gemma":[0.9883535,0.0000122812935,0.010697971,0.00022819887,0.00022380774,0.00007113505,0.000009473922,0.000011460957,0.00039220482],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950197,0.00079285575,0.0011405223,0.00021139723,0.0025418177,0.00029373163],"domain_scores_gemma":[0.99367017,0.00014215155,0.00088814844,0.00035402415,0.004444869,0.0005006256],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023800347,0.00013291463,0.00023765898,0.0008252805,0.00022954273,0.00026576186,0.0005366179,0.00009926945,0.011271434],"category_scores_gemma":[0.0026565166,0.00010262055,0.00015138682,0.0010776499,0.000109473425,0.0009565235,0.000010320622,0.00021636974,0.00029355646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001898837,0.000049869897,0.018650042,0.0000023490459,0.00002415693,0.0000070270335,0.004517838,0.0004951057,0.000065365566,0.0012082695,0.0053834417,0.96957755],"study_design_scores_gemma":[0.0024752268,0.001967605,0.6582496,0.00009075103,0.0002436959,0.00016503205,0.0036682987,0.10537877,0.0014647237,0.11889352,0.10697034,0.00043242608],"about_ca_topic_score_codex":0.0016190053,"about_ca_topic_score_gemma":0.029167535,"teacher_disagreement_score":0.9691451,"about_ca_system_score_codex":0.00042073702,"about_ca_system_score_gemma":0.008149194,"threshold_uncertainty_score":0.99747366},"labels":[],"label_agreement":null},{"id":"W4366384492","doi":"10.3138/cjpe.0025.001","title":"Guest Editor’s Remarks: As I Recall—or How to take Advantage of Less-Than-Successful Evaluation Experiences","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Recall; Psychology; Cognitive psychology","score_opus":0.3693533046613303,"score_gpt":0.5143513771140032,"score_spread":0.14499807245267293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96599096,0.00059270125,0.0017402376,0.002872818,0.014851342,0.0031371352,0.00001689469,0.000018827744,0.01077911],"genre_scores_gemma":[0.98985374,0.000018544912,0.007176994,0.00017328386,0.002005881,0.00034110862,0.000016593414,0.000018397175,0.00039546908],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.990565,0.0012577509,0.0015365392,0.0004254547,0.0057732086,0.0004420552],"domain_scores_gemma":[0.988177,0.0003132763,0.001657329,0.0005817862,0.00840089,0.0008696899],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027689371,0.00023812543,0.00046745734,0.001234518,0.00025356113,0.00041900552,0.0010792192,0.0001617174,0.0075989803],"category_scores_gemma":[0.011703657,0.00017279817,0.00018946294,0.0014896902,0.00023310709,0.0017238023,0.0000323687,0.00023977198,0.00009789646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026795382,0.00016716571,0.025206354,0.000016729444,0.00006266917,0.000014707496,0.03195287,0.000337325,0.00021990415,0.00020262747,0.026700173,0.91485155],"study_design_scores_gemma":[0.0065136277,0.013552928,0.2091686,0.0010314867,0.0009292806,0.0002816917,0.38628814,0.051724404,0.010947675,0.014391521,0.30355367,0.0016169975],"about_ca_topic_score_codex":0.00095092686,"about_ca_topic_score_gemma":0.03613507,"teacher_disagreement_score":0.91323453,"about_ca_system_score_codex":0.0005020298,"about_ca_system_score_gemma":0.008927947,"threshold_uncertainty_score":0.9966905},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055308387,0.07622077,0.00013269487,0.0040867897,0.012947579,0.0010561196,0.0001504574,0.000015501604,0.8500817],"genre_scores_gemma":[0.9858729,0.00016858349,0.0012228636,0.00013584192,0.0060951333,0.000016077858,0.000023364715,0.000024184808,0.0064410297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834543,0.00017615361,0.00057185045,0.00012136883,0.00040767793,0.00037753652],"domain_scores_gemma":[0.9962703,0.000024033821,0.0004528814,0.00016002866,0.0024198603,0.00067291514],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015904295,0.00015287526,0.00023874761,0.00040476953,0.00038589112,0.00036247607,0.0002083588,0.00009577258,0.031104771],"category_scores_gemma":[0.00039735742,0.00014611134,0.00026738137,0.00009199587,0.0004041793,0.0002539174,0.0000054826555,0.00022464644,0.00013608702],"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":[0.000010881785,0.00023545264,0.00318066,0.00005573225,0.0005387712,0.00022814571,0.021826,0.00005969198,9.503751e-7,0.49783564,0.021617351,0.45441073],"study_design_scores_gemma":[0.0004903693,0.0005996386,0.0019305209,0.00020214722,0.0020573633,0.000037438513,0.0038083463,0.002398748,0.000019831285,0.025360338,0.9628677,0.00022756383],"about_ca_topic_score_codex":0.06135813,"about_ca_topic_score_gemma":0.18920276,"teacher_disagreement_score":0.9412503,"about_ca_system_score_codex":0.0002706041,"about_ca_system_score_gemma":0.0030668129,"threshold_uncertainty_score":0.9697809},"labels":[],"label_agreement":null},{"id":"W4366384499","doi":"10.3138/cjpe.0025.013","title":"Learning from Evaluation Misadventures: The Importance of Good Communication","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Relevance (law); Key (lock); Order (exchange); Quality (philosophy); Government (linguistics); Knowledge management; Process management; Management science; Computer science; Business; Psychology; Risk analysis (engineering); Engineering ethics; Political science; Engineering; Epistemology; Artificial intelligence; Computer security","score_opus":0.48907842534633805,"score_gpt":0.5126845869829371,"score_spread":0.02360616163659901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98349124,0.0025646926,0.0005850393,0.0012642194,0.0005171812,0.0013148063,0.0000054768793,0.0000072129137,0.010250123],"genre_scores_gemma":[0.9965019,0.000036823123,0.003092759,0.00011166276,0.000082904095,0.00007113209,0.000033622448,0.000008825474,0.000060360253],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934087,0.0020265,0.0012603165,0.0001719098,0.0029415176,0.00019107682],"domain_scores_gemma":[0.99181134,0.0004937689,0.0019261243,0.0005817923,0.0049822126,0.00020475488],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030684248,0.00011319663,0.000223231,0.0003335026,0.00030044228,0.00014657735,0.00087194913,0.00008327534,0.006040428],"category_scores_gemma":[0.005285184,0.00007468922,0.00014619941,0.0006598761,0.00013360394,0.0006088484,0.000020293972,0.0003222617,0.000036457866],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027685037,0.00005768621,0.2747269,0.0000022461184,0.00006027301,7.164481e-7,0.011284951,0.003020111,0.00005550102,0.00077290856,0.0009532202,0.7090378],"study_design_scores_gemma":[0.0014042839,0.00064076704,0.76617485,0.0001024008,0.00037007313,0.000013253682,0.01257116,0.13405116,0.00048473835,0.06894502,0.015067846,0.00017444162],"about_ca_topic_score_codex":0.0016906819,"about_ca_topic_score_gemma":0.032220334,"teacher_disagreement_score":0.7088634,"about_ca_system_score_codex":0.0002780368,"about_ca_system_score_gemma":0.0035901815,"threshold_uncertainty_score":0.9981145},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9839216,0.0033135933,0.000004937929,0.0015230027,0.0005492384,0.00068325555,0.000012564339,0.000011827829,0.009979983],"genre_scores_gemma":[0.99870104,0.00017398599,0.0006415092,0.000010510468,0.00023942381,0.0000145759595,0.000012761455,6.2481087e-7,0.00020555538],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99925977,0.0000663563,0.00019943333,0.00009544967,0.00019944632,0.00017957328],"domain_scores_gemma":[0.9995506,0.000009114913,0.00011610614,0.000032329823,0.000101298145,0.00019059764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005636903,0.00006572949,0.00009581484,0.0000394232,0.000073053845,0.000030489009,0.00014791552,0.00005846142,0.00043078038],"category_scores_gemma":[0.0000099937715,0.000014026048,0.000051712694,0.00013025416,0.000025736588,0.0000989369,0.0000053784415,0.00007972844,0.000014957888],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008533078,0.00003760287,0.0019887884,0.0000019743277,0.000017597424,0.000022453227,0.003347187,0.0000017178334,0.000020549478,0.000109837856,0.000052824827,0.9943909],"study_design_scores_gemma":[0.00047631227,0.00041171128,0.59824646,0.00010244302,0.000065203574,0.00000994223,0.002545155,0.00008401303,0.000069094545,0.025717586,0.3720904,0.00018168229],"about_ca_topic_score_codex":0.0014629608,"about_ca_topic_score_gemma":0.11424135,"teacher_disagreement_score":0.99420923,"about_ca_system_score_codex":0.000061927814,"about_ca_system_score_gemma":0.000044648124,"threshold_uncertainty_score":0.90192145},"labels":[],"label_agreement":null},{"id":"W4366384617","doi":"10.3138/cjpe.0025.003","title":"Evaluation, Valuation, Negotiation: Some Reflections Towards a Culture of Evaluation","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Negotiation; Valuation (finance); Consolidation (business); Contingent valuation; Program evaluation; Management science; Political science; Process management; Business; Knowledge management; Computer science; Economics; Public administration; Willingness to pay; Accounting","score_opus":0.6159822124301794,"score_gpt":0.5735759694267458,"score_spread":0.04240624300343354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7571459,0.013092341,0.0255772,0.0061448347,0.015654394,0.022472931,0.00012999165,0.00013604909,0.15964638],"genre_scores_gemma":[0.98851514,0.00004180587,0.010029952,0.00019061402,0.000492281,0.00044803473,0.00008195639,0.000025001678,0.00017523066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98073864,0.0037310813,0.0027534482,0.0004962781,0.011823661,0.00045687507],"domain_scores_gemma":[0.952684,0.00018241446,0.0027084446,0.00074367144,0.043093164,0.000588345],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.084139585,0.0002980059,0.0005269877,0.0018469035,0.00048239797,0.00030166726,0.0007405121,0.00025791215,0.013526122],"category_scores_gemma":[0.017272515,0.00024422017,0.00035541272,0.0025193298,0.00022097465,0.0024763579,0.000026486015,0.0003747576,0.00012852564],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050102288,0.00025008636,0.007004163,0.000011327901,0.00021077014,0.0000018447244,0.019618278,0.009565724,0.00022206994,0.0029501845,0.0055449395,0.95457053],"study_design_scores_gemma":[0.0050906944,0.0022925148,0.2550907,0.00016989544,0.00279909,0.00012905415,0.009465184,0.36409116,0.0020537106,0.3386957,0.0195192,0.0006030861],"about_ca_topic_score_codex":0.0011059708,"about_ca_topic_score_gemma":0.011632577,"teacher_disagreement_score":0.95396745,"about_ca_system_score_codex":0.0015798485,"about_ca_system_score_gemma":0.025886485,"threshold_uncertainty_score":0.9959009},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8982754,0.003989898,0.00071136735,0.07642004,0.0040674536,0.0017139696,0.000020750034,0.000029760631,0.0147713795],"genre_scores_gemma":[0.98524904,0.0003648415,0.01028883,0.0014959505,0.0019069539,0.00019154263,0.00003468914,0.000027219741,0.00044092766],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9908542,0.0063285013,0.00078851235,0.0002870029,0.0009697778,0.00077202136],"domain_scores_gemma":[0.9953545,0.0012558561,0.00090412115,0.00018958627,0.0014343553,0.0008615821],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030995516,0.00024381369,0.00029102978,0.00037864118,0.0010252423,0.00019567464,0.00045247236,0.00041445103,0.0009535811],"category_scores_gemma":[0.0043599964,0.00025436492,0.00018097214,0.0007508248,0.0013296437,0.00055777514,0.000009013795,0.0005990966,0.00004058741],"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":[0.000020304558,0.00033877962,0.05714842,0.000038360093,0.0001800747,0.000008689108,0.41352454,0.00028481724,0.000025483188,0.11063871,0.0040012994,0.41379052],"study_design_scores_gemma":[0.0023715203,0.0025756543,0.31950578,0.00068259414,0.0014798737,0.00015764235,0.32176548,0.007795956,0.00035990038,0.095691524,0.24654573,0.0010683446],"about_ca_topic_score_codex":0.019408338,"about_ca_topic_score_gemma":0.010826451,"teacher_disagreement_score":0.4127222,"about_ca_system_score_codex":0.0017481218,"about_ca_system_score_gemma":0.011500776,"threshold_uncertainty_score":0.9999909},"labels":[],"label_agreement":null},{"id":"W4366384635","doi":"10.3138/cjpe.0025.014","title":"Reflections Over 25 Years: Evaluation Then, Now, and Into the Future","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Political science","score_opus":0.390329876993874,"score_gpt":0.5523569994362977,"score_spread":0.16202712244242368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9777834,0.0024265065,0.00039012806,0.0044446685,0.0023291882,0.0016430827,0.0000034436996,0.000011891012,0.010967724],"genre_scores_gemma":[0.9960481,0.000062631356,0.0028075576,0.00035817543,0.00047841747,0.00008940808,0.0000054825705,0.000009188659,0.0001410713],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99573195,0.00089868746,0.0006725783,0.00019751543,0.0022947558,0.00020448738],"domain_scores_gemma":[0.99584407,0.00014339578,0.0005617092,0.00034085737,0.0028146305,0.0002953543],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021562753,0.00011052439,0.00015385001,0.0005075449,0.00037114622,0.00036264912,0.00039681574,0.00008925428,0.0043801377],"category_scores_gemma":[0.0011892116,0.00006999607,0.000092359754,0.0007801391,0.00013503843,0.00072832586,0.000016060825,0.00025247628,0.00007182585],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012778564,0.00002482437,0.016900415,0.0000013679336,0.000027401305,0.0000013801549,0.013927299,0.00010255013,0.000026614523,0.00080100907,0.004039551,0.9641348],"study_design_scores_gemma":[0.00084608333,0.0004277351,0.7497673,0.000025108931,0.00020213812,0.000043633005,0.0068784496,0.023637976,0.000034849894,0.051822532,0.16618027,0.00013390533],"about_ca_topic_score_codex":0.00062795356,"about_ca_topic_score_gemma":0.08852159,"teacher_disagreement_score":0.9640009,"about_ca_system_score_codex":0.000316314,"about_ca_system_score_gemma":0.0032836727,"threshold_uncertainty_score":0.99653},"labels":[],"label_agreement":null},{"id":"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2799338,0.05091825,0.00050716527,0.65113676,0.0021647792,0.0049790367,0.000056053872,0.00003094669,0.010273209],"genre_scores_gemma":[0.98145854,0.001186665,0.0017194509,0.0026104117,0.0016337076,0.000080588,0.000050002403,0.000035231893,0.011225372],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99159163,0.0016869203,0.0011093006,0.00048382324,0.004224852,0.00090344815],"domain_scores_gemma":[0.9909075,0.0006646961,0.0005142001,0.0007791628,0.00579337,0.0013410846],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022415955,0.00024182431,0.00035776282,0.0010243303,0.0010203237,0.0068721524,0.0013453446,0.00017535254,0.0014030808],"category_scores_gemma":[0.006313437,0.00015599439,0.000152437,0.0016902538,0.00041030973,0.002017258,0.0000767287,0.00082277926,0.00011129406],"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":[0.00007429593,0.000022901955,0.00024834508,0.0000019137813,0.000020275333,0.000015892703,0.004653396,0.0000890571,0.00007759877,0.00015623539,0.41397572,0.58066434],"study_design_scores_gemma":[0.0010958703,0.0017892136,0.0040749256,0.00026136046,0.000060348404,0.00011948629,0.029051898,0.0024602306,0.00010060302,0.04690547,0.9138268,0.00025374326],"about_ca_topic_score_codex":0.001540473,"about_ca_topic_score_gemma":0.3351215,"teacher_disagreement_score":0.70152473,"about_ca_system_score_codex":0.000478366,"about_ca_system_score_gemma":0.0076854485,"threshold_uncertainty_score":0.99950975},"labels":[],"label_agreement":null},{"id":"W4366384698","doi":"10.3138/cjpe.0025.005","title":"Successful Evaluation Management: Engaging Mind and Spirit","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outcome (game theory); Quality (philosophy); Affect (linguistics); Psychology; Key (lock); Evaluation methods; Engineering ethics; Business; Process management; Public relations; Computer science; Political science; Epistemology; Engineering; Philosophy; Economics","score_opus":0.5238099666472505,"score_gpt":0.5252574195694363,"score_spread":0.0014474529221857324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94864225,0.0010190253,0.0011883726,0.0010639961,0.0009906779,0.0017417334,0.0000038020132,0.000007345458,0.045342803],"genre_scores_gemma":[0.990713,0.00002124864,0.008821833,0.0001159107,0.00011244835,0.00006720421,0.000007328913,0.000009397293,0.00013163085],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949167,0.00079630874,0.0009348377,0.00026305995,0.0028062174,0.0002828804],"domain_scores_gemma":[0.99545974,0.0001189463,0.00069718354,0.0002906614,0.0029792439,0.00045420136],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.031249056,0.0001352096,0.00020522413,0.0010376524,0.0002877122,0.00040984538,0.00040416172,0.00006920767,0.007722329],"category_scores_gemma":[0.0013045293,0.00011036064,0.000083074425,0.00070881046,0.00010995297,0.001061169,0.000020376203,0.00019239313,0.00009293137],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011326739,0.000025531308,0.055941585,0.000004552759,0.000031895855,0.0000065947606,0.0023895504,0.00013846744,0.0000065183635,0.00048175242,0.00048376634,0.94047844],"study_design_scores_gemma":[0.0031388227,0.0007003672,0.723285,0.00014295791,0.00064918376,0.00012143422,0.011445577,0.15508203,0.0002752786,0.046666272,0.05810463,0.0003884111],"about_ca_topic_score_codex":0.00031433234,"about_ca_topic_score_gemma":0.0067791953,"teacher_disagreement_score":0.94009006,"about_ca_system_score_codex":0.0002800931,"about_ca_system_score_gemma":0.0017502793,"threshold_uncertainty_score":0.99753296},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6029388,0.0009946726,0.0011956607,0.0069670025,0.0011007229,0.0021257775,0.00001313089,0.00004738749,0.38461685],"genre_scores_gemma":[0.99637544,0.0000103823895,0.0032018626,0.00006132245,0.00022855106,0.000029389705,0.0000020695666,0.0000043027117,0.00008666368],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914896,0.00013394446,0.00019556073,0.000055821696,0.0002890549,0.00017665974],"domain_scores_gemma":[0.998673,0.000019641997,0.00016662064,0.00007430092,0.0006974698,0.00036894222],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016958143,0.00003990121,0.00006560461,0.000112085065,0.000351639,0.000084250205,0.0002212138,0.000039191393,0.0011450918],"category_scores_gemma":[0.00030717975,0.000037489863,0.00004584786,0.00024675962,0.00013664938,0.0002558766,0.0000035624462,0.00008596962,0.000027821065],"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":[0.000005199137,0.00005676416,0.023922123,0.0000053176586,0.000030350053,0.000008537526,0.02153683,0.000016843174,0.000019116556,0.16050515,0.0018890437,0.7920047],"study_design_scores_gemma":[0.00022936372,0.00011804596,0.06261388,0.000021485952,0.00006734691,0.000006368382,0.0025679779,0.00013821045,0.000054865184,0.02309301,0.9109842,0.00010520465],"about_ca_topic_score_codex":0.059427153,"about_ca_topic_score_gemma":0.34509408,"teacher_disagreement_score":0.90909517,"about_ca_system_score_codex":0.00018762,"about_ca_system_score_gemma":0.0029450392,"threshold_uncertainty_score":0.999768},"labels":[],"label_agreement":null},{"id":"W4366384728","doi":"10.3138/cjpe.0025.009","title":"Navigating Expectations, Values and Context: A Canadian Evaluator Abroad","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Politics; Political science; Psychology; Public relations; Sociology; History; Law; Archaeology","score_opus":0.3205900033941147,"score_gpt":0.530989583284331,"score_spread":0.2103995798902163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366384728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874447,0.0028605787,0.0002278511,0.0016681186,0.0009523461,0.0012189492,0.000015620048,0.000012816902,0.0055990284],"genre_scores_gemma":[0.99327075,0.00001467131,0.0060396637,0.0003456643,0.00014284928,0.00008025703,0.000009846634,0.000014039881,0.00008226998],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995653,0.00071004237,0.0010906088,0.00026697386,0.0018717363,0.00040767086],"domain_scores_gemma":[0.9936472,0.00022053043,0.0007116297,0.0002950145,0.0038179809,0.0013075995],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013024749,0.00016441217,0.00027770226,0.0005661823,0.00049653376,0.00044517982,0.0004304566,0.00010286165,0.0044950154],"category_scores_gemma":[0.004216396,0.00013539844,0.00010761699,0.00069884537,0.00017052445,0.0009318901,0.000011174412,0.00032902227,0.00012051237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000087161425,0.000016922211,0.055688,0.0000026273533,0.000028976536,0.000009616746,0.017410642,0.00003589058,0.000009383557,0.00035530922,0.001770074,0.92466384],"study_design_scores_gemma":[0.0040832893,0.0022009523,0.64523643,0.00046204164,0.00049607205,0.00045366012,0.1087494,0.11248974,0.00051332556,0.08099003,0.043389127,0.0009359333],"about_ca_topic_score_codex":0.07461027,"about_ca_topic_score_gemma":0.63902986,"teacher_disagreement_score":0.9237279,"about_ca_system_score_codex":0.00055274664,"about_ca_system_score_gemma":0.009426222,"threshold_uncertainty_score":0.996415},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9375418,0.0031323235,0.00019209835,0.011608076,0.0026637136,0.002716151,0.0000010442831,0.000016265632,0.042128526],"genre_scores_gemma":[0.9990454,0.000059634902,0.00022271668,0.00009019696,0.00016637877,0.00009780081,0.0000018645599,0.0000034266438,0.00031263262],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989229,0.0003562699,0.00014670551,0.00005914315,0.00038359762,0.0001314142],"domain_scores_gemma":[0.99879444,0.00017480504,0.00014232757,0.000035978755,0.0007006285,0.00015179622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026444353,0.000043982353,0.000052021347,0.000080732105,0.00038599066,0.00014298767,0.000097517695,0.000038091595,0.00020272576],"category_scores_gemma":[0.00054323615,0.00003309461,0.00002449736,0.000066445995,0.00014450583,0.00026297476,0.0000017137269,0.00008882755,0.00002107691],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023498613,0.00002320411,0.017146906,0.000006250105,0.00004587439,0.000002794386,0.0055423826,0.000064378466,0.00011547125,0.061914176,0.017692197,0.89742285],"study_design_scores_gemma":[0.00048474676,0.00028076454,0.28545976,0.000084943196,0.000031130963,0.0000028556633,0.0011703948,0.0009269016,0.00009867227,0.023192093,0.68813634,0.00013138638],"about_ca_topic_score_codex":0.0060336357,"about_ca_topic_score_gemma":0.025019076,"teacher_disagreement_score":0.8972915,"about_ca_system_score_codex":0.0009822682,"about_ca_system_score_gemma":0.0021288402,"threshold_uncertainty_score":0.9927718},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8828085,0.00097448006,0.00025081835,0.0037627656,0.0019059705,0.0006186031,0.0000037209945,0.000029370407,0.10964574],"genre_scores_gemma":[0.9913967,0.000054994405,0.0068605086,0.00019747249,0.0011587789,0.000052842966,0.0000086459595,0.0000115068715,0.00025852182],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971566,0.0017170944,0.00029194955,0.00010839121,0.0003949152,0.00033100834],"domain_scores_gemma":[0.99795854,0.00028083616,0.00027821472,0.00008584661,0.0009394533,0.00045710627],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013436038,0.00007869549,0.00010915181,0.00020637538,0.0004533077,0.000084182095,0.00025283993,0.00015961238,0.0010914671],"category_scores_gemma":[0.0034999312,0.0000849578,0.00008875509,0.00028897333,0.00042638465,0.00024093698,0.0000029732212,0.00024359916,0.000019704074],"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":[0.000009417949,0.00015593153,0.12659782,0.000019412551,0.00011351109,0.00001899335,0.32168436,0.000052012172,0.000030010533,0.031729765,0.012206482,0.5073823],"study_design_scores_gemma":[0.0012054247,0.00052704086,0.33155772,0.00019301995,0.00038622585,0.00009335195,0.21909977,0.0003741119,0.00008967737,0.05321895,0.39279497,0.00045972207],"about_ca_topic_score_codex":0.006420785,"about_ca_topic_score_gemma":0.018410992,"teacher_disagreement_score":0.5069226,"about_ca_system_score_codex":0.00032742164,"about_ca_system_score_gemma":0.0075892243,"threshold_uncertainty_score":0.99982166},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9871233,0.00048528865,0.0031431299,0.0039713727,0.00044796345,0.0006602884,0.0000044985754,0.000019178477,0.004144949],"genre_scores_gemma":[0.9919119,0.00016476742,0.0068331654,0.00015811795,0.00076435664,0.000044394015,0.0000038969306,0.000005653062,0.00011373171],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969276,0.0011054731,0.0003280961,0.00013864036,0.00081700896,0.00068313576],"domain_scores_gemma":[0.99815047,0.00011333595,0.0003516509,0.00007023957,0.0006916094,0.00062267465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01220382,0.00010601877,0.00013825255,0.0001390579,0.000985692,0.0004083365,0.00025843803,0.00012967274,0.00013431069],"category_scores_gemma":[0.0030940159,0.00010615629,0.00008758858,0.00058390736,0.00044719575,0.00081876124,0.0000027566048,0.0001527961,0.0000012406995],"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":[0.000029547302,0.00009206124,0.08118709,0.000009324571,0.000023025981,0.000010372924,0.37505996,0.0030259925,0.00082581723,0.009777156,0.0029703882,0.5269893],"study_design_scores_gemma":[0.0010255664,0.001263795,0.6734304,0.00030871044,0.00016112976,0.0000340254,0.0543056,0.0058724917,0.0011843445,0.2363582,0.025637427,0.00041832833],"about_ca_topic_score_codex":0.25799373,"about_ca_topic_score_gemma":0.8079144,"teacher_disagreement_score":0.5922433,"about_ca_system_score_codex":0.003818433,"about_ca_system_score_gemma":0.015056577,"threshold_uncertainty_score":0.99850696},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1119356,0.0021052305,0.80053335,0.018662212,0.0004211851,0.0068909638,0.000058267775,0.00006457217,0.059328612],"genre_scores_gemma":[0.13017927,0.00008119861,0.8683713,0.00013902207,0.0001977913,0.0004774958,0.00002444583,0.000023906356,0.0005055736],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9718074,0.024956109,0.0006662909,0.0003707478,0.001428863,0.00077054877],"domain_scores_gemma":[0.9883984,0.0044999165,0.0003079222,0.0003125749,0.004630703,0.001850488],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13011473,0.00015235871,0.00032513877,0.00078697555,0.0012917009,0.00044377617,0.00055377884,0.00013710489,0.00028998437],"category_scores_gemma":[0.021423956,0.0001431023,0.000055792756,0.0013463047,0.00095298345,0.00051364413,0.000030128625,0.0005120963,0.000051252875],"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":[0.000027557257,0.00004798406,0.000033373577,0.000012934231,0.000024885992,4.1209822e-7,0.047639035,0.000017724153,0.0022723333,0.2878623,0.008070543,0.6539909],"study_design_scores_gemma":[0.0003964987,0.0007066415,0.0011623842,0.00005429819,0.000034673503,0.0000017370296,0.06259271,0.0001997888,0.00022845312,0.15689099,0.77751994,0.00021188703],"about_ca_topic_score_codex":0.013308297,"about_ca_topic_score_gemma":0.17015247,"teacher_disagreement_score":0.7694494,"about_ca_system_score_codex":0.00046666013,"about_ca_system_score_gemma":0.0037548454,"threshold_uncertainty_score":0.993485},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9780146,0.0004112266,0.00002506895,0.01929166,0.000064853244,0.00041493302,0.0000048390652,0.000011474865,0.0017613388],"genre_scores_gemma":[0.9988628,0.00007479667,0.00040487104,0.00033270568,0.00017342369,0.000009452428,0.000051783096,3.8323182e-7,0.000089766356],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990258,0.0001609025,0.00018834832,0.00007679332,0.00030617413,0.00024198707],"domain_scores_gemma":[0.99932426,0.000023658873,0.0000911858,0.000016131802,0.00024018453,0.00030457173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009948871,0.00007094666,0.00008348973,0.000031095184,0.00015420181,0.000098464756,0.000119794284,0.00006489543,0.0006104707],"category_scores_gemma":[0.0000474368,0.000026344725,0.00006641786,0.00017136429,0.00002756605,0.00022165569,0.0000013905246,0.00013577938,0.000010042414],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000081034805,0.00004501818,0.0020109063,0.0000015386164,0.000011040395,0.000010843521,0.00031675756,0.000011130799,0.016103242,0.00038191743,0.0023949891,0.9787045],"study_design_scores_gemma":[0.00015960619,0.0008103118,0.9684525,0.00003567258,0.000024371451,0.0000882408,0.0007003465,0.00006786031,0.0016304282,0.0048073945,0.023123732,0.00009951617],"about_ca_topic_score_codex":0.0019855648,"about_ca_topic_score_gemma":0.025184585,"teacher_disagreement_score":0.978605,"about_ca_system_score_codex":0.00022171179,"about_ca_system_score_gemma":0.00023264202,"threshold_uncertainty_score":0.99260324},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9562357,0.00078903005,0.00010538834,0.011754087,0.0012312476,0.0026887117,0.000045864435,0.000007620475,0.027142338],"genre_scores_gemma":[0.9973893,0.000009959801,0.0010907768,0.0008903092,0.00033024504,0.0000612368,0.0000034913776,0.000010771849,0.00021390592],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973761,0.0005300663,0.00047506383,0.00015868554,0.00089488446,0.0005652268],"domain_scores_gemma":[0.9969178,0.000053477943,0.00026085408,0.00014032796,0.0014913586,0.0011361827],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006808414,0.00009547874,0.0001834257,0.00068563316,0.0002994084,0.00007050806,0.00025617203,0.00011190384,0.0010677773],"category_scores_gemma":[0.002431205,0.00011103222,0.00006798982,0.00093571644,0.00012362878,0.00047466485,0.00000407341,0.00021932553,0.000016322125],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010814312,0.00005608776,0.048364826,0.000030084084,0.000056913075,0.00005112463,0.075599045,0.0014554561,0.00009016248,0.010766348,0.019208845,0.84421295],"study_design_scores_gemma":[0.002418473,0.0010651262,0.693332,0.0005291714,0.00014984656,0.000029204148,0.0070069414,0.004264935,0.00028212467,0.014741157,0.27558586,0.0005951612],"about_ca_topic_score_codex":0.95604414,"about_ca_topic_score_gemma":0.99843985,"teacher_disagreement_score":0.8436178,"about_ca_system_score_codex":0.0026074734,"about_ca_system_score_gemma":0.021409573,"threshold_uncertainty_score":0.9998454},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70721877,0.07965434,0.0002581966,0.029857304,0.011654918,0.0014911485,0.00020695865,0.000030796968,0.16962756],"genre_scores_gemma":[0.98482215,0.0006583641,0.0003921069,0.00018573797,0.009405499,0.000014283226,0.000043243377,0.000027951879,0.0044506406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803156,0.00029031292,0.000606422,0.0001422348,0.00054637314,0.00038311165],"domain_scores_gemma":[0.9964596,0.00006226453,0.00045966535,0.0001608134,0.002197255,0.0006604214],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016533872,0.00018078151,0.00028850153,0.0003819252,0.0007469793,0.00033310568,0.00022012884,0.00011325668,0.012062436],"category_scores_gemma":[0.0008335252,0.00017328668,0.0002891658,0.000116655974,0.0003776445,0.00025198824,0.000007856193,0.00029428318,0.00010428886],"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":[0.000025605561,0.0005356057,0.0120020015,0.00008766994,0.0013251255,0.0009916414,0.052310556,0.0014892973,0.0000068107015,0.26397035,0.043060984,0.6241943],"study_design_scores_gemma":[0.0007540884,0.00041072883,0.0048608254,0.0001134324,0.0013822885,0.0001639286,0.0020632169,0.008364422,0.00001804027,0.0057049566,0.9759208,0.0002432903],"about_ca_topic_score_codex":0.0194801,"about_ca_topic_score_gemma":0.052087456,"teacher_disagreement_score":0.9328598,"about_ca_system_score_codex":0.00042905842,"about_ca_system_score_gemma":0.003360976,"threshold_uncertainty_score":0.9888407},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943707,0.00015270723,0.000005686452,0.0006892988,0.0011787465,0.001603386,0.000015025831,0.0000036415065,0.0019807955],"genre_scores_gemma":[0.99957126,0.0000029324003,0.00014867127,0.00006437288,0.00010171057,0.000029237519,0.000009323091,0.000007948734,0.000064561216],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981925,0.00046644316,0.0004670694,0.00017746234,0.00047226614,0.00022427934],"domain_scores_gemma":[0.99789035,0.000036229772,0.00032734318,0.0006826975,0.00071192614,0.00035145786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024446503,0.00008571988,0.00015008838,0.00024297656,0.00041494193,0.000028097535,0.00054443476,0.000070884984,0.0006325915],"category_scores_gemma":[0.00051498314,0.00006607705,0.000055548888,0.0005384665,0.00014735346,0.0001906492,0.000015836764,0.00025884327,0.000011332088],"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":[0.000030200368,0.00025779512,0.8688853,0.0000044657245,0.000103883,0.000036554327,0.0088951895,0.0001515086,0.0000029303944,0.00006231168,0.006976848,0.114593014],"study_design_scores_gemma":[0.0008979072,0.00044704942,0.9925233,0.000025636662,0.000117490184,0.00017287147,0.00086982467,0.00035513664,0.000013149556,0.00014227211,0.004369525,0.000065816326],"about_ca_topic_score_codex":0.65175956,"about_ca_topic_score_gemma":0.9852864,"teacher_disagreement_score":0.33352685,"about_ca_system_score_codex":0.0007421917,"about_ca_system_score_gemma":0.0074826987,"threshold_uncertainty_score":0.998144},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8824575,0.022665333,0.020506913,0.037071336,0.005220027,0.011583896,0.00016435553,0.00015495805,0.020175677],"genre_scores_gemma":[0.9931004,0.00024524887,0.0036346042,0.001420443,0.000624635,0.0001297323,0.00014666343,0.000032255655,0.0006659854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98778033,0.0019061469,0.0022799196,0.0006041366,0.0066646575,0.00076477823],"domain_scores_gemma":[0.98788613,0.00044159405,0.001530346,0.0008137083,0.008239373,0.0010888225],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03191987,0.00039595205,0.00060690666,0.0014356202,0.00069326,0.0010990578,0.001013333,0.00026598322,0.00915054],"category_scores_gemma":[0.0060430756,0.00032776254,0.00031539428,0.002177897,0.0001805763,0.001683839,0.000022069748,0.00049634086,0.00033214752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035248187,0.0001258872,0.0063682115,0.0000051705547,0.000050064977,0.000011687961,0.0019941726,0.041204456,0.00004698317,0.00015424102,0.04980158,0.9002023],"study_design_scores_gemma":[0.0046261833,0.0012286681,0.09148887,0.00018307047,0.0005108892,0.000121605604,0.0024361294,0.6637795,0.000236296,0.017164534,0.2175931,0.00063115545],"about_ca_topic_score_codex":0.00029313672,"about_ca_topic_score_gemma":0.008708686,"teacher_disagreement_score":0.8995711,"about_ca_system_score_codex":0.0010547637,"about_ca_system_score_gemma":0.011894179,"threshold_uncertainty_score":0.9999379},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986568,0.0005593566,0.000034190518,0.007411106,0.00032062706,0.0023201734,0.0000053972467,0.000004703854,0.0027764416],"genre_scores_gemma":[0.9961636,0.000046910376,0.0027924818,0.00054389815,0.00016360234,0.00014296583,0.000013889573,0.000010455461,0.00012221267],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979069,0.00018286012,0.00080785376,0.00009627464,0.00066573324,0.00034034706],"domain_scores_gemma":[0.99596417,0.00026967932,0.0002655974,0.00017501278,0.0023934275,0.0009321004],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00277074,0.000086804335,0.00026216637,0.0005662634,0.00004512953,0.000034041732,0.000092697555,0.000118402546,0.0013872861],"category_scores_gemma":[0.00952892,0.000077582125,0.00006708378,0.0005164646,0.00006647675,0.00014199744,0.000006602976,0.0003213327,0.000044420867],"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":[0.000082042985,0.00022374853,0.55685145,0.00051331933,0.00009916627,0.000028721059,0.01210233,0.00065099634,0.00016535341,0.0011257599,0.015878314,0.41227877],"study_design_scores_gemma":[0.004959147,0.0036085187,0.9567245,0.0016891212,0.00048554692,0.000062592015,0.0055138916,0.004181019,0.00037812014,0.005010693,0.017091485,0.00029536072],"about_ca_topic_score_codex":0.02553543,"about_ca_topic_score_gemma":0.17683244,"teacher_disagreement_score":0.41198343,"about_ca_system_score_codex":0.0007190103,"about_ca_system_score_gemma":0.01523454,"threshold_uncertainty_score":0.9995256},"labels":[],"label_agreement":null},{"id":"W4366446575","doi":"10.3138/cjpe.023.007","title":"Reconnecting Knowledge Utilization and Evaluation Utilization Domains of Inquiry","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Social Sciences and Humanities Research Council","funders":"","keywords":"Situated; Variety (cybernetics); Context (archaeology); Domain (mathematical analysis); Knowledge management; Epistemology; Cognate; Thematic analysis; Sociology; Psychology; Computer science; Qualitative research; Social science; Geography; Artificial intelligence; Philosophy; Mathematics","score_opus":0.7789619921436738,"score_gpt":0.5916862318486936,"score_spread":0.18727576029498016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98786736,0.0022629471,0.003974179,0.0003226426,0.0010889069,0.0012686136,0.000003991852,0.000009402376,0.003201985],"genre_scores_gemma":[0.9968048,0.00013134125,0.0026757193,0.000040081955,0.00020710376,0.00004632295,0.00003024204,0.000012361341,0.00005203797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945815,0.001236237,0.0014098736,0.00026086968,0.0022785775,0.00023292513],"domain_scores_gemma":[0.98985136,0.00042428923,0.0013451007,0.00027348552,0.00777777,0.00032800497],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023362968,0.00014344169,0.0003056074,0.0011452074,0.00037940734,0.00015196898,0.00026402684,0.00012198122,0.0011540637],"category_scores_gemma":[0.007597326,0.00012314481,0.00009824011,0.0013004254,0.00020838852,0.0010347051,0.000016170174,0.00015774976,0.000018207824],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019136538,0.000056130284,0.053160414,0.000010776373,0.000023803457,0.0000012755816,0.008010616,0.0020364812,0.00009891672,0.00049832417,0.0007450093,0.9353391],"study_design_scores_gemma":[0.0024854962,0.0007956948,0.43190527,0.00014558849,0.00022373065,0.00017913748,0.005467159,0.5316531,0.0008522536,0.010611736,0.015435747,0.00024507853],"about_ca_topic_score_codex":0.00015042388,"about_ca_topic_score_gemma":0.0053326604,"teacher_disagreement_score":0.93509406,"about_ca_system_score_codex":0.0003975362,"about_ca_system_score_gemma":0.005771321,"threshold_uncertainty_score":0.99986506},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8032418,0.0011940325,0.0002777019,0.06791899,0.08674231,0.0020466777,0.0000071886343,0.000067382,0.038503893],"genre_scores_gemma":[0.9519594,0.000029606043,0.00036091104,0.000048895985,0.047383048,0.000009867938,0.0000044968356,0.000005727539,0.00019809534],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987316,0.00024932798,0.000186461,0.000071976705,0.00056442287,0.00019617828],"domain_scores_gemma":[0.99837345,0.000027673703,0.00018798611,0.00006774528,0.0010186613,0.0003244833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002979053,0.000047939702,0.00007868833,0.00016048833,0.00072611915,0.00007876566,0.00013046175,0.000080249905,0.00031780408],"category_scores_gemma":[0.0010076811,0.00004721036,0.000050937342,0.00019361971,0.0002681344,0.00033806008,0.000001964493,0.00020546072,0.000018964309],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019708892,0.00016414638,0.008067027,0.000008817229,0.00008530694,0.00008802052,0.06028273,0.00010474879,0.00022591827,0.02131401,0.46377885,0.4458607],"study_design_scores_gemma":[0.00016202836,0.0001239165,0.0048618624,0.00000903033,0.000024199604,0.000030153815,0.00070184085,0.000050904917,0.0000512879,0.0025211792,0.99140006,0.000063512955],"about_ca_topic_score_codex":0.008141913,"about_ca_topic_score_gemma":0.04911997,"teacher_disagreement_score":0.5276212,"about_ca_system_score_codex":0.00041632552,"about_ca_system_score_gemma":0.004472704,"threshold_uncertainty_score":0.998463},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98752916,0.004395809,0.0036121935,0.0011444893,0.0001566053,0.0015501826,0.000015621783,0.000025986717,0.0015699548],"genre_scores_gemma":[0.969007,0.00059269235,0.028835883,0.0005419168,0.0003785449,0.00044776095,0.000050287294,0.000019682499,0.00012621164],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99253345,0.0056111203,0.0006428,0.00013937177,0.00034091732,0.0007323446],"domain_scores_gemma":[0.9972667,0.0008068763,0.00043843882,0.00013978999,0.00044549056,0.0009026739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013223949,0.0001402172,0.00022677446,0.00017954492,0.0007853505,0.000027872557,0.0002077589,0.0003170092,0.00021776003],"category_scores_gemma":[0.0007169,0.00013431448,0.00006873405,0.00021896188,0.00022228138,0.0001753012,0.000005894382,0.0008172222,0.000019937455],"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":[0.00010439751,0.00012448347,0.7430367,0.00033292532,0.00003500817,0.000013006053,0.060935773,0.00031121436,0.00047178863,0.00045374714,0.006499964,0.18768102],"study_design_scores_gemma":[0.0023957468,0.001337411,0.88018245,0.0011078579,0.00016291173,0.000111785426,0.027457574,0.011830324,0.001189512,0.017302012,0.05661462,0.00030782894],"about_ca_topic_score_codex":0.038490973,"about_ca_topic_score_gemma":0.07445118,"teacher_disagreement_score":0.18737319,"about_ca_system_score_codex":0.0047144047,"about_ca_system_score_gemma":0.011490352,"threshold_uncertainty_score":0.99910635},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99096256,0.00067012676,0.0012262986,0.00097048795,0.0003349824,0.00071090314,0.000007981535,0.000025229045,0.0050914376],"genre_scores_gemma":[0.9938422,0.000050832055,0.0056181527,0.0000919014,0.00024218224,0.000035401354,0.000004221987,0.000009545497,0.000105599785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979744,0.00050658634,0.00031677968,0.0001334925,0.0005655729,0.000503198],"domain_scores_gemma":[0.998061,0.000069857626,0.00046288501,0.000076969845,0.0008069443,0.00052234984],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004087878,0.00009628076,0.00014055194,0.00007643657,0.0013435876,0.00023237546,0.0003686202,0.000102727114,0.00023471052],"category_scores_gemma":[0.00065675087,0.00009402802,0.00006994962,0.00039934256,0.00047897056,0.00082168414,0.0000056882436,0.00011859048,0.0000059577596],"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":[0.000016815507,0.00006808379,0.119530454,0.000013718589,0.000032950604,0.000016599317,0.32236373,0.000019529538,0.000182691,0.014901142,0.00009692394,0.54275733],"study_design_scores_gemma":[0.0009098476,0.0002334813,0.7859053,0.000097943084,0.0000777834,0.00002945974,0.15346056,0.00048442854,0.0005209266,0.050914116,0.0071578617,0.00020830033],"about_ca_topic_score_codex":0.22641458,"about_ca_topic_score_gemma":0.7405908,"teacher_disagreement_score":0.6663748,"about_ca_system_score_codex":0.0007034196,"about_ca_system_score_gemma":0.006258548,"threshold_uncertainty_score":0.99995655},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95678604,0.0003107024,0.00008447168,0.010190019,0.0009983964,0.0022820916,0.000019075387,0.0000071472264,0.029322064],"genre_scores_gemma":[0.9976436,0.0000037519144,0.00059474417,0.0012736429,0.00034951293,0.00007012513,0.000004747108,0.000008892608,0.00005098079],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99714637,0.00070965185,0.00046664497,0.00014513193,0.0010058414,0.0005263846],"domain_scores_gemma":[0.99771696,0.00007095316,0.00020585397,0.000119389035,0.0009429704,0.0009438736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006745183,0.00009086687,0.00018777735,0.00030887555,0.00027188167,0.00006035999,0.00019691052,0.00008925041,0.0005829512],"category_scores_gemma":[0.00122232,0.00009246944,0.00006546072,0.00045509083,0.000088802684,0.00023929104,0.0000042078236,0.00019863143,0.000012700295],"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":[0.00014146877,0.00012919302,0.16263144,0.00003392868,0.00006860317,0.00003129188,0.030301338,0.0010359226,0.000047908565,0.014111488,0.012100727,0.7793667],"study_design_scores_gemma":[0.002275517,0.0019182428,0.8545262,0.00090122764,0.00011038361,0.000008117311,0.0062448764,0.0042421552,0.00012256464,0.0072079776,0.122039355,0.00040334326],"about_ca_topic_score_codex":0.8949767,"about_ca_topic_score_gemma":0.9846062,"teacher_disagreement_score":0.7789633,"about_ca_system_score_codex":0.0027550736,"about_ca_system_score_gemma":0.0059902985,"threshold_uncertainty_score":0.9996448},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9761451,0.0002487369,0.00042707048,0.010675709,0.0011182029,0.010962773,0.0000476756,0.000043276184,0.00033147624],"genre_scores_gemma":[0.98377514,0.00007641504,0.0067098467,0.006908153,0.0003525287,0.0020365804,0.000033614328,0.000034134082,0.0000736092],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9827181,0.01253517,0.0020776354,0.00022751391,0.001278244,0.0011633298],"domain_scores_gemma":[0.9910916,0.0010873078,0.001987369,0.0004556774,0.004051865,0.0013261888],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.027058765,0.0002156059,0.0004118858,0.00043648164,0.0063112075,0.00007622973,0.0005579954,0.00012319136,0.00040316532],"category_scores_gemma":[0.004626681,0.00017202122,0.00011368549,0.0013868569,0.00027366824,0.00065754744,0.00005187792,0.0011486022,0.00003455258],"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":[0.00012298553,0.0001506897,0.069460966,0.00022628633,0.00007262422,0.0000039520623,0.10549267,0.0003266462,0.000089118344,0.000019825484,0.006090257,0.817944],"study_design_scores_gemma":[0.003675461,0.002744631,0.9188464,0.0008939861,0.0001520912,0.000053895626,0.011333734,0.0061313827,0.000023845612,0.0014149239,0.054341655,0.00038794897],"about_ca_topic_score_codex":0.058329206,"about_ca_topic_score_gemma":0.26617134,"teacher_disagreement_score":0.8493855,"about_ca_system_score_codex":0.006100352,"about_ca_system_score_gemma":0.063386075,"threshold_uncertainty_score":0.99771506},"labels":[],"label_agreement":null},{"id":"W4366446952","doi":"10.3138/cjpe.28.008","title":"Barbier, J. C., &amp; Hawkins, P. (Eds.). (2012). <i>Evaluation Cultures: Sense-making in Complex Times.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sense (electronics); Psychology; Sociology; Chemistry; Physical chemistry","score_opus":0.3467359600038095,"score_gpt":0.5222283353461814,"score_spread":0.1754923753423719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366446952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.890911,0.009044093,0.0036325187,0.018225538,0.0037250437,0.011682485,0.000033817938,0.00006953339,0.06267596],"genre_scores_gemma":[0.99037856,0.000047226138,0.0074820463,0.0009476631,0.00030047266,0.00023431328,0.00008366287,0.000021101829,0.00050497736],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99110854,0.0016446877,0.0017813782,0.0003853763,0.004520143,0.00055989815],"domain_scores_gemma":[0.99094945,0.000329469,0.0011702903,0.00051850436,0.0064795995,0.00055267854],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.025100403,0.00024684813,0.00042468886,0.0013299672,0.0003297133,0.001008863,0.0005671851,0.00016810292,0.03015934],"category_scores_gemma":[0.004422703,0.00019553713,0.00018462173,0.0014355406,0.00012875973,0.0019604736,0.000025206105,0.0004255268,0.001113294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012662311,0.00006953298,0.01051447,0.0000061548058,0.00002768305,0.000004403989,0.0017406514,0.0076662735,0.00023276,0.00023381296,0.08814576,0.89134586],"study_design_scores_gemma":[0.0024912476,0.0002987219,0.22042426,0.00014774279,0.00013894273,0.0001242078,0.0016217364,0.23508134,0.00004077086,0.02743776,0.5117676,0.00042564413],"about_ca_topic_score_codex":0.0016681252,"about_ca_topic_score_gemma":0.07341417,"teacher_disagreement_score":0.89092016,"about_ca_system_score_codex":0.00089136517,"about_ca_system_score_gemma":0.005445173,"threshold_uncertainty_score":0.9996644},"labels":[],"label_agreement":null},{"id":"W4366447009","doi":"10.3138/cjpe.022.007","title":"Considérations théoriques et méthodologiques lors de l’évaluation de programmes d’intervention de crise","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Confusion; Valuation (finance); Psychology; Intervention (counseling); Crisis intervention; Applied psychology; Social psychology; Business; Psychoanalysis; Psychiatry; Finance","score_opus":0.4661128635653234,"score_gpt":0.5942212119329685,"score_spread":0.12810834836764512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7502248,0.00046878294,0.24016541,0.004241486,0.00047388845,0.0011887127,0.0000058589994,0.000041591935,0.0031894124],"genre_scores_gemma":[0.8910345,0.000048838538,0.10784513,0.0005338902,0.00023311595,0.00009420695,0.000025195415,0.000014805191,0.00017032838],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9923487,0.0036522497,0.0013958295,0.00024546753,0.0017631202,0.00059465057],"domain_scores_gemma":[0.9931828,0.0010182912,0.0010430568,0.00027545152,0.0038338862,0.0006465645],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12513782,0.00016945865,0.00026157586,0.000986108,0.00028954627,0.0007051828,0.0004180031,0.00018950799,0.0009236758],"category_scores_gemma":[0.013854074,0.00014499466,0.00024234153,0.0007409345,0.00015803573,0.00097084953,0.000014304237,0.0003748124,0.00002582193],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046726334,0.0001235778,0.09658396,0.000008436649,0.00003951263,0.000014727149,0.0058071627,0.0030167173,0.00028987633,0.0031931628,0.003267374,0.88760877],"study_design_scores_gemma":[0.0023685468,0.002356587,0.5491494,0.00024788541,0.00035685138,0.000474902,0.015881876,0.11557038,0.0048331786,0.2619573,0.046317715,0.00048540148],"about_ca_topic_score_codex":0.0015374384,"about_ca_topic_score_gemma":0.07232608,"teacher_disagreement_score":0.88712335,"about_ca_system_score_codex":0.0013150093,"about_ca_system_score_gemma":0.011105989,"threshold_uncertainty_score":0.9999896},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6804674,0.0072638365,0.00006696713,0.26790643,0.0005541676,0.0059615276,0.000025730973,0.000026156184,0.03772775],"genre_scores_gemma":[0.99146914,0.000012110277,0.0005728069,0.00045535358,0.0006049435,0.0000790092,0.0000017606171,0.0000067660717,0.0067981295],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984673,0.00015290888,0.00026208075,0.00011283054,0.00049150875,0.0005133176],"domain_scores_gemma":[0.99764663,0.000052389212,0.00017239964,0.000069031084,0.0014387078,0.0006208393],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005313707,0.00007361694,0.000093784576,0.00016900117,0.001413675,0.00040942954,0.00020939113,0.000029927078,0.00008058962],"category_scores_gemma":[0.0014742202,0.00006543017,0.000028356362,0.00021529004,0.00013363376,0.0003888065,0.000009084562,0.00010735664,0.0000134813645],"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":[0.000025806848,0.000018797053,0.0017748965,0.000017670467,0.0000500051,0.0000150462165,0.030594965,0.0015884832,0.0000014566863,0.15366976,0.18337269,0.6288704],"study_design_scores_gemma":[0.00020794055,0.000029984927,0.015175022,0.00001463922,0.000011344121,0.00000847401,0.006101639,0.00012328572,0.000014664983,0.0019343157,0.9762927,0.000085943284],"about_ca_topic_score_codex":0.085595615,"about_ca_topic_score_gemma":0.866312,"teacher_disagreement_score":0.79292005,"about_ca_system_score_codex":0.0041296897,"about_ca_system_score_gemma":0.018781392,"threshold_uncertainty_score":0.99988633},"labels":[],"label_agreement":null},{"id":"W4366447032","doi":"10.3138/cjpe.0022.009","title":"La comparabilité des échantillons dans les enquêtes de l’international association for the evaluation of educational achievement","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Association (psychology); Perspective (graphical); Educational research; Student achievement; Psychology; Pedagogy; Mathematics education; Sociology; Academic achievement; Political science; Mathematics","score_opus":0.4409650328077531,"score_gpt":0.5430028838125461,"score_spread":0.10203785100479301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98274577,0.000656489,0.0040312954,0.0068218973,0.00078081194,0.0016272947,0.00003777118,0.0000039365823,0.0032947408],"genre_scores_gemma":[0.9951145,0.000047563302,0.0039399615,0.00005147524,0.00023527768,0.0003163211,0.000033055552,0.00000831917,0.00025349317],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939507,0.0011455546,0.0009798344,0.0001681464,0.0035243265,0.00023142743],"domain_scores_gemma":[0.986644,0.0026251895,0.0012203977,0.00021128192,0.009122533,0.00017654683],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03810959,0.000110980465,0.00018871558,0.00040046315,0.00053160253,0.00015047964,0.00054584537,0.000088683,0.0013503319],"category_scores_gemma":[0.013222459,0.00007917223,0.0001953795,0.00042619833,0.0002155907,0.0004167692,0.000011673389,0.00015309358,0.000008525287],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032792723,0.000179202,0.6268654,0.0000069415114,0.00014492197,2.1572475e-7,0.0069275666,0.029002216,0.0002094722,0.00158445,0.0026207382,0.33242607],"study_design_scores_gemma":[0.0011200599,0.00016384572,0.7661241,0.000030743555,0.00022040858,0.00003034867,0.0023019288,0.19517687,0.00029191785,0.013985945,0.020471377,0.00008240715],"about_ca_topic_score_codex":0.00073913834,"about_ca_topic_score_gemma":0.018809289,"teacher_disagreement_score":0.33234367,"about_ca_system_score_codex":0.0018120845,"about_ca_system_score_gemma":0.008648986,"threshold_uncertainty_score":0.99956256},"labels":[],"label_agreement":null},{"id":"W4366447033","doi":"10.3138/cjpe.020.001","title":"Un état des lieux théoriques de l’évaluation: une discipline à la remorque d’une révolution scientifique qui n’en finit pas","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Schism; Epistemology; Sociology; Acknowledgement; Scientific revolution; Valuation (finance); Humanities; Philosophy; Political science; Law; Economics","score_opus":0.2405922775106585,"score_gpt":0.48362414033165124,"score_spread":0.24303186282099273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93495184,0.0013585632,0.018778054,0.031574532,0.0007581407,0.0013564056,0.00001652226,0.000040365336,0.01116558],"genre_scores_gemma":[0.96491325,0.00013783242,0.032994382,0.00029223974,0.0006395678,0.00009330681,0.000038687453,0.00002050412,0.00087025255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929368,0.001980242,0.0013899991,0.00036784736,0.0028217009,0.0005034014],"domain_scores_gemma":[0.99297756,0.0006503906,0.0009064129,0.00043289573,0.0043586227,0.00067410874],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03915531,0.00022130311,0.0003235284,0.00089420547,0.0006642426,0.0008538562,0.00066774135,0.00017922895,0.0017802184],"category_scores_gemma":[0.005149105,0.00017879924,0.00019988368,0.0020973163,0.0003391494,0.0013825836,0.000031037776,0.00038529208,0.000111399815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025836218,0.00009012124,0.014190555,0.0000080819855,0.00003055092,0.000008060877,0.006084208,0.016877573,0.0002086561,0.001254176,0.003478124,0.95774406],"study_design_scores_gemma":[0.0022369358,0.00066463463,0.32789552,0.0002889699,0.00024548318,0.00031733664,0.004164377,0.3402348,0.0012951802,0.1379523,0.18422927,0.0004752057],"about_ca_topic_score_codex":0.0010323654,"about_ca_topic_score_gemma":0.0756707,"teacher_disagreement_score":0.95726883,"about_ca_system_score_codex":0.001263826,"about_ca_system_score_gemma":0.0077701504,"threshold_uncertainty_score":0.9991323},"labels":[],"label_agreement":null},{"id":"W4366447375","doi":"10.3138/cjpe.021.008","title":"Impacts du pirs en milieu scolaire","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Reading (process); Scale (ratio); Medical education; Mathematics education; Pedagogy; Geography; Political science; Medicine; Cartography","score_opus":0.18663340726645056,"score_gpt":0.48755375552323066,"score_spread":0.3009203482567801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98582083,0.0007738388,0.00056280626,0.0049668597,0.00096331927,0.0007553344,0.000005617515,0.000010859326,0.006140509],"genre_scores_gemma":[0.996891,0.00000863511,0.0021549996,0.00021544598,0.0005306771,0.00002711967,0.00001183283,0.000009630752,0.00015061993],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955572,0.0005637048,0.0009708445,0.00017502479,0.0024245153,0.00030870998],"domain_scores_gemma":[0.99587786,0.00023630737,0.0006440374,0.00025581458,0.002523218,0.0004627605],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01610037,0.0001227152,0.00021557084,0.0007321568,0.00024566875,0.0005024636,0.00046145674,0.00008613459,0.0026376273],"category_scores_gemma":[0.002480204,0.00009275004,0.00014508964,0.00079132064,0.00007664936,0.0007993436,0.000009565932,0.00018424145,0.0001913195],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015300146,0.000059138274,0.23766205,0.0000038510398,0.00001855533,0.00001624497,0.0011222839,0.006032993,0.00010479349,0.00059428,0.024625493,0.72974503],"study_design_scores_gemma":[0.0011908778,0.0005031454,0.855973,0.0000518567,0.00007542063,0.00010528341,0.0010574494,0.035196174,0.00021191961,0.012529869,0.09292638,0.00017860248],"about_ca_topic_score_codex":0.0034381656,"about_ca_topic_score_gemma":0.12478558,"teacher_disagreement_score":0.7295664,"about_ca_system_score_codex":0.00051958725,"about_ca_system_score_gemma":0.0061470866,"threshold_uncertainty_score":0.99948716},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86018807,0.0021101474,0.00008206912,0.08853716,0.00339186,0.005237726,0.00009134168,0.000007648945,0.040353987],"genre_scores_gemma":[0.9966404,0.000011157671,0.00044820737,0.0015728229,0.0010171639,0.000050890223,0.0000042094434,0.000009227312,0.0002459101],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974658,0.00066875294,0.0003924073,0.00013134853,0.00083976367,0.0005019586],"domain_scores_gemma":[0.997517,0.000036364287,0.00022751384,0.0001521045,0.0012071735,0.00085988076],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0071560834,0.00009024159,0.00014756294,0.000428171,0.0004003995,0.000094317504,0.00031768114,0.00011020643,0.0019922997],"category_scores_gemma":[0.00069164997,0.00008178039,0.000073158575,0.00089194276,0.00011379439,0.0003513032,0.000004457698,0.00024665162,0.00002997922],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007411745,0.000036808327,0.032538768,0.000019794008,0.000061009756,0.000021359127,0.0927236,0.0010815249,0.000018317593,0.008481991,0.06647743,0.79846525],"study_design_scores_gemma":[0.0010514624,0.00041371834,0.42577836,0.00015025694,0.00008612982,0.000017139833,0.010398164,0.00186395,0.000040406958,0.0037152485,0.55623114,0.00025401704],"about_ca_topic_score_codex":0.9321412,"about_ca_topic_score_gemma":0.9991841,"teacher_disagreement_score":0.7982113,"about_ca_system_score_codex":0.0018093183,"about_ca_system_score_gemma":0.018162854,"threshold_uncertainty_score":0.99892},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18152311,0.00482014,0.14601004,0.022743663,0.050562132,0.008199218,0.000034563556,0.00032204864,0.5857851],"genre_scores_gemma":[0.98352957,0.000006885754,0.0093576275,0.0004506035,0.005934407,0.00025907235,0.000011880081,0.000022887292,0.00042708567],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990795,0.00016109078,0.00027418995,0.00009892094,0.00019924276,0.00018702065],"domain_scores_gemma":[0.9988322,0.000031579595,0.00022135083,0.00021702668,0.00041531003,0.00028252968],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001757022,0.0000678337,0.00009986082,0.00018297399,0.00007977591,0.000045783814,0.0001858296,0.00009143253,0.0020095694],"category_scores_gemma":[0.00007445213,0.00006285708,0.000069460504,0.00017145085,0.000047956906,0.000064199055,0.0000012397127,0.0001558549,0.000048995964],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005999607,0.00003286882,0.0007831471,0.0000012720449,0.000021469885,8.574768e-7,0.00028295466,0.0000042639317,0.000053531927,0.0061179325,0.21628217,0.7764135],"study_design_scores_gemma":[0.00042466717,0.00034089718,0.014704328,0.000019458945,0.000036860787,0.00003586598,0.000068872396,0.00044742692,0.000023676672,0.009952204,0.9738663,0.00007942901],"about_ca_topic_score_codex":0.0005390092,"about_ca_topic_score_gemma":0.0024296804,"teacher_disagreement_score":0.8020064,"about_ca_system_score_codex":0.00010549101,"about_ca_system_score_gemma":0.00033367224,"threshold_uncertainty_score":0.99890274},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75021005,0.00020351098,0.24842566,0.00016913882,0.00026622706,0.00046200433,0.0000034880695,0.000013898437,0.00024604017],"genre_scores_gemma":[0.9688399,3.8919035e-7,0.030744798,0.00003027199,0.00019019432,0.000011576761,0.0000067792084,0.000016055372,0.00016004976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948045,0.00048647774,0.0020218864,0.00031794707,0.0018802019,0.0004890105],"domain_scores_gemma":[0.994151,0.0005203999,0.001650249,0.00033579304,0.0030110758,0.00033150238],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014648557,0.00016604344,0.00037057282,0.0022161035,0.0005803181,0.0009475021,0.00046405295,0.0001031206,0.00021196355],"category_scores_gemma":[0.010652966,0.00012986622,0.00031787314,0.004101548,0.00009630063,0.0008214933,0.000024208632,0.0002466851,0.000019935327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010226748,0.00006540496,0.0038336301,0.0000038282124,0.000022244998,0.000009153747,0.0003326593,0.9193611,0.00042765273,0.0000789088,0.00016640636,0.07568878],"study_design_scores_gemma":[0.00050749176,0.00016076853,0.002988052,0.00010732918,0.00029739688,0.000047003778,0.0005703164,0.9886628,0.00025659832,0.0061503937,0.00010617105,0.00014571153],"about_ca_topic_score_codex":0.0037479298,"about_ca_topic_score_gemma":0.020183269,"teacher_disagreement_score":0.21862985,"about_ca_system_score_codex":0.00064991874,"about_ca_system_score_gemma":0.0030781515,"threshold_uncertainty_score":0.9976958},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83035696,0.050774764,0.00043617352,0.084228136,0.0028666102,0.007965439,0.00030239538,0.00008117377,0.022988375],"genre_scores_gemma":[0.98358953,0.0007058017,0.011638339,0.0007516198,0.0020341887,0.00015039214,0.0001373835,0.0000050132235,0.0009877589],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742776,0.00055045635,0.00053882797,0.00019494242,0.00086030446,0.00042770867],"domain_scores_gemma":[0.9971571,0.00035610382,0.00040031472,0.000083992476,0.0018023617,0.00020013665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071159755,0.00014219226,0.00024412973,0.00014259986,0.0009798255,0.00018612349,0.00041444018,0.00010983118,0.0007787231],"category_scores_gemma":[0.00062619196,0.00006412715,0.000113288974,0.0012199841,0.00034453938,0.00016390489,0.0000218377,0.00037299973,0.000020643556],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020634528,0.00008880013,0.00023683897,0.000004182604,0.000045057393,0.0000013028836,0.0008151835,0.000032001553,0.0072066025,0.00046506623,0.06463659,0.92644775],"study_design_scores_gemma":[0.000532444,0.0005344063,0.09621593,0.00012852343,0.00016699589,0.000017183762,0.0031557747,0.000077972414,0.0013166068,0.013545711,0.88402987,0.00027856434],"about_ca_topic_score_codex":0.0013093828,"about_ca_topic_score_gemma":0.015460404,"teacher_disagreement_score":0.92616916,"about_ca_system_score_codex":0.00023312855,"about_ca_system_score_gemma":0.0007130008,"threshold_uncertainty_score":0.8627268},"labels":[],"label_agreement":null},{"id":"W4366447855","doi":"10.3138/cjpe.20.009","title":"How Can Information About the Competencies Required for Evaluation Be Useful?","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Accreditation; Certification; Medical education; Psychology; Thematic analysis; Knowledge management; Engineering ethics; Computer science; Political science; Medicine; Sociology; Engineering; Qualitative research","score_opus":0.407391146677462,"score_gpt":0.4961895575741692,"score_spread":0.0887984108967072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366447855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69728875,0.0018489175,0.01582069,0.26389745,0.003857742,0.011784176,0.00013278083,0.00004498548,0.0053245397],"genre_scores_gemma":[0.9919239,0.000014576266,0.0053978823,0.001403885,0.0005026566,0.00040411906,0.000092220536,0.000009385327,0.00025132377],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938718,0.00070240686,0.0011495911,0.00016770305,0.0037492248,0.0003592789],"domain_scores_gemma":[0.9897866,0.0004757538,0.00137183,0.00041049384,0.007614833,0.00034048432],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.026919512,0.00016209397,0.00024189326,0.00067919894,0.0006229107,0.0017699337,0.0006925385,0.00009899083,0.0006325649],"category_scores_gemma":[0.0070977705,0.00010441929,0.00019578543,0.00074900774,0.00014527369,0.002969915,0.000013002199,0.00018972933,0.000022814751],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022191141,0.000015836522,0.0022079414,0.0000040593222,0.000028374237,1.3106181e-7,0.0035174964,0.0077982517,0.000024982804,0.0012448564,0.009809147,0.9753267],"study_design_scores_gemma":[0.0018014271,0.00036949004,0.032022696,0.000028321794,0.00017210706,0.000022612492,0.004931949,0.35170645,0.00016741609,0.0055781677,0.60305125,0.00014815206],"about_ca_topic_score_codex":0.00013714534,"about_ca_topic_score_gemma":0.026750227,"teacher_disagreement_score":0.9751786,"about_ca_system_score_codex":0.0006899135,"about_ca_system_score_gemma":0.006721322,"threshold_uncertainty_score":0.9992663},"labels":[],"label_agreement":null},{"id":"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33114335,0.48771122,0.013769506,0.11473501,0.016263515,0.0061903642,0.0018302724,0.000052968582,0.02830379],"genre_scores_gemma":[0.98670995,0.0025092498,0.0049895374,0.00034322732,0.0016309719,0.000030301984,0.00035108876,0.00003770948,0.003397958],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99248314,0.0040826304,0.0011472437,0.00026645383,0.0011813071,0.0008392451],"domain_scores_gemma":[0.9960778,0.0005354042,0.001264935,0.0006271937,0.0006333681,0.000861316],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029669672,0.0002404739,0.0005193003,0.00029337438,0.0006680538,0.00033439574,0.0011340154,0.0001238098,0.002571321],"category_scores_gemma":[0.0018097789,0.00019310383,0.00026198933,0.00064727414,0.00082632806,0.0018497817,0.000115462026,0.00056419015,0.00018025051],"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":[0.000008556377,0.0001440243,0.00300445,0.000076618635,0.00036071963,0.000004342429,0.07343457,0.00010810383,0.000052620242,0.0012651585,0.082544744,0.8389961],"study_design_scores_gemma":[0.0003633606,0.00012306024,0.0042761676,0.00070585863,0.0010499733,0.000024147348,0.018962154,0.0018141064,0.00002227593,0.0013704742,0.97103155,0.00025687335],"about_ca_topic_score_codex":0.01672335,"about_ca_topic_score_gemma":0.23837969,"teacher_disagreement_score":0.8884868,"about_ca_system_score_codex":0.00044689074,"about_ca_system_score_gemma":0.0024691839,"threshold_uncertainty_score":0.9991593},"labels":[],"label_agreement":null},{"id":"W4366448017","doi":"10.3138/cjpe.22.002","title":"Collaborative Evaluation in a Community Change Initiative: Dilemmas of Control Over Technical Decision Making","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Control (management); Process (computing); Dimension (graph theory); Work (physics); Meaning (existential); Process management; Knowledge management; Management science; Computer science; Sociology; Public relations; Political science; Psychology; Business; Engineering","score_opus":0.3796100750810484,"score_gpt":0.568284039236673,"score_spread":0.18867396415562465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98446304,0.0006512589,0.00805053,0.000495675,0.0005645411,0.0030920687,0.000025558566,0.000006605586,0.002650707],"genre_scores_gemma":[0.9951327,0.00000829743,0.004318028,0.00026387585,0.00012547283,0.00012629699,0.000012371552,0.000010551272,0.000002435352],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9903293,0.002917317,0.0019855993,0.0001980279,0.0042132386,0.000356515],"domain_scores_gemma":[0.9873325,0.0024564792,0.0016269127,0.00038006096,0.007923323,0.00028067175],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09480893,0.00016198223,0.00043719937,0.0018065335,0.00023105215,0.00016362696,0.0005502667,0.00017497323,0.0014002124],"category_scores_gemma":[0.014924889,0.00013261542,0.00012425538,0.0024774082,0.00017918134,0.0010774138,0.000023734394,0.0005835519,0.0000118651915],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019070909,0.00014220795,0.13732606,0.000005194037,0.000019423582,0.000005534035,0.004216906,0.0012076118,0.00010154469,0.0002887101,0.00029549163,0.85620064],"study_design_scores_gemma":[0.0033066943,0.0008663366,0.93432635,0.00031205203,0.000095551666,0.000016201802,0.0037793608,0.04055121,0.00008369236,0.014774297,0.0017426804,0.00014559703],"about_ca_topic_score_codex":0.00062424195,"about_ca_topic_score_gemma":0.146796,"teacher_disagreement_score":0.856055,"about_ca_system_score_codex":0.0012261871,"about_ca_system_score_gemma":0.0049884254,"threshold_uncertainty_score":0.9995127},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950351,0.0011082971,0.0000025112192,0.0015206138,0.000431259,0.00046762108,0.0000027921678,7.6838245e-7,0.0014310466],"genre_scores_gemma":[0.9995318,0.0000022602974,0.000017042352,0.00009812015,0.00028294223,0.000007032205,9.797196e-7,0.0000037514435,0.00005604554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989122,0.000101298254,0.0003624549,0.000046866073,0.00047206305,0.000105113875],"domain_scores_gemma":[0.9983383,0.00006474987,0.00089159823,0.00012383284,0.00056979427,0.000011753988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011992239,0.00005506506,0.00010909657,0.00004849943,0.00012381504,0.00005689321,0.00029317,0.000024859582,0.000033260072],"category_scores_gemma":[0.00040564183,0.000025289353,0.000046720746,0.0002937279,0.00021035015,0.00015579308,0.000017842549,0.00012862415,1.7398246e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012642406,0.000052936364,0.70727676,0.000059775986,0.00008336673,0.0000018973441,0.0013898535,0.017561,0.00052750943,0.07911015,0.0059048105,0.18790554],"study_design_scores_gemma":[0.0011673869,0.0000140423135,0.90280104,0.00010047197,0.000104328516,0.0000031591453,0.0018207382,0.012261965,0.00078089535,0.0032714002,0.07760226,0.00007232592],"about_ca_topic_score_codex":0.9487553,"about_ca_topic_score_gemma":0.99212295,"teacher_disagreement_score":0.19552429,"about_ca_system_score_codex":0.00009647162,"about_ca_system_score_gemma":0.0015877883,"threshold_uncertainty_score":0.28166685},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9612735,0.00050090754,0.0057370253,0.01195158,0.00034889375,0.0006504698,0.0000033631725,0.000021459367,0.019512834],"genre_scores_gemma":[0.9911308,0.0000369473,0.007922757,0.00021987442,0.0004424327,0.000018222743,0.0000027411618,0.000008475045,0.00021770022],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979061,0.0003633303,0.0003425152,0.00011632301,0.0006962995,0.0005754686],"domain_scores_gemma":[0.9981312,0.000095977615,0.00039707485,0.000067770205,0.0006856592,0.00062227884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012043784,0.000085868094,0.00011907342,0.00014913316,0.000804305,0.00022353121,0.00028834344,0.00015228182,0.00010613517],"category_scores_gemma":[0.0023910364,0.00008692156,0.00007371361,0.0008606088,0.0003913322,0.00062964374,0.0000052512282,0.0001973967,0.0000042265015],"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":[0.000013724486,0.00006849973,0.08997816,0.0000088133975,0.000029120196,0.000028293345,0.096752405,0.00024484485,0.0003179688,0.04313242,0.006151765,0.76327395],"study_design_scores_gemma":[0.0004667208,0.00022499796,0.83909106,0.000103809216,0.000052051993,0.00001991543,0.027713276,0.00059409614,0.00026993922,0.054491267,0.07676541,0.00020747927],"about_ca_topic_score_codex":0.13303986,"about_ca_topic_score_gemma":0.85845816,"teacher_disagreement_score":0.76306653,"about_ca_system_score_codex":0.0019117788,"about_ca_system_score_gemma":0.0143917985,"threshold_uncertainty_score":0.9911957},"labels":[],"label_agreement":null},{"id":"W4366448066","doi":"10.3138/cjpe.026.007","title":"Stake, R. E. (2010). <i>Qualitative Research: Studying How Things Work.</i> New York, NY: Guilford Press. 244 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Work (physics); Media studies; Engineering; Mechanical engineering","score_opus":0.9420309666332343,"score_gpt":0.5946086491900977,"score_spread":0.34742231744313656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6655935,0.03326553,0.024495166,0.072200365,0.016077714,0.020529706,0.00007102297,0.00022733344,0.16753964],"genre_scores_gemma":[0.9724773,0.000086737855,0.020590203,0.0004444065,0.0004422494,0.00012214975,0.000012034285,0.000033572407,0.0057913535],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98793954,0.003571084,0.0012968077,0.00043826734,0.0059971116,0.0007572009],"domain_scores_gemma":[0.98901784,0.000992142,0.0011957573,0.0006442399,0.006907349,0.001242693],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07296109,0.00022942669,0.00041806087,0.001186101,0.00054623745,0.0012344558,0.001291025,0.00015369545,0.00280443],"category_scores_gemma":[0.011022671,0.00017577002,0.00019539145,0.001870133,0.00027942672,0.0020911426,0.000052071886,0.00082420884,0.0001554745],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056181736,0.00006455366,0.0033407356,0.000005376372,0.00006198808,0.000011603741,0.07592668,0.00009117483,0.000009840199,0.0005728257,0.2060902,0.71376884],"study_design_scores_gemma":[0.0032753171,0.0026612196,0.039209977,0.0003692451,0.0002399041,0.000043369542,0.10835056,0.0052697198,0.00037931552,0.06086,0.77868474,0.00065666443],"about_ca_topic_score_codex":0.0030411493,"about_ca_topic_score_gemma":0.014746446,"teacher_disagreement_score":0.7131122,"about_ca_system_score_codex":0.00061057415,"about_ca_system_score_gemma":0.008502355,"threshold_uncertainty_score":0.99980235},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4366448126","doi":"10.3138/cjpe.0027.005","title":"The Paris Declaration Evaluation Process and Methods","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; Process (computing); Process management; Engineering ethics; Corporate governance; Quality (philosophy); Perspective (graphical); Management science; Political science; Computer science; Business; Engineering; Epistemology; Law","score_opus":0.42934184573180173,"score_gpt":0.6085040427500894,"score_spread":0.17916219701828767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.950446,0.0050000614,0.01291034,0.01733658,0.0017945153,0.0057053566,0.0000022623208,0.000016158212,0.006788692],"genre_scores_gemma":[0.9897284,0.000046567468,0.00934705,0.00017106657,0.00015084012,0.00041668522,0.0000065580593,0.00000819201,0.00012464901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937469,0.0020278068,0.0010002991,0.00020121073,0.0027631328,0.00026065484],"domain_scores_gemma":[0.98896545,0.00076119584,0.00085853075,0.00028207563,0.008744044,0.00038871696],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.051660173,0.00011662649,0.00017835958,0.00037005957,0.00063965167,0.0014448732,0.00037007724,0.00008340405,0.0018569787],"category_scores_gemma":[0.008005951,0.000069990536,0.00007067515,0.00069412106,0.00013955767,0.001312132,0.000010351428,0.00020131063,0.00007098776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044124627,0.000009814838,0.010643428,0.0000017143999,0.000016341683,1.5584607e-7,0.0008978848,0.000979886,0.00004133323,0.0002456071,0.0026659644,0.98449343],"study_design_scores_gemma":[0.0008162277,0.00035241127,0.20226845,0.000024779374,0.00014489579,0.000035598685,0.0037700376,0.64684963,0.00023753478,0.106069684,0.039284926,0.00014579513],"about_ca_topic_score_codex":0.00042549727,"about_ca_topic_score_gemma":0.0068227253,"teacher_disagreement_score":0.98434764,"about_ca_system_score_codex":0.00027755141,"about_ca_system_score_gemma":0.0046030646,"threshold_uncertainty_score":0.9995917},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86052185,0.019273005,0.017760998,0.026996408,0.002320881,0.028211305,0.000058459096,0.00024680267,0.044610318],"genre_scores_gemma":[0.8990533,0.00001244504,0.09825234,0.00072119734,0.00026494142,0.0013907101,0.000093010385,0.000032100117,0.00017996768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99108106,0.006026336,0.0014739413,0.00020015569,0.0007169017,0.00050158106],"domain_scores_gemma":[0.9932295,0.00036757856,0.0012274695,0.00079910486,0.003652802,0.0007235189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007631026,0.00016301939,0.00028029695,0.00063636625,0.0010358078,0.000057045883,0.00077568245,0.00018852897,0.0004654563],"category_scores_gemma":[0.0039520855,0.0001604964,0.00013952568,0.0005733456,0.00007649398,0.000497395,0.000070750946,0.0008993068,0.00016475955],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009742809,0.00018094308,0.009080822,0.00013505407,0.00006973752,3.7089532e-7,0.041088395,0.004997189,0.00004145533,0.006391999,0.0039938972,0.9339227],"study_design_scores_gemma":[0.013681912,0.004004809,0.10455464,0.006179541,0.0010245182,0.00009265437,0.1258859,0.51442385,0.000074544565,0.031161033,0.19750826,0.0014083592],"about_ca_topic_score_codex":0.0022174167,"about_ca_topic_score_gemma":0.025030354,"teacher_disagreement_score":0.93251437,"about_ca_system_score_codex":0.002175679,"about_ca_system_score_gemma":0.003494938,"threshold_uncertainty_score":0.9927603},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98835224,0.00081203127,0.0000024968883,0.006226358,0.0006975852,0.002148563,0.000021414768,0.000036440768,0.0017028471],"genre_scores_gemma":[0.99654275,0.000029804014,0.0016978144,0.00055184716,0.0003157531,0.0005105251,0.00019325047,0.000003611408,0.00015466656],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974519,0.0002369317,0.00061300973,0.0002774068,0.0010661866,0.0003545553],"domain_scores_gemma":[0.99723643,0.00015734212,0.00045266756,0.00008044113,0.0016767854,0.00039632752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016635313,0.00022798596,0.0002483954,0.00011863726,0.0007617878,0.00016213054,0.0001922046,0.0001011064,0.00027026964],"category_scores_gemma":[0.0008264821,0.00011815121,0.00007495992,0.00050499814,0.00020266433,0.0003003594,0.000012763102,0.00021960137,0.000019551459],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007988467,0.0003960406,0.028733563,0.0000129776445,0.000085519314,0.000015251804,0.0006186557,0.00071775244,0.00007873063,0.0005055128,0.013637835,0.9551183],"study_design_scores_gemma":[0.0014582983,0.0034339796,0.62470216,0.00017269223,0.00016858002,0.00007520733,0.0010824658,0.00080792146,0.00092846056,0.00044221774,0.3662044,0.0005236054],"about_ca_topic_score_codex":0.0005497864,"about_ca_topic_score_gemma":0.009132387,"teacher_disagreement_score":0.9545947,"about_ca_system_score_codex":0.00061288645,"about_ca_system_score_gemma":0.0014524703,"threshold_uncertainty_score":0.5859133},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.904419,0.01873856,0.0060462425,0.028508164,0.0038837784,0.005995408,0.0003782584,0.00012619724,0.03190436],"genre_scores_gemma":[0.9943982,0.00011285202,0.003618263,0.00082815107,0.00039705096,0.000037103004,0.0000793087,0.000029496314,0.0004996059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933903,0.0011360955,0.0012069136,0.0004994839,0.003186394,0.00058080285],"domain_scores_gemma":[0.99488896,0.00072804256,0.0006336538,0.00057744543,0.0020690127,0.0011028607],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021674497,0.00023774376,0.00041862464,0.0006490992,0.00060012675,0.0006167089,0.000491778,0.00013826256,0.002856594],"category_scores_gemma":[0.0026188337,0.00019714773,0.000073229996,0.0006974121,0.00071756623,0.0009914035,0.00006577424,0.00036124076,0.00008281536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033879074,0.0000680417,0.050255366,0.000008051599,0.00009349023,0.00003512925,0.0005966114,0.00059747056,0.000028822516,0.0015762132,0.03242318,0.91428375],"study_design_scores_gemma":[0.0062636477,0.0006836988,0.18898977,0.00030442997,0.0008470583,0.0028013305,0.0035561733,0.46360582,0.000040305236,0.021893978,0.31013852,0.00087526644],"about_ca_topic_score_codex":0.00047936424,"about_ca_topic_score_gemma":0.006397446,"teacher_disagreement_score":0.91340846,"about_ca_system_score_codex":0.00042797092,"about_ca_system_score_gemma":0.007168343,"threshold_uncertainty_score":0.9984601},"labels":[{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.957476,0.0073269415,0.00012748176,0.0050294735,0.00021394636,0.0011053107,0.00012529877,0.000007934051,0.028587587],"genre_scores_gemma":[0.99869627,0.00028888794,0.0007337158,0.0000148924255,0.00017528892,0.000009318304,0.000027062264,0.000003783535,0.0000507871],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967028,0.001143127,0.00030254436,0.00016245896,0.00140413,0.00028497682],"domain_scores_gemma":[0.9978396,0.00013506242,0.0003094107,0.00044883427,0.0010056527,0.00026139992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011036229,0.00006187044,0.00020053716,0.00049981475,0.00084213336,0.000087052795,0.00091763976,0.000042366835,0.00016541725],"category_scores_gemma":[0.0008314489,0.00004112242,0.0001057882,0.0014506838,0.0006333314,0.000550647,0.000040145824,0.00030332126,0.0000013198392],"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":[0.000021333979,0.00016440774,0.21939571,0.000028649927,0.001194728,0.000021763453,0.027315613,0.00016945064,0.000017919812,0.003730464,0.003963827,0.7439761],"study_design_scores_gemma":[0.00056995894,0.00032709463,0.83051014,0.000102675665,0.0016835035,0.000021125144,0.021055069,0.0043586507,0.000010612174,0.0012991353,0.13987096,0.00019107084],"about_ca_topic_score_codex":0.04778578,"about_ca_topic_score_gemma":0.8503561,"teacher_disagreement_score":0.80257034,"about_ca_system_score_codex":0.00020307026,"about_ca_system_score_gemma":0.0049262955,"threshold_uncertainty_score":0.9585551},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21720637,0.07417683,0.3241494,0.1129106,0.02761862,0.015184668,0.000037120255,0.00022601202,0.22849037],"genre_scores_gemma":[0.7572712,0.00010750014,0.23758951,0.00086002157,0.001276803,0.00012135512,0.000015969648,0.000049463968,0.002708213],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9839431,0.008096215,0.00129091,0.00034197338,0.0053501315,0.0009776425],"domain_scores_gemma":[0.9866231,0.003602004,0.0012592193,0.00073006627,0.00605758,0.0017280371],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1709859,0.00023078558,0.00040510483,0.0015161204,0.0005942101,0.00093280274,0.00092561514,0.00014769468,0.0034832638],"category_scores_gemma":[0.021923333,0.00015808671,0.00015393611,0.0023810267,0.0002552706,0.002885966,0.00004034897,0.0008345735,0.00023434343],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089345966,0.00007486258,0.0035684227,0.0000044154804,0.00007971633,0.000005899375,0.003390273,0.00054397597,0.00006252079,0.0027584375,0.06667337,0.92274874],"study_design_scores_gemma":[0.001570656,0.0009150644,0.017183194,0.00011470898,0.00029202868,0.0002433921,0.014458935,0.004676933,0.00062802614,0.022082848,0.9375132,0.00032104683],"about_ca_topic_score_codex":0.0009806114,"about_ca_topic_score_gemma":0.007979186,"teacher_disagreement_score":0.9224277,"about_ca_system_score_codex":0.00070522743,"about_ca_system_score_gemma":0.012174797,"threshold_uncertainty_score":0.9974277},"labels":[],"label_agreement":null},{"id":"W4366448452","doi":"10.3138/cjpe.0021.017","title":"Les dispositifs de la participation aux étapes stratégiques de l’évaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deliberation; Participatory evaluation; Valuation (finance); Citizen journalism; Relevance (law); Knowledge management; Rationality; Process management; Sociology; Management science; Psychology; Business; Computer science; Political science; Engineering; Social science; Accounting","score_opus":0.4004949898556033,"score_gpt":0.5989514537971734,"score_spread":0.19845646394157013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95347667,0.00024419662,0.035724,0.0010035201,0.0002574892,0.0005340303,0.0000030243684,0.000015063128,0.008741991],"genre_scores_gemma":[0.98895985,0.000013683033,0.010466863,0.00015486224,0.00022590489,0.00003867309,0.000012155456,0.000010750235,0.00011726812],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950023,0.0014733023,0.0009981783,0.00017133405,0.0019508287,0.00040401582],"domain_scores_gemma":[0.9951497,0.00087730616,0.00065272156,0.0001965551,0.0025805756,0.00054315233],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.052756462,0.00012178185,0.00018057968,0.00065778644,0.0003202434,0.0005958475,0.00032031382,0.00014798272,0.0012107735],"category_scores_gemma":[0.00549432,0.00010141644,0.00011721548,0.0006023719,0.00013339247,0.0006866785,0.000007027856,0.00025137136,0.000023919178],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023594208,0.00004764537,0.122630484,0.0000030419394,0.000017395074,0.0000074049094,0.0033590868,0.0050287833,0.0003903994,0.0020173215,0.00050456135,0.86597025],"study_design_scores_gemma":[0.0006256153,0.00041823206,0.8728573,0.000046220368,0.0001159749,0.000052760846,0.0018230482,0.0803071,0.0013272121,0.0242128,0.018073505,0.00014024862],"about_ca_topic_score_codex":0.0018487063,"about_ca_topic_score_gemma":0.03816045,"teacher_disagreement_score":0.86583,"about_ca_system_score_codex":0.0009059088,"about_ca_system_score_gemma":0.0072425455,"threshold_uncertainty_score":0.9997023},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56793004,0.0020202282,0.0067408793,0.0033367302,0.0039344872,0.0020857125,0.000019844372,0.00019467695,0.4137374],"genre_scores_gemma":[0.99480873,0.0000046869636,0.0015557257,0.0002299097,0.0015891762,0.00003105023,0.0000542844,0.000022719754,0.001703735],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981849,0.0003797306,0.0005010331,0.00014527433,0.00047446415,0.00031460312],"domain_scores_gemma":[0.9982793,0.000103237515,0.0004833389,0.0002338554,0.0005431253,0.00035717114],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004152968,0.00014960952,0.00031298463,0.0006029798,0.00045023288,0.00046587433,0.00022819584,0.000056531237,0.0036071597],"category_scores_gemma":[0.00037790457,0.00012598916,0.00020202527,0.0001644137,0.00012718544,0.00023122707,0.000006039855,0.00036351432,0.00012636455],"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":[0.000020935644,0.00011887134,0.0024681855,0.00007484596,0.0010712532,0.0000057136194,0.0633992,0.0033262332,0.00004301055,0.04296563,0.031685755,0.8548204],"study_design_scores_gemma":[0.00048757627,0.00017142274,0.0008749012,0.00006488933,0.0013393004,0.000012206003,0.0016894536,0.003896719,0.0000060036755,0.0033684107,0.98786587,0.0002232273],"about_ca_topic_score_codex":0.002093293,"about_ca_topic_score_gemma":0.11522528,"teacher_disagreement_score":0.95618016,"about_ca_system_score_codex":0.00015200558,"about_ca_system_score_gemma":0.00042080748,"threshold_uncertainty_score":0.99730366},"labels":[],"label_agreement":null},{"id":"W4366448482","doi":"10.3138/cjpe.020.005","title":"The Delphi Technique as a Method for Increasing Inclusion in the Evaluation Process","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Delphi method; Delphi; Compromise; Inclusion (mineral); Process (computing); Set (abstract data type); Evaluation methods; Psychology; Economic Justice; Representation (politics); Public relations; Management science; Sociology; Engineering ethics; Computer science; Social psychology; Political science; Engineering; Social science; Artificial intelligence; Law","score_opus":0.3689523270921288,"score_gpt":0.6178187315297932,"score_spread":0.2488664044376644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7846106,0.003387119,0.07454904,0.103009254,0.0011375145,0.02417315,0.00001156022,0.000026485151,0.009095257],"genre_scores_gemma":[0.9740414,0.000011867147,0.023542747,0.000714045,0.0002856642,0.0013635232,0.000009716074,0.000010026166,0.000020979674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9898994,0.003581483,0.0012876746,0.00023571022,0.0046421387,0.00035359806],"domain_scores_gemma":[0.991171,0.0021832504,0.0009108325,0.00034639132,0.0052075614,0.00018096682],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18912262,0.00013084718,0.00018777214,0.00058867433,0.0012203808,0.0006664667,0.0010673276,0.00009939401,0.00026235828],"category_scores_gemma":[0.018750962,0.00007047594,0.00012574122,0.0011808376,0.00007494464,0.0007575926,0.000042325064,0.00028641446,0.000013384752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052819392,0.000032205357,0.0008700857,0.0000027269846,0.000007951707,5.3794565e-7,0.0051557957,0.00598011,0.000082322214,0.0005739133,0.0005906152,0.98665094],"study_design_scores_gemma":[0.0015486518,0.00059616595,0.014405023,0.000093474795,0.00014049154,0.0001616433,0.0071220137,0.7008614,0.0004952725,0.18245977,0.09194803,0.00016806836],"about_ca_topic_score_codex":0.0006280525,"about_ca_topic_score_gemma":0.052134223,"teacher_disagreement_score":0.98648286,"about_ca_system_score_codex":0.0007672923,"about_ca_system_score_gemma":0.007992775,"threshold_uncertainty_score":0.997631},"labels":[],"label_agreement":null},{"id":"W4366448488","doi":"10.3138/cjpe.26.009","title":"M. Q. Patton. (2011). <i>Developmental Evaluation: Applying Complexity Concepts to Enhance Innovation and Use.</i> New York, NY: Guilford Press. 373 pages.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognitive science; Psychology; Management; Economics","score_opus":0.692320291059202,"score_gpt":0.5156360293542,"score_spread":0.17668426170500195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96868014,0.0012271354,0.009549137,0.002249229,0.0018825426,0.0062376442,0.000028145128,0.000036942933,0.010109069],"genre_scores_gemma":[0.9533579,0.000017868048,0.044813894,0.00077705923,0.00022396835,0.00026559414,0.000042973094,0.000018963523,0.00048180632],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99348074,0.0006549112,0.0016453872,0.0004538812,0.0033372063,0.0004278612],"domain_scores_gemma":[0.9921696,0.00020258164,0.0011366975,0.00035986063,0.005401112,0.0007301383],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017990474,0.0002441997,0.00036545872,0.0008254603,0.0003728295,0.00069144065,0.0005586009,0.000120846045,0.005665628],"category_scores_gemma":[0.003157468,0.00021283558,0.00007485494,0.001080999,0.00016575227,0.001549919,0.000047731653,0.00027389923,0.00014349728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004337492,0.00004077497,0.01977017,0.000005437481,0.00003662194,0.0000023820987,0.005284006,0.0002387213,0.00013841985,0.000868277,0.02828813,0.9452837],"study_design_scores_gemma":[0.003319258,0.0014591237,0.49840778,0.00023838875,0.00032146022,0.00014811929,0.0058883284,0.034322795,0.003234188,0.026773646,0.42489854,0.0009883866],"about_ca_topic_score_codex":0.00241706,"about_ca_topic_score_gemma":0.018375183,"teacher_disagreement_score":0.9442953,"about_ca_system_score_codex":0.0007145877,"about_ca_system_score_gemma":0.007132832,"threshold_uncertainty_score":0.99953693},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95855707,0.00026289155,0.005721221,0.022289354,0.00043211618,0.0015733048,0.000004148163,0.000023005457,0.011136876],"genre_scores_gemma":[0.99398834,0.00003630764,0.005373631,0.00017589869,0.00026419014,0.000068013665,0.000010085947,0.000009645347,0.00007388411],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9968432,0.0006420045,0.0005155559,0.00019487235,0.0012844381,0.00051989034],"domain_scores_gemma":[0.9968443,0.00013223477,0.0006219479,0.000088117056,0.00186638,0.00044702043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016952954,0.00011775371,0.00016461834,0.00015910136,0.0010681,0.00024111717,0.0002629547,0.000100089805,0.00008253127],"category_scores_gemma":[0.0026369197,0.00011474826,0.000084772975,0.001059063,0.0004016753,0.00083768455,0.00000918321,0.00015624684,0.000006728087],"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":[0.00003106103,0.00018381543,0.048135214,0.00000911124,0.00003569293,0.000008879861,0.30767494,0.0005679756,0.00014156399,0.017760301,0.0013559855,0.62409544],"study_design_scores_gemma":[0.0018428296,0.0004758493,0.8070295,0.000101815174,0.000116859606,0.000007387044,0.10710845,0.0042682886,0.00064446294,0.038013097,0.0400334,0.00035807263],"about_ca_topic_score_codex":0.15874216,"about_ca_topic_score_gemma":0.6843061,"teacher_disagreement_score":0.75889426,"about_ca_system_score_codex":0.00076424395,"about_ca_system_score_gemma":0.011300688,"threshold_uncertainty_score":0.9943043},"labels":[],"label_agreement":null},{"id":"W4366448611","doi":"10.3138/cjpe.0028.010","title":"M&amp;E Competencies in Support of the AIDS Response: A Sector-Specific Example","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Human immunodeficiency virus (HIV); Service delivery framework; Process (computing); Business; Psychology; Service (business); Knowledge management; Nursing; Medical education; Public relations; Medicine; Political science; Marketing; Computer science; Family medicine","score_opus":0.4760414459172037,"score_gpt":0.4932620036647494,"score_spread":0.017220557747545717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366448611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942073,0.00014293655,0.0008660119,0.0020856322,0.0007786487,0.000570178,0.000005807888,0.0000032096966,0.0013402387],"genre_scores_gemma":[0.99632907,0.0000039372253,0.0030894116,0.0002114751,0.000083404564,0.00002199111,0.0000034001464,0.0000066392663,0.0002506496],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944065,0.0018803481,0.00106552,0.00015844022,0.0022574388,0.00023171448],"domain_scores_gemma":[0.9959723,0.00070612814,0.00075694156,0.00043910637,0.0019107409,0.00021478995],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03626521,0.00009637344,0.000247046,0.00068157766,0.00012947278,0.00016226765,0.0006497186,0.00006209517,0.0030438309],"category_scores_gemma":[0.003958457,0.00006192355,0.00013147354,0.0011571392,0.00015707675,0.00031971576,0.000017524988,0.00020047453,0.00004373369],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001776641,0.000090296744,0.3135061,0.000008437475,0.000022228909,0.0000020260882,0.006921491,0.0052737026,0.0017072238,0.0035097508,0.016211884,0.6525692],"study_design_scores_gemma":[0.00074657775,0.00045813082,0.4774944,0.000030018462,0.000014938683,0.000021057638,0.00065434095,0.002585146,0.00017425662,0.0069126943,0.5108309,0.00007756926],"about_ca_topic_score_codex":0.00079256797,"about_ca_topic_score_gemma":0.050491903,"teacher_disagreement_score":0.6524916,"about_ca_system_score_codex":0.00030586417,"about_ca_system_score_gemma":0.0040325737,"threshold_uncertainty_score":0.9978675},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58033943,0.0179087,0.001913398,0.37513658,0.01540679,0.0037697786,0.000066031214,0.000028828314,0.005430471],"genre_scores_gemma":[0.9814541,0.0014364216,0.0030635798,0.0050234925,0.005829187,0.00008222191,0.000011560803,0.00005225977,0.0030472118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926546,0.0040739593,0.0012707216,0.00020430688,0.0007912063,0.0010052015],"domain_scores_gemma":[0.992776,0.0008175139,0.0008856408,0.00027805733,0.0028152291,0.0024276073],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016365433,0.00020374294,0.0004108166,0.00026463138,0.0007044998,0.000035334604,0.00026914407,0.00094393065,0.0088431975],"category_scores_gemma":[0.0072988425,0.00014673066,0.00020835553,0.00041823374,0.00026731525,0.00045542183,0.000011460501,0.0015408145,0.0004749879],"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":[0.000012777212,0.000063139,0.016555069,0.00014090403,0.00007340191,0.00005602853,0.0120403385,0.0000027875947,0.000019478653,0.0014972641,0.07230386,0.897235],"study_design_scores_gemma":[0.0032873582,0.001066367,0.079395294,0.0021569494,0.00037312106,0.00010984545,0.004911565,0.0005322766,0.000011859062,0.0036607487,0.9042971,0.00019749875],"about_ca_topic_score_codex":0.007577257,"about_ca_topic_score_gemma":0.037281413,"teacher_disagreement_score":0.89703745,"about_ca_system_score_codex":0.002323768,"about_ca_system_score_gemma":0.030892022,"threshold_uncertainty_score":0.99903136},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65097004,0.0021140093,0.0028480554,0.0740171,0.16368926,0.003456576,0.000008480668,0.00010272456,0.10279378],"genre_scores_gemma":[0.9503343,0.000009155642,0.0005395648,0.000062795974,0.048897542,0.000003964019,0.000004011698,0.0000057347443,0.00014293943],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99871004,0.00016070929,0.00022215163,0.00007084145,0.00058491615,0.0002513367],"domain_scores_gemma":[0.9981944,0.000045228073,0.00021044319,0.000065407636,0.0011014264,0.0003830874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010447819,0.00004715703,0.000071030765,0.00020514628,0.0004375177,0.00014089057,0.00013156903,0.00009266402,0.00026981492],"category_scores_gemma":[0.0011842243,0.000046847577,0.000046696263,0.00021186612,0.00017350182,0.00030102726,0.000001932056,0.00022183599,0.000014216088],"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":[0.000014381986,0.000060416525,0.002187811,0.0000045254405,0.000032739335,0.000018017208,0.015171324,0.000019320372,0.00017790135,0.02808072,0.07302521,0.88120764],"study_design_scores_gemma":[0.00015092341,0.00011717256,0.0048833895,0.0000111187765,0.000029654564,0.0000067186734,0.0018438254,0.000024026935,0.00009581125,0.004844111,0.98793125,0.000061989],"about_ca_topic_score_codex":0.0074293003,"about_ca_topic_score_gemma":0.23188406,"teacher_disagreement_score":0.914906,"about_ca_system_score_codex":0.0005674662,"about_ca_system_score_gemma":0.002816658,"threshold_uncertainty_score":0.9991803},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9019973,0.000913251,0.0044923816,0.081476025,0.00043315874,0.0017604604,0.0000054686557,0.000039481918,0.00888247],"genre_scores_gemma":[0.98352844,0.000053959837,0.015160484,0.00012038406,0.0007530711,0.00010393136,0.0000037647067,0.000011301305,0.0002646764],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973578,0.00042189262,0.00040642553,0.00016724328,0.00092783786,0.0007188263],"domain_scores_gemma":[0.9979092,0.000029862644,0.00044743632,0.000087830784,0.0008774869,0.0006481669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006141647,0.00011958148,0.00015821803,0.00013458643,0.0012098365,0.00024286451,0.00031379788,0.00012403884,0.0001759593],"category_scores_gemma":[0.00059435517,0.00011636739,0.00012210198,0.000598635,0.0006635732,0.00053540093,0.0000068752875,0.00017328624,0.000012240597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060429634,0.00006821747,0.037736274,0.0000068448935,0.000022550164,0.0000042509964,0.035151202,0.00026137067,0.000030116797,0.0021887172,0.0034329928,0.92109144],"study_design_scores_gemma":[0.003057897,0.00083723187,0.46991718,0.00036994606,0.00035115978,0.000058996902,0.09635356,0.0069496576,0.00032879008,0.06956057,0.3513658,0.0008491866],"about_ca_topic_score_codex":0.28358272,"about_ca_topic_score_gemma":0.8864022,"teacher_disagreement_score":0.92024225,"about_ca_system_score_codex":0.0023343596,"about_ca_system_score_gemma":0.020853654,"threshold_uncertainty_score":0.9846972},"labels":[],"label_agreement":null},{"id":"W4366449208","doi":"10.3138/cjpe.23.011","title":"L’examen de la qualité des évaluations fédérales: une méta-évaluation réussie?","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Credibility; Treasury; Valuation (finance); Quality (philosophy); Relevance (law); Political science; Psychology; Accounting; Business; Philosophy; Epistemology","score_opus":0.5449930809225783,"score_gpt":0.5670762013901169,"score_spread":0.022083120467538686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97703487,0.0006864899,0.007699292,0.0020453508,0.0005022644,0.0010500642,0.000009870124,0.000026093589,0.010945709],"genre_scores_gemma":[0.9767848,0.0000854379,0.021909982,0.0002509445,0.00028621996,0.0001339614,0.000026651285,0.000020947255,0.00050101464],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99028695,0.0035844739,0.0015474121,0.0003034954,0.0037885157,0.0004891738],"domain_scores_gemma":[0.9924003,0.0011759577,0.0010394352,0.0004453339,0.004199058,0.0007398976],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04576758,0.00020679508,0.0003572161,0.0011258154,0.0008639415,0.0004803896,0.00063743803,0.00017297608,0.0028593522],"category_scores_gemma":[0.009944887,0.00017123614,0.0002373949,0.0018912675,0.0005705472,0.0011663187,0.000016936967,0.00035247664,0.0001788303],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022625592,0.000111475085,0.15262681,0.0000062310605,0.000057140274,0.000018702209,0.012367698,0.01413113,0.00014584317,0.0010799483,0.006209887,0.8132225],"study_design_scores_gemma":[0.0017461365,0.00055038463,0.78610677,0.00008264019,0.00018796697,0.000457292,0.003573942,0.097239666,0.0001757377,0.07249853,0.03709116,0.00028978937],"about_ca_topic_score_codex":0.0016626847,"about_ca_topic_score_gemma":0.013037832,"teacher_disagreement_score":0.8129327,"about_ca_system_score_codex":0.0010829445,"about_ca_system_score_gemma":0.01522051,"threshold_uncertainty_score":0.9983948},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037827305,0.0021099485,0.9848981,0.0019470372,0.0044243704,0.0018254562,0.00005544205,0.00004583105,0.00091108744],"genre_scores_gemma":[0.011697839,0.00009588903,0.986493,0.0002797368,0.0008657794,0.00015277573,0.000027175556,0.00004633484,0.00034149914],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99747175,0.0003866359,0.0010321314,0.0002223923,0.0004402033,0.00044689476],"domain_scores_gemma":[0.9935159,0.0017910994,0.0010555823,0.00024502992,0.0030839317,0.00030846513],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008421293,0.00019646376,0.00036405367,0.0003045131,0.00028088735,0.00019896012,0.00022245121,0.00014842159,0.0005505344],"category_scores_gemma":[0.043795906,0.00018156771,0.00014621741,0.00019710955,0.000091859765,0.00033239872,0.000014680433,0.00026371985,0.0000052842224],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010727091,0.00022840402,0.00086310244,0.00034723966,0.00033535325,0.000020440193,0.0040536094,0.00015541809,0.00037098187,0.014197069,0.20232831,0.7769928],"study_design_scores_gemma":[0.002456122,0.000564078,0.0023865683,0.0011245109,0.0023069219,0.000509538,0.006577369,0.0073644095,0.0013242849,0.34521392,0.62932396,0.00084833254],"about_ca_topic_score_codex":0.00016123401,"about_ca_topic_score_gemma":0.0054697385,"teacher_disagreement_score":0.77614444,"about_ca_system_score_codex":0.00023003924,"about_ca_system_score_gemma":0.0024132533,"threshold_uncertainty_score":0.9642586},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9305697,0.007832851,0.0041991468,0.0016459684,0.00031865935,0.010512269,0.000046273064,0.000025211966,0.0448499],"genre_scores_gemma":[0.9972655,0.00007416007,0.0012218,0.000012451828,0.00016796903,0.0003367908,0.000004915389,0.000012754696,0.00090366293],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99061173,0.0061627347,0.0006735338,0.00021451771,0.0018108767,0.0005266246],"domain_scores_gemma":[0.9914601,0.00048016844,0.00042306873,0.00030199738,0.006532258,0.00080244255],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026975244,0.000110029236,0.0002921134,0.0009970763,0.0009578322,0.00013721302,0.00051359925,0.00007979929,0.0034365312],"category_scores_gemma":[0.001992563,0.00010225552,0.0001240408,0.0019858212,0.000920883,0.00049732625,0.000023666164,0.00046786078,0.000057548674],"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":[0.000052152336,0.0011984854,0.03033729,0.000030176423,0.00054351846,0.00062983215,0.301241,0.000041798976,0.00010230874,0.0029149745,0.0329698,0.62993866],"study_design_scores_gemma":[0.0020528655,0.002832502,0.02473746,0.000119601274,0.0006669189,0.00014663085,0.63832265,0.00071326,0.0002830176,0.020397233,0.30926093,0.00046691264],"about_ca_topic_score_codex":0.086984895,"about_ca_topic_score_gemma":0.6991318,"teacher_disagreement_score":0.6294717,"about_ca_system_score_codex":0.0006094357,"about_ca_system_score_gemma":0.006507295,"threshold_uncertainty_score":0.9991249},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96562517,0.0006038552,0.000015868176,0.031331424,0.0003061954,0.0006945799,0.0000010032543,0.0000145455,0.0014073671],"genre_scores_gemma":[0.99656475,0.00035803724,0.0024900248,0.00011460309,0.00029875012,0.000067450186,0.000016474636,0.000009640544,0.00008028985],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981144,0.0004594475,0.00036479658,0.0001445442,0.00055180304,0.00036498206],"domain_scores_gemma":[0.99869645,0.000069273134,0.0002446984,0.00007359654,0.00049924396,0.0004167181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054537025,0.000083502906,0.00014411457,0.00029634632,0.0006791021,0.0004362704,0.00011863,0.000079146164,0.000030621475],"category_scores_gemma":[0.00038821285,0.0000906284,0.000040208324,0.0003325363,0.00020501058,0.00048116044,0.000005429718,0.00025625405,5.7161503e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026974676,0.0000882386,0.13730304,0.000011922253,0.000012559992,0.000019000907,0.032860376,0.000026299696,0.00001794657,0.003067298,0.00017877879,0.82641184],"study_design_scores_gemma":[0.00249947,0.0010492716,0.55447793,0.0019204321,0.00017367666,0.00018092757,0.36549228,0.0015280966,0.00004727096,0.0054189526,0.066574536,0.0006371526],"about_ca_topic_score_codex":0.014904827,"about_ca_topic_score_gemma":0.19544894,"teacher_disagreement_score":0.82577467,"about_ca_system_score_codex":0.0008536302,"about_ca_system_score_gemma":0.004621448,"threshold_uncertainty_score":0.991655},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9108245,0.0003689668,0.000090274356,0.019858629,0.002136377,0.0030886272,0.0000058505275,0.000008100544,0.06361873],"genre_scores_gemma":[0.99862176,0.000009549151,0.0007509077,0.000061697225,0.00020226117,0.000055172746,0.000011608781,0.0000035981789,0.00028345297],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99769604,0.00050424656,0.00041429634,0.000066097295,0.0011745901,0.0001447252],"domain_scores_gemma":[0.99566376,0.000053908498,0.0004892926,0.000078211124,0.003582137,0.00013271211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005506114,0.00005036415,0.00007422831,0.00014640419,0.00026474497,0.00011127017,0.00021569409,0.0000638282,0.00072580384],"category_scores_gemma":[0.002040609,0.000038100512,0.00006731758,0.00029623584,0.000112367285,0.00042477698,0.0000044365224,0.00009363421,0.000019139456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017330085,0.000052213843,0.018152585,0.0000055994783,0.000066288005,5.1553087e-7,0.015297083,0.0007631268,0.0002394331,0.010341041,0.029752184,0.9253126],"study_design_scores_gemma":[0.0026438946,0.00029043376,0.75811183,0.00024571244,0.0002812128,0.0000071544587,0.0051375027,0.01923379,0.001487727,0.0695661,0.14271103,0.0002835849],"about_ca_topic_score_codex":0.014562674,"about_ca_topic_score_gemma":0.07144127,"teacher_disagreement_score":0.92502904,"about_ca_system_score_codex":0.0005018852,"about_ca_system_score_gemma":0.0050022732,"threshold_uncertainty_score":0.99199945},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74849373,0.00863419,0.00048399015,0.19335322,0.03406131,0.0060764956,0.000031306852,0.0000314109,0.008834344],"genre_scores_gemma":[0.9547773,0.000811234,0.0038183643,0.008596766,0.030501045,0.00023523394,0.000049318307,0.000071926246,0.0011387907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918406,0.0041659493,0.0015670374,0.0002459798,0.00096379675,0.0012166158],"domain_scores_gemma":[0.9910253,0.0005683996,0.0010270058,0.00028655533,0.0041300044,0.0029627145],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012394022,0.0002742588,0.0005366485,0.00030074723,0.0011454119,0.00011906225,0.0003396532,0.001150423,0.029294834],"category_scores_gemma":[0.006050491,0.00025782394,0.00026229097,0.0005727483,0.00026457934,0.0007249995,0.000017344537,0.0028859538,0.0011007055],"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":[0.000008013435,0.00010221256,0.021596728,0.00018893075,0.0000772846,0.000043887132,0.021499954,0.000016298243,0.0000058596233,0.0006499602,0.3604839,0.59532696],"study_design_scores_gemma":[0.0029336645,0.0011218892,0.14883016,0.0009236991,0.00037963077,0.00014686314,0.016188918,0.007804676,0.0000042495553,0.0053719967,0.8160098,0.0002844479],"about_ca_topic_score_codex":0.051174328,"about_ca_topic_score_gemma":0.043467958,"teacher_disagreement_score":0.5950425,"about_ca_system_score_codex":0.0021456222,"about_ca_system_score_gemma":0.028445058,"threshold_uncertainty_score":0.9999874},"labels":[],"label_agreement":null},{"id":"W4366449571","doi":"10.3138/cjpe.0022.005","title":"Design and Development Issues in Provincial Large-Scale Assessments: Designing Assessments to Inform Policy and Practice","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Accountability; Scale (ratio); Quality (philosophy); Key (lock); Management science; Engineering ethics; Political science; Psychology; Public relations; Computer science; Engineering","score_opus":0.4087057107089686,"score_gpt":0.5695313585263149,"score_spread":0.16082564781734626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449571","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81436086,0.0006595979,0.1690318,0.0076364246,0.00049530435,0.0045701056,0.0000052085275,0.000019184437,0.003221522],"genre_scores_gemma":[0.621602,0.000046654535,0.3771822,0.0007204772,0.000119329416,0.00012922603,0.0000055584637,0.000011855274,0.00018273246],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952442,0.000879843,0.00104136,0.00025872161,0.0021776666,0.0003982183],"domain_scores_gemma":[0.9960716,0.00059876236,0.00057806424,0.0001629941,0.0019803126,0.00060828077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024467463,0.00015918746,0.00027754676,0.0013296533,0.00045440492,0.00046571982,0.0002554074,0.00008495163,0.00015613758],"category_scores_gemma":[0.0055237007,0.00013446283,0.000024519277,0.0010233357,0.000064510816,0.0019010013,0.000038620256,0.0002112392,0.000021489006],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011047111,0.00010889753,0.052884147,0.0000074442173,0.00003120242,0.00002623957,0.014529834,0.0023237835,0.00007129442,0.00012818647,0.000939897,0.9288386],"study_design_scores_gemma":[0.005258287,0.0029972505,0.5591237,0.000249765,0.00008926293,0.0006682501,0.018214123,0.074183196,0.0005553088,0.0019053782,0.33607885,0.00067663623],"about_ca_topic_score_codex":0.0006427153,"about_ca_topic_score_gemma":0.0094253635,"teacher_disagreement_score":0.928162,"about_ca_system_score_codex":0.000845706,"about_ca_system_score_gemma":0.013948,"threshold_uncertainty_score":0.991642},"labels":[],"label_agreement":null},{"id":"W4366449572","doi":"10.3138/cjpe.0021.004","title":"Will Evaluation Prosper in the Future?","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Professionalization; Accountability; Audit; Public sector; Public relations; Professional standards; Business; Political science; Accounting; Public administration; Sociology; Engineering ethics; Engineering; Law","score_opus":0.2834746849839425,"score_gpt":0.5446628427125925,"score_spread":0.26118815772864995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9687702,0.0016732259,0.0014438792,0.011278585,0.0023290638,0.0031429587,0.000002553174,0.0000063701063,0.011353142],"genre_scores_gemma":[0.9971578,0.000009196498,0.001399246,0.00056762696,0.0007210475,0.00007129558,0.000009730231,0.000006992642,0.00005704399],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9916764,0.0011137711,0.0012524682,0.0002046903,0.005386578,0.00036609586],"domain_scores_gemma":[0.9943455,0.00035940556,0.00066826364,0.00035635135,0.0040091146,0.00026136075],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.11714514,0.0001185937,0.00018211913,0.00092324684,0.00020268478,0.000436083,0.00067307864,0.000094292525,0.002379502],"category_scores_gemma":[0.0029751614,0.000071731505,0.00011327069,0.0015456368,0.00007748537,0.0012468583,0.000006936251,0.00031129693,0.00006900783],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015853464,0.000042151627,0.06645361,0.0000013149817,0.0000072036523,0.000005767629,0.0027168037,0.0010149529,0.000013492368,0.0010845064,0.0021873643,0.926457],"study_design_scores_gemma":[0.0014098473,0.0003867812,0.7832654,0.000029043595,0.000076528704,0.0000784437,0.006737735,0.034609206,0.00003567822,0.026040548,0.14719115,0.00013959964],"about_ca_topic_score_codex":0.00022612646,"about_ca_topic_score_gemma":0.09114942,"teacher_disagreement_score":0.9263174,"about_ca_system_score_codex":0.00063521654,"about_ca_system_score_gemma":0.0048015546,"threshold_uncertainty_score":0.9985325},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4366449591","doi":"10.3138/cjpe.023.006","title":"La méthode de cartographie conceptuelle pour identifier les priorités de recherche sur le transfert des connaissances en santé des populations : quelques enjeux méthodologiques","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"The Quebec Population Health Research Network; Université de Montréal","funders":"","keywords":"Identifier; Computer science","score_opus":0.9068279838512547,"score_gpt":0.6204096034709966,"score_spread":0.28641838038025813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8815304,0.005372169,0.109715514,0.0009193147,0.00017146686,0.00058864267,0.000011282588,0.000036572612,0.0016546517],"genre_scores_gemma":[0.8179191,0.0006373817,0.18091984,0.00010286844,0.00013628723,0.00006832678,0.000008473242,0.000016261125,0.0001914708],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9843362,0.01271199,0.0010233617,0.00027496164,0.0011791354,0.00047437623],"domain_scores_gemma":[0.99320126,0.0023571465,0.00043031047,0.00025682192,0.0032329394,0.00052154064],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054259103,0.00020185222,0.00035951962,0.00069342006,0.00080051355,0.00036039855,0.00056239683,0.00033361226,0.0010202867],"category_scores_gemma":[0.014397008,0.00016995834,0.00024909855,0.0009024695,0.00090804545,0.0010599027,0.00001198491,0.00057090685,0.000010733031],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029131248,0.00007929098,0.34200144,0.000015355628,0.00004599181,0.00002436864,0.0150999315,0.001489278,0.000768716,0.0025250013,0.0021020374,0.63581944],"study_design_scores_gemma":[0.0010533277,0.00036403607,0.68683904,0.0001675922,0.00012162423,0.00043288147,0.01015325,0.00913715,0.0023233038,0.2820655,0.0070633315,0.00027894863],"about_ca_topic_score_codex":0.00638996,"about_ca_topic_score_gemma":0.107361734,"teacher_disagreement_score":0.6355405,"about_ca_system_score_codex":0.0007861748,"about_ca_system_score_gemma":0.012733182,"threshold_uncertainty_score":0.9998929},"labels":[],"label_agreement":null},{"id":"W4366449610","doi":"10.3138/cjpe.22.001","title":"Methodological and Conceptual Challenges in Studying Evaluation Process Use","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Operationalization; Process (computing); Construct (python library); Context (archaeology); Exploratory research; Process management; Quality (philosophy); Knowledge management; Management science; Computer science; Qualitative research; Conceptual model; Scale (ratio); Psychology; Sociology; Epistemology; Business; Engineering","score_opus":0.9321012710267086,"score_gpt":0.6602703593788898,"score_spread":0.2718309116478188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449610","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922889,0.0023612245,0.0011440008,0.0013014884,0.0004129914,0.0013463072,0.0000013080796,0.0000058889173,0.0011379258],"genre_scores_gemma":[0.99450266,0.000069716974,0.005143095,0.00009718464,0.00011512822,0.00004966801,0.000003686429,0.000006676995,0.000012164578],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99299234,0.0020617822,0.0011976735,0.000296294,0.0031133401,0.00033857537],"domain_scores_gemma":[0.99331766,0.0016797344,0.00067315367,0.00018660966,0.0037433165,0.00039950287],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1153398,0.00012716404,0.0003065356,0.000967785,0.00014298837,0.0002896587,0.0002718073,0.000117433985,0.000612001],"category_scores_gemma":[0.02073213,0.00009567966,0.000058646554,0.0007021486,0.00016607191,0.0010996584,0.000012403335,0.00027349358,0.000008953082],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026070347,0.00003696245,0.12535278,0.00000308702,0.000010770671,0.000005326743,0.00569647,0.0014916984,0.000019214316,0.00053361204,0.000035670226,0.8667883],"study_design_scores_gemma":[0.0016850107,0.00062302273,0.915161,0.00006250143,0.00007230428,0.00004261631,0.024897318,0.03975852,0.00006410205,0.01413625,0.0033413768,0.00015599145],"about_ca_topic_score_codex":0.00017491577,"about_ca_topic_score_gemma":0.036528412,"teacher_disagreement_score":0.86663234,"about_ca_system_score_codex":0.00040178513,"about_ca_system_score_gemma":0.00268061,"threshold_uncertainty_score":0.98751664},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8236799,0.0012610002,0.000036260462,0.0737927,0.048169635,0.0032293426,0.000024295874,0.000010578043,0.049796276],"genre_scores_gemma":[0.9321309,0.000025408302,0.0003368393,0.00029559963,0.06691256,0.00001826127,0.000002430797,0.00000518522,0.00027281605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983342,0.0005146454,0.00023377987,0.000052951225,0.0007015951,0.00016282193],"domain_scores_gemma":[0.9984358,0.000107187516,0.00027645825,0.00011650091,0.0008934687,0.00017060776],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025383628,0.00004314339,0.000083963496,0.000022977625,0.00047737476,0.00019524853,0.00041705192,0.00008521674,0.0031336579],"category_scores_gemma":[0.0014704451,0.000027220914,0.00012612811,0.00022382727,0.0003344766,0.00027080945,0.000007749436,0.00018867203,0.000028024693],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.4254434e-7,0.000017176419,0.0258951,0.0000018793965,0.000037617818,3.8212934e-7,0.017029457,0.000013529417,0.000010959853,0.0008965357,0.8016556,0.15444122],"study_design_scores_gemma":[0.0001831449,0.000033920212,0.20229498,0.00003920786,0.00007368767,5.3845054e-7,0.011161968,0.000094115094,0.000013319954,0.009357372,0.7766991,0.000048627266],"about_ca_topic_score_codex":0.11899359,"about_ca_topic_score_gemma":0.31941953,"teacher_disagreement_score":0.20042595,"about_ca_system_score_codex":0.000247669,"about_ca_system_score_gemma":0.0027229022,"threshold_uncertainty_score":0.99777764},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739197,0.0031039552,0.0030927449,0.011172095,0.0017764173,0.002412696,0.000011040485,0.000008873436,0.004502467],"genre_scores_gemma":[0.9985262,0.00004516835,0.00082273234,0.0002820731,0.00020944429,0.00004655704,0.000010278144,0.000007774967,0.000049726463],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9918206,0.0009551927,0.0017961583,0.00017002498,0.0049647833,0.0002932744],"domain_scores_gemma":[0.98659676,0.00080693053,0.0017969861,0.0003287498,0.010240123,0.00023044278],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07960297,0.00013694513,0.00031149221,0.0007803059,0.00033141143,0.0001714244,0.00044548552,0.00008525326,0.0007678888],"category_scores_gemma":[0.0060374034,0.00008464888,0.0001728983,0.0011624171,0.0001931782,0.001029379,0.000009335649,0.00022783503,0.00002801048],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004888551,0.000043949898,0.0063183536,0.000012620621,0.00007524605,0.0000018930687,0.009665096,0.0058789467,0.00012671581,0.0007180395,0.001822944,0.9752873],"study_design_scores_gemma":[0.0042729382,0.0014983607,0.6412517,0.00035166473,0.0009702812,0.00012723127,0.09883677,0.14982268,0.0063404455,0.030367712,0.065709606,0.00045062165],"about_ca_topic_score_codex":0.00018450181,"about_ca_topic_score_gemma":0.024377735,"teacher_disagreement_score":0.9748367,"about_ca_system_score_codex":0.00052793534,"about_ca_system_score_gemma":0.003415695,"threshold_uncertainty_score":0.99342483},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53121966,0.006770839,0.0010211727,0.07129756,0.04265896,0.0038965936,0.000009426616,0.0001132933,0.34301248],"genre_scores_gemma":[0.9923715,0.000032882966,0.0012630553,0.00026362846,0.005924599,0.0000037609805,0.00000266501,0.0000028712332,0.00013505596],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986425,0.00025375484,0.00020348444,0.000059298065,0.0006115321,0.00022941203],"domain_scores_gemma":[0.99844605,0.00002235343,0.00015842299,0.00006263212,0.0008683542,0.000442196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042158016,0.000043808395,0.00008437356,0.00010027925,0.0003997516,0.00021442126,0.00017659146,0.00010096751,0.00032081082],"category_scores_gemma":[0.0010500235,0.0000458283,0.00009431706,0.00024876863,0.00010342686,0.00038256944,0.0000011726021,0.00016051585,0.0000134334405],"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":[0.0000011655458,0.000043647826,0.005711724,0.000002542278,0.00002202919,0.000011758134,0.009325822,0.000039416365,0.000012186672,0.010180242,0.16806395,0.8065855],"study_design_scores_gemma":[0.00040895792,0.0002691608,0.068569645,0.000047487312,0.00008480662,0.000006333881,0.0045292624,0.00020838107,0.000008398882,0.02231476,0.90342706,0.00012576352],"about_ca_topic_score_codex":0.005934939,"about_ca_topic_score_gemma":0.073106654,"teacher_disagreement_score":0.8064597,"about_ca_system_score_codex":0.0005111651,"about_ca_system_score_gemma":0.004182344,"threshold_uncertainty_score":0.9438067},"labels":[],"label_agreement":null},{"id":"W4366449951","doi":"10.3138/cjpe.0023.003","title":"Perceptions of Evaluation Capacity Building in the United States: A Descriptive Study of American Evaluation Association Members","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Association (psychology); Descriptive research; Psychology; Organizational change; Descriptive statistics; Organizational learning; Capacity building; Political science; Public relations; Social psychology; Medical education; Sociology; Management; Economics; Medicine; Social science; Law; Statistics","score_opus":0.40916432990698465,"score_gpt":0.5208469713431527,"score_spread":0.11168264143616807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99388105,0.000059469698,0.00045738835,0.0013372361,0.00026871587,0.003535574,0.0000118768485,0.0000044706208,0.00044422058],"genre_scores_gemma":[0.99843776,0.000010867204,0.0011520927,0.0001357206,0.000061976,0.00014244133,0.00004499428,0.000007190676,0.0000069674647],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9827407,0.00660236,0.0020085182,0.0002808867,0.008044859,0.00032269515],"domain_scores_gemma":[0.9829806,0.00073848746,0.00307496,0.00039813606,0.012629001,0.00017878652],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.081975855,0.00017240584,0.00043673927,0.002075916,0.00021276806,0.00019868815,0.00050535664,0.00008240029,0.00063624466],"category_scores_gemma":[0.010504852,0.00012830913,0.00014699451,0.0040010195,0.00011636127,0.0007837272,0.000008167492,0.00034093426,0.000003986513],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006319961,0.0007831089,0.19484866,0.000004541963,0.00008956449,0.0000011099423,0.0908198,0.20633921,0.00026290378,0.00012883217,0.00060059543,0.5060585],"study_design_scores_gemma":[0.0016827097,0.001954551,0.5453241,0.000045832418,0.000372205,0.000004823621,0.09351583,0.35247222,0.00003130089,0.0043054037,0.00019354091,0.00009749578],"about_ca_topic_score_codex":0.01058646,"about_ca_topic_score_gemma":0.075181395,"teacher_disagreement_score":0.505961,"about_ca_system_score_codex":0.0026587306,"about_ca_system_score_gemma":0.0037868167,"threshold_uncertainty_score":0.9978301},"labels":[],"label_agreement":null},{"id":"W4366449986","doi":"10.3138/cjpe.0021.002","title":"Evaluation Practice in Canada: Results of a National Survey","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Merck Canada Inc. (Canada); Environment and Climate Change Canada","funders":"","keywords":"Certification; Workforce; Professionalization; Public relations; Work (physics); Psychology; Accountability; Population; Medical education; Action (physics); Position (finance); Professional certification (computer technology); Political science; Business; Sociology; Medicine; Engineering; Law","score_opus":0.5394801885554342,"score_gpt":0.5848590900140788,"score_spread":0.04537890145864454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366449986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9628789,0.00094969774,0.00068707607,0.003282418,0.0017954491,0.0020779318,0.00008577148,0.0000034328268,0.02823935],"genre_scores_gemma":[0.99783146,0.000007593165,0.0017816945,0.00018734393,0.00009253799,0.00001784685,0.000045164434,0.0000063613606,0.00003000462],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98204696,0.0028032681,0.0026291492,0.00025934778,0.011899378,0.00036186865],"domain_scores_gemma":[0.9681452,0.0030611458,0.0019084433,0.00022680454,0.026309745,0.00034864474],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23255762,0.00011029548,0.0002580688,0.0011307102,0.00008436247,0.000102031976,0.00041449844,0.000070509705,0.00062068907],"category_scores_gemma":[0.103612065,0.000094465635,0.00006141485,0.001801026,0.000055135995,0.0008494453,0.0000097003685,0.00023817974,0.00001138275],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00017490133,0.00006898066,0.07484857,0.0000021423646,0.000033375276,0.000007589738,0.00114151,0.019479757,0.000017871065,0.00011487176,0.005365419,0.898745],"study_design_scores_gemma":[0.0023479452,0.00024582012,0.91322356,0.000040829644,0.00005382737,0.000030584248,0.0024219449,0.06383089,0.00010568088,0.0027729927,0.01481097,0.00011497939],"about_ca_topic_score_codex":0.8062789,"about_ca_topic_score_gemma":0.99895996,"teacher_disagreement_score":0.89863,"about_ca_system_score_codex":0.0042181704,"about_ca_system_score_gemma":0.10595804,"threshold_uncertainty_score":0.99960446},"labels":[],"label_agreement":null},{"id":"W4366450235","doi":"10.3138/cjpe.0024.001","title":"Challenges and Approaches to Evaluating Comprehensive Complex Tobacco Control Strategies","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tobacco Research Unit; Public Health Ontario; University of Toronto","funders":"","keywords":"Variety (cybernetics); Management science; Computer science; Control (management); Risk analysis (engineering); Ideal (ethics); Intervention (counseling); Attribution; Psychological intervention; Process management; Psychology; Epistemology; Artificial intelligence; Business; Economics; Social psychology","score_opus":0.8095393556398636,"score_gpt":0.5490757212984705,"score_spread":0.2604636343413931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803233,0.0011681063,0.0007751385,0.008372535,0.00076931267,0.0016174306,0.000007014783,0.000011799211,0.0069553712],"genre_scores_gemma":[0.9864987,0.000015290685,0.012831307,0.0002881205,0.0002513874,0.00007907355,0.000004918741,0.000010246714,0.00002091595],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959336,0.0006225259,0.0008480906,0.0002867991,0.002000146,0.0003088249],"domain_scores_gemma":[0.995116,0.0005269552,0.0005588367,0.00031462393,0.0028109076,0.0006726652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013429469,0.00016008427,0.0003339999,0.000618965,0.00025445863,0.0007372664,0.00042269868,0.00009156838,0.00079869747],"category_scores_gemma":[0.0021612744,0.00012368095,0.000083020146,0.0003392222,0.00013864983,0.0007563839,0.000018088012,0.0003197666,0.000046157667],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002043953,0.0000213677,0.004853634,0.000004331269,0.000027183847,0.0000018646936,0.0022611888,0.0024836115,0.0005510495,0.004683302,0.00027195408,0.98482007],"study_design_scores_gemma":[0.0020371454,0.0013450389,0.8192794,0.000041795425,0.000117108204,0.000109858534,0.018003814,0.10573103,0.000039802177,0.023224022,0.029789524,0.00028148454],"about_ca_topic_score_codex":0.00017127728,"about_ca_topic_score_gemma":0.05176646,"teacher_disagreement_score":0.9845386,"about_ca_system_score_codex":0.000094276016,"about_ca_system_score_gemma":0.0030429035,"threshold_uncertainty_score":0.96553636},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4127546,0.32957703,0.033963095,0.06405917,0.0059587043,0.04025992,0.00071539404,0.00023399718,0.1124781],"genre_scores_gemma":[0.7794095,0.0063201287,0.20562732,0.0007771636,0.0032409944,0.00075533683,0.00012620704,0.00008474042,0.0036585568],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949156,0.002246515,0.00064048375,0.00037645063,0.0010468083,0.0007741559],"domain_scores_gemma":[0.995626,0.00078330236,0.00043346864,0.00016385937,0.0019831886,0.0010101818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025780512,0.00020424313,0.0003853199,0.00044869588,0.0010770948,0.00049457524,0.00021945273,0.00021469916,0.00028401645],"category_scores_gemma":[0.005268101,0.00017990427,0.00006363603,0.0005861354,0.0006147248,0.00057282863,0.000022794868,0.00051682314,0.000007874624],"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":[0.00012840504,0.00008053198,0.00033960718,0.000038168862,0.0000692561,0.000026033445,0.008677612,0.00000443073,0.000039357106,0.0033956745,0.15304874,0.83415216],"study_design_scores_gemma":[0.0023403123,0.0014121444,0.009409009,0.00016698039,0.00023865355,0.000029841665,0.011315818,0.00037093976,0.000032710075,0.02310292,0.95124125,0.0003394423],"about_ca_topic_score_codex":0.0035238443,"about_ca_topic_score_gemma":0.09069684,"teacher_disagreement_score":0.8338128,"about_ca_system_score_codex":0.00064214674,"about_ca_system_score_gemma":0.003958883,"threshold_uncertainty_score":0.9258956},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24124074,0.0013487629,0.7563674,0.00012966024,0.00062769826,0.00022713403,5.3878813e-7,0.000037240556,0.000020829239],"genre_scores_gemma":[0.44137388,0.000035441644,0.55841637,0.00005182337,0.000096875396,0.00000477159,0.0000021302774,0.000008365149,0.0000103005605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856704,0.00016980825,0.00033110654,0.00020309107,0.00034591643,0.0003830613],"domain_scores_gemma":[0.9985012,0.00016140111,0.00019962437,0.00023101784,0.000422178,0.0004845787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047061737,0.00012640856,0.0001632823,0.00036831398,0.00014447012,0.00040045282,0.00035905762,0.00008522249,0.000003775958],"category_scores_gemma":[0.00047533077,0.000119937664,0.000038735227,0.00028474344,0.00005746711,0.0013686222,0.000016615884,0.00025904967,6.4634145e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030369877,0.000010061723,0.0017663345,0.00000808121,0.000012136457,0.00004475188,0.0014411012,0.23911563,0.000041535386,0.0018708085,0.00000604313,0.7556805],"study_design_scores_gemma":[0.0015213351,0.0014092313,0.035266835,0.00046480156,0.00011296974,0.00073267735,0.0021160843,0.86268854,0.0011405448,0.091494724,0.002208536,0.000843739],"about_ca_topic_score_codex":0.00042130062,"about_ca_topic_score_gemma":0.004124705,"teacher_disagreement_score":0.75483674,"about_ca_system_score_codex":0.00033840336,"about_ca_system_score_gemma":0.00052055577,"threshold_uncertainty_score":0.4890916},"labels":[],"label_agreement":null},{"id":"W4366450277","doi":"10.3138/cjpe.022.008","title":"Navigating Uncharted Waters: Project Monitoring at Cida","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Monitoring and evaluation; Agency (philosophy); Citizen journalism; Interpretation (philosophy); Participatory evaluation; Set (abstract data type); Process management; Relation (database); International development; Knowledge management; Computer science; Public relations; Business; Sociology; Political science; Public administration","score_opus":0.49079338051818244,"score_gpt":0.592320400631158,"score_spread":0.10152702011297554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941261,0.00024753035,0.0007570098,0.00083080103,0.0015748012,0.00083082676,0.0000024314038,0.000013059367,0.0016174418],"genre_scores_gemma":[0.9940707,0.0000047345475,0.0051884507,0.00006746641,0.00047426965,0.000023478902,0.000008901531,0.000011309207,0.00015069192],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951634,0.00032762048,0.0011526169,0.00020597842,0.0027261304,0.00042428044],"domain_scores_gemma":[0.99521166,0.00028414873,0.0008000101,0.0002524441,0.003000038,0.000451715],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029178454,0.0001289341,0.00020780766,0.0003966908,0.00037197795,0.00039102655,0.00040300674,0.000084461426,0.0007433026],"category_scores_gemma":[0.002326097,0.000097186414,0.0001231926,0.0009556574,0.000068455556,0.00070563966,0.000017840328,0.00031807245,0.00010710418],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017286004,0.0000150651185,0.1531457,0.0000027371916,0.000017357526,0.000012940746,0.0032638754,0.00059643324,0.0003374784,0.000015311323,0.0006377941,0.841938],"study_design_scores_gemma":[0.00453661,0.0020830785,0.7269671,0.0006993108,0.00027440593,0.000439135,0.02597302,0.054929234,0.015366461,0.0049078125,0.1629781,0.00084573554],"about_ca_topic_score_codex":0.00067915465,"about_ca_topic_score_gemma":0.007882214,"teacher_disagreement_score":0.8410923,"about_ca_system_score_codex":0.0010076044,"about_ca_system_score_gemma":0.002566126,"threshold_uncertainty_score":0.9996651},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9624171,0.00019752549,0.0046769334,0.023801288,0.0011391173,0.0014604469,0.000003092793,0.000030101042,0.0062743775],"genre_scores_gemma":[0.9972608,0.00009813778,0.001628376,0.0003075156,0.00055574154,0.000069656955,0.000012170918,0.000011668912,0.00005590114],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972822,0.00034622636,0.00063922413,0.0002470874,0.0009092978,0.000575948],"domain_scores_gemma":[0.9974007,0.00008607572,0.0008529903,0.00012368763,0.0008889004,0.00064766995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011638219,0.00014238726,0.00018545377,0.00021371183,0.0010603088,0.00022580374,0.00037885283,0.00015628386,0.00010837501],"category_scores_gemma":[0.00081215904,0.00015017572,0.0001109357,0.0009400693,0.00041620692,0.00073605165,0.000009637479,0.00019413831,0.000016933183],"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":[0.000065607084,0.00018974487,0.11923017,0.000009908653,0.00003760111,0.000025008872,0.049917348,0.0008321668,0.00055900274,0.02047764,0.0055654575,0.80309033],"study_design_scores_gemma":[0.0015765039,0.00055657397,0.8360279,0.00011362911,0.00011258179,0.000019660472,0.025922807,0.0010360796,0.00081487256,0.022821534,0.1105216,0.000476239],"about_ca_topic_score_codex":0.10597342,"about_ca_topic_score_gemma":0.59492934,"teacher_disagreement_score":0.8026141,"about_ca_system_score_codex":0.0012827272,"about_ca_system_score_gemma":0.009506918,"threshold_uncertainty_score":0.99610823},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8744881,0.0053385766,0.0000113366,0.031960756,0.0001295255,0.001447454,0.000004369161,0.000009672451,0.08661022],"genre_scores_gemma":[0.99886864,0.00060833106,0.0001187065,0.000027718948,0.00017677508,0.00007469889,0.000011852354,0.000004121168,0.00010916896],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980501,0.0004966287,0.00027073993,0.000116952375,0.00077115506,0.0002944057],"domain_scores_gemma":[0.9990117,0.000036598296,0.0001421215,0.00006543597,0.00040419857,0.00033994732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006150761,0.00006689182,0.00009893884,0.00050342496,0.00025361514,0.00031278908,0.0001125887,0.00007020515,0.0001111669],"category_scores_gemma":[0.00035695382,0.00005938685,0.00002022502,0.00022950118,0.00016322349,0.0004715213,0.000008286876,0.000121460806,0.0000010914458],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039647616,0.000038752092,0.0044600572,0.000014208381,0.00001071032,0.000005116509,0.001117075,0.0000070721676,0.00000238168,0.098559275,0.00023952693,0.89554185],"study_design_scores_gemma":[0.001804189,0.00023486764,0.756873,0.00010363847,0.000064527696,0.000016855985,0.006099225,0.0040741144,0.0000068752406,0.102863215,0.12767474,0.00018471606],"about_ca_topic_score_codex":0.0053575854,"about_ca_topic_score_gemma":0.49541703,"teacher_disagreement_score":0.89535713,"about_ca_system_score_codex":0.00047081526,"about_ca_system_score_gemma":0.0016003391,"threshold_uncertainty_score":0.80991024},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98642457,0.001089777,0.000030112336,0.00631322,0.0009626479,0.004295031,0.0000035283724,8.0676955e-7,0.00088033266],"genre_scores_gemma":[0.9950083,0.000022562734,0.0029524032,0.00010701194,0.00080035615,0.0009396509,0.000022758628,0.0000060991338,0.00014087444],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99298507,0.0031743136,0.0009788773,0.00019644477,0.0018090094,0.0008562835],"domain_scores_gemma":[0.99066913,0.002511918,0.0004887743,0.00017395067,0.0057433997,0.000412809],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.041326355,0.00008158249,0.00022094863,0.00019473175,0.0018751582,0.000021392276,0.0002927972,0.000059464754,0.00026888284],"category_scores_gemma":[0.0034460882,0.000056916477,0.000019121853,0.0008729476,0.00065680244,0.00015488379,0.00005240713,0.0004971594,2.4955344e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012568588,0.00014365924,0.5589169,0.0006386554,0.00004923444,4.6473724e-7,0.07788074,0.00060519687,0.000026908601,0.004265335,0.16195552,0.19539167],"study_design_scores_gemma":[0.00093355874,0.00095093803,0.8246324,0.0010861845,0.000025452802,0.0000045601805,0.09632447,0.0033902875,0.00003014513,0.020377345,0.05215015,0.00009448001],"about_ca_topic_score_codex":0.86847794,"about_ca_topic_score_gemma":0.96653014,"teacher_disagreement_score":0.2657155,"about_ca_system_score_codex":0.001726468,"about_ca_system_score_gemma":0.09173727,"threshold_uncertainty_score":0.9994243},"labels":[],"label_agreement":null},{"id":"W4366450581","doi":"10.3138/cjpe.0021.011","title":"Un outil d’évaluation de <i>l’empowerment</i> : une tentative en haïti","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Empowerment; Valuation (finance); Sociology; Psychology; Promotion (chess); Management science; Epistemology; Political science; Business; Economics; Philosophy","score_opus":0.2649696778036359,"score_gpt":0.5361563451404582,"score_spread":0.2711866673368223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366450581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9276348,0.0004678373,0.0466601,0.0066586607,0.0015680242,0.0015927928,0.000009378342,0.00002031545,0.015388121],"genre_scores_gemma":[0.98268694,0.000014064859,0.016074954,0.0005965257,0.00027976712,0.000033046585,0.000019051848,0.000014165099,0.0002814924],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935391,0.0010181803,0.0013737928,0.00025294398,0.0033203403,0.0004956758],"domain_scores_gemma":[0.9937952,0.0006379415,0.0009951753,0.00029181316,0.0035776226,0.0007022561],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.056212872,0.00016768386,0.00026441916,0.00093596865,0.0003035433,0.00037297423,0.0005274259,0.00012467902,0.0024090314],"category_scores_gemma":[0.0041465038,0.0001354727,0.00017106949,0.001382048,0.00011684463,0.0007373668,0.000014500316,0.00030560783,0.00014571274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034832887,0.000059385202,0.03880226,0.0000021261696,0.000039406284,0.000014725691,0.0071565914,0.0015840717,0.00037215665,0.0005074251,0.0018444911,0.9495825],"study_design_scores_gemma":[0.0033283217,0.0013320266,0.7876799,0.000080261154,0.000281823,0.00017873476,0.015160476,0.045725316,0.0032416326,0.052707337,0.08988912,0.00039507213],"about_ca_topic_score_codex":0.00078666344,"about_ca_topic_score_gemma":0.016307246,"teacher_disagreement_score":0.94918746,"about_ca_system_score_codex":0.0010772394,"about_ca_system_score_gemma":0.006800991,"threshold_uncertainty_score":0.99882954},"labels":[],"label_agreement":null},{"id":"W4366451079","doi":"10.3138/cjpe.23.010","title":"A Journey Through Five Evaluation Projects with the Same Analysis Framework","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Strengths and weaknesses; Accountability; Process (computing); Interpretation (philosophy); Process management; Principal (computer security); Context (archaeology); Field (mathematics); Management science; Computer science; Knowledge management; Business; Political science; Psychology; Engineering; Social psychology; Computer security; Law","score_opus":0.46380024285771465,"score_gpt":0.5339974314860121,"score_spread":0.07019718862829744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9623138,0.0010996086,0.016608292,0.012247009,0.00059631525,0.0028192196,0.000009246373,0.00001509733,0.0042914473],"genre_scores_gemma":[0.98807395,0.000029515082,0.010380981,0.0007273756,0.00029215173,0.00018722216,0.000017809723,0.000013065504,0.00027792537],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99021894,0.0017280146,0.0010178664,0.000322662,0.006320398,0.00039214926],"domain_scores_gemma":[0.98824567,0.0006962408,0.001417343,0.000603152,0.008665842,0.0003717386],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023375375,0.00019946722,0.00040782196,0.000979442,0.00083257,0.00051352184,0.0007563584,0.00012408005,0.003429533],"category_scores_gemma":[0.0051635895,0.000110002366,0.00028659886,0.0045707054,0.00028160028,0.001127916,0.000014566508,0.0004875935,0.000074900905],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015905633,0.00019133285,0.14798598,0.0000068833583,0.0014662417,0.000045444263,0.0808295,0.16093746,0.000011906868,0.0015514971,0.025418213,0.58139646],"study_design_scores_gemma":[0.002662925,0.0020276827,0.48864514,0.0001237824,0.0042250655,0.00041720804,0.025754513,0.40738901,0.000079331374,0.026802534,0.041335497,0.00053732283],"about_ca_topic_score_codex":0.0010178047,"about_ca_topic_score_gemma":0.03441466,"teacher_disagreement_score":0.5808591,"about_ca_system_score_codex":0.0006467789,"about_ca_system_score_gemma":0.012360037,"threshold_uncertainty_score":0.99748147},"labels":[],"label_agreement":null},{"id":"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43795952,0.014445119,0.0075728344,0.45907512,0.018641992,0.018656986,0.000550991,0.00004648199,0.043050952],"genre_scores_gemma":[0.98989975,0.00046547782,0.0050445315,0.00019144904,0.0025152394,0.00063216814,0.000095750234,0.000016304972,0.0011393394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957758,0.0009694545,0.00085188035,0.00019353835,0.0019073562,0.00030197023],"domain_scores_gemma":[0.99179655,0.0010715282,0.0014176969,0.00019539655,0.005199117,0.0003197145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017627453,0.00013179795,0.00020234639,0.00031461162,0.00088788674,0.00019575501,0.00032536092,0.00017720567,0.0008649093],"category_scores_gemma":[0.0052466486,0.00011740398,0.00012692803,0.0003976996,0.00020039831,0.00039298454,0.000008847057,0.00023475189,0.0000072027447],"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":[0.000024032703,0.0004855578,0.3373066,0.000037418158,0.0004913197,3.7582032e-7,0.027730161,0.0010485578,0.00005949986,0.08560191,0.1973078,0.3499068],"study_design_scores_gemma":[0.00085054856,0.00011888725,0.44002008,0.00009720749,0.00038294063,0.000009672926,0.0063914186,0.001966244,0.000020002282,0.008923172,0.5410394,0.00018042758],"about_ca_topic_score_codex":0.0037820067,"about_ca_topic_score_gemma":0.010432135,"teacher_disagreement_score":0.5519402,"about_ca_system_score_codex":0.0023759578,"about_ca_system_score_gemma":0.010413062,"threshold_uncertainty_score":0.995197},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98846805,0.00079244346,0.0005543883,0.00024130006,0.0006465947,0.0016569884,0.000003699607,0.000010222344,0.0076263156],"genre_scores_gemma":[0.9981159,0.000015008645,0.0012540215,0.000012214118,0.0004851432,0.000065614404,0.000004152228,0.000012942047,0.000035001583],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9809486,0.011055598,0.0008135965,0.00018910537,0.006049624,0.0009434698],"domain_scores_gemma":[0.9865939,0.00064934185,0.00046094868,0.00020396938,0.010967759,0.0011240591],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26124737,0.00008875116,0.00019678591,0.0010602956,0.000591389,0.000116357915,0.00034842608,0.00016633859,0.0005892872],"category_scores_gemma":[0.02888243,0.00008932872,0.000100576384,0.001396319,0.00079913106,0.0005854733,0.000010751196,0.00046591408,0.000017467697],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006382753,0.00011608355,0.018481987,0.000018547476,0.000052001447,0.0000050568265,0.047261726,0.00027250964,0.0007194399,0.0012993086,0.0002593147,0.9314502],"study_design_scores_gemma":[0.005656881,0.003948134,0.4410921,0.0007852058,0.001800808,0.000011451864,0.3798693,0.027254144,0.020427119,0.039413385,0.078918956,0.00082248234],"about_ca_topic_score_codex":0.01596213,"about_ca_topic_score_gemma":0.2456339,"teacher_disagreement_score":0.9306277,"about_ca_system_score_codex":0.0024376088,"about_ca_system_score_gemma":0.019227663,"threshold_uncertainty_score":0.9905907},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90213233,0.019368125,0.00052305765,0.048158307,0.0055205896,0.0007202552,0.0000098673145,0.000016526183,0.023550926],"genre_scores_gemma":[0.98299074,0.0011153433,0.010639435,0.00042587076,0.003995471,0.000034002125,0.000012285147,0.000014443437,0.00077239366],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99534863,0.003185327,0.000418089,0.00012677726,0.0004885362,0.00043261048],"domain_scores_gemma":[0.9966693,0.0009503022,0.00042549675,0.00008979186,0.0011686203,0.0006965009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013444437,0.000114335264,0.00016749022,0.00023634055,0.0008579319,0.00007908972,0.00024973173,0.00028031252,0.00066860183],"category_scores_gemma":[0.0043840064,0.00013022083,0.00012496514,0.00063675304,0.0017570731,0.00037946473,0.0000031198208,0.0004166859,0.00002723779],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004073353,0.000212845,0.066873394,0.00002249142,0.00015526176,0.00003537466,0.14778304,0.00040603135,0.000013869575,0.056479294,0.012235496,0.7157788],"study_design_scores_gemma":[0.000996047,0.00042758623,0.25276244,0.00016256895,0.0003877976,0.00060274353,0.045704223,0.0014304228,0.000020455136,0.03932445,0.6578428,0.00033845348],"about_ca_topic_score_codex":0.009642484,"about_ca_topic_score_gemma":0.005338328,"teacher_disagreement_score":0.7154404,"about_ca_system_score_codex":0.0011209339,"about_ca_system_score_gemma":0.015497178,"threshold_uncertainty_score":0.9969524},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9369704,0.00013276562,0.0056651062,0.049926836,0.0008142061,0.004042508,0.000086829765,0.00006803404,0.0022932994],"genre_scores_gemma":[0.9859405,0.00001609404,0.009361568,0.002870611,0.00065081596,0.0008397305,0.00018405385,0.00004621258,0.00009038108],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9909192,0.003963682,0.0020629002,0.0003425057,0.001186977,0.0015247699],"domain_scores_gemma":[0.9944945,0.00089099095,0.001609534,0.00033019003,0.0014687802,0.0012060112],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.01521211,0.00029414255,0.0004107923,0.0007497028,0.0016039684,0.00014296132,0.00042858568,0.00027921013,0.00066530553],"category_scores_gemma":[0.0013178778,0.00028249793,0.00020432593,0.0012220558,0.00020207844,0.0005904165,0.0000352807,0.0008882852,0.00009333772],"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":[0.0000957068,0.0003063043,0.21259637,0.0002916852,0.00011189874,0.00008484184,0.04976049,0.00032181432,0.00034409759,0.001815369,0.011310082,0.7229613],"study_design_scores_gemma":[0.0053230613,0.0007989859,0.85154235,0.0004928416,0.00030866958,0.00020807974,0.012690494,0.0038993596,0.000313256,0.0057501355,0.11826403,0.00040873463],"about_ca_topic_score_codex":0.120781645,"about_ca_topic_score_gemma":0.29414278,"teacher_disagreement_score":0.7225526,"about_ca_system_score_codex":0.003579628,"about_ca_system_score_gemma":0.008796028,"threshold_uncertainty_score":0.99996275},"labels":[],"label_agreement":null},{"id":"W4366451139","doi":"10.3138/cjpe.0024.008","title":"Advocacy Evaluation Theory as a Tool for Strategic Conversation: A 25-Year Review of Tobacco Control Advocacy at the Canadian Cancer Society","year":2010,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Circumstantial evidence; Conversation; Tobacco control; Control (management); Key (lock); Public relations; Political science; Policy advocacy; Sociology; Medicine; Management; Nursing; Law; Public health; Computer science; Economics","score_opus":0.3649842729698006,"score_gpt":0.551830417055927,"score_spread":0.18684614408612632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451139","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004198205,0.9777974,0.00008221772,0.0036306423,0.0019498772,0.014467658,0.0002441522,0.0000075550533,0.0014006759],"genre_scores_gemma":[0.0051467223,0.98701733,0.00068443955,0.0016665079,0.0008551723,0.0036362237,0.00044663344,0.000065236236,0.00048174133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9874939,0.0032757558,0.003231166,0.0005656444,0.0047888746,0.0006447159],"domain_scores_gemma":[0.97778285,0.0018608267,0.005034089,0.00096960674,0.013563036,0.00078957464],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07461086,0.00050961913,0.0016973107,0.00069901143,0.0006728804,0.0005299328,0.0013713919,0.0005308716,0.0146449],"category_scores_gemma":[0.008797126,0.0003271608,0.0015853589,0.0013714144,0.00036159612,0.0005465247,0.000024626745,0.00086107,0.00013337002],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000012981954,0.000020985257,0.00019004758,0.0016685032,0.00025666965,9.428984e-7,0.00066036335,0.00010284922,2.6659063e-7,0.0005994269,0.007725628,0.9887613],"study_design_scores_gemma":[0.0016784578,0.0003587983,0.00022041898,0.011603451,0.004664811,0.00004690022,0.0007920481,0.0027265812,8.3507297e-7,0.005402865,0.9721281,0.0003767473],"about_ca_topic_score_codex":0.01724536,"about_ca_topic_score_gemma":0.42430502,"teacher_disagreement_score":0.9883846,"about_ca_system_score_codex":0.0040260074,"about_ca_system_score_gemma":0.17273363,"threshold_uncertainty_score":0.99991804},"labels":[],"label_agreement":null},{"id":"W4366451145","doi":"10.3138/cjpe.031.1.v","title":"Editor’s Remarks","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Philosophy","score_opus":0.2352312171100758,"score_gpt":0.5173110315008186,"score_spread":0.2820798143907428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70734173,0.0021938912,0.03592408,0.09790035,0.07559558,0.004779668,0.000048293296,0.00007085258,0.07614554],"genre_scores_gemma":[0.9935613,0.000010244632,0.0025691402,0.00019054784,0.0027680278,0.000027874888,0.0000017814228,0.0000072550424,0.0008637827],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958554,0.0004423026,0.0008024528,0.00015376564,0.0025077513,0.00023831196],"domain_scores_gemma":[0.9944455,0.00035156467,0.00060138653,0.00028514204,0.0038056388,0.0005107857],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017838495,0.000085654596,0.00016609985,0.00057251786,0.00013777999,0.00024997292,0.00045657804,0.000071138784,0.008335228],"category_scores_gemma":[0.0062385886,0.00004694643,0.000113905895,0.00047170804,0.00008704193,0.0007777386,0.000008196827,0.00010031377,0.0003532674],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069854896,0.000011265409,0.015546544,6.105932e-7,0.000009550195,0.0000023351624,0.00015865812,0.000045067194,0.00008708281,0.00029007465,0.09130763,0.8925342],"study_design_scores_gemma":[0.0011292034,0.00045871342,0.082593635,0.00007258218,0.000044628698,0.00003873236,0.0003466939,0.0030456726,0.00019578553,0.021925647,0.89001626,0.00013245881],"about_ca_topic_score_codex":0.00011594232,"about_ca_topic_score_gemma":0.008389437,"teacher_disagreement_score":0.89240175,"about_ca_system_score_codex":0.00040046746,"about_ca_system_score_gemma":0.0055036694,"threshold_uncertainty_score":0.9925713},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944084,0.0012566382,0.000017419929,0.001089027,0.00007286531,0.00067626504,0.0000011375872,0.00000418723,0.0024740433],"genre_scores_gemma":[0.99700403,0.00023964272,0.002545303,0.000019296787,0.0001278272,0.00001421891,0.0000021953692,0.0000074192653,0.00004005324],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997858,0.00064889336,0.0002804466,0.00012076357,0.00086369144,0.00022824165],"domain_scores_gemma":[0.99857336,0.00015505728,0.00023501583,0.000053118718,0.0007088583,0.00027459426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009059384,0.00007156649,0.00014515987,0.00023075099,0.0004429129,0.00014068317,0.00007608528,0.000063928994,0.00006527927],"category_scores_gemma":[0.0005842899,0.00007213814,0.00002406049,0.00019115952,0.00033669145,0.000320657,0.00001258434,0.0001607957,1.4802193e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032958028,0.0000113771885,0.71177614,0.000007708783,0.000034071076,0.000003490575,0.041983306,0.0000074391346,0.00015716173,0.0002541887,0.0000791306,0.24568269],"study_design_scores_gemma":[0.00082269066,0.0001999492,0.96380156,0.00012391234,0.00012326789,0.000019136727,0.031656936,0.0017165705,0.000021415763,0.0006724509,0.0007405401,0.000101569196],"about_ca_topic_score_codex":0.011072668,"about_ca_topic_score_gemma":0.035909973,"teacher_disagreement_score":0.25202543,"about_ca_system_score_codex":0.00040914916,"about_ca_system_score_gemma":0.0021693336,"threshold_uncertainty_score":0.99551266},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.984796,0.0006557947,0.00062677235,0.0011645516,0.0007666255,0.0032872597,0.000009718397,0.000007682317,0.008685635],"genre_scores_gemma":[0.99774873,0.000006356279,0.0014607538,0.000059461374,0.0001591822,0.0004030536,0.000047825743,0.000011194683,0.00010345964],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99181306,0.0016292334,0.0021027098,0.00018853761,0.0039658975,0.00030057042],"domain_scores_gemma":[0.99209607,0.00020645114,0.0013225607,0.00030476044,0.005896973,0.00017318633],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035647385,0.00015402687,0.00032932233,0.0018071097,0.00015256686,0.00022598688,0.00036520863,0.000112917594,0.002031639],"category_scores_gemma":[0.0027093142,0.00012017972,0.000114154915,0.0015299619,0.000099622666,0.0014449953,0.0000056423996,0.00020546914,0.000024325886],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055761324,0.00035848387,0.021645376,0.00002455482,0.00002190161,0.0000012577034,0.008245746,0.012342844,0.00009717346,0.002390056,0.0024106528,0.95240617],"study_design_scores_gemma":[0.0044796714,0.0011203288,0.66356665,0.00034313832,0.00043746716,0.00005674243,0.014766334,0.24786822,0.00040685813,0.047946304,0.018647403,0.0003608769],"about_ca_topic_score_codex":0.005383559,"about_ca_topic_score_gemma":0.24671665,"teacher_disagreement_score":0.9520453,"about_ca_system_score_codex":0.00094594073,"about_ca_system_score_gemma":0.028632052,"threshold_uncertainty_score":0.9988806},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936973,0.000097432785,0.0003149075,0.0039631515,0.00023942532,0.00160761,0.0000065898957,0.000008254111,0.000065317305],"genre_scores_gemma":[0.99084973,0.000014021843,0.008852765,0.000028992268,0.00013933434,0.00007447393,0.000013981416,0.000009165389,0.00001750775],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970954,0.0013140312,0.0005038256,0.00011008777,0.00079247786,0.00018415182],"domain_scores_gemma":[0.9964997,0.00013168632,0.0011801205,0.00014156473,0.0018182233,0.00022870585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014176953,0.00008334224,0.00015662785,0.00020934732,0.00043187238,0.00013243157,0.00031717954,0.000092854265,0.000028315693],"category_scores_gemma":[0.0037800283,0.000065683555,0.00006615078,0.00033970544,0.0003087141,0.0025684102,0.000006856771,0.00021811723,6.678246e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003694054,0.00010257646,0.05733177,0.000026266374,0.000024645718,9.7177114e-8,0.013526877,0.00032847165,0.00006767642,0.0009297056,0.000026212734,0.9275988],"study_design_scores_gemma":[0.005213313,0.0056958646,0.77797604,0.0010867784,0.0015119981,0.000031536933,0.026638515,0.039033324,0.013515798,0.011183554,0.117354006,0.0007592601],"about_ca_topic_score_codex":0.0018839559,"about_ca_topic_score_gemma":0.054433692,"teacher_disagreement_score":0.9268395,"about_ca_system_score_codex":0.00026406988,"about_ca_system_score_gemma":0.0033423945,"threshold_uncertainty_score":0.9628204},"labels":[],"label_agreement":null},{"id":"W4366451556","doi":"10.3138/cjpe.020.004","title":"The Changing Role of the Evaluator in the Process of Organizational Learning","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Facilitator; Organizational learning; Knowledge management; Process (computing); Context (archaeology); Organization development; Participatory evaluation; Psychology; Computer science; Process management; Social psychology; Business; Sociology","score_opus":0.12489349374341881,"score_gpt":0.4789306428987973,"score_spread":0.3540371491553785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451556","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99018663,0.0008010201,0.000091156,0.006295251,0.0002226553,0.00082896964,0.000001931295,0.0000018217239,0.0015705867],"genre_scores_gemma":[0.9994642,0.000008655445,0.00019009545,0.00010415214,0.00013159555,0.000028457718,0.0000017722856,0.000005482169,0.0000656007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950241,0.0010114897,0.00086283375,0.00009579852,0.0028092514,0.00019654767],"domain_scores_gemma":[0.9951274,0.000504825,0.0010198676,0.00022254983,0.0030521376,0.00007322464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027491428,0.0000729309,0.00013549362,0.0003266529,0.00036407847,0.00014221611,0.0008414163,0.00004069064,0.00046547456],"category_scores_gemma":[0.0057150633,0.000033947934,0.00008156299,0.0017627856,0.00012828298,0.00028427475,0.000014673839,0.00023419547,0.000007354482],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016141634,0.000054124303,0.16663218,0.0000056138997,0.000022899883,2.44755e-7,0.025953611,0.05829283,0.00015385795,0.0027834028,0.00021394649,0.7458711],"study_design_scores_gemma":[0.001372018,0.0004221712,0.32722405,0.00016349353,0.00012831755,0.00004698502,0.06734931,0.5433532,0.0019832398,0.026021134,0.031769328,0.0001667857],"about_ca_topic_score_codex":0.00006835081,"about_ca_topic_score_gemma":0.008206646,"teacher_disagreement_score":0.74570435,"about_ca_system_score_codex":0.00015782901,"about_ca_system_score_gemma":0.004251224,"threshold_uncertainty_score":0.9528035},"labels":[],"label_agreement":null},{"id":"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":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9748642,0.0016218023,0.0001834415,0.0046591926,0.00015774448,0.0008236971,0.0000093979315,0.0000027258236,0.01767783],"genre_scores_gemma":[0.99819905,0.000044740314,0.0013368838,0.00007220638,0.00018474052,0.000042023163,0.000006439801,0.00001220685,0.000101731726],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99728936,0.0012145743,0.000684057,0.00017352843,0.00024748314,0.00039097905],"domain_scores_gemma":[0.9985913,0.0001764213,0.00018562567,0.00017356589,0.0007373498,0.00013571537],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.052488744,0.00006884997,0.00014348082,0.001453479,0.00057626393,0.0001234282,0.00030758695,0.000055614888,0.000093911454],"category_scores_gemma":[0.0011104555,0.000059382357,0.000041232197,0.0011337926,0.00031596445,0.00023902566,0.000015779182,0.00075027125,0.00004248262],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007705874,0.000540431,0.119074985,0.00009995433,0.00008748918,0.0003866275,0.21260712,0.0009027012,0.0000908546,0.04147245,0.007436203,0.61722416],"study_design_scores_gemma":[0.0039086025,0.0018682971,0.81726164,0.0002802151,0.000012425834,0.0005851546,0.012426566,0.05769379,0.000022933726,0.08030591,0.025295328,0.00033911786],"about_ca_topic_score_codex":0.0016873697,"about_ca_topic_score_gemma":0.005992547,"teacher_disagreement_score":0.6981867,"about_ca_system_score_codex":0.00026687986,"about_ca_system_score_gemma":0.0005744361,"threshold_uncertainty_score":0.97566223},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5634787,0.06241748,0.0010092827,0.33048669,0.022774845,0.004439555,0.000039311475,0.000038708662,0.015315449],"genre_scores_gemma":[0.97173095,0.0013934211,0.0068292655,0.000816629,0.014722566,0.00010557705,0.0000188111,0.000046037454,0.0043367483],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98259366,0.014687021,0.0011412,0.00019251207,0.00063184276,0.0007537756],"domain_scores_gemma":[0.99346256,0.001137681,0.0013679992,0.0002343485,0.0023183841,0.0014789971],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025386963,0.00017594031,0.00033962735,0.00052537024,0.0010515148,0.00007531369,0.0001865067,0.0007011094,0.003689547],"category_scores_gemma":[0.0102738,0.00017990498,0.0001265126,0.00066847936,0.00025535034,0.0008573038,0.0000077237355,0.0019784756,0.00023221345],"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":[0.000038338796,0.00009108312,0.017199842,0.00033109728,0.0000841031,0.00018411913,0.018319115,0.00018967899,0.000024282528,0.0015229064,0.2599096,0.7021058],"study_design_scores_gemma":[0.0007554307,0.00054174644,0.047523517,0.00037528347,0.0001905741,0.0021096496,0.0026361228,0.001358786,0.000009137146,0.000903253,0.9434494,0.00014713782],"about_ca_topic_score_codex":0.045423787,"about_ca_topic_score_gemma":0.036934674,"teacher_disagreement_score":0.7019587,"about_ca_system_score_codex":0.0027845362,"about_ca_system_score_gemma":0.03290806,"threshold_uncertainty_score":0.9980631},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9791055,0.0016690763,0.009654846,0.0012673745,0.0007387552,0.00053314975,0.000029352632,0.000011271694,0.0069907145],"genre_scores_gemma":[0.9965178,0.000060922343,0.0021358526,0.00011404071,0.00038195445,0.000013395737,0.00001076191,0.000022669588,0.0007426475],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982328,0.00007678268,0.0009971547,0.00014459144,0.00010786248,0.00044084355],"domain_scores_gemma":[0.9983064,0.00007917619,0.0006460411,0.00014421082,0.00033085365,0.00049334246],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065499223,0.00014735328,0.00028504865,0.00082985044,0.00015737832,0.00014756325,0.00026310384,0.00010287879,0.0011151355],"category_scores_gemma":[0.001508029,0.00013908361,0.0002452943,0.00026066994,0.00008406465,0.00041533654,0.000014716879,0.00019116115,0.00014447089],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013575991,0.00015742332,0.23343273,0.00005068514,0.00024159327,0.000076744254,0.008152821,0.00015123551,0.00004495305,0.0035619773,0.007787211,0.7462069],"study_design_scores_gemma":[0.0043619983,0.0030389668,0.55961055,0.0005226193,0.0001371215,0.0005140942,0.003840055,0.009572355,0.0007813268,0.025278712,0.3916081,0.00073411904],"about_ca_topic_score_codex":0.001516405,"about_ca_topic_score_gemma":0.0141473,"teacher_disagreement_score":0.7454727,"about_ca_system_score_codex":0.0009202732,"about_ca_system_score_gemma":0.00051825837,"threshold_uncertainty_score":0.999798},"labels":[],"label_agreement":null},{"id":"W4366452033","doi":"10.3138/cjpe.0027.009","title":"Lessons Learned and the Contributions of the Paris Declaration Evaluation to Evaluation Theory and Practice","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Declaration; General partnership; Stakeholder; Declaration of independence; Political science; Management; Public relations; Engineering ethics; Sociology; Law; Engineering; Economics","score_opus":0.4365949081454484,"score_gpt":0.5688416158670923,"score_spread":0.13224670772164387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7865028,0.0037472358,0.008980947,0.18310039,0.0010858136,0.012156845,0.00002316706,0.000009125709,0.0043937275],"genre_scores_gemma":[0.9975872,0.000059535698,0.0009702207,0.0006963794,0.000093958944,0.00050919334,0.000009705867,0.000007523215,0.000066264365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9843504,0.010072556,0.0011265905,0.00025901836,0.00393211,0.00025931833],"domain_scores_gemma":[0.9801468,0.0035276418,0.0013199919,0.0004395283,0.014266276,0.00029972132],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1322017,0.00013445289,0.0002588102,0.0003670478,0.0006519375,0.00062404247,0.0003596601,0.00009888516,0.0010431936],"category_scores_gemma":[0.0739798,0.00007441109,0.00009791045,0.000906574,0.00035681878,0.001417658,0.00004021361,0.00024771714,0.000025493411],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011470826,0.00003294366,0.001416131,0.0000028605668,0.000058514182,8.96656e-8,0.0039309906,0.004441598,0.00031824462,0.01845139,0.0019433798,0.9692891],"study_design_scores_gemma":[0.006006219,0.00048752656,0.23891471,0.0001036852,0.0014885752,0.00008453905,0.012935339,0.39597058,0.0004971705,0.3278815,0.015406488,0.00022367446],"about_ca_topic_score_codex":0.0009844056,"about_ca_topic_score_gemma":0.0045406884,"teacher_disagreement_score":0.9690655,"about_ca_system_score_codex":0.0003891121,"about_ca_system_score_gemma":0.0047939783,"threshold_uncertainty_score":0.99987},"labels":[],"label_agreement":null},{"id":"W4366452150","doi":"10.3138/cjpe.0021.001","title":"Special Edition / Edition Speciale Crossing Borders / Crossing Boundaries Editors’ Remarks","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.1617430004729702,"score_gpt":0.49414516120917895,"score_spread":0.33240216073620876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6190321,0.0006788787,0.11612828,0.015366707,0.19910944,0.0033302428,0.00006470352,0.000081422084,0.046208236],"genre_scores_gemma":[0.8611904,0.0000034522532,0.009470173,0.00047415486,0.12848793,0.000018649971,0.00007890925,0.000026168895,0.0002501652],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928471,0.00039718335,0.0016790567,0.00032425232,0.0041598156,0.00059258775],"domain_scores_gemma":[0.9919553,0.00038143765,0.0014046328,0.00031032786,0.005291217,0.00065707834],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.030562721,0.00020939833,0.00032671753,0.001197374,0.0033236481,0.010866922,0.00044144978,0.00020712915,0.005321485],"category_scores_gemma":[0.005864068,0.00018589875,0.00021222811,0.0012067311,0.0013162462,0.0024311242,0.000016629027,0.00044617895,0.00008213129],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007111848,0.00005065466,0.006951703,0.0000053536614,0.000021362228,0.00001867303,0.00334998,0.0005793231,0.00007606256,0.00052496855,0.2150825,0.7732683],"study_design_scores_gemma":[0.0010440814,0.0003589519,0.07368757,0.00009263828,0.00006783751,0.0000621053,0.002536295,0.003996861,0.00039488848,0.013790071,0.90374386,0.00022482593],"about_ca_topic_score_codex":0.00068171724,"about_ca_topic_score_gemma":0.052149765,"teacher_disagreement_score":0.77304345,"about_ca_system_score_codex":0.0013342409,"about_ca_system_score_gemma":0.021751272,"threshold_uncertainty_score":0.9982397},"labels":[],"label_agreement":null},{"id":"W4366452167","doi":"10.3138/cjpe.23.014","title":"Carl F. Brun. (2005). <i>A Practical Guide to Social Service Evaluation.</i> Chicago: Lyceum Books. 204 pages, plus preface, appendices, glossary, references, and index.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Glossary; Index (typography); Library science; Gerontology; Medicine; Computer science; Philosophy; World Wide Web; Linguistics","score_opus":0.36228510341394915,"score_gpt":0.5103163508900976,"score_spread":0.1480312474761485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8424137,0.004558499,0.0031898173,0.07947901,0.0033296235,0.009281473,0.00013122303,0.00008787953,0.057528764],"genre_scores_gemma":[0.9878877,0.00013269183,0.0073876423,0.0024238068,0.0006836837,0.00022943655,0.0000764978,0.000027570706,0.0011509648],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9885263,0.001566633,0.0017672698,0.00058967207,0.0068372195,0.000712945],"domain_scores_gemma":[0.98947257,0.00037368856,0.0012329055,0.0004614711,0.007095484,0.0013638785],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026040895,0.0003181742,0.00054804044,0.00092521793,0.0010104778,0.0007070873,0.00071410026,0.00026954204,0.0025436082],"category_scores_gemma":[0.0039790086,0.00026812023,0.00013376698,0.0012462294,0.00021251533,0.0014283898,0.0000715013,0.0006242152,0.00021023458],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023261509,0.00016569559,0.03409702,0.000027254548,0.00016850517,0.00005433457,0.007327041,0.00415617,0.000064013395,0.0005478699,0.2954055,0.65775394],"study_design_scores_gemma":[0.003062343,0.0005844365,0.17869328,0.00007674282,0.0002716735,0.0004940462,0.00249956,0.057655595,0.0000314047,0.0018251338,0.7543748,0.00043095785],"about_ca_topic_score_codex":0.0031069147,"about_ca_topic_score_gemma":0.108584285,"teacher_disagreement_score":0.657323,"about_ca_system_score_codex":0.0011351827,"about_ca_system_score_gemma":0.026524203,"threshold_uncertainty_score":0.9999771},"labels":[],"label_agreement":null},{"id":"W4366452169","doi":"10.3138/cjpe.20.007","title":"Preparing School Evaluators: Hiroshima Pilot Test of the Japan Evaluation Society’s Accreditation Project","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Accreditation; Certification; Certification and Accreditation; Test (biology); Context (archaeology); Medical education; Sustainability; Program evaluation; Government (linguistics); Political science; Quality (philosophy); Public relations; Psychology; Medicine; Public administration","score_opus":0.3502415788863397,"score_gpt":0.5226132347110275,"score_spread":0.17237165582468778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452169","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841619,0.00076113327,0.0003891916,0.0035913028,0.0014188705,0.0047020637,0.00002095376,0.000018559225,0.004936033],"genre_scores_gemma":[0.9929133,0.000012511953,0.0056686373,0.00023596865,0.0006810112,0.00025141405,0.000021625945,0.000019887653,0.00019560858],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892831,0.0013354825,0.0018962985,0.00035651794,0.00673305,0.00039557077],"domain_scores_gemma":[0.98738813,0.0006271991,0.0022227764,0.00066163164,0.008734359,0.00036592752],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04267324,0.00022079,0.00034623788,0.0006034301,0.00044195366,0.0004879745,0.000979954,0.00012238992,0.001677089],"category_scores_gemma":[0.018634915,0.0001522946,0.00035037994,0.001679314,0.0001878203,0.0016541448,0.000041208463,0.00037256142,0.00006432168],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031354997,0.00018478662,0.08682996,0.000013658993,0.000067968715,1.3022934e-7,0.0029663832,0.019439561,0.0010070107,0.000091718124,0.023228027,0.8661395],"study_design_scores_gemma":[0.0028889521,0.0013957503,0.36206108,0.00020369019,0.0005332331,0.000037090485,0.0032437192,0.59556854,0.0016653576,0.0039145583,0.028202182,0.00028582485],"about_ca_topic_score_codex":0.0004803687,"about_ca_topic_score_gemma":0.016572587,"teacher_disagreement_score":0.8658536,"about_ca_system_score_codex":0.0016281845,"about_ca_system_score_gemma":0.021868998,"threshold_uncertainty_score":0.9992355},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8070602,0.0037451223,0.00026278733,0.010945833,0.05077097,0.0021093523,0.000009098126,0.00006453756,0.12503214],"genre_scores_gemma":[0.98580444,0.00010626611,0.0010128253,0.000103825594,0.0126875555,0.000011067491,0.000004568566,0.000005940821,0.0002634963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841547,0.00030836876,0.00023172742,0.00006882099,0.0007269391,0.0002486463],"domain_scores_gemma":[0.9981198,0.000034952827,0.00018130145,0.0000726508,0.0010913189,0.0004999891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034483478,0.0000503461,0.00009809359,0.00010769772,0.00076074305,0.00010637263,0.00019307087,0.00011300637,0.00034391868],"category_scores_gemma":[0.0012621662,0.000053257587,0.00010433421,0.00027010235,0.00029426778,0.00041480377,0.0000028957036,0.00018286018,0.000027454069],"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":[0.000002441642,0.000095687115,0.105986424,0.000010926448,0.00008361528,0.00009207075,0.03833757,0.000054793894,0.000013993063,0.004357008,0.7367266,0.11423892],"study_design_scores_gemma":[0.00032555358,0.00010452613,0.045149654,0.00002938967,0.000051363553,0.000025769445,0.0032825288,0.000088934656,0.0000075618977,0.0013152948,0.94951856,0.000100891084],"about_ca_topic_score_codex":0.020053247,"about_ca_topic_score_gemma":0.1484294,"teacher_disagreement_score":0.21279198,"about_ca_system_score_codex":0.00055751525,"about_ca_system_score_gemma":0.00643722,"threshold_uncertainty_score":0.99919534},"labels":[],"label_agreement":null},{"id":"W4366452402","doi":"10.3138/cjpe.22.005","title":"Thickening the Plot: Combining Objectives- and Methods-Oriented Approaches in the Evaluation of a Provincial Superintendents’ Qualification Program","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Commensurability (mathematics); Legislature; Evaluation methods; Program evaluation; Plot (graphics); Computer science; Management science; Political science; Public administration; Mathematics; Engineering; Statistics","score_opus":0.5865720125219641,"score_gpt":0.5866314486560237,"score_spread":0.00005943613405956505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98243713,0.000620006,0.00888208,0.0015733138,0.0004270785,0.0042112684,0.0000027998876,0.000008440259,0.0018378798],"genre_scores_gemma":[0.98802847,0.000005022293,0.011494473,0.00007028268,0.000101880054,0.00027195542,0.000011106961,0.000009454495,0.0000073328424],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98829865,0.0051694503,0.0015985644,0.00029063903,0.004297716,0.00034496028],"domain_scores_gemma":[0.99339914,0.0012855821,0.0011562783,0.00035517945,0.0036441614,0.00015965273],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17891058,0.00014754085,0.0002654702,0.00073974126,0.00032640973,0.0003325697,0.00055635424,0.00009985803,0.00008676052],"category_scores_gemma":[0.009842666,0.000085117674,0.000105286934,0.001496029,0.0002854053,0.0006055042,0.000020783431,0.00040946473,0.0000024392386],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000455361,0.00010632855,0.0400851,0.000006091957,0.000025847206,7.1148355e-7,0.025304122,0.000854888,0.00007566638,0.0019226973,0.000029594548,0.9315434],"study_design_scores_gemma":[0.0016317294,0.00076846615,0.6679095,0.00007404151,0.00021854349,0.000045738092,0.07555797,0.24258983,0.0002796846,0.008477227,0.0023052758,0.00014197508],"about_ca_topic_score_codex":0.00081666023,"about_ca_topic_score_gemma":0.026028495,"teacher_disagreement_score":0.93140143,"about_ca_system_score_codex":0.00039122815,"about_ca_system_score_gemma":0.0033089544,"threshold_uncertainty_score":0.99849784},"labels":[],"label_agreement":null},{"id":"W4366452409","doi":"10.3138/cjpe.022.001","title":"Value-for-Money Analysis of Active Labour Market Programs","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec; Employment and Social Development Canada; University of Manitoba","funders":"","keywords":"Value for money; Value (mathematics); Time value of money; Context (archaeology); Accountability; Disadvantaged; Relevance (law); Economics; Government (linguistics); Money measurement concept; Business; Microeconomics; Actuarial science; Public economics; Endogenous money; Finance; Computer science; Monetary policy; Macroeconomics; Economic growth; Velocity of money; Political science","score_opus":0.29403001195915573,"score_gpt":0.5330757016348798,"score_spread":0.2390456896757241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9684392,0.0003297965,0.01888452,0.0009813785,0.0008659956,0.0022246386,0.000051667663,0.000010779046,0.008212028],"genre_scores_gemma":[0.99030685,0.000006029974,0.008958234,0.00010777879,0.0001282461,0.00004683225,0.000035348145,0.000009722461,0.0004009648],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948673,0.0004132785,0.0014581615,0.00023219004,0.0026460318,0.0003830282],"domain_scores_gemma":[0.990964,0.0006014423,0.0015202774,0.0003325051,0.006041188,0.0005405786],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03733911,0.00013791413,0.00045918225,0.0022827885,0.00016370312,0.00021093008,0.0005140954,0.00010952381,0.0018219317],"category_scores_gemma":[0.003593438,0.00010814518,0.0004162251,0.0035002227,0.000119444245,0.0005257817,0.000010321054,0.00016197348,0.000008138562],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009159558,0.000070388196,0.056770746,0.000005181917,0.00042065146,0.000002062063,0.0010858943,0.0018220567,0.00003687181,0.0012630248,0.00067028916,0.93776125],"study_design_scores_gemma":[0.0013641806,0.0010483472,0.8256498,0.00004106652,0.0016104257,0.000009543438,0.00367457,0.10171395,0.0006065803,0.0069348565,0.05714495,0.00020171772],"about_ca_topic_score_codex":0.0007873904,"about_ca_topic_score_gemma":0.038794536,"teacher_disagreement_score":0.93755955,"about_ca_system_score_codex":0.00042659728,"about_ca_system_score_gemma":0.0035853158,"threshold_uncertainty_score":0.99909055},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99684024,0.00021696788,0.000034701974,0.0005735154,0.00034437995,0.00045611558,0.000006451059,0.000005692739,0.001521913],"genre_scores_gemma":[0.99805856,0.000016159225,0.0013692402,0.00003953774,0.00040512637,0.000026095264,0.000003623934,0.0000063604975,0.00007530721],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983095,0.00044366161,0.00043375802,0.00007534263,0.00049137627,0.00024636826],"domain_scores_gemma":[0.9983751,0.00010587504,0.00031703745,0.000082103565,0.0008648365,0.00025503198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037930142,0.000060482642,0.00014893679,0.0003395367,0.00037066656,0.000055826036,0.00020582743,0.00006251009,0.00026278206],"category_scores_gemma":[0.0008652661,0.000056246092,0.000052908443,0.0005775901,0.00011911858,0.00023241034,0.0000037369132,0.00012555967,0.0000044725757],"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":[0.0000010702618,0.000061305305,0.77457386,0.0000059373947,0.000008926842,0.0000018722727,0.18920055,0.0000887719,0.000037245485,0.0002911048,0.00026156395,0.03546782],"study_design_scores_gemma":[0.00037754557,0.00009623917,0.85600907,0.00014684722,0.000019501325,0.000012563984,0.13626255,0.00013580889,0.000010428503,0.00043612745,0.006411742,0.00008160767],"about_ca_topic_score_codex":0.03582073,"about_ca_topic_score_gemma":0.28766286,"teacher_disagreement_score":0.25184214,"about_ca_system_score_codex":0.00040734862,"about_ca_system_score_gemma":0.0036710475,"threshold_uncertainty_score":0.97059983},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79841423,0.025154114,0.03854559,0.05811275,0.02302373,0.014658146,0.0001115938,0.00019114224,0.041788727],"genre_scores_gemma":[0.9854181,0.000032694916,0.012007971,0.0008144894,0.0012003944,0.00020040393,0.00006344911,0.000021771755,0.00024071548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98604625,0.011628661,0.001157386,0.00011988019,0.00047912137,0.0005686793],"domain_scores_gemma":[0.9948274,0.0007563765,0.0013401109,0.00018068915,0.0021019331,0.00079352374],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032106973,0.00013721368,0.0002998245,0.00026242054,0.00052326516,0.00004985592,0.00016066233,0.00024842322,0.0023836368],"category_scores_gemma":[0.0044010105,0.000117948584,0.000118707736,0.00030576074,0.000064550855,0.0010614308,0.000012293769,0.0007999395,0.00012653772],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064563035,0.00013940188,0.12077451,0.00035786268,0.000122268,0.000008156814,0.024838382,0.00007912324,0.000084266096,0.040038154,0.023725837,0.7897675],"study_design_scores_gemma":[0.0016746928,0.0007226033,0.22260435,0.0008867541,0.00016523211,0.00007477064,0.013525258,0.0007266761,0.000018759816,0.0058142887,0.75354797,0.00023864757],"about_ca_topic_score_codex":0.016700044,"about_ca_topic_score_gemma":0.06249636,"teacher_disagreement_score":0.78952885,"about_ca_system_score_codex":0.0006542201,"about_ca_system_score_gemma":0.0041004787,"threshold_uncertainty_score":0.9985283},"labels":[],"label_agreement":null},{"id":"W4366452424","doi":"10.3138/cjpe.28.010","title":"King, J. A., &amp; Stevahn, L. (2013). <i>Interactive Evaluation Practice: Mastering the Interpersonal Dynamics of Program Evaluation.</i>","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpersonal communication; Dynamics (music); Psychology; Interpersonal relationship; Sociology; Applied psychology; Social psychology; Pedagogy","score_opus":0.3003669884072015,"score_gpt":0.5346756791914403,"score_spread":0.23430869078423883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88839346,0.0022234337,0.009775876,0.042321876,0.006473302,0.02765401,0.000051283794,0.000059454545,0.02304729],"genre_scores_gemma":[0.98638314,0.000024105508,0.010828592,0.0003938513,0.00031966722,0.0017174009,0.00011289594,0.000030515179,0.00018982349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9847866,0.0035775509,0.0022437284,0.00046932994,0.0083728405,0.00054989144],"domain_scores_gemma":[0.9673536,0.0014714848,0.003297125,0.0007561121,0.02662628,0.0004954308],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051099855,0.0003203756,0.00047222487,0.000956614,0.00043013974,0.0014824409,0.0010924897,0.00016807759,0.013618639],"category_scores_gemma":[0.018832989,0.00022260583,0.00031109664,0.0013437745,0.0002938432,0.0038490046,0.00006275623,0.0006303937,0.00033701074],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053552798,0.00017688467,0.0037489617,0.000009154544,0.00014738506,8.812497e-7,0.0036179624,0.009698751,0.000055203174,0.00016402801,0.006000682,0.9763265],"study_design_scores_gemma":[0.0018214165,0.0009368428,0.032463934,0.00022165525,0.0006998175,0.00012286102,0.0139291035,0.8900659,0.000055098455,0.0067937127,0.052605778,0.00028387358],"about_ca_topic_score_codex":0.0029364203,"about_ca_topic_score_gemma":0.047876187,"teacher_disagreement_score":0.9760427,"about_ca_system_score_codex":0.0019544715,"about_ca_system_score_gemma":0.008580472,"threshold_uncertainty_score":0.9995541},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99015504,0.0008442114,0.00008492605,0.0017557607,0.00086908345,0.0056745056,0.000010670417,0.000012787753,0.00059304194],"genre_scores_gemma":[0.9926107,0.000028930861,0.005962159,0.0001246247,0.00083462964,0.00029904512,0.00010669597,0.00001905645,0.000014168617],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9843583,0.008875685,0.0017477518,0.000261308,0.0032078268,0.0015491336],"domain_scores_gemma":[0.9907875,0.0010313098,0.0008573175,0.00027237984,0.0052198083,0.0018316596],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14567482,0.00013333987,0.00037553324,0.0017056921,0.00078044203,0.00008969714,0.00036493072,0.00020256045,0.00032247478],"category_scores_gemma":[0.0075131087,0.00012267721,0.000055362736,0.0015914025,0.00022130992,0.0007778527,0.000016100093,0.0011963856,0.000013713676],"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":[0.000057956127,0.00012992116,0.3556775,0.00003952032,0.0000073815254,0.00000191111,0.030317668,0.000056727404,0.000029602652,0.000011998263,0.00010883874,0.613561],"study_design_scores_gemma":[0.0019554966,0.0015575552,0.93789196,0.0011007414,0.000022238022,0.000010648283,0.042588092,0.010535171,0.0000038913627,0.0018641168,0.0023632606,0.00010685496],"about_ca_topic_score_codex":0.2893336,"about_ca_topic_score_gemma":0.85082847,"teacher_disagreement_score":0.6134541,"about_ca_system_score_codex":0.004932226,"about_ca_system_score_gemma":0.058448616,"threshold_uncertainty_score":0.99888766},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7040118,0.016876968,0.0035219518,0.23216324,0.021626899,0.004745084,0.00003180065,0.00003934872,0.016982915],"genre_scores_gemma":[0.9777095,0.00046101358,0.0051312963,0.00819349,0.0071378746,0.000065352346,0.000031274245,0.000050415056,0.0012198074],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907459,0.0060048103,0.0012792461,0.00020058293,0.0008066409,0.0009628134],"domain_scores_gemma":[0.9929796,0.0007237194,0.00091515575,0.00028899853,0.0026510498,0.0024414614],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024407338,0.0002086752,0.00045972448,0.00026537746,0.00088636647,0.00005559274,0.00027647955,0.0009802282,0.004346308],"category_scores_gemma":[0.008716483,0.00019768147,0.00020662183,0.0004769559,0.00021264555,0.00032963767,0.000010850941,0.0026722408,0.00032091388],"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":[0.000009114202,0.000072305695,0.01247281,0.0002634913,0.000063197804,0.000020608395,0.019796161,0.000044918917,0.0000036959443,0.0029281802,0.06246899,0.90185654],"study_design_scores_gemma":[0.0021967187,0.0011797611,0.066794135,0.00095296814,0.0004016878,0.00007853638,0.00565681,0.013001016,0.000003622417,0.0036703192,0.90588146,0.00018294455],"about_ca_topic_score_codex":0.012643886,"about_ca_topic_score_gemma":0.045610916,"teacher_disagreement_score":0.90167356,"about_ca_system_score_codex":0.0014546025,"about_ca_system_score_gemma":0.020593798,"threshold_uncertainty_score":0.9996335},"labels":[],"label_agreement":null},{"id":"W4366452622","doi":"10.3138/cjpe.0026.005","title":"L’approche <i>Realist</i> à l’épreuve du réel de l’évaluation des programmes","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"","keywords":"Epistemology; Context (archaeology); Valuation (finance); Psychological intervention; Outcome (game theory); Sociology; Psychology; GRASP; Mechanism (biology); Philosophy; Computer science; Economics; History","score_opus":0.4946108818232891,"score_gpt":0.5147343735641988,"score_spread":0.020123491740909716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9705555,0.0014464353,0.011910757,0.003403249,0.0012832982,0.0017583914,0.000008951802,0.000032269865,0.009601187],"genre_scores_gemma":[0.97286177,0.000030992876,0.025520813,0.00039381743,0.0007195025,0.00017698713,0.000025725267,0.00001896087,0.00025145625],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9937447,0.0013712643,0.0011391782,0.00021058261,0.002817339,0.00071696716],"domain_scores_gemma":[0.9933913,0.00039078057,0.00088187173,0.00034431068,0.0039122095,0.0010795635],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.047357675,0.000192258,0.0002899536,0.0006935721,0.00043539575,0.00062600797,0.0005697161,0.00016777006,0.0013883599],"category_scores_gemma":[0.007978791,0.00015029217,0.00020263939,0.0010959326,0.00021304029,0.0016894074,0.00001892493,0.00032042235,0.00011805171],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014047397,0.00009640321,0.23180704,0.000006305317,0.000028078424,0.0000016496614,0.008050774,0.00077630545,0.000060523595,0.000417196,0.0066518015,0.75208986],"study_design_scores_gemma":[0.0019892808,0.0008937028,0.63328785,0.00010094865,0.00038266944,0.00037793122,0.008991606,0.05536036,0.00048820587,0.04106676,0.25660837,0.00045234367],"about_ca_topic_score_codex":0.0008721581,"about_ca_topic_score_gemma":0.010221943,"teacher_disagreement_score":0.7516375,"about_ca_system_score_codex":0.000876735,"about_ca_system_score_gemma":0.005596429,"threshold_uncertainty_score":0.99952453},"labels":[],"label_agreement":null},{"id":"W4366452662","doi":"10.3138/cjpe.22.006","title":"Developing a Special Education Accountability Framework Using Program Evaluation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Bureaucracy; Context (archaeology); Citizen journalism; Public administration; Public relations; Political science; Business; Politics; Geography","score_opus":0.5571351357964983,"score_gpt":0.6246417530511743,"score_spread":0.067506617254676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366452662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9530271,0.0005240141,0.028949987,0.0012890443,0.005953388,0.005478737,0.0000038902494,0.00002508241,0.0047487346],"genre_scores_gemma":[0.8791885,0.000005070065,0.11763718,0.0002740025,0.002664022,0.00016350207,0.000024338433,0.000017317452,0.000026073314],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99097395,0.0009076966,0.0019290977,0.00039972208,0.0052427244,0.0005468156],"domain_scores_gemma":[0.98488694,0.00048915594,0.0014947541,0.00047525455,0.0120447865,0.0006090918],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065369956,0.00022143,0.00033984098,0.001312916,0.0004918073,0.0008865869,0.0006204667,0.00023069796,0.00370354],"category_scores_gemma":[0.010727579,0.00019047766,0.0001921672,0.0021375422,0.00014869329,0.0014270778,0.000021716916,0.00043372673,0.00007368723],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029118453,0.00011577373,0.032827497,0.0000062208564,0.000021699356,0.0000011426729,0.0016968191,0.0011269774,0.000018504968,0.0012577722,0.000514385,0.9623841],"study_design_scores_gemma":[0.0016403039,0.0008261994,0.4946539,0.00040578117,0.00046555558,0.00015194353,0.012406186,0.1493244,0.0003397163,0.16632807,0.1727775,0.00068043254],"about_ca_topic_score_codex":0.0006546345,"about_ca_topic_score_gemma":0.02555283,"teacher_disagreement_score":0.96170366,"about_ca_system_score_codex":0.0036061956,"about_ca_system_score_gemma":0.036656246,"threshold_uncertainty_score":0.9976055},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94990796,0.0001726993,0.0031520214,0.015440034,0.0006174466,0.0006506254,0.00000672941,0.000016581089,0.03003593],"genre_scores_gemma":[0.99829066,0.00006483927,0.00047702217,0.00031931678,0.0003990365,0.000011836556,0.0000029290577,0.000006749421,0.0004276273],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980294,0.00023251583,0.0003345637,0.00011321342,0.00086521934,0.00042506173],"domain_scores_gemma":[0.9987348,0.0000648332,0.00031562214,0.000064642845,0.00032676465,0.0004933595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054623894,0.000092126786,0.00011753422,0.00013065757,0.00042447695,0.00020076422,0.00019447779,0.00009121716,0.00021634334],"category_scores_gemma":[0.00022727568,0.00008042557,0.000098356926,0.00041541315,0.00014533765,0.00046677547,0.0000019606232,0.00017632553,0.0000070213896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003171335,0.00007195996,0.02461125,0.0000065832983,0.000025448036,0.000023358682,0.108276434,0.00020614525,0.00008216292,0.0060901083,0.0027449487,0.85782987],"study_design_scores_gemma":[0.0010437369,0.00067987305,0.6994433,0.00013790971,0.00016236369,0.00001851463,0.118230574,0.0008814967,0.00040017813,0.0075939526,0.17106228,0.0003458552],"about_ca_topic_score_codex":0.15128878,"about_ca_topic_score_gemma":0.8784928,"teacher_disagreement_score":0.85748404,"about_ca_system_score_codex":0.0016348412,"about_ca_system_score_gemma":0.004658944,"threshold_uncertainty_score":0.85436285},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45778444,0.10332395,0.0025405379,0.12434097,0.070452586,0.0028917335,0.00016479095,0.000055136126,0.23844586],"genre_scores_gemma":[0.93336236,0.00021678873,0.00064166595,0.00022300292,0.060151786,0.0000068110926,0.00006190018,0.000028981955,0.00530667],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99804395,0.00014786159,0.0007160608,0.00015066986,0.0005208318,0.0004206414],"domain_scores_gemma":[0.99564815,0.000048516427,0.00056183856,0.00015738448,0.0029596703,0.00062447187],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004992948,0.00015891416,0.00023361761,0.0006007456,0.00048670292,0.0005667218,0.00015207227,0.00010890103,0.009420433],"category_scores_gemma":[0.0010878191,0.00015604412,0.00021912134,0.0001575749,0.00031504282,0.00031955872,0.0000055022056,0.00029103065,0.00009512434],"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":[0.000023957746,0.00015943567,0.0017532634,0.000039650407,0.00030363904,0.00012045426,0.005950667,0.0004044086,0.0000073255746,0.24381688,0.060774222,0.6866461],"study_design_scores_gemma":[0.00040924965,0.00049130036,0.0015773919,0.000067775974,0.0011358199,0.00007444217,0.0027888962,0.0021321424,0.000030654435,0.00551136,0.9856092,0.00017181018],"about_ca_topic_score_codex":0.018288875,"about_ca_topic_score_gemma":0.22754999,"teacher_disagreement_score":0.9248349,"about_ca_system_score_codex":0.0005955336,"about_ca_system_score_gemma":0.0017852539,"threshold_uncertainty_score":0.9914851},"labels":[],"label_agreement":null},{"id":"W4366453107","doi":"10.3138/cjpe.023.004","title":"L’utilisation de l’évaluation fondée sur la théorie du programme comme stratégie d’application des connaissances issues de la recherche","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Centre intégré universitaire de santé et de services sociaux de la Mauricie-et-du-Centre-du-Québec; Université du Québec à Trois-Rivières; Université du Québec à Montréal","funders":"","keywords":"Knowledge management; Tacit knowledge; Valuation (finance); Sociology; Psychology; Business; Computer science","score_opus":0.8056653558025793,"score_gpt":0.5756305185019046,"score_spread":0.23003483730067464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580388,0.0016212736,0.023694,0.006598135,0.00026954888,0.0016308039,0.000008019139,0.00005019516,0.008089212],"genre_scores_gemma":[0.9721085,0.00030322987,0.026598394,0.00017393482,0.00034418597,0.0002565693,0.000036010024,0.000020762991,0.00015845709],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98959714,0.0062953695,0.0011424416,0.00031127047,0.002151061,0.00050273817],"domain_scores_gemma":[0.9910523,0.0030692609,0.0009646255,0.00035986156,0.0039944006,0.00055952586],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07160706,0.00020760247,0.00030939744,0.000548322,0.00059788756,0.0006138445,0.0005778901,0.00033810295,0.0005454243],"category_scores_gemma":[0.02051094,0.00017866587,0.00016146031,0.0010698441,0.0006466025,0.0013138542,0.000014089985,0.0005383619,0.000032990112],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003452245,0.00013062602,0.19336209,0.000011380024,0.000033905384,0.000009574605,0.007606053,0.0028706596,0.00026850007,0.0023184337,0.0036515899,0.78970265],"study_design_scores_gemma":[0.0020675438,0.00073724875,0.42229894,0.000096636235,0.00017026463,0.0005001313,0.005073654,0.19253737,0.0008948524,0.28533056,0.08994008,0.00035269],"about_ca_topic_score_codex":0.0020664807,"about_ca_topic_score_gemma":0.006417267,"teacher_disagreement_score":0.78935,"about_ca_system_score_codex":0.001469095,"about_ca_system_score_gemma":0.013423405,"threshold_uncertainty_score":0.99216956},"labels":[],"label_agreement":null},{"id":"W4366453124","doi":"10.3138/cjpe.020.006","title":"Participatory Evaluation in the Context of CBPD: Theory and Practice in International Development","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Citizen journalism; Context (archaeology); International development; Political science; Democracy; Participatory development; Participatory evaluation; Sociology; International community; Engineering ethics; Public administration; Politics; Engineering; Law; Geography","score_opus":0.4738059708487722,"score_gpt":0.5804406649322703,"score_spread":0.10663469408349813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869854,0.001142106,0.00018424376,0.0070228977,0.00030840738,0.0009801418,0.000001545368,0.00000138072,0.0033738657],"genre_scores_gemma":[0.9972674,0.00001768108,0.0019152804,0.00060136506,0.00007030676,0.000102017446,0.000005239723,0.0000035891576,0.000017089516],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99244994,0.0032864653,0.0012139233,0.00013372742,0.0027400162,0.00017590918],"domain_scores_gemma":[0.99509424,0.001739636,0.0006999156,0.00015447591,0.002200057,0.00011167066],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10343567,0.0000786463,0.0001529337,0.00069685915,0.00006440941,0.00014706788,0.00035389725,0.000050053484,0.0007807884],"category_scores_gemma":[0.01709892,0.000054236567,0.000034158213,0.00047697476,0.000089739806,0.00088856934,0.000010772401,0.00017525477,0.00001398244],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057743244,0.00007716769,0.023432655,0.0000013972773,0.000013125892,0.0000014461608,0.030204706,0.0017417766,0.000016309668,0.0011203068,0.00018496269,0.9431484],"study_design_scores_gemma":[0.003315239,0.0002986642,0.71374017,0.000116344476,0.00009823997,0.000076595694,0.08734853,0.073905334,0.00020381856,0.009462789,0.111264214,0.0001700897],"about_ca_topic_score_codex":0.00019620392,"about_ca_topic_score_gemma":0.04265371,"teacher_disagreement_score":0.9429783,"about_ca_system_score_codex":0.0004725236,"about_ca_system_score_gemma":0.004349501,"threshold_uncertainty_score":0.9911805},"labels":[],"label_agreement":null},{"id":"W4366453126","doi":"10.3138/cjpe.23.016","title":"Donna M. Mertens. (2009). <i>Transformative Research and Evaluation.</i> New York: Guilford Press. 402 pages.","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transformative learning; Psychology; Pedagogy","score_opus":0.7747036186145636,"score_gpt":0.5580962906247038,"score_spread":0.21660732798985982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85835034,0.028672252,0.0038200545,0.03035682,0.0029446722,0.009998109,0.00005863097,0.00005710603,0.065742046],"genre_scores_gemma":[0.994066,0.00043574325,0.003667755,0.00034517876,0.00039709883,0.00013525924,0.000024982468,0.000019806495,0.0009081639],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98831093,0.001645452,0.001508974,0.0003907493,0.007500171,0.0006436997],"domain_scores_gemma":[0.98632485,0.00056876603,0.00068646134,0.0004910624,0.010745513,0.0011833578],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04281211,0.00021617333,0.00039723172,0.0012047263,0.0008712383,0.0005851151,0.0007308683,0.00015686353,0.0024290187],"category_scores_gemma":[0.0044866283,0.00016754455,0.00013132258,0.0014661581,0.00043788215,0.001479276,0.000027011612,0.000586969,0.00010353308],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004833996,0.00006311267,0.005081261,0.0000062302593,0.000054000535,0.000011136714,0.0071244817,0.0013003722,0.00003226106,0.0002857672,0.18938059,0.79661244],"study_design_scores_gemma":[0.00582243,0.0025612796,0.114764325,0.00017029185,0.00026027326,0.00070152147,0.0038519618,0.13117242,0.0005846654,0.038607404,0.70095205,0.0005513892],"about_ca_topic_score_codex":0.0022101284,"about_ca_topic_score_gemma":0.01711246,"teacher_disagreement_score":0.79606104,"about_ca_system_score_codex":0.00056970713,"about_ca_system_score_gemma":0.0140418345,"threshold_uncertainty_score":0.9984829},"labels":[],"label_agreement":null},{"id":"W4366453138","doi":"10.3138/cjpe.28.007","title":"The Five Cs for Innovating in Evaluation Capacity Building: Lessons from the Field","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Ontario Centre of Excellence for Child and Youth Mental Health","funders":"","keywords":"Excellence; Coaching; Curiosity; Capacity building; Courage; Key (lock); Field (mathematics); Public relations; Business; Psychology; Knowledge management; Political science; Economic growth; Management; Economics; Computer science; Social psychology","score_opus":0.5626414314017943,"score_gpt":0.558423062289945,"score_spread":0.004218369111849363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93155926,0.0004477229,0.0028542958,0.060239814,0.0011037006,0.0031771169,0.000009804258,0.0000043938066,0.00060389616],"genre_scores_gemma":[0.99317634,0.0000074240766,0.0049661393,0.0009494089,0.00028649007,0.0005547203,0.000010134911,0.000007170192,0.000042145974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99542874,0.0009285325,0.0010475519,0.00019057113,0.0021044852,0.0003000992],"domain_scores_gemma":[0.9880474,0.004697798,0.00088200055,0.00035187212,0.0058641895,0.00015672922],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035017442,0.00010951881,0.00016917224,0.00024685045,0.0006178138,0.0009340288,0.0006971493,0.00008364285,0.00082716095],"category_scores_gemma":[0.02851769,0.00006022901,0.00009965921,0.0008752045,0.000086748296,0.000667791,0.000015856347,0.0003009583,0.000023363558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007953139,0.000012005782,0.014538422,8.275077e-7,0.000016612941,1.3685998e-7,0.0015410719,0.0022327583,0.0000541423,0.0012942336,0.014541472,0.96576035],"study_design_scores_gemma":[0.001136034,0.0002739337,0.24074544,0.00006331279,0.00006570035,0.0000036959775,0.0040986845,0.56871736,0.00017208907,0.15101436,0.03358428,0.00012508688],"about_ca_topic_score_codex":0.0067052683,"about_ca_topic_score_gemma":0.09823795,"teacher_disagreement_score":0.9656353,"about_ca_system_score_codex":0.00044582557,"about_ca_system_score_gemma":0.0035365757,"threshold_uncertainty_score":0.99990916},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.976556,0.00021796861,0.008085341,0.011203616,0.0003096306,0.003169535,0.000028826285,0.000050345756,0.00037875367],"genre_scores_gemma":[0.98404276,0.000041777195,0.013581436,0.0016323866,0.00027522037,0.00031225162,0.00007399247,0.000018604811,0.0000215541],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9925885,0.003966236,0.0015662529,0.00021784226,0.00077660335,0.0008845689],"domain_scores_gemma":[0.9950279,0.00043747848,0.0014624294,0.00019222984,0.0020676567,0.0008123103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015019464,0.00019571763,0.00027766352,0.00046293242,0.00091142487,0.000121394165,0.00027714262,0.00020022587,0.00032860384],"category_scores_gemma":[0.002997854,0.00018336768,0.000116744544,0.0007427412,0.000097195094,0.0006628153,0.000009505564,0.0005375962,0.000029094372],"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":[0.000039311133,0.00010570808,0.16127208,0.00030072464,0.00003324924,0.000014730898,0.024514588,0.00012861153,0.00041843334,0.000793719,0.0020816743,0.8102972],"study_design_scores_gemma":[0.0027174363,0.0007317047,0.9504008,0.0013298079,0.00013960688,0.00008024496,0.010071871,0.0032759632,0.00031712095,0.02149304,0.009235439,0.00020691863],"about_ca_topic_score_codex":0.004573964,"about_ca_topic_score_gemma":0.028395822,"teacher_disagreement_score":0.81009024,"about_ca_system_score_codex":0.0017154685,"about_ca_system_score_gemma":0.0056256996,"threshold_uncertainty_score":0.997975},"labels":[],"label_agreement":null},{"id":"W4366453266","doi":"10.3138/cjpe.0027.004","title":"Preparing, Governing, and Managing the Paris Declaration Evaluation","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credibility; Declaration; Stakeholder; Process management; Corporate governance; Joint (building); Stakeholder engagement; Business; Quality (philosophy); Public relations; Environmental resource management; Political science; Economics; Engineering","score_opus":0.30437993122529117,"score_gpt":0.5013173760618445,"score_spread":0.1969374448365533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627181,0.0022209876,0.002794249,0.008813122,0.0009879594,0.003520888,0.0000024599417,0.00001398902,0.01892824],"genre_scores_gemma":[0.9976253,0.00003589051,0.0014372418,0.00027422505,0.00016692218,0.00022327721,0.000010070746,0.000008441475,0.00021861865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947201,0.0009598923,0.0008510794,0.00021565658,0.0030086047,0.00024465454],"domain_scores_gemma":[0.99448884,0.00029147943,0.00089301285,0.00032104107,0.0037002412,0.000305381],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025586603,0.00012032038,0.0001682313,0.0003624253,0.00045245598,0.0012604416,0.0003630781,0.00006941166,0.0032998493],"category_scores_gemma":[0.0031200568,0.000077134886,0.000076550365,0.0005100387,0.000104495746,0.0013780709,0.00002036324,0.00021182759,0.0001655178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037691902,0.0000111519175,0.03467151,0.0000022338659,0.00002168622,2.8699276e-7,0.001428561,0.0035158559,0.00002453644,0.00029313544,0.013881922,0.94614536],"study_design_scores_gemma":[0.00063322537,0.00022123444,0.29035982,0.000031128886,0.00013683275,0.00003516933,0.002028074,0.6224361,0.000032583506,0.020883063,0.06308763,0.00011509719],"about_ca_topic_score_codex":0.0017052249,"about_ca_topic_score_gemma":0.017037885,"teacher_disagreement_score":0.94603026,"about_ca_system_score_codex":0.00039319962,"about_ca_system_score_gemma":0.0025190695,"threshold_uncertainty_score":0.99977636},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97690445,0.00021803248,0.00048824959,0.01667208,0.00039775862,0.0052833646,0.000007496795,0.0000026990554,0.00002586951],"genre_scores_gemma":[0.99689907,0.000004349727,0.0011439698,0.0005716652,0.00012293176,0.0012461987,0.000001155407,0.000004446619,0.0000062147915],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996791,0.0015256404,0.0006761945,0.0001361226,0.00058888167,0.00028218539],"domain_scores_gemma":[0.99582356,0.0013173172,0.0007278422,0.0001548295,0.0016172648,0.0003592067],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028015625,0.00006372221,0.00011742588,0.00021231042,0.000949537,0.00007187643,0.0002185304,0.00002595107,0.000022276741],"category_scores_gemma":[0.023979919,0.000041580675,0.00002264557,0.0004656588,0.00029583828,0.0008145927,0.000014780198,0.00029374982,5.277666e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002831697,0.000037407663,0.15329996,0.00009520124,0.000009061052,6.089633e-7,0.060037747,0.0001581161,0.00058425905,0.0016698698,0.00014478712,0.78367984],"study_design_scores_gemma":[0.0031124686,0.0008183346,0.96012497,0.0003279199,0.000075449134,0.000009418584,0.01976962,0.0042610825,0.000032988846,0.002147829,0.009225705,0.00009423006],"about_ca_topic_score_codex":0.004198344,"about_ca_topic_score_gemma":0.12685096,"teacher_disagreement_score":0.806825,"about_ca_system_score_codex":0.00033035022,"about_ca_system_score_gemma":0.003705219,"threshold_uncertainty_score":0.9842415},"labels":[],"label_agreement":null},{"id":"W4366453408","doi":"10.3138/cjpe.020.002","title":"Ensuring Quality for Evaluation: Lessons from Auditors","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Documentation; Quality assurance; Quality (philosophy); Variety (cybernetics); Quality audit; Business; Point (geometry); Accounting; Process management; Computer science; Marketing","score_opus":0.6231916254204312,"score_gpt":0.6243646498296325,"score_spread":0.0011730244092013065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366453408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9556951,0.0013433308,0.0065457746,0.025293648,0.0040852237,0.0031450898,0.000086410764,0.000020656478,0.0037848016],"genre_scores_gemma":[0.9851113,0.0000067155224,0.012242304,0.00027139523,0.0019320875,0.00021837653,0.00005230441,0.000012488307,0.00015303973],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930303,0.0010257146,0.0014847036,0.00030077575,0.003828621,0.00032987838],"domain_scores_gemma":[0.9898871,0.000920682,0.0011974145,0.00039987045,0.007075246,0.00051969144],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043579314,0.00014812953,0.00031098988,0.0005469818,0.00036802955,0.000511034,0.0005448051,0.00011116214,0.0053337137],"category_scores_gemma":[0.009494307,0.00012204368,0.00023240656,0.0005267738,0.000074818534,0.00094577024,0.000011576918,0.00018953854,0.000118819364],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002184201,0.000036794005,0.0069794143,0.0000019570894,0.000036871483,3.428305e-7,0.0009794647,0.012489028,0.000050916362,0.00041907508,0.008313416,0.9706709],"study_design_scores_gemma":[0.0038944543,0.00034932978,0.25035056,0.000060651415,0.00028926702,0.000009107907,0.0018728751,0.31541735,0.00044674738,0.033565976,0.39344126,0.00030240495],"about_ca_topic_score_codex":0.000676141,"about_ca_topic_score_gemma":0.052502412,"teacher_disagreement_score":0.97036844,"about_ca_system_score_codex":0.0009757869,"about_ca_system_score_gemma":0.007917928,"threshold_uncertainty_score":0.99884915},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87794816,0.087915964,0.0004485109,0.02314277,0.0026768246,0.006599943,0.0001973681,0.000015247205,0.0010551749],"genre_scores_gemma":[0.92276883,0.009227838,0.008131448,0.0006488015,0.0010779271,0.0004457855,0.00038061073,0.00012232088,0.057196446],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99391294,0.0013106416,0.0010784538,0.0004977779,0.0017237285,0.0014764444],"domain_scores_gemma":[0.99313843,0.0002963239,0.0003874395,0.00033841666,0.0031096728,0.002729719],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011885131,0.00042617763,0.0008135729,0.0008176963,0.00022231338,0.000253744,0.00030463215,0.0003681918,0.0018166311],"category_scores_gemma":[0.012457908,0.00039712415,0.00023563637,0.000541327,0.0007435696,0.00081664074,0.000033371085,0.000719384,0.00027235996],"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":[0.00019190006,0.00029229678,0.23828812,0.001529844,0.00027540955,0.00044513558,0.0019560605,0.0000092966,0.000044614764,0.00006012536,0.07780981,0.6790974],"study_design_scores_gemma":[0.00945296,0.0060643163,0.62706125,0.0063748937,0.001109034,0.0006255273,0.0016839255,0.00867841,0.000053421092,0.0029773095,0.33547878,0.00044015463],"about_ca_topic_score_codex":0.012321936,"about_ca_topic_score_gemma":0.04258936,"teacher_disagreement_score":0.67865723,"about_ca_system_score_codex":0.0024375615,"about_ca_system_score_gemma":0.0038661773,"threshold_uncertainty_score":0.99984807},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40052813,0.057557777,0.00015986328,0.0075129494,0.0058204965,0.0010762279,0.00008936279,0.000013498595,0.5272417],"genre_scores_gemma":[0.9892085,0.0001814398,0.0006632937,0.00016386701,0.0030319782,0.000008178652,0.000016040693,0.000020737094,0.0067059346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983675,0.00038311066,0.00040818818,0.000109092405,0.0003887324,0.0003433718],"domain_scores_gemma":[0.99759,0.000117662494,0.00037596334,0.00014239002,0.0012757749,0.00049817894],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029530702,0.000128816,0.00021412961,0.00034441042,0.00024224436,0.0007150358,0.00017667456,0.00011414802,0.014160823],"category_scores_gemma":[0.0005158273,0.00012481783,0.00020999036,0.00010726789,0.00020230428,0.00018354793,0.0000051194834,0.0002885928,0.00015555207],"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":[0.0000136520175,0.00017829773,0.0069220625,0.00007706481,0.00050379086,0.00011916766,0.007910335,0.0016948306,0.000008093631,0.47532684,0.007997751,0.49924812],"study_design_scores_gemma":[0.0006722757,0.00036583448,0.0027224277,0.00015708164,0.0013271376,0.00005872224,0.0020477201,0.017758623,0.000015335747,0.020517865,0.9541776,0.00017937303],"about_ca_topic_score_codex":0.020664338,"about_ca_topic_score_gemma":0.015971983,"teacher_disagreement_score":0.94617987,"about_ca_system_score_codex":0.0004919072,"about_ca_system_score_gemma":0.0038176544,"threshold_uncertainty_score":0.98674035},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98563004,0.0008786369,0.00004897773,0.0015876556,0.0012201476,0.0018378042,0.0000012792052,0.000007071316,0.008788383],"genre_scores_gemma":[0.99756706,0.000007871157,0.0011995161,0.000126092,0.00042690663,0.0001871304,0.000008244011,0.000013935379,0.0004632324],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973255,0.001063744,0.0005277462,0.00010605649,0.0004608229,0.0005161637],"domain_scores_gemma":[0.9965102,0.00018211162,0.0002576745,0.00011667377,0.0024625442,0.00047076595],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0063620596,0.00007192282,0.00013894815,0.0005844108,0.00047792005,0.000064351225,0.00013761928,0.00011580475,0.0015066648],"category_scores_gemma":[0.0012043944,0.00006531014,0.000035062407,0.0005170317,0.000086492975,0.0006848225,0.0000063253588,0.00069304975,0.00020389355],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021144097,0.0001478033,0.06967267,0.00006978061,0.00002954736,0.000008772133,0.07025197,0.0007086087,0.00021990924,0.00044943957,0.08034378,0.7780766],"study_design_scores_gemma":[0.003862595,0.0016120152,0.27951482,0.0029702692,0.000096939,0.00004677899,0.25202897,0.021583833,0.00007451757,0.06795461,0.36954808,0.00070654927],"about_ca_topic_score_codex":0.02192348,"about_ca_topic_score_gemma":0.040391717,"teacher_disagreement_score":0.77737004,"about_ca_system_score_codex":0.001513871,"about_ca_system_score_gemma":0.007638728,"threshold_uncertainty_score":0.9994061},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94122744,0.00034604725,0.00027127765,0.035501257,0.0013868901,0.0036479405,0.000003330812,0.000033484546,0.01758235],"genre_scores_gemma":[0.99523205,0.000005858082,0.00027571456,0.0029828905,0.0009732029,0.00039143424,0.00009150427,0.000017452201,0.000029926297],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99768925,0.00013730772,0.00060790055,0.00018876579,0.0009789073,0.00039787524],"domain_scores_gemma":[0.99754864,0.000024173298,0.00056975114,0.00014372256,0.0016846588,0.000029039304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053635538,0.00018900074,0.00021641192,0.00055916567,0.0004412892,0.0006841749,0.00041701665,0.00017988397,0.0003983003],"category_scores_gemma":[0.00060283527,0.00014987758,0.00009271497,0.0009164068,0.00017073653,0.001261877,0.0000336596,0.0003928534,0.00012000299],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013051469,0.00011124529,0.0039929496,0.000055956676,0.00006204191,0.000012848222,0.0020534014,0.00006551847,0.000029245004,0.0032036717,0.07462769,0.9157724],"study_design_scores_gemma":[0.0041319495,0.00020283357,0.572295,0.00020767024,0.00082807784,0.00004323884,0.018928686,0.015715972,0.00006352195,0.056421377,0.33020106,0.0009606251],"about_ca_topic_score_codex":0.0009429449,"about_ca_topic_score_gemma":0.0019565509,"teacher_disagreement_score":0.91481173,"about_ca_system_score_codex":0.0005681206,"about_ca_system_score_gemma":0.0007585901,"threshold_uncertainty_score":0.6597514},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36855164,0.100911915,0.004321489,0.4553647,0.0226982,0.03141162,0.00013656847,0.00014459311,0.016459266],"genre_scores_gemma":[0.83555996,0.0027362667,0.106468126,0.007073084,0.010384028,0.005421389,0.0004592958,0.00037844112,0.031519435],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9793709,0.012714374,0.003062456,0.00053054746,0.0018432782,0.0024784568],"domain_scores_gemma":[0.9829851,0.0010448096,0.0031893607,0.0007500629,0.008748639,0.0032820408],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.039146896,0.0005388783,0.0008497551,0.0009378537,0.0014687943,0.00059727585,0.00061631284,0.0010379159,0.012563191],"category_scores_gemma":[0.008670246,0.0005418681,0.0003590813,0.0011300273,0.00024871336,0.0028743583,0.00004743991,0.0022390939,0.0015549405],"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":[0.000022455217,0.0002501516,0.006580127,0.00065574737,0.00019275489,0.000016084348,0.006687073,0.00019911608,0.00004444082,0.0006232487,0.28884786,0.69588095],"study_design_scores_gemma":[0.0026780341,0.0009867869,0.032939192,0.0015103787,0.00054305646,0.0001544342,0.00431501,0.004187675,0.00001196556,0.0040372666,0.94814235,0.0004938243],"about_ca_topic_score_codex":0.2872326,"about_ca_topic_score_gemma":0.39157403,"teacher_disagreement_score":0.6953871,"about_ca_system_score_codex":0.0033503354,"about_ca_system_score_gemma":0.048117436,"threshold_uncertainty_score":0.99983114},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9088619,0.0057816454,0.0051053073,0.047782842,0.0024183965,0.027075496,0.00017973341,0.00006917359,0.002725554],"genre_scores_gemma":[0.9720731,0.000060388094,0.024409756,0.0007407426,0.00017831608,0.002285128,0.00021892668,0.000029918298,0.00000376367],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995852,0.0015676359,0.0010945138,0.00025708083,0.0007258627,0.00050292024],"domain_scores_gemma":[0.9897156,0.0004997889,0.0014164482,0.00018968065,0.0076710344,0.0005074703],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0039123925,0.00016485403,0.00024268951,0.00034588756,0.0013154335,0.000041918316,0.00005871799,0.00015288657,0.0001437044],"category_scores_gemma":[0.0018078511,0.00014520335,0.000035907382,0.0003517703,0.00011026561,0.0004176793,0.000007828173,0.00039042765,0.000005364896],"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":[0.00011013689,0.00001881208,0.23123272,0.000087701796,0.000031548203,3.392667e-7,0.0033548486,0.00015652864,0.0000030676672,0.008371785,0.0023211562,0.7543114],"study_design_scores_gemma":[0.0029298235,0.0014554599,0.94456226,0.00028694654,0.00022814276,0.000046280395,0.0066717914,0.00055906025,0.000006285448,0.0070267497,0.03603192,0.00019528822],"about_ca_topic_score_codex":0.006790909,"about_ca_topic_score_gemma":0.08061209,"teacher_disagreement_score":0.75411606,"about_ca_system_score_codex":0.0042142314,"about_ca_system_score_gemma":0.015296278,"threshold_uncertainty_score":0.99998474},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995887,0.00007640303,0.00028048494,0.0015029128,0.0006066313,0.001504005,0.0000069652156,0.0000022356874,0.00013340333],"genre_scores_gemma":[0.9992303,0.0000074444765,0.00017943712,0.00007578458,0.00038056867,0.00010278466,0.00001109901,0.0000054492716,0.0000071345894],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998832,0.0001826433,0.00027644093,0.00007815667,0.0004211221,0.00020966634],"domain_scores_gemma":[0.99840397,0.00006206748,0.00028950823,0.0000713469,0.0010957826,0.00007730688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036810848,0.000066465815,0.00009026563,0.00016055605,0.00084763294,0.000080815174,0.00036389442,0.00008558293,0.000017579285],"category_scores_gemma":[0.00013220473,0.000042865642,0.0000699735,0.0004770524,0.00018639128,0.000634609,0.000002917967,0.00013547683,1.3414751e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007764134,0.00007243913,0.09864161,0.00018893997,0.000064971275,3.9091316e-7,0.12214591,0.015406959,0.00015401011,0.007597094,0.000045390327,0.7556046],"study_design_scores_gemma":[0.0010958844,0.0003064674,0.94872797,0.00012829856,0.00010984425,0.0000023330533,0.020879878,0.01909192,0.0002464759,0.0014090863,0.007886143,0.000115676194],"about_ca_topic_score_codex":0.34822732,"about_ca_topic_score_gemma":0.98495394,"teacher_disagreement_score":0.8500864,"about_ca_system_score_codex":0.0006752034,"about_ca_system_score_gemma":0.0042183036,"threshold_uncertainty_score":0.74830896},"labels":[],"label_agreement":null},{"id":"W4366675053","doi":"10.3138/cjpe.0017.005","title":"Evaluation Capacity Building in the Voluntary/Nonprofit Sector","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Ontario","funders":"","keywords":"Nonprofit sector; Work (physics); Capacity building; Business; Process (computing); Resource (disambiguation); Public relations; Knowledge management; Political science; Economic growth; Economics; Computer science","score_opus":0.582860873132594,"score_gpt":0.5211126018594392,"score_spread":0.06174827127315485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9875314,0.00049924076,0.000986337,0.001731324,0.0011188982,0.001812441,0.0000037099605,0.0000045164466,0.0063121044],"genre_scores_gemma":[0.99569595,0.0000043139344,0.0036238977,0.00033899618,0.00015252309,0.0001408284,0.000004822446,0.00000820053,0.000030449035],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98853713,0.0040572253,0.001135702,0.00024702182,0.00566037,0.00036253882],"domain_scores_gemma":[0.9939224,0.0004631955,0.0006939337,0.0003876329,0.00427187,0.0002609563],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.105819605,0.00014066575,0.0002226507,0.00082134403,0.00027045913,0.0005022038,0.00061242824,0.000090051,0.0042285025],"category_scores_gemma":[0.011439119,0.00009298242,0.00012956753,0.0014956807,0.000087695575,0.0008248312,0.0000053140348,0.00036115825,0.0000596488],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011437353,0.000088354966,0.16528088,0.000004636265,0.00003484364,0.0000070215324,0.005522183,0.009857107,0.00010822889,0.0038868308,0.0032225165,0.81197596],"study_design_scores_gemma":[0.0029910868,0.0007308521,0.5688617,0.00009314353,0.00032283418,0.00020429656,0.0066983765,0.2254775,0.0003234816,0.113138266,0.0807993,0.00035917544],"about_ca_topic_score_codex":0.001103383,"about_ca_topic_score_gemma":0.05064383,"teacher_disagreement_score":0.8116168,"about_ca_system_score_codex":0.0009895322,"about_ca_system_score_gemma":0.0072561917,"threshold_uncertainty_score":0.9983717},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.955736,0.005644724,0.00033632052,0.0164858,0.0049318774,0.0028652723,0.000018374925,0.00010404253,0.013877581],"genre_scores_gemma":[0.99491334,0.0000049431846,0.0026644005,0.00004016774,0.0020820238,0.00002977025,0.000011056295,0.000030757084,0.00022355172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840426,0.0002387126,0.00038907063,0.000113343325,0.0005776953,0.0002768912],"domain_scores_gemma":[0.9975369,0.000012479542,0.00035416734,0.00016387695,0.0014164617,0.0005161239],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00242122,0.000092342925,0.0001258799,0.0005753178,0.00012344666,0.00012576117,0.00014549395,0.000059548795,0.008415763],"category_scores_gemma":[0.0010172152,0.0000907141,0.00008139178,0.00054700766,0.00007421289,0.00046812868,0.0000020484254,0.00020417904,0.0014818809],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006220046,0.000048418264,0.001708392,0.0000039141305,0.000040210274,0.000014015316,0.00058812555,0.00083389244,0.00041207692,0.00023725424,0.1757445,0.820363],"study_design_scores_gemma":[0.0014368858,0.0007679202,0.015640529,0.000035681627,0.00031568986,0.000708345,0.00027362726,0.04281256,0.00045723,0.0015666765,0.9357403,0.0002445798],"about_ca_topic_score_codex":0.00043342367,"about_ca_topic_score_gemma":0.0103263855,"teacher_disagreement_score":0.8201184,"about_ca_system_score_codex":0.00087802607,"about_ca_system_score_gemma":0.0006110067,"threshold_uncertainty_score":0.9992956},"labels":[],"label_agreement":null},{"id":"W4366675147","doi":"10.3138/cjpe.0016.009","title":"Program Evaluation in the Government of the Northwest Territories, 1967–2000","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Northwest Territories","funders":"","keywords":"Cabinet (room); Documentation; Government (linguistics); Business; Public administration; Political science; Public relations; Geography; Archaeology; Computer science","score_opus":0.29140734594736467,"score_gpt":0.46572274541019243,"score_spread":0.17431539946282776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.974967,0.0010621111,0.000036906065,0.009629678,0.0017719705,0.0057133217,0.00003234162,0.0000066902544,0.006780004],"genre_scores_gemma":[0.99844897,0.000016411448,0.00062031014,0.00020671413,0.00021697175,0.00038619922,0.000008489916,0.000007834803,0.00008812411],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98809665,0.0016944478,0.0013049414,0.00020540363,0.008400128,0.0002984269],"domain_scores_gemma":[0.9957556,0.00030407318,0.001096418,0.00055609486,0.0021117448,0.00017607759],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025967246,0.00014431165,0.00022782598,0.00024143452,0.00023742829,0.00033901914,0.0010423209,0.00008370956,0.0023083403],"category_scores_gemma":[0.0030159804,0.00007897049,0.00017108688,0.0014755435,0.00016230498,0.00051344343,0.000017907927,0.00030455829,0.000014478865],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006913751,0.000147009,0.15572533,0.0000031736133,0.00001201996,0.0000012977248,0.0037689975,0.002193182,0.0000057485654,0.000118800104,0.0012217009,0.8367958],"study_design_scores_gemma":[0.001275206,0.00060252415,0.70814395,0.00008516943,0.00014083284,0.00003445077,0.0035029955,0.14757909,0.00005940901,0.0024168945,0.13602704,0.00013243228],"about_ca_topic_score_codex":0.001585361,"about_ca_topic_score_gemma":0.1698806,"teacher_disagreement_score":0.8366634,"about_ca_system_score_codex":0.0010432311,"about_ca_system_score_gemma":0.0031088777,"threshold_uncertainty_score":0.9986037},"labels":[],"label_agreement":null},{"id":"W4366675148","doi":"10.3138/cjpe.0016.005","title":"Evaluation Policy and Practice in Ontario","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Optimism; Government (linguistics); Public service; Public policy; Public administration; Service (business); Political science; Business; Public relations; Program evaluation; Psychology; Marketing; Social psychology","score_opus":0.5598804861443701,"score_gpt":0.5713121749383623,"score_spread":0.011431688793992145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.866139,0.0028368838,0.00020002469,0.021185178,0.0009431038,0.0023981836,0.0000023715531,0.000007862753,0.10628742],"genre_scores_gemma":[0.9962285,0.00003092564,0.002710732,0.0004228483,0.00013586406,0.00005320732,0.0000029469356,0.0000060641332,0.00040887084],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99333286,0.0016159018,0.0008989659,0.00019820592,0.0037022752,0.00025179322],"domain_scores_gemma":[0.9933898,0.00073191174,0.00064682175,0.00021690346,0.004641399,0.00037317726],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04925423,0.000101494166,0.000184635,0.0012831511,0.00013087588,0.0004347314,0.00023807648,0.00007621585,0.006143807],"category_scores_gemma":[0.034330625,0.00008398706,0.00005252044,0.00090726983,0.00007035401,0.0014338404,0.000009764545,0.00026440664,0.00008033397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008368435,0.000045310015,0.018666396,7.304803e-7,0.000012959136,0.000004580003,0.005237186,0.0016932487,0.0000070637484,0.00034865053,0.0011880453,0.97278744],"study_design_scores_gemma":[0.0027819881,0.0007163089,0.45129615,0.00006040657,0.00020778143,0.00029486668,0.0029384657,0.2410479,0.000010777023,0.023540344,0.27688834,0.00021667806],"about_ca_topic_score_codex":0.05250958,"about_ca_topic_score_gemma":0.8428295,"teacher_disagreement_score":0.9725708,"about_ca_system_score_codex":0.0019338197,"about_ca_system_score_gemma":0.009651016,"threshold_uncertainty_score":0.99596334},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8659606,0.000082581595,0.000019174626,0.065931715,0.00050649286,0.0011260259,0.0000038306125,0.000014302343,0.0663553],"genre_scores_gemma":[0.991234,0.00008309274,0.001770716,0.0012777764,0.000441145,0.00004667814,0.000014381109,0.000011997695,0.0051202183],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986903,0.0002103726,0.0003672676,0.0001136291,0.00029795722,0.00032045206],"domain_scores_gemma":[0.9989225,0.000038813698,0.000117078605,0.00008209527,0.00036601906,0.00047344915],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022320878,0.00007746822,0.00013456676,0.00042718055,0.00021314717,0.00013452662,0.00015026073,0.000060885828,0.0019284798],"category_scores_gemma":[0.00030528262,0.000080608595,0.00004099209,0.00056645257,0.000088995876,0.00025267515,0.0000026046546,0.00009134743,0.000158427],"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":[0.00004027281,0.000029351395,0.015888276,0.0000063349385,0.00003079739,0.00009211544,0.025407532,0.0011998538,0.0000028720804,0.0064125876,0.06786537,0.88302463],"study_design_scores_gemma":[0.00032489587,0.00004689047,0.15374874,0.000045668792,0.000013440062,0.000032522774,0.0007557552,0.000045224755,0.0000017074719,0.0036954915,0.84116966,0.00011998926],"about_ca_topic_score_codex":0.0323169,"about_ca_topic_score_gemma":0.51992106,"teacher_disagreement_score":0.88290465,"about_ca_system_score_codex":0.001045458,"about_ca_system_score_gemma":0.014054556,"threshold_uncertainty_score":0.9989839},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902215,0.0007134711,0.00019350715,0.00054071617,0.0012450084,0.0058668875,0.00004645916,0.000011526167,0.0011609156],"genre_scores_gemma":[0.99163896,0.0000046257173,0.0068167555,0.0009331489,0.00013452023,0.00034043548,0.000038539056,0.000017472665,0.00007552089],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969854,0.001138327,0.0010487526,0.00012021067,0.0003221769,0.00038512744],"domain_scores_gemma":[0.99488354,0.0004161459,0.00089559436,0.00016549486,0.0032679858,0.0003712383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044007455,0.00010823588,0.00033719966,0.0003198309,0.0009294687,0.000017113274,0.000102662125,0.00009734807,0.00040317117],"category_scores_gemma":[0.00067981007,0.000099397934,0.000084628875,0.00026102687,0.000023920507,0.00022846705,0.0000059218346,0.00035081984,0.000004258966],"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":[0.00006956664,0.00026403833,0.822125,0.001165044,0.00015785353,0.00031943692,0.023113815,0.00041526087,0.000023132854,0.0007964214,0.010729012,0.1408214],"study_design_scores_gemma":[0.0172605,0.0075393263,0.1453086,0.0006480619,0.0017596892,0.0017504194,0.33516085,0.0037979803,0.00003715511,0.00655815,0.47947413,0.0007051417],"about_ca_topic_score_codex":0.013609805,"about_ca_topic_score_gemma":0.16025938,"teacher_disagreement_score":0.6768164,"about_ca_system_score_codex":0.0006735974,"about_ca_system_score_gemma":0.0099893985,"threshold_uncertainty_score":0.99562305},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1580469,0.0008002758,0.00008464785,0.10948921,0.0077900523,0.002585665,0.00001207971,0.00001972703,0.72117144],"genre_scores_gemma":[0.99512196,0.000026349187,0.00025241106,0.0014014263,0.0029782364,0.000028158378,0.000002611239,0.000006663007,0.00018216838],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974139,0.0014752791,0.00022682197,0.00007114127,0.00051338476,0.0002995012],"domain_scores_gemma":[0.998477,0.00040969715,0.00011996435,0.000096363015,0.0005281707,0.00036880505],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005893961,0.000058663678,0.000099986835,0.00007620814,0.0005135229,0.00009129528,0.00021770713,0.000091340866,0.004906576],"category_scores_gemma":[0.00839481,0.00004461131,0.00006539988,0.00019053934,0.00045739906,0.00009318533,0.0000021539875,0.00023826178,0.00008379477],"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":[0.000007089294,0.000056146848,0.0021768536,0.0000020309635,0.000024724024,0.000014286706,0.012635767,0.000018227738,0.0000021650649,0.42959,0.12668586,0.42878687],"study_design_scores_gemma":[0.00018828388,0.00016328659,0.0010131807,0.000012175112,0.00002892009,0.0000035832163,0.005093841,0.000012903375,0.000009474293,0.045223672,0.9482011,0.000049589038],"about_ca_topic_score_codex":0.0021134373,"about_ca_topic_score_gemma":0.043987952,"teacher_disagreement_score":0.83707505,"about_ca_system_score_codex":0.00055986666,"about_ca_system_score_gemma":0.0021029983,"threshold_uncertainty_score":0.9999579},"labels":[],"label_agreement":null},{"id":"W4366675196","doi":"10.3138/cjpe.0016.008","title":"Evaluation in Newfoundland: Then Was Then and Now Is Now","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Accountability; Plan (archaeology); Audit; Business; Program evaluation; Strategic planning; Public administration; Political science; Public relations; Accounting; Process management; Environmental resource management; Geography; Marketing; Economics; Archaeology","score_opus":0.39082580630976066,"score_gpt":0.49751921985585973,"score_spread":0.10669341354609907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674581,0.0026635749,0.00020320968,0.012690771,0.00079661934,0.0017647385,0.00000788684,0.000008520543,0.0144065535],"genre_scores_gemma":[0.997668,0.000110602836,0.0010411469,0.00044468744,0.00018062026,0.00007253363,0.0000062598583,0.00001108633,0.00046502834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99357027,0.001026075,0.0009987672,0.00027642574,0.003807208,0.000321271],"domain_scores_gemma":[0.99535173,0.00026904087,0.00060862006,0.00031666493,0.0030426802,0.0004112534],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029139921,0.00015252663,0.00027247355,0.0009813786,0.00018738477,0.00056574005,0.00038438808,0.000107214735,0.010154459],"category_scores_gemma":[0.0022368806,0.00011586969,0.00008971823,0.0008203166,0.00009393789,0.0009492162,0.000014727623,0.00024833466,0.00025023022],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007896987,0.000041096595,0.10203213,0.0000023833884,0.000021218713,0.0000031023471,0.0046679783,0.0009360438,0.000013933472,0.00007601506,0.0056857504,0.88651246],"study_design_scores_gemma":[0.0022261867,0.00045186267,0.30296546,0.00006762569,0.00014480474,0.000054361044,0.0012850494,0.61196613,0.000015056553,0.021788988,0.058839448,0.00019501481],"about_ca_topic_score_codex":0.0009619505,"about_ca_topic_score_gemma":0.121901825,"teacher_disagreement_score":0.88631743,"about_ca_system_score_codex":0.00081850594,"about_ca_system_score_gemma":0.0020499618,"threshold_uncertainty_score":0.9997048},"labels":[],"label_agreement":null},{"id":"W4366675198","doi":"10.3138/cjpe.0020.010","title":"Program Evaluation in the Government of Canada: Plus ça change …","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Treasury; Government (linguistics); Public administration; State (computer science); Function (biology); State government; Political science; Business; Accounting; Local government; Computer science; Law","score_opus":0.4207187134281067,"score_gpt":0.5004735994535432,"score_spread":0.07975488602543651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675198","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96526164,0.0013881245,0.00016141654,0.009419677,0.0012216889,0.007873292,0.000023692122,0.000006531378,0.014643953],"genre_scores_gemma":[0.99782443,0.0000061301707,0.0008658917,0.0002355331,0.00026085353,0.0007054285,0.00001638308,0.000007785037,0.0000775486],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98748535,0.0011934239,0.001358171,0.00020555346,0.009395984,0.000361502],"domain_scores_gemma":[0.9954495,0.00028136472,0.0011036822,0.00035132223,0.0026297814,0.00018434525],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032794233,0.00014105448,0.0002708852,0.0003184435,0.00015706898,0.0002116436,0.0006350332,0.000071240866,0.0010627916],"category_scores_gemma":[0.0017902871,0.0000941436,0.00010155954,0.0011348684,0.00007872443,0.00049315393,0.000011443785,0.00021381413,0.000004586788],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018903935,0.00009594686,0.030382296,0.000005928741,0.000010496578,0.00000567317,0.0011984837,0.0062994044,0.000009360567,0.0004696889,0.005651333,0.9558525],"study_design_scores_gemma":[0.0017113424,0.0005321056,0.73396325,0.000074849806,0.000113006216,0.000024084406,0.0037239674,0.1895694,0.000081656384,0.0050247046,0.06502542,0.00015619502],"about_ca_topic_score_codex":0.17170388,"about_ca_topic_score_gemma":0.95555145,"teacher_disagreement_score":0.9556963,"about_ca_system_score_codex":0.00235609,"about_ca_system_score_gemma":0.015591209,"threshold_uncertainty_score":0.9998504},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5491281,0.005751979,0.0005646117,0.018885849,0.07016134,0.003108876,0.000017482067,0.00009623015,0.3522855],"genre_scores_gemma":[0.9784977,0.000016849135,0.0009992948,0.00006243463,0.020076405,0.000011249482,0.0000091475595,0.000006004685,0.00032095585],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848723,0.00028169344,0.00024911165,0.000067645145,0.0006633532,0.00025093378],"domain_scores_gemma":[0.9984268,0.000032309596,0.00019572803,0.00006570762,0.0009811254,0.0002983253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041188197,0.000049978607,0.000089380446,0.000106383675,0.00045983028,0.00025701872,0.00017357711,0.000112361085,0.000292679],"category_scores_gemma":[0.00061633065,0.000053083153,0.00009844459,0.00025862787,0.00018098537,0.0003723936,0.0000024710323,0.00015399278,0.000020289988],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015512207,0.00009122027,0.06946056,0.000011239591,0.000041891835,0.000025689782,0.00525506,0.0001294874,0.000022671178,0.019440688,0.7879262,0.117593735],"study_design_scores_gemma":[0.00027493198,0.00006472697,0.041313674,0.000029270657,0.00006228841,0.000004269411,0.001986893,0.00010659427,0.000008960063,0.007158431,0.9489002,0.00008975299],"about_ca_topic_score_codex":0.07224754,"about_ca_topic_score_gemma":0.46100274,"teacher_disagreement_score":0.42936954,"about_ca_system_score_codex":0.0006065971,"about_ca_system_score_gemma":0.003961849,"threshold_uncertainty_score":0.93393046},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5092081,0.015387669,0.01900356,0.3579188,0.01644172,0.013687093,0.000041998803,0.00006971655,0.06824139],"genre_scores_gemma":[0.99052256,0.00016110693,0.0044742017,0.00036213305,0.0017771178,0.000117605465,0.0000028857976,0.000008806549,0.002573558],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955263,0.0004535406,0.00034221922,0.00016454466,0.0030981102,0.00041529],"domain_scores_gemma":[0.99805313,0.0002005463,0.00033846972,0.00015645067,0.00060248794,0.00064892205],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054180482,0.0000884604,0.00010146827,0.000054628832,0.0010008711,0.0006112702,0.0004986048,0.00007884244,0.0019061929],"category_scores_gemma":[0.0017067833,0.00007335567,0.00007903476,0.00061273354,0.00012684836,0.00046468133,0.00001424857,0.00015560687,0.000055592427],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052145533,0.000012336799,0.0018758796,7.666401e-7,0.000025866835,0.0000033680976,0.012461857,0.00026926366,5.3484234e-7,0.0038195504,0.034863967,0.9466614],"study_design_scores_gemma":[0.0007266314,0.00022192647,0.32491335,0.00016260215,0.0002569329,0.0000013176492,0.030680072,0.005197643,0.000006297728,0.036649507,0.6009141,0.00026963095],"about_ca_topic_score_codex":0.14623076,"about_ca_topic_score_gemma":0.8388378,"teacher_disagreement_score":0.94639176,"about_ca_system_score_codex":0.002219865,"about_ca_system_score_gemma":0.0020615142,"threshold_uncertainty_score":0.9990062},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86072797,0.021217108,0.0013926951,0.10419946,0.002081356,0.0026012796,0.00006214388,0.000060377093,0.0076575982],"genre_scores_gemma":[0.973979,0.00023343098,0.023549087,0.0012409614,0.0005498626,0.00015014148,0.00001065555,0.000024886405,0.0002619728],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955791,0.0003518661,0.0031854662,0.00023501138,0.0001821397,0.0004663717],"domain_scores_gemma":[0.9966968,0.000101526835,0.0020867784,0.0002779161,0.0003096713,0.0005272992],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024458254,0.0001326633,0.0006030919,0.0008880756,0.00030667626,0.0001334211,0.00028171987,0.00012720347,0.002097928],"category_scores_gemma":[0.0012847006,0.00016682128,0.000105536325,0.0004216208,0.00008086509,0.00045714277,0.0000051281945,0.0002748161,0.00035466455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000688148,0.00009866909,0.21450318,0.00014748971,0.0001665483,0.000007891545,0.003805669,0.002684534,0.0000028638028,0.018400917,0.012941809,0.74723357],"study_design_scores_gemma":[0.0027627982,0.001763267,0.33285594,0.0007146693,0.00005285245,0.00018252667,0.011057038,0.02167451,0.000021681724,0.056048084,0.57206357,0.0008030824],"about_ca_topic_score_codex":0.0031654562,"about_ca_topic_score_gemma":0.0032096813,"teacher_disagreement_score":0.74643046,"about_ca_system_score_codex":0.0033934829,"about_ca_system_score_gemma":0.0047710645,"threshold_uncertainty_score":0.9988143},"labels":[],"label_agreement":null},{"id":"W4366675251","doi":"10.3138/cjpe.019.005","title":"An Empirical Study of Building the Evaluation Capacity of K–12 Site-Managed Project Personnel","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Argument (complex analysis); Psychology; Medical education; Program evaluation; Professional development; Evaluation methods; Capacity building; Applied psychology; Pedagogy; Political science; Engineering; Medicine","score_opus":0.5928942452671162,"score_gpt":0.566262734771,"score_spread":0.02663151049611623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944438,0.00009907216,0.0012111448,0.0006277495,0.00038557878,0.0029040407,0.000007249643,0.0000055465807,0.00031582586],"genre_scores_gemma":[0.9969576,0.00000232172,0.0027468028,0.000060917668,0.00012281143,0.000087918175,0.0000066468738,0.000010163681,0.0000048149377],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9907619,0.0022716732,0.0014578227,0.00027240903,0.0049729184,0.0002633174],"domain_scores_gemma":[0.9929871,0.00029284475,0.0015444566,0.000541518,0.004391194,0.00024289322],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037384216,0.00015375638,0.00036089946,0.0009283377,0.00033496783,0.00021041048,0.00070394174,0.00008309857,0.0003394002],"category_scores_gemma":[0.0041059125,0.00009972147,0.00015595979,0.0013183652,0.00016670524,0.0008497999,0.000015408137,0.0002865021,0.00000414697],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107049505,0.0010994736,0.30569777,0.000018014194,0.00014733127,0.000003895128,0.10800434,0.14520067,0.0017426342,0.0002048066,0.00024998165,0.43752405],"study_design_scores_gemma":[0.005159802,0.005559172,0.67198354,0.00010071629,0.0006424922,0.000036261645,0.07724205,0.23164016,0.00080289756,0.006179592,0.00041333836,0.00023996043],"about_ca_topic_score_codex":0.0044833035,"about_ca_topic_score_gemma":0.065653175,"teacher_disagreement_score":0.43728408,"about_ca_system_score_codex":0.0004810285,"about_ca_system_score_gemma":0.0062503275,"threshold_uncertainty_score":0.99938333},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8302968,0.02863151,0.00061205693,0.11666109,0.010646359,0.0037272796,0.000047385613,0.00002913811,0.00934834],"genre_scores_gemma":[0.9800391,0.0004342179,0.004200757,0.005336104,0.0080520045,0.000081258884,0.0000735226,0.00005549488,0.001727534],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99258506,0.0037664038,0.0015175705,0.00021267346,0.000875889,0.0010423835],"domain_scores_gemma":[0.9941176,0.0004680156,0.0009966944,0.00025932395,0.0025286267,0.0016297369],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014349357,0.00023175936,0.0004568253,0.00031880624,0.00092525425,0.00006381718,0.00025338092,0.001058772,0.0037118078],"category_scores_gemma":[0.0026806355,0.00022483972,0.00022455103,0.00063567923,0.00023254594,0.00038538128,0.000010861237,0.0026481287,0.00021596538],"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":[0.000012548747,0.00015596072,0.03550511,0.00029290502,0.00006474042,0.00011173659,0.011330921,0.00012456719,0.0000103162365,0.0027765112,0.17994633,0.76966834],"study_design_scores_gemma":[0.00261789,0.0010617862,0.15486382,0.00097138487,0.00047122294,0.00013090462,0.006003262,0.004542744,0.000008521986,0.0063634454,0.822729,0.00023602288],"about_ca_topic_score_codex":0.061254855,"about_ca_topic_score_gemma":0.14176278,"teacher_disagreement_score":0.7694323,"about_ca_system_score_codex":0.002074144,"about_ca_system_score_gemma":0.02527232,"threshold_uncertainty_score":0.9996528},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9488712,0.0075170756,0.00023542372,0.0032906595,0.0020149113,0.0028092214,0.00004376681,0.00008425783,0.035133477],"genre_scores_gemma":[0.99654007,0.000004769892,0.002821984,0.00007842734,0.00030848308,0.00003307309,0.000010431522,0.00003449855,0.00016826848],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832076,0.00019589397,0.0004255324,0.00010210185,0.0006091232,0.00034658116],"domain_scores_gemma":[0.997427,0.000026864682,0.0003675426,0.00016629882,0.0012501263,0.0007621577],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023853437,0.00010496436,0.00015226066,0.0005491577,0.00012567047,0.00012337418,0.00021522844,0.00006861894,0.0048337867],"category_scores_gemma":[0.0008118772,0.00010119856,0.00010293951,0.0004947198,0.0000891405,0.00035768937,0.0000028061702,0.00021378891,0.001625443],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000639125,0.00007105944,0.007784182,0.0000054326742,0.000061725295,0.00006831487,0.00092938513,0.0006026659,0.00021818864,0.00046988245,0.043679383,0.9461034],"study_design_scores_gemma":[0.0053896704,0.0025027723,0.093586296,0.00024345385,0.00088855793,0.0016932586,0.0006959091,0.13532944,0.0006078869,0.014126582,0.7441243,0.0008118577],"about_ca_topic_score_codex":0.0009080933,"about_ca_topic_score_gemma":0.02678112,"teacher_disagreement_score":0.9452915,"about_ca_system_score_codex":0.000753117,"about_ca_system_score_gemma":0.0007534609,"threshold_uncertainty_score":0.9991519},"labels":[],"label_agreement":null},{"id":"W4366675260","doi":"10.3138/cjpe.016.005","title":"The Politics and Practice of Empowerment Evaluation and Social Interventions: Lessons from the Atlantic Community Action Program for Children Regional Evaluation","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nova Scotia Health Authority; Health Canada; Saint Mary's University","funders":"Health Canada","keywords":"Empowerment; Popularity; Politics; Context (archaeology); Sociology; Participatory action research; Action (physics); Citizen journalism; Psychological intervention; Public relations; Political science; Psychology; Social psychology; Law","score_opus":0.596221525877389,"score_gpt":0.6159796392535666,"score_spread":0.01975811337617761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9706271,0.001928654,0.00080149836,0.02131672,0.00038295757,0.0047841626,0.000029371513,0.000006949749,0.00012255163],"genre_scores_gemma":[0.99733293,0.00016752041,0.001425062,0.00014810653,0.00022390252,0.0004826315,0.0001924307,0.000010071079,0.00001734624],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9905504,0.0050215693,0.0011364849,0.00019688474,0.0028362712,0.00025840147],"domain_scores_gemma":[0.98722243,0.0032152894,0.0016004278,0.00031166524,0.007494313,0.00015587086],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05776846,0.00014679575,0.000226723,0.00023289371,0.0016813725,0.000640118,0.0003934441,0.000098262084,0.00015354661],"category_scores_gemma":[0.010431172,0.000090658425,0.0001971945,0.00041567668,0.00035126103,0.0007475113,0.000030745545,0.00032433262,0.000002054069],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099797144,0.00015458156,0.028171808,0.00000642394,0.00016050713,1.1103976e-7,0.003356091,0.00033209712,0.000012631869,0.0007026338,0.0021952125,0.9648081],"study_design_scores_gemma":[0.0025055297,0.0011216697,0.84136564,0.00011611452,0.001270877,0.000093591894,0.013533179,0.089159064,0.0000071159357,0.033785105,0.016901733,0.0001404074],"about_ca_topic_score_codex":0.0053422265,"about_ca_topic_score_gemma":0.049401447,"teacher_disagreement_score":0.9646677,"about_ca_system_score_codex":0.00053645816,"about_ca_system_score_gemma":0.002924424,"threshold_uncertainty_score":0.9996183},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942908,0.00060900464,0.0011416222,0.0007643241,0.000049794544,0.00079723564,0.000006365846,0.00003398717,0.0023068357],"genre_scores_gemma":[0.9844551,0.00043922034,0.014580083,0.00007011792,0.0002558313,0.00011031463,0.000020142434,0.000014912264,0.000054260967],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957914,0.0025968712,0.00031162376,0.00016546667,0.0006787179,0.00045593648],"domain_scores_gemma":[0.99857354,0.00024158774,0.00031088185,0.00007889135,0.00038755438,0.00040753745],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0073080016,0.00012864977,0.00012951913,0.00010789325,0.0013901088,0.00039253387,0.00025919685,0.0001864472,0.00023066765],"category_scores_gemma":[0.0005293038,0.00012815832,0.00008197816,0.00039294883,0.0008978064,0.00084908574,0.000004715468,0.00016491911,0.000007400385],"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":[0.000020784006,0.00010135014,0.13809001,0.000021291231,0.000018089297,0.0000049668147,0.24743526,0.00084166334,0.00056994613,0.00033011095,0.000044959383,0.6125216],"study_design_scores_gemma":[0.00065371394,0.00023143842,0.9492256,0.00015029027,0.000116775824,0.00007491775,0.01741126,0.0041585215,0.000754445,0.023995351,0.003053765,0.00017394124],"about_ca_topic_score_codex":0.53896445,"about_ca_topic_score_gemma":0.75855184,"teacher_disagreement_score":0.8111356,"about_ca_system_score_codex":0.00449637,"about_ca_system_score_gemma":0.0113316225,"threshold_uncertainty_score":0.99990994},"labels":[],"label_agreement":null},{"id":"W4366675286","doi":"10.3138/cjpe.0020.003","title":"Program Evaluation in Canada Seen through the Articles Published in CJPE","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"St. Lawrence College; Université Laval","funders":"","keywords":"Honour; Audit; Political science; Library science; Sociology; Public administration; Law; Management; Computer science; Economics","score_opus":0.3053697535010307,"score_gpt":0.4944470437878705,"score_spread":0.18907729028683984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760589,0.00074259826,0.000087107204,0.012577037,0.0007951326,0.0037925625,0.0000055234796,0.0000074716622,0.0059336456],"genre_scores_gemma":[0.99759537,0.0000048470697,0.0013226824,0.00029081813,0.00016826416,0.0005200034,0.00002577429,0.000010599564,0.000061639694],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.991391,0.001554294,0.0017317845,0.00029493298,0.0045227488,0.00050522835],"domain_scores_gemma":[0.99529666,0.00039475615,0.00081234117,0.00040782397,0.0028819938,0.00020643674],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027122023,0.00016378806,0.00029105807,0.0006267376,0.00017416629,0.0007509827,0.0006864196,0.00007677641,0.0023275716],"category_scores_gemma":[0.0035320648,0.00010987124,0.00008558932,0.002428126,0.0000905477,0.0014352925,0.000016700687,0.00037216654,0.000019516758],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012605017,0.0000668171,0.22276624,0.0000022488935,0.0000073314245,0.000007855936,0.0007311204,0.03761829,0.000006682436,0.00028503305,0.0055539105,0.73294187],"study_design_scores_gemma":[0.0014036762,0.00015729229,0.6818048,0.00004291845,0.00003980393,0.000016903745,0.0028912162,0.25060043,0.000045668563,0.02862828,0.03422983,0.00013919237],"about_ca_topic_score_codex":0.8542695,"about_ca_topic_score_gemma":0.99891144,"teacher_disagreement_score":0.7328027,"about_ca_system_score_codex":0.0032143628,"about_ca_system_score_gemma":0.032147393,"threshold_uncertainty_score":0.99858445},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9606794,0.00016709622,0.0016268624,0.017068077,0.0003430721,0.00046988332,0.000009761214,0.000026767335,0.019609049],"genre_scores_gemma":[0.9977563,0.000081345504,0.0006324026,0.00019974753,0.000786095,0.000044183063,0.0000072544667,0.0000092594055,0.00048340685],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9963061,0.0022586237,0.000338173,0.00012476959,0.0005919391,0.00038034868],"domain_scores_gemma":[0.99818456,0.00027621945,0.0005337608,0.00006446476,0.00066908414,0.00027188528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010500223,0.000088763074,0.00012906842,0.0001751372,0.0007294224,0.00038010147,0.00021395051,0.00023765383,0.00029348678],"category_scores_gemma":[0.002572921,0.000093778,0.00007750503,0.0010609857,0.00030878047,0.0007910941,0.0000039093884,0.00025219857,0.0000061898636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000943218,0.00013812154,0.023323828,0.000010360443,0.00004335665,0.000020847001,0.115298316,0.00026897195,0.00074339536,0.08491857,0.0144365085,0.76078826],"study_design_scores_gemma":[0.0013407621,0.00019644597,0.6011645,0.0000885399,0.00007360993,0.000056046978,0.09184989,0.003982337,0.00018105746,0.106289625,0.1944227,0.00035448393],"about_ca_topic_score_codex":0.10819778,"about_ca_topic_score_gemma":0.31238276,"teacher_disagreement_score":0.7604338,"about_ca_system_score_codex":0.0015002018,"about_ca_system_score_gemma":0.00741272,"threshold_uncertainty_score":0.9982143},"labels":[],"label_agreement":null},{"id":"W4366675294","doi":"10.3138/cjpe.0020.007","title":"Evaluation in Canada’s Social Services: Progress, Rifts, and Challenges","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conceptualization; Empowerment; Business; Investment (military); Service (business); Public relations; Knowledge management; Tertiary sector of the economy; Marketing; Economic growth; Economics; Political science; Computer science","score_opus":0.3307560674375689,"score_gpt":0.4735947203942487,"score_spread":0.1428386529566798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366675294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96505666,0.016029723,0.000013820543,0.012170779,0.00066200836,0.0015296459,0.000010236571,0.000005883834,0.0045212703],"genre_scores_gemma":[0.9989713,0.00007301563,0.0004759105,0.0000976578,0.00024570886,0.000088889436,0.000021188225,0.000008863849,0.000017482342],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9932548,0.00096793403,0.0010020022,0.00024290843,0.0042150295,0.00031733242],"domain_scores_gemma":[0.99527663,0.00011728756,0.00069776515,0.00016250976,0.0035161413,0.00022964357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022686614,0.00013687517,0.0002586883,0.0005799301,0.0001997511,0.00028632232,0.00031342116,0.00007892254,0.0005331728],"category_scores_gemma":[0.0003618398,0.000114231785,0.000049823222,0.0005189286,0.00007490754,0.00062978955,0.000011860652,0.00018022135,0.00000787005],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007671422,0.000025001898,0.08728406,0.000013902796,0.000011182377,0.000005351703,0.0008295034,0.00085634796,0.0000023788664,0.0004670437,0.00055892963,0.90993863],"study_design_scores_gemma":[0.0012774951,0.00011945634,0.8521433,0.000062134925,0.000087388755,0.000021584816,0.0035865076,0.09116993,0.000010268304,0.0141871115,0.037188817,0.0001460011],"about_ca_topic_score_codex":0.574364,"about_ca_topic_score_gemma":0.9985322,"teacher_disagreement_score":0.9097926,"about_ca_system_score_codex":0.0017950571,"about_ca_system_score_gemma":0.027459234,"threshold_uncertainty_score":0.97805417},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61686146,0.033245225,0.003135149,0.0287069,0.091515444,0.007538665,0.000093421164,0.0001165491,0.21878718],"genre_scores_gemma":[0.9867438,0.000040612635,0.0017139628,0.000085353975,0.010114203,0.000023344059,0.000008769741,0.000015325866,0.0012546001],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986137,0.00023568215,0.00030443113,0.00007237017,0.00055670243,0.00021710501],"domain_scores_gemma":[0.998306,0.000026289888,0.00035671433,0.00007518371,0.0009220681,0.00031376004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002522499,0.00005429902,0.00013996767,0.0006249543,0.00040259387,0.0002615129,0.0001738262,0.00006156075,0.00072303106],"category_scores_gemma":[0.00022853218,0.000060146245,0.00007417193,0.0003865398,0.00037654105,0.00032003855,0.0000021208123,0.00011558258,0.000008163179],"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":[0.000019149424,0.00008606829,0.005983746,0.00008432353,0.000081593425,0.000044074313,0.009337922,0.00019586716,0.00003040216,0.01220701,0.4843892,0.48754066],"study_design_scores_gemma":[0.00026112446,0.00015864627,0.0046125622,0.00013978907,0.00009001903,0.0000068750574,0.001156774,0.000032215856,0.000003004318,0.00093739806,0.9925289,0.000072681134],"about_ca_topic_score_codex":0.5286445,"about_ca_topic_score_gemma":0.99209696,"teacher_disagreement_score":0.5081397,"about_ca_system_score_codex":0.0015871859,"about_ca_system_score_gemma":0.008796552,"threshold_uncertainty_score":0.99682266},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99449164,0.0011825408,0.0003334238,0.0023978776,0.00008224977,0.0005775325,0.0000038345834,0.000014218916,0.00091671076],"genre_scores_gemma":[0.99638253,0.00016046721,0.0025737481,0.0005435302,0.00020252806,0.00005331623,0.000026699852,0.00001032317,0.000046827023],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987768,0.00024184745,0.0003619147,0.000093927825,0.00021988915,0.00030560777],"domain_scores_gemma":[0.9984552,0.000025413226,0.0002139899,0.00008747757,0.00065716245,0.0005607008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020402062,0.00009330261,0.00015360767,0.00017082944,0.00012405976,0.00007886333,0.00007686959,0.0000854099,0.00014039536],"category_scores_gemma":[0.00016732964,0.00008258858,0.000052833224,0.0001570015,0.000056191166,0.00022773803,0.000004163284,0.00013383532,0.000006846163],"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":[0.000102901075,0.00012569636,0.53598386,0.00020517071,0.00006405365,0.000052372474,0.0021773833,0.0025112052,0.00016423802,0.00048476848,0.00024232248,0.457886],"study_design_scores_gemma":[0.0015263947,0.00063625217,0.95043606,0.00048111746,0.00028705824,0.00043281043,0.0009994375,0.024698637,0.00039464183,0.0095570255,0.010447066,0.00010351299],"about_ca_topic_score_codex":0.0103347115,"about_ca_topic_score_gemma":0.049285796,"teacher_disagreement_score":0.45778248,"about_ca_system_score_codex":0.0008960166,"about_ca_system_score_gemma":0.0024891857,"threshold_uncertainty_score":0.9962556},"labels":[],"label_agreement":null},{"id":"W4366678314","doi":"10.3138/cjpe.017.001","title":"Les coûts de la non-évaluation des politiques de l’éducation au Québec","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université TÉLUQ; Université Laval","funders":"","keywords":"Ideology; Sociology; Interpretation (philosophy); Valuation (finance); Positive economics; Welfare economics; Relevance (law); Epistemology; Political science; Economics; Philosophy; Law","score_opus":0.6347540541420319,"score_gpt":0.5938711188532354,"score_spread":0.040882935288796496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366678314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789403,0.0004790098,0.0034220142,0.0023653763,0.00029315075,0.0004734095,0.000002905034,0.000012102304,0.014011742],"genre_scores_gemma":[0.9920227,0.00006735255,0.006954966,0.00016200825,0.00028886544,0.00006992748,0.0000059183953,0.000012492046,0.0004157791],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955552,0.0016151993,0.000762905,0.00016822205,0.0015291215,0.0003693419],"domain_scores_gemma":[0.99525785,0.00056508597,0.0005764858,0.00022453158,0.0028398002,0.00053622737],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020063901,0.0001260785,0.00018613736,0.0006662761,0.0005316754,0.00037729362,0.0003615159,0.00012504078,0.002339484],"category_scores_gemma":[0.006728522,0.00010755255,0.00012216094,0.00054634415,0.0002464478,0.0006975997,0.000007386429,0.0002198393,0.00007469084],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000004869396,0.000054434357,0.16855009,0.0000044188814,0.00001584634,0.0000033435297,0.025131248,0.0015929266,0.00007652918,0.00019660697,0.004081676,0.800288],"study_design_scores_gemma":[0.00068478467,0.00035991654,0.7981979,0.00006515071,0.000079103105,0.00020968722,0.0042497437,0.1627588,0.00027846007,0.0120991375,0.02085995,0.00015733397],"about_ca_topic_score_codex":0.1319085,"about_ca_topic_score_gemma":0.42641595,"teacher_disagreement_score":0.80013067,"about_ca_system_score_codex":0.0050131883,"about_ca_system_score_gemma":0.020311449,"threshold_uncertainty_score":0.9988064},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9779304,0.0025437535,0.009157835,0.0061856355,0.0024509123,0.0009642563,0.0000055817154,0.000035552363,0.00072607625],"genre_scores_gemma":[0.9937439,0.0003021247,0.0047749053,0.0006729783,0.00028578824,0.000057851263,0.00006269189,0.000034772605,0.0000649758],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99535555,0.0026240544,0.00076262775,0.0002494902,0.0006687535,0.00033952732],"domain_scores_gemma":[0.9965927,0.00031783417,0.0005773329,0.0002632902,0.0018751683,0.00037364644],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016697127,0.00018801651,0.00023875,0.00035982585,0.0003178683,0.00016012801,0.00019830772,0.0002745641,0.0014394132],"category_scores_gemma":[0.0013117497,0.0001925999,0.00013453026,0.0005199049,0.000031212432,0.000584411,0.0000028836973,0.0004818722,0.00012040813],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021723803,0.000265155,0.07512242,0.00006375035,0.00015900613,0.0000650451,0.052898724,0.009844866,0.00037569366,0.0008600532,0.0029856486,0.8571424],"study_design_scores_gemma":[0.013391938,0.0026299055,0.13841516,0.0010014522,0.002477221,0.0018197143,0.0108579835,0.15229422,0.0008608059,0.015346447,0.6593573,0.0015478237],"about_ca_topic_score_codex":0.008165311,"about_ca_topic_score_gemma":0.015414024,"teacher_disagreement_score":0.8555946,"about_ca_system_score_codex":0.000293898,"about_ca_system_score_gemma":0.0019402211,"threshold_uncertainty_score":0.9994734},"labels":[],"label_agreement":null},{"id":"W4366678681","doi":"10.3138/cjpe.0017.003","title":"The Pitfalls and the Potential of Early Evaluation Efforts: Lessons Learned from the Health Services Sector","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Accountability; Protocol (science); Program evaluation; Outcome (game theory); Service delivery framework; Service (business); Psychology; Public relations; Process management; Computer science; Business; Medical education; Medicine; Political science; Marketing; Alternative medicine; Public administration","score_opus":0.2971180000051674,"score_gpt":0.5015325592971431,"score_spread":0.20441455929197572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366678681","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9543964,0.006664301,0.00048952637,0.03454263,0.0010688186,0.0022229857,0.00001883728,0.0000043551613,0.00059214584],"genre_scores_gemma":[0.9986508,0.00022084166,0.00036530616,0.0004881961,0.00014155122,0.000068576875,0.000008843999,0.000008223141,0.00004768752],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9911102,0.0040151346,0.0011030303,0.00020331432,0.0032880714,0.00028022693],"domain_scores_gemma":[0.9938389,0.0012801313,0.0014908133,0.00044924102,0.0027050464,0.00023583547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.055949647,0.00012519685,0.0002547297,0.00014276369,0.00095548853,0.0007609216,0.0006187178,0.00005995704,0.000571428],"category_scores_gemma":[0.0022250763,0.000055815985,0.00013586089,0.00053938385,0.0003269739,0.00040300068,0.000015921498,0.00025327233,0.000011906956],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011177121,0.000022828895,0.008701558,0.0000044771164,0.00008901554,4.187998e-7,0.006629696,0.002317073,0.000021129243,0.0049816766,0.00076896546,0.9763514],"study_design_scores_gemma":[0.0073310346,0.0010411124,0.5272668,0.00018880768,0.0005253495,0.000036798374,0.020455293,0.1766882,0.00007067976,0.20158556,0.064570114,0.00024024936],"about_ca_topic_score_codex":0.005009561,"about_ca_topic_score_gemma":0.06785122,"teacher_disagreement_score":0.9761111,"about_ca_system_score_codex":0.00020205214,"about_ca_system_score_gemma":0.005712977,"threshold_uncertainty_score":0.9999237},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8781418,0.0011395537,0.0025755686,0.046796937,0.002479595,0.0013324815,0.000004683766,0.000025664647,0.06750372],"genre_scores_gemma":[0.99725896,0.000019263753,0.0020413178,0.0001695737,0.0004418223,0.0000119113565,0.0000020638752,0.0000034159664,0.000051644558],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987539,0.00018431622,0.00019829186,0.00007520036,0.00057146937,0.0002168122],"domain_scores_gemma":[0.9988158,0.00002241748,0.00028729538,0.00004436824,0.00055257377,0.00027758558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036803605,0.00004485023,0.00007938546,0.00008168938,0.00048037025,0.00023576528,0.00015999321,0.000057873563,0.00008568599],"category_scores_gemma":[0.00066937716,0.000046074714,0.000055624154,0.00039264245,0.00016156647,0.0005616679,0.0000023748285,0.00010027722,0.000004994182],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052695527,0.000043776457,0.008356667,0.0000026728667,0.000015144836,0.000012784132,0.036744036,0.0019419002,0.000050572762,0.25774083,0.0021903366,0.692896],"study_design_scores_gemma":[0.0023329323,0.0006643414,0.16835518,0.00023333525,0.0000997225,0.000016315804,0.029983133,0.0004883728,0.00013229373,0.13831754,0.65894943,0.00042739286],"about_ca_topic_score_codex":0.18990827,"about_ca_topic_score_gemma":0.84807336,"teacher_disagreement_score":0.69246864,"about_ca_system_score_codex":0.00040747577,"about_ca_system_score_gemma":0.013589346,"threshold_uncertainty_score":0.99200267},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23240685,0.17883481,0.00041303673,0.029163903,0.011937056,0.0017622086,0.0006044765,0.000031166288,0.5448465],"genre_scores_gemma":[0.99198186,0.000116485775,0.00051726965,0.00025459746,0.0029654778,0.000041169154,0.00003144104,0.000021482136,0.0040702117],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777865,0.00082651374,0.0004103282,0.00010442784,0.0005462844,0.00033380627],"domain_scores_gemma":[0.9980745,0.000109003675,0.000403248,0.000119432625,0.00083081,0.00046304477],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004357631,0.000114878836,0.00018010597,0.00041493113,0.0010842774,0.00054916745,0.0002235641,0.000049994353,0.023343585],"category_scores_gemma":[0.00053948665,0.00012417213,0.00021093557,0.00015824617,0.00022835354,0.00011666381,0.000013833664,0.00043627742,0.000014500047],"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":[0.000016043996,0.00028181035,0.0013144792,0.000030416524,0.00045060687,0.00035549692,0.013078188,0.007863948,0.0000029526568,0.42928192,0.02256234,0.5247618],"study_design_scores_gemma":[0.00047131488,0.00040744862,0.00068037806,0.000027297723,0.0012950425,0.00012758936,0.004975552,0.016806114,0.0000042180955,0.024642214,0.9504219,0.00014090425],"about_ca_topic_score_codex":0.028426161,"about_ca_topic_score_gemma":0.0151615245,"teacher_disagreement_score":0.9278596,"about_ca_system_score_codex":0.0010015641,"about_ca_system_score_gemma":0.0050789863,"threshold_uncertainty_score":0.9780436},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38609836,0.019396707,0.020511186,0.044127163,0.10625002,0.017102921,0.00029969087,0.0004422422,0.40577173],"genre_scores_gemma":[0.99031377,0.0000061390274,0.0038112404,0.00057049363,0.003123364,0.0012915129,0.000030200516,0.00002613489,0.0008271748],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989323,0.00021463768,0.0002658982,0.00010012797,0.0003052501,0.00018178944],"domain_scores_gemma":[0.9990868,0.000019993351,0.0002357374,0.00019351029,0.00025084737,0.00021313953],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016991018,0.00005937241,0.000085647756,0.0002317584,0.00023246116,0.000031499974,0.00024057778,0.000038554197,0.012090714],"category_scores_gemma":[0.000023674203,0.00006202511,0.00007483218,0.00028398522,0.000034074357,0.000050039485,0.0000040752284,0.00026160365,0.00001510552],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013648735,0.00007084126,0.0007152871,8.3479284e-7,0.000032590804,0.00000679686,0.0007212163,0.000033865155,0.000051748335,0.0030625323,0.46070194,0.5345887],"study_design_scores_gemma":[0.00039282825,0.00044534678,0.0059144823,0.0000041779076,0.000032326698,0.00010703597,0.00046295972,0.00018948648,0.000007236017,0.00505492,0.9873178,0.00007141658],"about_ca_topic_score_codex":0.0007603403,"about_ca_topic_score_gemma":0.001237728,"teacher_disagreement_score":0.6042154,"about_ca_system_score_codex":0.0003006601,"about_ca_system_score_gemma":0.0007367085,"threshold_uncertainty_score":0.9888124},"labels":[],"label_agreement":null},{"id":"W4366679319","doi":"10.3138/cjpe.35.2.v","title":"Editor’s Remarks","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology; Business","score_opus":0.3130698758640696,"score_gpt":0.5203254987844013,"score_spread":0.20725562292033167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366679319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52900785,0.0040491326,0.027930891,0.27963135,0.053766813,0.0069849757,0.00004936131,0.000109825014,0.09846981],"genre_scores_gemma":[0.99058664,0.0000053420094,0.0038575812,0.0013054257,0.0041178796,0.000018446484,0.00000620796,0.0000075254093,0.00009497755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958979,0.00040524476,0.00080519787,0.00016036778,0.0025289329,0.00020235057],"domain_scores_gemma":[0.9951727,0.000161213,0.00056355965,0.00017884086,0.0030918855,0.0008318189],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010229976,0.00008598123,0.00018712904,0.0002938923,0.00013863586,0.00038374503,0.0004830046,0.0000647104,0.0061310297],"category_scores_gemma":[0.0065565505,0.000064959335,0.00011773652,0.0007403048,0.000056413235,0.00059451355,0.000009513816,0.00020880539,0.00028931972],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013141119,0.000012106104,0.0115501555,0.0000022819681,0.000014669857,0.000005402182,0.0012205056,0.0013830048,0.000036111567,0.00020052133,0.20221043,0.78335166],"study_design_scores_gemma":[0.00076907175,0.000649044,0.028208481,0.000020196903,0.00005483759,0.000017999322,0.0011803188,0.087478034,0.00007881379,0.004332372,0.877088,0.00012279728],"about_ca_topic_score_codex":0.00010812263,"about_ca_topic_score_gemma":0.0030603046,"teacher_disagreement_score":0.7832289,"about_ca_system_score_codex":0.00018679582,"about_ca_system_score_gemma":0.0055253017,"threshold_uncertainty_score":0.9947775},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13064277,0.2443947,0.00075603026,0.025300723,0.0071314885,0.00068272545,0.0001890354,0.000018712188,0.5908838],"genre_scores_gemma":[0.9854279,0.0005861974,0.0019141036,0.00028791415,0.0051831715,0.0000105215295,0.000037359077,0.00002323766,0.006529599],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981881,0.00056876714,0.0004217033,0.00011363414,0.00037850405,0.00032930585],"domain_scores_gemma":[0.996414,0.00012440288,0.00030932852,0.00013541541,0.002448489,0.0005683833],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024284315,0.00012122046,0.00020434165,0.00023681615,0.0003923096,0.0009389626,0.00012851729,0.00010996852,0.010759417],"category_scores_gemma":[0.0014329602,0.00012525555,0.00022974797,0.00014874463,0.00025061436,0.00014786649,0.000006256969,0.0002893187,0.000032700642],"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":[0.0000057247053,0.00021156625,0.0012888411,0.000050572853,0.0005072359,0.0008566306,0.006481401,0.00081884005,0.000008920461,0.4092085,0.010475079,0.57008666],"study_design_scores_gemma":[0.0005057712,0.00014695109,0.001392827,0.00014552151,0.0018981938,0.00018864087,0.002898057,0.008309436,0.00006777037,0.030566128,0.953722,0.0001587208],"about_ca_topic_score_codex":0.012958672,"about_ca_topic_score_gemma":0.042966418,"teacher_disagreement_score":0.9432469,"about_ca_system_score_codex":0.00048036038,"about_ca_system_score_gemma":0.008020966,"threshold_uncertainty_score":0.99760264},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98022103,0.004118596,0.0041238805,0.008970995,0.00080513634,0.00085173204,0.000020552285,0.000028651677,0.0008594406],"genre_scores_gemma":[0.9931514,0.00007813001,0.005989691,0.0005110961,0.00018090913,0.000014623678,0.000014562915,0.000009275074,0.000050304036],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97009116,0.028649691,0.00042524224,0.0001672391,0.00038153314,0.0002851231],"domain_scores_gemma":[0.9949524,0.003080184,0.00029665913,0.000081700404,0.0009330867,0.0006560103],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.086769275,0.00009373388,0.00022170668,0.00014130487,0.0005138564,0.00014847497,0.00017595016,0.00015322742,0.0001579142],"category_scores_gemma":[0.044387266,0.000096128686,0.000058953003,0.00047952266,0.00031367576,0.0002841076,0.0000059185877,0.0002773334,0.0000083854],"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":[0.0011520913,0.000046887257,0.48652288,0.00001821736,0.000113767965,0.000025634545,0.01992429,0.00015345616,0.00037646573,0.001477021,0.008010387,0.4821789],"study_design_scores_gemma":[0.0005444444,0.00026443898,0.95881414,0.00003173859,0.00006650638,0.000006088027,0.0015114759,0.00018719428,0.000055591874,0.0008503861,0.03752817,0.00013983305],"about_ca_topic_score_codex":0.03279456,"about_ca_topic_score_gemma":0.25490233,"teacher_disagreement_score":0.48203906,"about_ca_system_score_codex":0.00018421296,"about_ca_system_score_gemma":0.0045453436,"threshold_uncertainty_score":0.97364616},"labels":[],"label_agreement":null},{"id":"W4366706691","doi":"10.3138/cjpe.34.3.521","title":"Peer Reviewers for Volume 34 / Examinateurs des manuscrits du volume 34","year":2020,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Psychology; Art; Thermodynamics; Physics","score_opus":0.44556158096013765,"score_gpt":0.4911233468799333,"score_spread":0.04556176591979566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366706691","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18019208,0.08272624,0.03768063,0.66145,0.018055426,0.010945417,0.00033439175,0.000057257985,0.008558517],"genre_scores_gemma":[0.90872353,0.001576338,0.039519552,0.0052546966,0.003945916,0.00047736106,0.00016348666,0.00010473278,0.040234376],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99183095,0.0012886066,0.0018798687,0.0004831813,0.0037296505,0.00078771985],"domain_scores_gemma":[0.98130196,0.00029333917,0.0012551649,0.00033864455,0.014918064,0.0018928177],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027295433,0.00033695914,0.000630691,0.0005141935,0.0006108164,0.0011059793,0.0009028508,0.00023264028,0.011731302],"category_scores_gemma":[0.018961819,0.0003135777,0.00046130392,0.0013150497,0.00045287315,0.0018428903,0.0000290066,0.00044780393,0.0007539425],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003221082,0.000050492872,0.016492423,0.000119994686,0.00005978346,0.000016378273,0.0031754964,0.0011492248,0.00000907297,0.00030976924,0.20148015,0.777105],"study_design_scores_gemma":[0.0012451335,0.0017908213,0.020337861,0.0003097536,0.00043663045,0.00006744353,0.0033529643,0.20513165,0.000020469419,0.0027451394,0.7642815,0.0002806293],"about_ca_topic_score_codex":0.0011711783,"about_ca_topic_score_gemma":0.011237496,"teacher_disagreement_score":0.77682436,"about_ca_system_score_codex":0.0014509691,"about_ca_system_score_gemma":0.009754323,"threshold_uncertainty_score":0.99993163},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40052813,0.057557777,0.00015986328,0.0075129494,0.0058204965,0.0010762279,0.00008936279,0.000013498595,0.5272417],"genre_scores_gemma":[0.9892085,0.0001814398,0.0006632937,0.00016386701,0.0030319782,0.000008178652,0.000016040693,0.000020737094,0.0067059346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983675,0.00038311066,0.00040818818,0.000109092405,0.0003887324,0.0003433718],"domain_scores_gemma":[0.99759,0.000117662494,0.00037596334,0.00014239002,0.0012757749,0.00049817894],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029530702,0.000128816,0.00021412961,0.00034441042,0.00024224436,0.0007150358,0.00017667456,0.00011414802,0.014160823],"category_scores_gemma":[0.0005158273,0.00012481783,0.00020999036,0.00010726789,0.00020230428,0.00018354793,0.0000051194834,0.0002885928,0.00015555207],"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":[0.0000136520175,0.00017829773,0.0069220625,0.00007706481,0.00050379086,0.00011916766,0.007910335,0.0016948306,0.000008093631,0.47532684,0.007997751,0.49924812],"study_design_scores_gemma":[0.0006722757,0.00036583448,0.0027224277,0.00015708164,0.0013271376,0.00005872224,0.0020477201,0.017758623,0.000015335747,0.020517865,0.9541776,0.00017937303],"about_ca_topic_score_codex":0.020664338,"about_ca_topic_score_gemma":0.015971983,"teacher_disagreement_score":0.94617987,"about_ca_system_score_codex":0.0004919072,"about_ca_system_score_gemma":0.0038176544,"threshold_uncertainty_score":0.98674035},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91698855,0.01270334,0.000057472727,0.058666077,0.0016870145,0.0073084445,0.00013117885,0.000025359672,0.0024325652],"genre_scores_gemma":[0.9916626,0.00036106206,0.0020245449,0.0050862343,0.0004932814,0.00013378111,0.00006766018,0.00002909679,0.00014169191],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951859,0.001913349,0.0013880437,0.0001739469,0.0003944875,0.0009442383],"domain_scores_gemma":[0.9962704,0.00020619476,0.0010816631,0.00019556837,0.00074809534,0.0014980623],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0062333304,0.0001665293,0.00049047766,0.0012088218,0.00048402048,0.000012942527,0.00019268722,0.00029169492,0.0025894942],"category_scores_gemma":[0.0006124954,0.0001478486,0.0001532315,0.0006626032,0.00002994928,0.0003908949,0.00001176063,0.000967362,0.000031230476],"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":[0.000024021474,0.00002170099,0.44570827,0.00017341189,0.000037318838,0.000020810567,0.034636874,0.000076159464,0.000022592463,0.000097551696,0.029138409,0.49004287],"study_design_scores_gemma":[0.0051241685,0.0014969584,0.87443006,0.0015406909,0.00015545987,0.00009813792,0.003456869,0.023235949,0.000011256554,0.00073897303,0.08917805,0.0005334],"about_ca_topic_score_codex":0.8054817,"about_ca_topic_score_gemma":0.98353356,"teacher_disagreement_score":0.48950946,"about_ca_system_score_codex":0.0172092,"about_ca_system_score_gemma":0.020200433,"threshold_uncertainty_score":0.99832225},"labels":[],"label_agreement":null},{"id":"W4366721381","doi":"10.3138/cjpe.15.006","title":"Logic Models in Primary Care Reform: Navigating the Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Primary care; Logic model; Nova scotia; Strengths and weaknesses; Quality (philosophy); Political science; Public administration; Process management; Business; Economic growth; Medicine; Psychology; Sociology; Economics; Family medicine","score_opus":0.4326891670577493,"score_gpt":0.5423916433560159,"score_spread":0.10970247629826657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9403664,0.0025593964,0.00017703093,0.0038480964,0.00047204233,0.0020921177,0.0000058011406,0.000008605857,0.050470505],"genre_scores_gemma":[0.99734557,0.000034240653,0.001665738,0.0005179776,0.00015261887,0.00014759727,0.000039813305,0.00000964805,0.00008680016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930535,0.0012735514,0.0012239162,0.00023358518,0.0038878676,0.000327595],"domain_scores_gemma":[0.99514365,0.00017081501,0.0005827518,0.0003877822,0.0034669477,0.00024806894],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029461728,0.00013795053,0.00023216766,0.00033624299,0.00031941093,0.0004184403,0.0006356841,0.00009531771,0.0038038446],"category_scores_gemma":[0.0007618512,0.00008566247,0.00012416978,0.0011132478,0.000096017626,0.001172638,0.000010297338,0.00047605802,0.00008853933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013046743,0.000014849825,0.0026712392,0.00000345215,0.0000063220555,0.000002122456,0.003910898,0.092586264,0.000005176884,0.00017594366,0.00014111765,0.90046954],"study_design_scores_gemma":[0.0019609411,0.00044830565,0.14740767,0.00023702742,0.000112348374,0.00006022556,0.010895811,0.7681948,0.00002430668,0.06321129,0.0072179665,0.00022932191],"about_ca_topic_score_codex":0.001753441,"about_ca_topic_score_gemma":0.032365177,"teacher_disagreement_score":0.90024024,"about_ca_system_score_codex":0.002557547,"about_ca_system_score_gemma":0.0078569865,"threshold_uncertainty_score":0.9993734},"labels":[],"label_agreement":null},{"id":"W4366721395","doi":"10.3138/cjpe.0017.007","title":"Introducing Program Teams to Logic Models: Facilitating the Learning Process","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"University of Ottawa","keywords":"Logic model; Process (computing); Key (lock); Computer science; Articulation (sociology); Point (geometry); Facilitation; Knowledge management; Process management; Management science; Psychology; Business; Engineering; Sociology; Political science; Mathematics","score_opus":0.367515472877912,"score_gpt":0.5381391714975737,"score_spread":0.17062369861966176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721395","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92899436,0.0008535786,0.0388575,0.0073682875,0.0013478481,0.005143493,0.0000032450764,0.00005396156,0.017377745],"genre_scores_gemma":[0.98772985,0.0000026484843,0.011353971,0.00027332263,0.00014074724,0.00026848473,0.0000037198695,0.000011451967,0.00021578811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99434304,0.0013388993,0.001022898,0.0002991863,0.0025637108,0.00043225088],"domain_scores_gemma":[0.9940469,0.00042956337,0.00064498663,0.0003052311,0.004079579,0.0004937344],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031031672,0.00015350571,0.00023770153,0.00052804104,0.0006339829,0.0008261352,0.00057002343,0.00006613876,0.00085496897],"category_scores_gemma":[0.01641264,0.0000957489,0.00011684025,0.0014856121,0.00008308391,0.0007759884,0.00001104028,0.0004470427,0.00008554665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004734057,0.000021845628,0.003547528,0.0000031089155,0.000010497071,0.0000011146326,0.0042879926,0.3951189,0.000008428144,0.00063106796,0.000321046,0.59604377],"study_design_scores_gemma":[0.00074956164,0.0015507749,0.004239885,0.00008811879,0.000083319916,0.00007682385,0.035074487,0.8327271,0.00008107216,0.054422323,0.070626065,0.0002805128],"about_ca_topic_score_codex":0.00019218375,"about_ca_topic_score_gemma":0.0056027086,"teacher_disagreement_score":0.5957632,"about_ca_system_score_codex":0.0004017035,"about_ca_system_score_gemma":0.0047791866,"threshold_uncertainty_score":0.9977568},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46357277,0.077642865,0.16000608,0.15580271,0.00846219,0.031887773,0.0008005694,0.00013708584,0.101687975],"genre_scores_gemma":[0.9944613,0.0000771252,0.004288072,0.0008552822,0.0001034663,0.00010965567,0.000019108078,0.000013895898,0.00007207487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99876654,0.00007429621,0.0007097021,0.00014525728,0.000043486772,0.00026071482],"domain_scores_gemma":[0.9987812,0.000030387264,0.0005869043,0.000105461055,0.000093218085,0.00040284588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005236139,0.00007807423,0.0002093191,0.00043450424,0.0002984514,0.00013065778,0.000081573744,0.0000444239,0.000106197636],"category_scores_gemma":[0.00018826003,0.00009408067,0.000056393794,0.00008189912,0.00002866987,0.00021799047,0.0000030477938,0.0000648308,0.000009188461],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029512428,0.000014572772,0.006046204,0.00011959888,0.000055593213,4.0189266e-7,0.0012355648,0.0002848628,3.8465882e-7,0.9718168,0.0023324632,0.018090647],"study_design_scores_gemma":[0.0014736594,0.00073561736,0.0039523337,0.000089125504,0.000027984412,0.000014831177,0.0014527605,0.0063229683,0.0000024986962,0.41006476,0.57568735,0.0001760948],"about_ca_topic_score_codex":0.009492524,"about_ca_topic_score_gemma":0.07386603,"teacher_disagreement_score":0.5733549,"about_ca_system_score_codex":0.0015532634,"about_ca_system_score_gemma":0.0012394266,"threshold_uncertainty_score":0.99710333},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9602477,0.0034920685,0.00029907367,0.027262185,0.00030425115,0.00093566295,0.00007862851,0.000007440693,0.0073729916],"genre_scores_gemma":[0.9963754,0.00019251005,0.00069703674,0.00079041073,0.00031518989,0.000038782855,0.000013275143,0.000015791411,0.0015616062],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986998,0.00004122242,0.0007533466,0.00016552828,0.000083842446,0.0002562588],"domain_scores_gemma":[0.99869895,0.000031449552,0.0005169205,0.00021747871,0.00023473565,0.00030049033],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019760192,0.00011682824,0.00029153127,0.00027939593,0.00017962354,0.00022471533,0.00026439887,0.00008247696,0.012605739],"category_scores_gemma":[0.00015905533,0.00008172987,0.00028690533,0.00035355313,0.000068813046,0.00024520303,0.000003808049,0.00020505072,0.00027005686],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014204803,0.00014024676,0.07114547,0.000016359932,0.0008837926,0.00002719562,0.0022874495,0.008338562,0.0000021115115,0.0120849395,0.02328697,0.88164485],"study_design_scores_gemma":[0.0018742387,0.0012260675,0.12361008,0.00005952551,0.00020949134,0.0001477361,0.00020314912,0.25460246,0.0000168126,0.075500324,0.5420537,0.0004964282],"about_ca_topic_score_codex":0.009256442,"about_ca_topic_score_gemma":0.01703353,"teacher_disagreement_score":0.88114846,"about_ca_system_score_codex":0.00034332412,"about_ca_system_score_gemma":0.00091273035,"threshold_uncertainty_score":0.997341},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9315636,0.00096016534,0.038087994,0.0019664085,0.0030169308,0.004117907,0.000009933043,0.00001900292,0.02025805],"genre_scores_gemma":[0.9822742,0.0000029495147,0.016925402,0.00013843924,0.00019051907,0.00007601397,0.000004863359,0.000008342716,0.00037926654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665785,0.0003458917,0.000923781,0.00021152846,0.0015764824,0.00028446998],"domain_scores_gemma":[0.9951376,0.00034232717,0.0006080746,0.00029260165,0.0030609583,0.0005584913],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02388776,0.0001056512,0.00021628017,0.0003812995,0.0002270124,0.00042526878,0.00034878548,0.00007680935,0.0016534266],"category_scores_gemma":[0.008669934,0.000082211634,0.00015334423,0.0005436637,0.000043356107,0.00073921256,0.0000050965796,0.00012323745,0.000036131933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020445761,0.000028347564,0.07016135,0.0000053152194,0.000022426568,3.6780835e-7,0.0008858706,0.002786078,0.000029631141,0.0013872351,0.010941492,0.91373146],"study_design_scores_gemma":[0.0033974114,0.001070883,0.114584655,0.00006392237,0.00019808151,0.000065282344,0.0018114732,0.06906839,0.0009193073,0.09639748,0.71209246,0.00033065956],"about_ca_topic_score_codex":0.00031310573,"about_ca_topic_score_gemma":0.028625732,"teacher_disagreement_score":0.91340077,"about_ca_system_score_codex":0.00040335057,"about_ca_system_score_gemma":0.010238446,"threshold_uncertainty_score":0.99968046},"labels":[],"label_agreement":null},{"id":"W4366722964","doi":"10.3138/cjpe.016.006","title":"An Evaluation Framework for the Maison Decision House Substance Abuse Treatment Program","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Substance abuse; Presentation (obstetrics); Abstinence; Intervention (counseling); Program evaluation; Psychology; Substance abuse treatment; Computer science; Applied psychology; Medicine; Psychiatry; Political science","score_opus":0.4319493016960513,"score_gpt":0.5692073647062006,"score_spread":0.1372580630101493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366722964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91015905,0.0020921712,0.07469605,0.0024199523,0.002006245,0.00837365,0.0000136677545,0.00005315444,0.00018607442],"genre_scores_gemma":[0.9419998,0.00030128955,0.055136524,0.00020726405,0.0006228775,0.0016150406,0.00002464238,0.000037616224,0.00005497787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99274457,0.00089729426,0.0013527744,0.0004282746,0.00405071,0.0005263641],"domain_scores_gemma":[0.98913157,0.0017025182,0.0011285461,0.0008923074,0.006501521,0.00064353744],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026400464,0.00025893375,0.0003515045,0.0006270228,0.0007516343,0.0011720987,0.0009063035,0.00018094009,0.0015928278],"category_scores_gemma":[0.0030319751,0.00015822078,0.0002847543,0.0013325843,0.00013490944,0.0011892719,0.0000035967973,0.00023559431,0.000071261195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014836609,0.0002306742,0.014273001,0.0000014920937,0.00004562346,0.00000308881,0.0032688752,0.015836533,0.0000100698635,0.0004219253,0.000785087,0.96497524],"study_design_scores_gemma":[0.0031576364,0.004603288,0.0912153,0.000106065425,0.0005275623,0.00006854632,0.0031642702,0.64494383,0.00009564419,0.055567347,0.1962488,0.0003016839],"about_ca_topic_score_codex":0.00031127868,"about_ca_topic_score_gemma":0.053620744,"teacher_disagreement_score":0.9646736,"about_ca_system_score_codex":0.0013477666,"about_ca_system_score_gemma":0.0042086444,"threshold_uncertainty_score":0.99986476},"labels":[],"label_agreement":null},{"id":"W4366723444","doi":"10.3138/cjpe.019.006","title":"The Lay of the Land: Evaluation Practice in Canada Today","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health Canada; University of Waterloo; Treasury Board of Canada Secretariat; Government of Canada; Ministry of Education, Recreation and Sports; Ministry of Children, Community and Social Services","funders":"","keywords":"Blueprint; Public relations; Rigour; General partnership; Variety (cybernetics); Psychology; Program evaluation; Competence (human resources); Political science; Medical education; Sociology; Computer science; Social psychology; Medicine; Public administration; Engineering","score_opus":0.22766863648326166,"score_gpt":0.5077868401683105,"score_spread":0.2801182036850489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95733815,0.0016703379,0.00009157909,0.032253426,0.0020799336,0.0018857163,0.0000067873207,0.0000018754652,0.004672209],"genre_scores_gemma":[0.99909425,0.000023026329,0.00039269705,0.0003272065,0.000073788164,0.000049621205,0.0000022876814,0.0000050225394,0.000032122618],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9928027,0.001370681,0.0010518067,0.00013220384,0.0044046463,0.00023800817],"domain_scores_gemma":[0.9930322,0.0008939496,0.001159818,0.00036957013,0.004367837,0.00017663123],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033709284,0.0000879633,0.00015759148,0.00020011913,0.00026398967,0.00018196549,0.00065725937,0.000041655305,0.00033289572],"category_scores_gemma":[0.016311144,0.0000466107,0.00007688431,0.0010106079,0.000078972196,0.00051076256,0.000014467427,0.00024859203,0.000007957528],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022168302,0.000027540313,0.063515656,0.0000017630013,0.000021608426,0.0000023780276,0.0012477881,0.09099854,0.000011868655,0.000497538,0.0012184287,0.8424347],"study_design_scores_gemma":[0.0030340431,0.00030396387,0.80854696,0.00013432473,0.0001868281,0.00007425074,0.0077985274,0.042039,0.00031907263,0.02694518,0.11044127,0.00017657042],"about_ca_topic_score_codex":0.6249642,"about_ca_topic_score_gemma":0.9963583,"teacher_disagreement_score":0.84225816,"about_ca_system_score_codex":0.0022516372,"about_ca_system_score_gemma":0.06220436,"threshold_uncertainty_score":0.99499965},"labels":[],"label_agreement":null},{"id":"W4366723551","doi":"10.3138/cjpe.0020.009","title":"Evaluating School Improvement in Canada: A Case Example","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Shared Health","funders":"","keywords":"Work (physics); Action (physics); Management science; Psychology; Engineering ethics; Process management; Political science; Business; Engineering","score_opus":0.4300939707557752,"score_gpt":0.5277537046643593,"score_spread":0.09765973390858412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946879,0.00034579798,0.00022993448,0.0010403991,0.00071462395,0.0011518404,0.0000103147395,0.0000037991208,0.0018153707],"genre_scores_gemma":[0.9959395,0.0000014994697,0.0033864882,0.00020537396,0.00020808101,0.00010035193,0.000011803673,0.0000099126555,0.00013699726],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99404883,0.00057829916,0.0016126243,0.00025714305,0.0030818146,0.00042125845],"domain_scores_gemma":[0.9954124,0.00029723046,0.0008581113,0.0003178005,0.0026195624,0.00049489894],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021045182,0.00014255225,0.00026972752,0.00075035245,0.00019953039,0.00033444012,0.0003589426,0.000051239498,0.0035707105],"category_scores_gemma":[0.0026578044,0.00011734617,0.000080075224,0.0010044095,0.000035462388,0.00055435585,0.000014201557,0.00026072154,0.000030608022],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000010938073,0.00003249814,0.12294089,0.0000036728554,0.000010027029,0.00027460366,0.00019260416,0.023975717,0.00010348437,0.0001382924,0.003516437,0.84880084],"study_design_scores_gemma":[0.0037914468,0.000992781,0.52443314,0.000091242175,0.00010411675,0.0011431391,0.0053563,0.42957702,0.000272111,0.012845618,0.020984164,0.00040890227],"about_ca_topic_score_codex":0.9705993,"about_ca_topic_score_gemma":0.99938196,"teacher_disagreement_score":0.84839195,"about_ca_system_score_codex":0.0042477488,"about_ca_system_score_gemma":0.053144295,"threshold_uncertainty_score":0.9995748},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9850242,0.0003130531,0.000060343667,0.011438997,0.0004511835,0.001662732,8.63433e-7,0.0000052774685,0.0010433092],"genre_scores_gemma":[0.99773234,0.0000035082803,0.00045235362,0.00046884848,0.0001768498,0.00023127603,0.00001631126,0.000010203139,0.000908335],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979311,0.00054268795,0.0005327522,0.00015602772,0.00044360964,0.000393829],"domain_scores_gemma":[0.9990394,0.00007307707,0.00017070422,0.00016793056,0.00027522512,0.00027364556],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070839133,0.000107244174,0.00015170858,0.0004931122,0.00010276633,0.00006382655,0.00019040822,0.00008204355,0.001393877],"category_scores_gemma":[0.00045122334,0.0000806478,0.00003483727,0.0008998605,0.00002636984,0.00010465139,0.000007520669,0.0002901715,0.00015799025],"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":[0.00031131628,0.00010578455,0.6663354,0.00000790815,0.000034904904,0.00003454877,0.117032334,0.019562704,0.000013113342,0.0002124915,0.004804255,0.19154522],"study_design_scores_gemma":[0.00062353304,0.00032300878,0.89007413,0.00014587278,0.000031407788,0.000018891104,0.006695431,0.0030855825,0.000003703847,0.000071199895,0.09882025,0.00010699867],"about_ca_topic_score_codex":0.0015616255,"about_ca_topic_score_gemma":0.16333346,"teacher_disagreement_score":0.2237387,"about_ca_system_score_codex":0.0007790904,"about_ca_system_score_gemma":0.00078982743,"threshold_uncertainty_score":0.999519},"labels":[],"label_agreement":null},{"id":"W4366723971","doi":"10.3138/cjpe.69574","title":"Strategies for Mentoring and Advising Evaluation Graduate Students of Colour","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ethnic group; Graduate students; Competence (human resources); Psychology; Salient; Cultural competence; Pedagogy; Medical education; Facilitation; Identity (music); Sociology; Social psychology; Medicine; Political science","score_opus":0.6206350525934264,"score_gpt":0.6121351996873615,"score_spread":0.00849985290606492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366723971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929984,0.00095531,0.0021982645,0.00090850436,0.0008156063,0.0012077217,0.000007859189,0.000003309257,0.000905001],"genre_scores_gemma":[0.9950054,0.00002193406,0.0046511507,0.000046248104,0.00010531647,0.00007355754,0.000014253723,0.0000073827505,0.00007472328],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947621,0.0005855638,0.0009478322,0.00019559606,0.0032987734,0.00021012829],"domain_scores_gemma":[0.989743,0.0002967427,0.00082175684,0.00018329869,0.008700674,0.00025451498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025287848,0.00009969567,0.0002504698,0.00041003223,0.00018861442,0.0006252756,0.0002471113,0.000054660773,0.0003619598],"category_scores_gemma":[0.0031065305,0.00008476281,0.00009492456,0.0005087145,0.00006309651,0.0007885097,0.000016351874,0.000103097635,0.0000025605923],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025744614,0.000059809197,0.027032034,0.000020400335,0.00007315041,0.0000023204987,0.0033648366,0.004578826,0.0006608844,0.0009656796,0.0006807494,0.96253556],"study_design_scores_gemma":[0.006883852,0.0017311303,0.48341492,0.00038270885,0.0008960406,0.000088716275,0.05110603,0.32761562,0.0028392768,0.10868774,0.01595386,0.00040010057],"about_ca_topic_score_codex":0.00011545256,"about_ca_topic_score_gemma":0.0055526,"teacher_disagreement_score":0.96213543,"about_ca_system_score_codex":0.00029486543,"about_ca_system_score_gemma":0.008093042,"threshold_uncertainty_score":0.99753016},"labels":[],"label_agreement":null},{"id":"W4366724034","doi":"10.3138/cjpe.019.001","title":"Toward a Best Practice for Evaluating the Impact of Government Programs on Job Creation","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Industry Canada","keywords":"Government (linguistics); Interpretation (philosophy); Strengths and weaknesses; Computer science; Management science; Engineering; Psychology","score_opus":0.5293612574148838,"score_gpt":0.6057482510986992,"score_spread":0.07638699368381541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366724034","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97755563,0.00029994783,0.0059277005,0.0068345247,0.0005835471,0.004501705,0.000028109569,0.000006702105,0.0042621135],"genre_scores_gemma":[0.98928976,0.000010437707,0.010035341,0.00010448677,0.00018340311,0.00026845394,0.00001085165,0.000012929036,0.000084350584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934768,0.0006118919,0.0011853502,0.0002173905,0.0042052846,0.00030327198],"domain_scores_gemma":[0.9918616,0.0008921915,0.0017912575,0.00035347466,0.004802335,0.00029913583],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026141243,0.00015903065,0.00026753478,0.00023863793,0.00028097208,0.00042799482,0.0005063194,0.000077861754,0.0002888215],"category_scores_gemma":[0.014999791,0.00009291763,0.00032959238,0.00070214015,0.00011277907,0.00074654724,0.000011011172,0.00020651364,0.000024568819],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022683232,0.00030321142,0.004665802,0.000006572122,0.0000987406,0.0000013207481,0.0029165526,0.074580505,0.00011231406,0.0010976166,0.00038571446,0.9156048],"study_design_scores_gemma":[0.021033894,0.1482309,0.16913868,0.0014045116,0.0022922885,0.00043625807,0.045681998,0.46767595,0.0018991004,0.10805155,0.032987516,0.0011673479],"about_ca_topic_score_codex":0.0017871564,"about_ca_topic_score_gemma":0.0038154824,"teacher_disagreement_score":0.9144375,"about_ca_system_score_codex":0.0017667419,"about_ca_system_score_gemma":0.007049449,"threshold_uncertainty_score":0.9985797},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9052779,0.0001592029,0.09131055,0.00073453,0.000041597552,0.0010118667,0.0000075382513,0.00006923676,0.0013875853],"genre_scores_gemma":[0.908368,0.00015802501,0.090537384,0.00007107864,0.00014933795,0.0006021954,0.000039903272,0.00003546103,0.000038640723],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99597996,0.0020347054,0.00046281307,0.0002567724,0.0003831787,0.00088258984],"domain_scores_gemma":[0.99842095,0.00012490446,0.00039160898,0.0001544698,0.0001035524,0.00080448657],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0058504115,0.0002500594,0.00021485232,0.0002253634,0.0009573875,0.0004649668,0.00026507862,0.00038847883,0.00007803068],"category_scores_gemma":[0.0011647663,0.0002577812,0.00018630226,0.0005765932,0.000695669,0.00093222834,0.000024534735,0.00053916115,0.0000030138624],"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":[0.000022333967,0.00096530013,0.6652139,0.00003119073,0.00011196378,0.000040888488,0.023232682,0.02553756,0.028298482,0.00041412193,0.00011750383,0.25601408],"study_design_scores_gemma":[0.000790728,0.0005060192,0.94444793,0.00008333765,0.0003181407,0.00090691826,0.00871967,0.0061097993,0.010199916,0.026794648,0.0008247892,0.00029809083],"about_ca_topic_score_codex":0.12740645,"about_ca_topic_score_gemma":0.41043803,"teacher_disagreement_score":0.28303158,"about_ca_system_score_codex":0.012686222,"about_ca_system_score_gemma":0.0066535613,"threshold_uncertainty_score":0.9999874},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9579992,0.00022277112,0.000030148574,0.0352657,0.00030107392,0.005067806,0.000008032342,0.000010551205,0.0010946594],"genre_scores_gemma":[0.9737408,0.000020646688,0.014887818,0.010542856,0.000112665635,0.0006293304,0.000019984092,0.000013857596,0.000032038046],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96654797,0.030873274,0.0012124364,0.00009326617,0.00043015456,0.00084293186],"domain_scores_gemma":[0.9967221,0.0016638014,0.0003372163,0.0003283785,0.0004305725,0.00051792426],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.052531023,0.00013771778,0.0004190327,0.0007338165,0.0011912141,0.000032116124,0.00043057068,0.00012979381,0.00029653704],"category_scores_gemma":[0.0028430016,0.00010984481,0.000051609575,0.001130272,0.000053828036,0.00015010082,0.000020401927,0.0027434435,0.000023503828],"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":[0.00021013049,0.00031903168,0.19685271,0.00031657223,0.000017797975,0.000013425866,0.26681313,0.00024675994,0.000013842302,0.0002817872,0.013471106,0.5214437],"study_design_scores_gemma":[0.0027070527,0.0009936248,0.8181653,0.0012241633,0.000017623537,0.000102310834,0.07501564,0.0012607493,0.0000015433122,0.0021416051,0.09815094,0.00021944496],"about_ca_topic_score_codex":0.28171712,"about_ca_topic_score_gemma":0.9415857,"teacher_disagreement_score":0.6598686,"about_ca_system_score_codex":0.0023007414,"about_ca_system_score_gemma":0.022043467,"threshold_uncertainty_score":0.99955726},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884766,0.00029247304,0.00009680328,0.007331121,0.0010934375,0.0006104242,0.0000013350718,0.000008228521,0.0020896157],"genre_scores_gemma":[0.99412113,0.000023392437,0.002045006,0.002839612,0.00062278466,0.00005919077,0.000035292618,0.000014772514,0.00023881871],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99818563,0.00016935811,0.00041305507,0.00012957907,0.00087199244,0.00023040485],"domain_scores_gemma":[0.997634,0.000040532963,0.00021758332,0.00021824458,0.0017077898,0.00018188255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027644325,0.00010226613,0.00015948815,0.00024416024,0.00023326429,0.00009668648,0.00018751873,0.0000736144,0.0004259791],"category_scores_gemma":[0.0015059097,0.00006968454,0.000081054655,0.0006168279,0.0001025848,0.00013858244,0.000009139763,0.0005144938,0.000026499269],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003078409,0.00024780456,0.03240775,0.000030407156,0.00009200708,0.000010826493,0.003477607,0.00005602638,0.00019233483,0.000027238037,0.00862072,0.9548065],"study_design_scores_gemma":[0.004240984,0.0031555726,0.788655,0.003204029,0.00061997,0.0018933981,0.011878366,0.02135173,0.0057269256,0.00041727486,0.15847605,0.0003807297],"about_ca_topic_score_codex":0.00004333533,"about_ca_topic_score_gemma":0.0005598191,"teacher_disagreement_score":0.95442575,"about_ca_system_score_codex":0.0008714278,"about_ca_system_score_gemma":0.00368718,"threshold_uncertainty_score":0.6540899},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23240685,0.17883481,0.00041303673,0.029163903,0.011937056,0.0017622086,0.0006044765,0.000031166288,0.5448465],"genre_scores_gemma":[0.99198186,0.000116485775,0.00051726965,0.00025459746,0.0029654778,0.000041169154,0.00003144104,0.000021482136,0.0040702117],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777865,0.00082651374,0.0004103282,0.00010442784,0.0005462844,0.00033380627],"domain_scores_gemma":[0.9980745,0.000109003675,0.000403248,0.000119432625,0.00083081,0.00046304477],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004357631,0.000114878836,0.00018010597,0.00041493113,0.0010842774,0.00054916745,0.0002235641,0.000049994353,0.023343585],"category_scores_gemma":[0.00053948665,0.00012417213,0.00021093557,0.00015824617,0.00022835354,0.00011666381,0.000013833664,0.00043627742,0.000014500047],"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":[0.000016043996,0.00028181035,0.0013144792,0.000030416524,0.00045060687,0.00035549692,0.013078188,0.007863948,0.0000029526568,0.42928192,0.02256234,0.5247618],"study_design_scores_gemma":[0.00047131488,0.00040744862,0.00068037806,0.000027297723,0.0012950425,0.00012758936,0.004975552,0.016806114,0.0000042180955,0.024642214,0.9504219,0.00014090425],"about_ca_topic_score_codex":0.028426161,"about_ca_topic_score_gemma":0.0151615245,"teacher_disagreement_score":0.9278596,"about_ca_system_score_codex":0.0010015641,"about_ca_system_score_gemma":0.0050789863,"threshold_uncertainty_score":0.9780436},"labels":[],"label_agreement":null},{"id":"W4366725054","doi":"10.3138/cjpe.36.1.intro-eng","title":"Editor’s Remarks","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Philosophy; Psychology","score_opus":0.24907328656822922,"score_gpt":0.5260421824238015,"score_spread":0.2769688958555723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66646135,0.00848469,0.013335736,0.060082927,0.09410904,0.0032767758,0.000038588798,0.000057031946,0.15415385],"genre_scores_gemma":[0.9874534,0.00001558392,0.007574041,0.0004703086,0.003367456,0.00002437757,0.000015936552,0.000008693564,0.0010701943],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955894,0.00059480726,0.00080670515,0.00016702883,0.0026236614,0.00021839343],"domain_scores_gemma":[0.99150455,0.00022448297,0.0004972822,0.0003039837,0.0069848844,0.0004848157],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014229705,0.0000816102,0.00018418452,0.0003943422,0.00016976148,0.0005016518,0.00033342568,0.00007408231,0.009902852],"category_scores_gemma":[0.0070112874,0.000064475185,0.00013294282,0.0008305793,0.000053689728,0.00055873836,0.0000106177695,0.00019507862,0.00017803586],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004771146,0.00002726466,0.013244866,0.0000018085882,0.000018455205,0.000020942118,0.00042631634,0.00077422464,0.000060187565,0.0003956445,0.1209155,0.86411],"study_design_scores_gemma":[0.0007432926,0.00022337108,0.060123153,0.000040304654,0.00006494038,0.00012366119,0.0014823956,0.019062001,0.00034195877,0.0147848455,0.9028835,0.000126558],"about_ca_topic_score_codex":0.00011833131,"about_ca_topic_score_gemma":0.016689826,"teacher_disagreement_score":0.86398345,"about_ca_system_score_codex":0.00030759434,"about_ca_system_score_gemma":0.012715749,"threshold_uncertainty_score":0.99288124},"labels":[],"label_agreement":null},{"id":"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38609836,0.019396707,0.020511186,0.044127163,0.10625002,0.017102921,0.00029969087,0.0004422422,0.40577173],"genre_scores_gemma":[0.99031377,0.0000061390274,0.0038112404,0.00057049363,0.003123364,0.0012915129,0.000030200516,0.00002613489,0.0008271748],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989323,0.00021463768,0.0002658982,0.00010012797,0.0003052501,0.00018178944],"domain_scores_gemma":[0.9990868,0.000019993351,0.0002357374,0.00019351029,0.00025084737,0.00021313953],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016991018,0.00005937241,0.000085647756,0.0002317584,0.00023246116,0.000031499974,0.00024057778,0.000038554197,0.012090714],"category_scores_gemma":[0.000023674203,0.00006202511,0.00007483218,0.00028398522,0.000034074357,0.000050039485,0.0000040752284,0.00026160365,0.00001510552],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013648735,0.00007084126,0.0007152871,8.3479284e-7,0.000032590804,0.00000679686,0.0007212163,0.000033865155,0.000051748335,0.0030625323,0.46070194,0.5345887],"study_design_scores_gemma":[0.00039282825,0.00044534678,0.0059144823,0.0000041779076,0.000032326698,0.00010703597,0.00046295972,0.00018948648,0.000007236017,0.00505492,0.9873178,0.00007141658],"about_ca_topic_score_codex":0.0007603403,"about_ca_topic_score_gemma":0.001237728,"teacher_disagreement_score":0.6042154,"about_ca_system_score_codex":0.0003006601,"about_ca_system_score_gemma":0.0007367085,"threshold_uncertainty_score":0.9888124},"labels":[],"label_agreement":null},{"id":"W4366725272","doi":"10.3138/cjpe.19.006","title":"Integrating Evaluative Inquiry into the Organizational Culture: A Review and Synthesis of the Knowledge Base","year":2004,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Knowledge management; Organizational culture; Organizational learning; Knowledge base; Conceptual framework; Empirical research; Sociology; Work (physics); Management science; Epistemology; Political science; Computer science; Public relations; Social science; Engineering","score_opus":0.3839810064574307,"score_gpt":0.5592321866859272,"score_spread":0.1752511802284965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366725272","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002965983,0.9939319,0.000115029936,0.0013822453,0.00066675333,0.0032004537,0.000015249584,0.0000035734142,0.00065512647],"genre_scores_gemma":[0.0019391691,0.99548846,0.0016003347,0.00020841787,0.0002584776,0.00034213148,0.00002112166,0.000028471119,0.00011341261],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907445,0.0039532837,0.0022614903,0.0003208791,0.0024737138,0.0002461489],"domain_scores_gemma":[0.98723143,0.0014413737,0.0034090765,0.0005855007,0.007030153,0.00030246054],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031963017,0.00032503402,0.0011955436,0.00047206323,0.0004879673,0.00029139727,0.0012788922,0.00018445292,0.0011147165],"category_scores_gemma":[0.033977337,0.00014422815,0.00046373307,0.0027182798,0.00044949408,0.00035246677,0.000074266114,0.00062508316,0.00003371994],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[8.683301e-7,0.000029654342,0.00004999515,0.0018073716,0.0001026794,4.922361e-7,0.004615124,0.000018903807,1.0445794e-7,0.00057961233,0.0015902461,0.991205],"study_design_scores_gemma":[0.00041371604,0.00025500494,0.00035918053,0.0577091,0.006331761,0.0001734913,0.0026715177,0.00083183736,0.0000042755896,0.007302665,0.9236063,0.0003411495],"about_ca_topic_score_codex":0.0001483265,"about_ca_topic_score_gemma":0.006192862,"teacher_disagreement_score":0.9908638,"about_ca_system_score_codex":0.0010366212,"about_ca_system_score_gemma":0.03164942,"threshold_uncertainty_score":0.9997984},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1357311,0.16651362,0.0019575278,0.13829799,0.005630152,0.001806561,0.0003147792,0.000045834226,0.5497024],"genre_scores_gemma":[0.9907136,0.00022618534,0.0010681461,0.00076637993,0.0064468132,0.000008411161,0.000016339975,0.000021084143,0.0007330587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840045,0.00039777716,0.00042064543,0.0001093611,0.0003654922,0.00030628938],"domain_scores_gemma":[0.99740046,0.00009143806,0.00034619728,0.00008291472,0.001147942,0.0009310533],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017762363,0.00012718134,0.00020719366,0.00018038102,0.0003259082,0.00073079974,0.00018076105,0.000097010714,0.00680096],"category_scores_gemma":[0.0013455988,0.00012614288,0.00020524887,0.00013383917,0.0002621826,0.00015613681,0.0000056592385,0.00030832196,0.0000516633],"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":[0.000019155654,0.00013144487,0.0014889578,0.00008212406,0.00053841836,0.000325566,0.022094257,0.0018129573,0.0000073227448,0.32254454,0.023805546,0.6271497],"study_design_scores_gemma":[0.0005319347,0.00039925455,0.0006975265,0.000077771365,0.0016578132,0.000032935364,0.0023493282,0.034848098,0.000018031336,0.010400374,0.94882995,0.00015700684],"about_ca_topic_score_codex":0.011858761,"about_ca_topic_score_gemma":0.009236932,"teacher_disagreement_score":0.9250244,"about_ca_system_score_codex":0.0003045457,"about_ca_system_score_gemma":0.0037287355,"threshold_uncertainty_score":0.99472135},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9544798,0.005996425,0.01103217,0.006949329,0.00084252027,0.00042083656,0.0000037812442,0.00010209209,0.020173004],"genre_scores_gemma":[0.99848217,0.000028169794,0.0011708929,0.00012242983,0.00015614612,0.0000059831277,0.0000034693142,0.0000079364,0.000022801958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995572,0.00003054974,0.00015421292,0.000042772594,0.00012442235,0.00009083136],"domain_scores_gemma":[0.99955416,0.000008495201,0.00004596388,0.000031474727,0.00009930829,0.0002605839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003131601,0.000045989284,0.0000649665,0.00008091933,0.000039428654,0.00004561589,0.000043234664,0.000027360045,0.000071797745],"category_scores_gemma":[0.00009090041,0.0000442821,0.000019980325,0.000095231044,0.0000115958,0.0000625821,0.0000018975707,0.00005997495,0.0000026582015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014708355,0.0000013659314,0.0007602436,0.000015336018,0.000025795687,0.0000051330553,0.0008080345,0.012998545,0.000038474052,0.000117740914,0.0033660445,0.9818618],"study_design_scores_gemma":[0.00047594673,0.00022469889,0.0058071148,0.00003816478,0.00009174796,0.000018076224,0.0003900152,0.6690122,0.00010755904,0.00026773708,0.32345143,0.00011531205],"about_ca_topic_score_codex":0.00008649577,"about_ca_topic_score_gemma":0.0004945913,"teacher_disagreement_score":0.9817465,"about_ca_system_score_codex":0.00007442034,"about_ca_system_score_gemma":0.00011034093,"threshold_uncertainty_score":0.18057716},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1357311,0.16651362,0.0019575278,0.13829799,0.005630152,0.001806561,0.0003147792,0.000045834226,0.5497024],"genre_scores_gemma":[0.9907136,0.00022618534,0.0010681461,0.00076637993,0.0064468132,0.000008411161,0.000016339975,0.000021084143,0.0007330587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840045,0.00039777716,0.00042064543,0.0001093611,0.0003654922,0.00030628938],"domain_scores_gemma":[0.99740046,0.00009143806,0.00034619728,0.00008291472,0.001147942,0.0009310533],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017762363,0.00012718134,0.00020719366,0.00018038102,0.0003259082,0.00073079974,0.00018076105,0.000097010714,0.00680096],"category_scores_gemma":[0.0013455988,0.00012614288,0.00020524887,0.00013383917,0.0002621826,0.00015613681,0.0000056592385,0.00030832196,0.0000516633],"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":[0.000019155654,0.00013144487,0.0014889578,0.00008212406,0.00053841836,0.000325566,0.022094257,0.0018129573,0.0000073227448,0.32254454,0.023805546,0.6271497],"study_design_scores_gemma":[0.0005319347,0.00039925455,0.0006975265,0.000077771365,0.0016578132,0.000032935364,0.0023493282,0.034848098,0.000018031336,0.010400374,0.94882995,0.00015700684],"about_ca_topic_score_codex":0.011858761,"about_ca_topic_score_gemma":0.009236932,"teacher_disagreement_score":0.9250244,"about_ca_system_score_codex":0.0003045457,"about_ca_system_score_gemma":0.0037287355,"threshold_uncertainty_score":0.99472135},"labels":[],"label_agreement":null},{"id":"W4366726230","doi":"10.3138/cjpe.35.3.473","title":"Peer Reviewers for Volume 35 and Manuscripts Submitted in 2020 / Examinateurs et examinatrices des manuscrits du volume 35 et des manuscrits soumis en 2020","year":2021,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Art; Humanities; Psychology; Physics","score_opus":0.2671932895686844,"score_gpt":0.46999302576202445,"score_spread":0.20279973619334007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8085819,0.09597771,0.0020517528,0.08493051,0.003497959,0.003208686,0.0002215164,0.000020381904,0.0015096075],"genre_scores_gemma":[0.9169813,0.017256794,0.028113235,0.0019635728,0.0007666412,0.0004334652,0.00033102214,0.00009688812,0.034057118],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9886049,0.004339749,0.0021605373,0.0008075732,0.00306683,0.0010204073],"domain_scores_gemma":[0.98696065,0.0008627511,0.0010774274,0.00044458208,0.009459217,0.0011953998],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040215615,0.0005111717,0.0008819715,0.00091880537,0.0005372673,0.001706701,0.0006949181,0.0003692338,0.0029200325],"category_scores_gemma":[0.016493341,0.00050917285,0.00032387843,0.0021140105,0.00058455596,0.0029834106,0.00008009687,0.00073726935,0.00008275478],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045875633,0.00017977206,0.1402274,0.0003768777,0.00008528513,0.00023682242,0.007638164,0.00055317493,0.000052048938,0.00020777322,0.04828731,0.8021095],"study_design_scores_gemma":[0.0025739255,0.001112519,0.5871414,0.0014033096,0.00051630044,0.0006138471,0.009029606,0.04407541,0.00007397331,0.007007673,0.3458993,0.00055269356],"about_ca_topic_score_codex":0.0028490338,"about_ca_topic_score_gemma":0.13016106,"teacher_disagreement_score":0.8015568,"about_ca_system_score_codex":0.0013442124,"about_ca_system_score_gemma":0.007346056,"threshold_uncertainty_score":0.999736},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5820639,0.045243893,0.00013859845,0.35411796,0.0050958088,0.0029738098,0.00008647457,0.000036576723,0.010242984],"genre_scores_gemma":[0.9693538,0.0015878266,0.004442686,0.0010487288,0.0024968658,0.000118303695,0.00062993745,0.0000073493825,0.020314492],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960579,0.001117466,0.00073426607,0.00029877922,0.0011556426,0.0006359445],"domain_scores_gemma":[0.99468803,0.00019680567,0.0004160328,0.0000853764,0.0038111485,0.0008025949],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037439668,0.00023649127,0.0003301667,0.0000978604,0.00044450987,0.00047931264,0.0002884875,0.0003011449,0.008845331],"category_scores_gemma":[0.0013939673,0.00011442438,0.00024840003,0.0011778387,0.00016974274,0.0006253463,0.000030978223,0.00051293534,0.00026170976],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012890933,0.00017800566,0.0037202237,0.000030928604,0.00010666648,0.00012697725,0.0010098068,0.00023563298,0.0039336532,0.0022587632,0.04416349,0.944223],"study_design_scores_gemma":[0.00082363177,0.0012174527,0.56244195,0.0006295982,0.00036622718,0.0006341433,0.0023882487,0.0023268056,0.0017080661,0.0070850495,0.4199229,0.00045596258],"about_ca_topic_score_codex":0.004081862,"about_ca_topic_score_gemma":0.08515842,"teacher_disagreement_score":0.943767,"about_ca_system_score_codex":0.0004532084,"about_ca_system_score_gemma":0.004657006,"threshold_uncertainty_score":0.9920607},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9121563,0.005830688,0.011141141,0.06702594,0.00027562678,0.0010427816,0.000037342757,0.000064449494,0.0024257554],"genre_scores_gemma":[0.9844439,0.00027193697,0.014498486,0.00048273616,0.00018583401,0.00006454027,0.000016343021,0.00001923555,0.00001700592],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968747,0.00063282234,0.0017184595,0.00022596026,0.00017964482,0.00036845152],"domain_scores_gemma":[0.9971847,0.00040014333,0.0014845297,0.00024387192,0.00042138196,0.0002654061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018415872,0.00015828766,0.00043682332,0.0006726503,0.0005526378,0.00012914339,0.0003368356,0.00018964648,0.00017857536],"category_scores_gemma":[0.0073802453,0.00019168398,0.00013696635,0.00026745026,0.00044578285,0.0005344929,0.000015622796,0.00024150763,0.00007581653],"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":[0.000031730313,0.0002868801,0.5457629,0.00017889643,0.000286057,0.00003820753,0.05004736,0.026754621,0.00002479607,0.05555686,0.022432085,0.2985996],"study_design_scores_gemma":[0.005891474,0.0013638122,0.46486744,0.00054170523,0.00020412264,0.0005562046,0.08441142,0.01987341,0.00014272175,0.19045296,0.23075232,0.00094238936],"about_ca_topic_score_codex":0.06341092,"about_ca_topic_score_gemma":0.11776311,"teacher_disagreement_score":0.2976572,"about_ca_system_score_codex":0.0068562105,"about_ca_system_score_gemma":0.0062530753,"threshold_uncertainty_score":0.9993805},"labels":[],"label_agreement":null},{"id":"W4366726740","doi":"10.3138/cjpe.19.003","title":"Stakeholder Involvement in a Government-Funded Outcome Evaluation: Lessons from the Front Line","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"","keywords":"Workload; Stakeholder; Government (linguistics); Strengths and weaknesses; Front line; Process (computing); Outcome (game theory); Data collection; Process management; Public relations; Program evaluation; Psychology; Business; Medical education; Knowledge management; Political science; Medicine; Computer science; Sociology; Public administration; Social psychology","score_opus":0.6625327886142328,"score_gpt":0.5396214187531866,"score_spread":0.12291136986104623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366726740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94737786,0.0017687388,0.0019842577,0.04230648,0.0016711856,0.0030367018,0.000058567806,0.0000091145275,0.0017870659],"genre_scores_gemma":[0.99570847,0.00001657276,0.002552383,0.001095412,0.0002826467,0.00020006206,0.000032219865,0.000012061375,0.000100192454],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99005085,0.0009635779,0.0016566437,0.00031444844,0.006651932,0.000362531],"domain_scores_gemma":[0.99561816,0.00040110652,0.0009792808,0.0005427422,0.0020857372,0.00037298587],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028095014,0.00018245897,0.00031340861,0.0002672546,0.00025825313,0.0005641945,0.00079197553,0.00009498122,0.0048917327],"category_scores_gemma":[0.00403271,0.00011894825,0.00015091345,0.0006796667,0.00010126154,0.000686403,0.000027861328,0.00036640608,0.00012394278],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034813613,0.0001633526,0.14387776,0.0000021669528,0.00006019249,0.000009338455,0.0054415683,0.04911865,0.00003590097,0.00073571794,0.0015560898,0.79896444],"study_design_scores_gemma":[0.0073620654,0.00061669794,0.8170996,0.0001566142,0.0002814468,0.000012740972,0.013593847,0.059903234,0.00015080956,0.069750935,0.030755898,0.0003161299],"about_ca_topic_score_codex":0.0054132645,"about_ca_topic_score_gemma":0.40579924,"teacher_disagreement_score":0.7986483,"about_ca_system_score_codex":0.0029772497,"about_ca_system_score_gemma":0.0060575656,"threshold_uncertainty_score":0.99957716},"labels":[],"label_agreement":null},{"id":"W4366728118","doi":"10.3138/cjpe.0016.003","title":"Evaluation in the Government of Alberta: Adapting to the “New Way”","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Government of Alberta","keywords":"Scrutiny; Government (linguistics); Meaning (existential); Emphasis (telecommunications); Focus (optics); Empowerment; Process management; Public relations; Management science; Political science; Sociology; Business; Computer science; Epistemology; Economics; Law","score_opus":0.4323374369274828,"score_gpt":0.49519588504531975,"score_spread":0.06285844811783697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8805529,0.0016504561,0.001487694,0.076815225,0.0013474543,0.0047011822,0.0000055646883,0.000003551823,0.033436],"genre_scores_gemma":[0.9979646,0.000009703971,0.00092866074,0.000559415,0.00019434514,0.00007694732,0.0000012292345,0.0000055233327,0.00025957302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9883861,0.0016191414,0.001111898,0.00016949902,0.008464206,0.000249135],"domain_scores_gemma":[0.9961305,0.00071636273,0.00071515515,0.00039105513,0.0018244585,0.00022242422],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052082513,0.00010147983,0.00017572877,0.00026080082,0.00016538614,0.00024360318,0.0007817299,0.000046754685,0.0045592976],"category_scores_gemma":[0.00996808,0.000054778215,0.00010253684,0.0011640284,0.000040669976,0.00037199695,0.000013616116,0.00019415191,0.000068033776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060643165,0.00003290709,0.0046204273,0.0000010050932,0.000011645282,6.389798e-7,0.010055653,0.017673649,0.000018170196,0.00026290264,0.0147359725,0.952581],"study_design_scores_gemma":[0.0016155296,0.0008340789,0.15805478,0.000118816264,0.00023703891,0.000028502138,0.015791455,0.65330917,0.00012081587,0.006214163,0.16349764,0.00017800074],"about_ca_topic_score_codex":0.0016069339,"about_ca_topic_score_gemma":0.13631433,"teacher_disagreement_score":0.95240295,"about_ca_system_score_codex":0.0005150855,"about_ca_system_score_gemma":0.0017836145,"threshold_uncertainty_score":0.99837136},"labels":[],"label_agreement":null},{"id":"W4366728120","doi":"10.3138/cjpe.0016.002","title":"Program Evaluation in British Columbia in a Time of Transition: 1995-2000","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Accountability; Transparency (behavior); Scarcity; Public administration; Government (linguistics); Politics; Performance measurement; Business; Performance management; Strategic planning; Public sector; Accounting; Political science; Public relations; Economics; Marketing; Law","score_opus":0.24730137240434352,"score_gpt":0.4603232882871255,"score_spread":0.21302191588278196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99207914,0.0009774574,0.000041900774,0.0010210923,0.000294112,0.0035732507,0.000014542658,0.000009017337,0.0019894775],"genre_scores_gemma":[0.9972563,0.000027262255,0.0018506367,0.000104182305,0.00008994946,0.00039058257,0.00002755224,0.000012096191,0.00024145051],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923738,0.0012597841,0.001815036,0.0002874738,0.0038980027,0.00036586102],"domain_scores_gemma":[0.9957491,0.0001781769,0.0007584779,0.00027204645,0.0027193774,0.00032280217],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02418496,0.000113705966,0.000402815,0.00089732895,0.00010218994,0.00075642864,0.00047494977,0.00014333008,0.019921102],"category_scores_gemma":[0.0017836328,0.00014758563,0.00014661333,0.0021677855,0.00012414208,0.00091583916,0.000007786718,0.00028732818,0.000079596546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008181476,0.00027902325,0.067855254,0.0000070092674,0.000010930825,0.000014095503,0.0024737096,0.004441462,0.000013965536,0.0000024769865,0.0021233526,0.92277056],"study_design_scores_gemma":[0.0032404053,0.00090778014,0.44843704,0.00027622285,0.00007329299,0.000087246495,0.0009862784,0.53443867,0.000011706231,0.0029084787,0.008442485,0.00019038648],"about_ca_topic_score_codex":0.014651485,"about_ca_topic_score_gemma":0.68194497,"teacher_disagreement_score":0.9225802,"about_ca_system_score_codex":0.0010308491,"about_ca_system_score_gemma":0.0036737537,"threshold_uncertainty_score":0.99191004},"labels":[],"label_agreement":null},{"id":"W4366728330","doi":"10.3138/cjpe.0016.007","title":"Evaluation Policy and Practice in the Provincial Government of Prince Edward Island","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health PEI","funders":"","keywords":"Accountability; Theme (computing); Government (linguistics); Public administration; Public policy; Public sector; Political science; History; Law; Philosophy; Computer science","score_opus":0.2650363576252401,"score_gpt":0.5108291781477593,"score_spread":0.24579282052251922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9076708,0.0024296464,0.00050577807,0.029081648,0.0005648217,0.0040353104,0.000019237252,0.000004044435,0.05568871],"genre_scores_gemma":[0.9981601,0.00006326862,0.001126165,0.00032405186,0.0001971358,0.00006303083,0.000001364445,0.0000045284637,0.00006032673],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9892968,0.0023034113,0.0009246358,0.00016601218,0.007106601,0.00020251864],"domain_scores_gemma":[0.99498385,0.0010171317,0.0009655141,0.00024067263,0.002638244,0.00015459649],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054558273,0.000093146184,0.00017218497,0.000354377,0.000117203585,0.00023767688,0.0003515729,0.000056824723,0.0007348929],"category_scores_gemma":[0.03331284,0.000060880884,0.00005361649,0.0007901493,0.00009838752,0.0007885569,0.000012539858,0.00017453628,0.000008706394],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001932101,0.000078280245,0.009087247,0.0000033833735,0.000012299253,0.0000022990355,0.006349814,0.0010544248,0.000019036199,0.000508804,0.00092195877,0.98194313],"study_design_scores_gemma":[0.004424782,0.0019329375,0.42986253,0.00014793266,0.00047830964,0.00031863127,0.014960333,0.36144146,0.00008792961,0.016630698,0.16941243,0.0003020327],"about_ca_topic_score_codex":0.000590729,"about_ca_topic_score_gemma":0.030144027,"teacher_disagreement_score":0.9816411,"about_ca_system_score_codex":0.00062187476,"about_ca_system_score_gemma":0.0034408015,"threshold_uncertainty_score":0.9875533},"labels":[],"label_agreement":null},{"id":"W4366728344","doi":"10.3138/cjpe.0016.004","title":"Program Evaluation in the Manitoba Government: Past, Present, and Future","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Program evaluation; Civil service; State (computer science); Service (business); State government; Political science; Psychology; Public administration; Business; Local government; Public service; Computer science; Marketing","score_opus":0.31480988225866346,"score_gpt":0.47898588581411383,"score_spread":0.16417600355545037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366728344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90323603,0.0053712605,0.0000985476,0.056671645,0.0018041217,0.01010939,0.000015866235,0.000018885296,0.022674238],"genre_scores_gemma":[0.99628687,0.00007434203,0.001152638,0.00031899547,0.0015319221,0.0005417237,0.000008244774,0.000009603872,0.000075677104],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99156725,0.0014859551,0.00091836636,0.0002524545,0.005450157,0.00032583214],"domain_scores_gemma":[0.99700725,0.00025227413,0.00063141657,0.0003526386,0.0014789011,0.00027749245],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02370249,0.00015125932,0.00020411142,0.000341455,0.0002465086,0.000798177,0.00054129766,0.00009502889,0.0022632652],"category_scores_gemma":[0.0006346563,0.00009694785,0.00009023756,0.00095313805,0.000098999306,0.0008106101,0.000014369574,0.00030456393,0.000044727203],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007165213,0.0000939384,0.027136886,0.000003152342,0.000012654132,0.0000049180685,0.0021316998,0.00034715695,0.0000022471445,0.00012666504,0.011467606,0.9586659],"study_design_scores_gemma":[0.0013503642,0.0005967364,0.28845322,0.00002776976,0.00010457322,0.00007870148,0.007946527,0.22062849,0.0000053143867,0.003295327,0.47738072,0.0001322698],"about_ca_topic_score_codex":0.0002337399,"about_ca_topic_score_gemma":0.018892271,"teacher_disagreement_score":0.95853364,"about_ca_system_score_codex":0.0005269195,"about_ca_system_score_gemma":0.00069472217,"threshold_uncertainty_score":0.9990104},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929795,0.00071126147,0.00009087733,0.000759614,0.0009799667,0.004059756,0.000027383798,0.000011223711,0.00038038063],"genre_scores_gemma":[0.998682,0.000055249664,0.0008729691,0.00008019804,0.000082904546,0.00017541161,0.000024140107,0.000017164866,0.000009962364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.985483,0.010255409,0.002064087,0.00013810517,0.0016211637,0.00043822973],"domain_scores_gemma":[0.9911583,0.00031461864,0.002549242,0.000247259,0.005411823,0.00031877594],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020038925,0.00013850936,0.00041302422,0.0009553782,0.000456616,0.0000073465694,0.00011974448,0.00020124343,0.001774836],"category_scores_gemma":[0.0032958244,0.00014528653,0.00009216027,0.00091321504,0.00006877734,0.0003403369,0.000009380381,0.0010297869,0.000012242524],"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":[0.000019499023,0.000052130734,0.6321415,0.00018779535,0.000023857969,1.6917076e-7,0.009118978,0.0015864857,0.000031003685,0.000052535124,0.00053733034,0.3562487],"study_design_scores_gemma":[0.0024346863,0.0008591273,0.9512898,0.00093239895,0.00012460026,0.0000068426357,0.005114258,0.037767008,0.000039566683,0.0009885957,0.0003423056,0.000100826524],"about_ca_topic_score_codex":0.1024374,"about_ca_topic_score_gemma":0.5966264,"teacher_disagreement_score":0.49418902,"about_ca_system_score_codex":0.005434757,"about_ca_system_score_gemma":0.006699658,"threshold_uncertainty_score":0.9991377},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99445033,0.0006140516,0.000032138974,0.0034102332,0.00033479466,0.0003500658,0.000001851383,0.000006707844,0.0007998228],"genre_scores_gemma":[0.99630225,0.000003808026,0.0032286446,0.00025624756,0.00006320815,0.000034682173,0.000009923235,0.000009118415,0.00009215014],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988745,0.00019965672,0.00033641927,0.00015654671,0.00019581521,0.00023704795],"domain_scores_gemma":[0.9991569,0.00007973833,0.00022843953,0.000046190293,0.00021722112,0.00027151091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001573239,0.00009713808,0.00016538623,0.00024916313,0.00012167185,0.00013954435,0.00006442182,0.00009105496,0.00018489583],"category_scores_gemma":[0.00029278538,0.0000846782,0.000031452044,0.0001365983,0.000066997396,0.00022333738,0.0000046308014,0.0003601778,0.000002163666],"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":[0.000007013267,0.00007086341,0.7014883,0.000004462519,0.000022819146,0.000021154568,0.010721459,0.000050155817,0.000047435366,0.0002630696,0.000009390114,0.28729385],"study_design_scores_gemma":[0.0010728978,0.0003801995,0.98714745,0.00008535371,0.000044125078,0.00016924736,0.008731144,0.000026703261,0.0000012336646,0.0017966733,0.00045323287,0.000091719776],"about_ca_topic_score_codex":0.0017154142,"about_ca_topic_score_gemma":0.0027295346,"teacher_disagreement_score":0.28720212,"about_ca_system_score_codex":0.00014835288,"about_ca_system_score_gemma":0.0006308915,"threshold_uncertainty_score":0.34530765},"labels":[],"label_agreement":null},{"id":"W4367029949","doi":"10.3138/cjpe.25.002","title":"Contribution Analysis Applied: Reflections on Scope and Methodology","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Perspective (graphical); Relation (database); Elaboration; Management science; Epistemology; Computer science; Engineering ethics; Sociology; Engineering; Data mining; Philosophy","score_opus":0.6370922382666173,"score_gpt":0.6304102886950795,"score_spread":0.006681949571537782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367029949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580563,0.00019568655,0.020845715,0.004537449,0.0017487154,0.0011334677,0.000011903018,0.000014345343,0.0134564685],"genre_scores_gemma":[0.98703414,0.0000070957367,0.012404017,0.000271026,0.00016343452,0.00004366703,0.000013878665,0.0000043900422,0.000058321242],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99710107,0.0006299663,0.000673239,0.00020414489,0.0011882762,0.0002032806],"domain_scores_gemma":[0.99555993,0.0005912374,0.0005623714,0.00025404032,0.0026317195,0.00040068745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024034401,0.000093125585,0.00027058035,0.0015434788,0.000301154,0.00030599043,0.00022229998,0.000111384106,0.002028733],"category_scores_gemma":[0.0056073354,0.00007051111,0.00011225827,0.0016011331,0.00011608314,0.0002522332,0.0000073142323,0.00035136475,0.000045330475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037109457,0.00003831101,0.016793266,0.0000010755865,0.00017128275,0.0000018647173,0.0006567735,0.0040079444,0.0012915178,0.019304512,0.0008308703,0.9568655],"study_design_scores_gemma":[0.0025456937,0.0018408059,0.69974864,0.000018206083,0.0019406669,0.00012983434,0.0018095269,0.053491604,0.0014998598,0.08617953,0.15039498,0.00040067956],"about_ca_topic_score_codex":0.0003017261,"about_ca_topic_score_gemma":0.08202588,"teacher_disagreement_score":0.95646477,"about_ca_system_score_codex":0.0001356015,"about_ca_system_score_gemma":0.0018222139,"threshold_uncertainty_score":0.99888355},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9828873,0.0008570233,0.00008778957,0.008416098,0.00028544065,0.0032074987,0.00006414574,0.000016076683,0.0041786176],"genre_scores_gemma":[0.98315024,0.0000396149,0.002291646,0.013277564,0.000056902863,0.0008144426,0.0003223184,0.000025071864,0.00002220738],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.953048,0.043125667,0.0023361936,0.000049149305,0.0008529571,0.00058803],"domain_scores_gemma":[0.98926985,0.0068726707,0.0015150908,0.000790042,0.0013250705,0.0002272885],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.048996065,0.00023236671,0.000538459,0.0011234237,0.0068377513,0.000059553688,0.0016838898,0.00019694264,0.0010540136],"category_scores_gemma":[0.0006796142,0.0001612463,0.00019490375,0.0011987415,0.00059797737,0.00029517617,0.00006600016,0.005079068,0.00001636073],"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":[0.00017770963,0.00044061607,0.053962134,0.000816774,0.000106509484,0.0000012510538,0.5768252,0.00028236955,7.915756e-7,0.0002874851,0.0022364224,0.36486274],"study_design_scores_gemma":[0.0028252609,0.0016508071,0.34316438,0.0016488015,0.00016588159,0.000008304938,0.6256738,0.0004220763,0.0000045432316,0.0015424318,0.022696435,0.00019727861],"about_ca_topic_score_codex":0.04171082,"about_ca_topic_score_gemma":0.6685953,"teacher_disagreement_score":0.6268845,"about_ca_system_score_codex":0.0018132246,"about_ca_system_score_gemma":0.021353988,"threshold_uncertainty_score":0.99985915},"labels":[],"label_agreement":null},{"id":"W4367029998","doi":"10.3138/cjpe.0015.007","title":"Critical Perspectives on Educational Evaluation","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Lifeworld; Mainstream; Rationality; Epistemology; Sociology; Critical theory; Critical thinking; Citizen journalism; Postmodernism; Formal education; Engineering ethics; Pedagogy; Social science; Political science; Law; Philosophy","score_opus":0.46646186255614186,"score_gpt":0.6165222477440031,"score_spread":0.15006038518786124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367029998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85182977,0.0022659786,0.0014676226,0.06768306,0.0037198786,0.0023476048,0.000011765715,0.000017427634,0.07065688],"genre_scores_gemma":[0.99661046,0.000018654968,0.0019452458,0.000309013,0.00067118485,0.0001139306,0.000013791821,0.000009939595,0.0003077765],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9927348,0.0010491951,0.00088420894,0.0002872429,0.004746827,0.00029771557],"domain_scores_gemma":[0.9867097,0.0008821857,0.00045498126,0.00033146987,0.011072213,0.00054946565],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023381507,0.00013675219,0.00020407532,0.001033584,0.00033311764,0.00057164714,0.00043720845,0.00008565185,0.024166163],"category_scores_gemma":[0.024185082,0.00010826304,0.00015116735,0.00094875187,0.00016084385,0.0009372358,0.0000072913076,0.00025417111,0.00042197775],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044096454,0.00020580651,0.025767665,0.0000018362974,0.000027793598,0.0000040415207,0.0031927896,0.004017093,0.000021501502,0.017437013,0.010081267,0.9391991],"study_design_scores_gemma":[0.0022027164,0.0017555689,0.521587,0.00011063976,0.00026274825,0.00023609336,0.01340381,0.17477646,0.000049123868,0.19185936,0.09337318,0.00038323848],"about_ca_topic_score_codex":0.00015105725,"about_ca_topic_score_gemma":0.004668118,"teacher_disagreement_score":0.93881583,"about_ca_system_score_codex":0.0010347714,"about_ca_system_score_gemma":0.010539088,"threshold_uncertainty_score":0.9950702},"labels":[],"label_agreement":null},{"id":"W4367030000","doi":"10.3138/cjpe.0015.004","title":"Evaluability Assessment of Staff Training in Special Care Units for Persons with Dementia: Strategic Issues","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dementia; Curriculum; Psychology; Training (meteorology); Work (physics); Medical education; Professional development; Nursing; Pedagogy; Disease; Medicine","score_opus":0.526951152664895,"score_gpt":0.5564320320386825,"score_spread":0.029480879373787516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897304,0.0004838454,0.00081412104,0.0008429778,0.00044218573,0.0017767418,0.000029205841,0.0000039771603,0.0058765025],"genre_scores_gemma":[0.99184173,0.000010497629,0.007588336,0.000019419713,0.0003265489,0.00013755515,0.00002687806,0.000009649399,0.000039358296],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99554926,0.00059208815,0.0010450253,0.00023997201,0.002246481,0.00032716236],"domain_scores_gemma":[0.9930261,0.00023333922,0.0007717693,0.00024055937,0.005438428,0.00028983408],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0131706465,0.00014231993,0.00035692178,0.0007168734,0.00016321626,0.00022056478,0.0003597945,0.00007484532,0.0019621144],"category_scores_gemma":[0.0008688709,0.00010808196,0.00009298367,0.0012147436,0.00011872841,0.0005174375,0.000007010434,0.00019299335,0.0000018490404],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105526626,0.00009448042,0.17390156,0.000029241208,0.00009101972,0.000009705448,0.024450777,0.027557334,0.000026923448,0.0015971682,0.0004196704,0.7717166],"study_design_scores_gemma":[0.0071284757,0.0078018503,0.39635324,0.00034512047,0.0005405388,0.00006066194,0.38521534,0.1451288,0.0000795874,0.018619059,0.03823796,0.0004893646],"about_ca_topic_score_codex":0.00052957836,"about_ca_topic_score_gemma":0.14542615,"teacher_disagreement_score":0.77122724,"about_ca_system_score_codex":0.0005953021,"about_ca_system_score_gemma":0.016714511,"threshold_uncertainty_score":0.99895024},"labels":[],"label_agreement":null},{"id":"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09456857,0.34451774,0.029371224,0.50030947,0.0022616028,0.023455352,0.000061099134,0.00008810412,0.0053668395],"genre_scores_gemma":[0.49924013,0.0071019675,0.46835986,0.02042497,0.0026496146,0.0004248654,0.00010998205,0.00008548449,0.0016031455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976711,0.00022356374,0.00065027195,0.00013042675,0.0010385145,0.00028610154],"domain_scores_gemma":[0.99239117,0.0016240003,0.0002816979,0.00018930773,0.0047742175,0.0007396207],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027467696,0.00007969812,0.00025752856,0.0001914715,0.00013337376,0.00004122008,0.00014059863,0.00028059457,0.00022057226],"category_scores_gemma":[0.07344625,0.0000682265,0.00016496122,0.00019652651,0.00010971645,0.00010882015,0.0000063405055,0.0019974892,0.000022607506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007060297,0.00011723355,0.008544317,0.002241216,0.00011033534,0.000035701378,0.001434922,0.00017688007,0.00006932131,0.00090456253,0.008432396,0.97786254],"study_design_scores_gemma":[0.007955953,0.0038618052,0.025102569,0.031849593,0.0015573554,0.0004310297,0.0003360191,0.057553522,0.00025950608,0.0054672174,0.8652541,0.00037133193],"about_ca_topic_score_codex":0.00015305549,"about_ca_topic_score_gemma":0.013774974,"teacher_disagreement_score":0.9774912,"about_ca_system_score_codex":0.0004668005,"about_ca_system_score_gemma":0.01061111,"threshold_uncertainty_score":0.9949978},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825459,0.015150971,0.000032315045,0.00055447855,0.00061479275,0.00071255065,8.185283e-7,0.000004752424,0.0003833988],"genre_scores_gemma":[0.99759704,0.00018107671,0.0017003177,0.00003154222,0.0001710482,0.00026370934,0.0000027782726,0.000007851808,0.000044664972],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954886,0.0014176811,0.0007449953,0.00026347887,0.0018095797,0.00027570024],"domain_scores_gemma":[0.9975698,0.00031661667,0.00044471893,0.0001526308,0.0011294056,0.00038681456],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01629402,0.00012863736,0.00023449856,0.00049458107,0.00022574363,0.0004658691,0.00015593054,0.000084140214,0.0017568348],"category_scores_gemma":[0.0041414206,0.00010857382,0.000034220597,0.00044223407,0.000116259565,0.00081794785,0.000010893359,0.00022856319,0.000015255099],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056383515,0.0000148000045,0.46431637,0.0000017797754,0.000008440802,0.0000030965443,0.022113265,0.00064857036,0.000015380547,0.00002933403,0.000075550735,0.5127678],"study_design_scores_gemma":[0.0018214736,0.0005534789,0.7558076,0.00017120298,0.00011958349,0.000024007193,0.08276766,0.13374667,0.00042587798,0.004339773,0.019924875,0.00029781347],"about_ca_topic_score_codex":0.0025855652,"about_ca_topic_score_gemma":0.0074135344,"teacher_disagreement_score":0.51246995,"about_ca_system_score_codex":0.00026991902,"about_ca_system_score_gemma":0.0021904672,"threshold_uncertainty_score":0.9991557},"labels":[],"label_agreement":null},{"id":"W4367030027","doi":"10.3138/cjpe.018.005","title":"Impacts of the Canadian Evaluation Society’s Evaluation Competitions for Students","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health Canada; Canadian Institutes of Health Research","funders":"","keywords":"Political science; Psychology; Business; Sociology","score_opus":0.4394839068331859,"score_gpt":0.5880745552752973,"score_spread":0.1485906484421114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97300494,0.0010565834,0.00089028466,0.004937757,0.0034775923,0.009998714,0.00008976061,0.000007727151,0.006536652],"genre_scores_gemma":[0.9963912,0.0000075457688,0.0026235923,0.00032752074,0.00012636938,0.0003866519,0.000045713834,0.000015866495,0.00007554281],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9884951,0.0020053973,0.0014384837,0.0002791755,0.007323669,0.00045815206],"domain_scores_gemma":[0.9801863,0.00039753382,0.0014337592,0.000535519,0.016774338,0.0006725527],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06834959,0.00018410731,0.00031174612,0.0006605746,0.0008881856,0.0005318697,0.0008398511,0.00015731085,0.0030862922],"category_scores_gemma":[0.013246658,0.00013300238,0.00042359895,0.0013448938,0.0001779381,0.0006629828,0.0000117580585,0.00024217635,0.000023164666],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033345474,0.00029606512,0.3593599,0.000035135625,0.0003624107,6.833237e-7,0.0075711207,0.039880056,0.0003109856,0.0074491594,0.02871062,0.5559905],"study_design_scores_gemma":[0.00654893,0.0008319111,0.5947446,0.00022688975,0.0014068332,0.000045999648,0.0049188347,0.25371173,0.00081964355,0.060323972,0.07600419,0.00041641446],"about_ca_topic_score_codex":0.016937673,"about_ca_topic_score_gemma":0.8244774,"teacher_disagreement_score":0.8075397,"about_ca_system_score_codex":0.0028010579,"about_ca_system_score_gemma":0.043780938,"threshold_uncertainty_score":0.997825},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9353388,0.0050707706,0.00019257348,0.050903156,0.000537732,0.00516265,0.000053713968,0.000006454953,0.0027341447],"genre_scores_gemma":[0.99638295,0.000009469358,0.0009278856,0.0017139792,0.00025571318,0.00039755416,0.00006250263,0.000008469633,0.00024149941],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99809563,0.0004567107,0.00040835794,0.0001285432,0.00051895966,0.00039176844],"domain_scores_gemma":[0.99874103,0.00019969075,0.0001273405,0.00017336951,0.00050632167,0.00025227029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066151456,0.00007244072,0.00012447644,0.00025652157,0.00015975247,0.0001089319,0.00023801632,0.00008137281,0.0007182053],"category_scores_gemma":[0.00050491584,0.00005703533,0.00006691415,0.00041658932,0.000058141544,0.00019972665,0.0000040467417,0.00024687234,0.000020522739],"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":[0.00017559908,0.00023737337,0.01762,0.000016794982,0.000030280717,0.0000043332784,0.014493725,0.00009987026,0.000022886368,0.0010220172,0.19099468,0.77528244],"study_design_scores_gemma":[0.0054135635,0.0052817925,0.3055127,0.00009331842,0.000038952738,0.00008282192,0.07028024,0.00472302,0.000047710488,0.0040141866,0.60425365,0.00025806963],"about_ca_topic_score_codex":0.0077180867,"about_ca_topic_score_gemma":0.24343732,"teacher_disagreement_score":0.77502435,"about_ca_system_score_codex":0.0005965721,"about_ca_system_score_gemma":0.0026883632,"threshold_uncertainty_score":0.9988896},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22542912,0.006903252,0.00037055084,0.1139891,0.03360453,0.003033856,0.000010286584,0.00009036458,0.6165689],"genre_scores_gemma":[0.9776112,0.000026718782,0.0012232735,0.00025785642,0.020481138,0.000011538573,0.0000036374668,0.0000038992853,0.00038073267],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979257,0.0011564457,0.00025296313,0.0000706207,0.00038876332,0.00020548687],"domain_scores_gemma":[0.99832547,0.00025359198,0.00025735397,0.00006942812,0.00063477375,0.0004593696],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009614613,0.000053176875,0.0000974129,0.00008829335,0.00042430137,0.00011834683,0.00018520454,0.000115064424,0.001586582],"category_scores_gemma":[0.004030812,0.00004799636,0.00007507492,0.00018129984,0.0001938989,0.0006651431,0.0000028117959,0.00023836472,0.000046024037],"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":[0.000022749333,0.00004135225,0.0026808882,0.0000019517015,0.000029362249,0.000014627097,0.009055616,0.000036742495,0.000008398851,0.008775923,0.05396255,0.92536986],"study_design_scores_gemma":[0.0001742138,0.00012485572,0.001277771,0.000013641658,0.00003306818,0.000005164736,0.001589282,0.000057107874,0.000006161562,0.0050031347,0.9916549,0.000060705137],"about_ca_topic_score_codex":0.002117321,"about_ca_topic_score_gemma":0.035299923,"teacher_disagreement_score":0.93769234,"about_ca_system_score_codex":0.00032240665,"about_ca_system_score_gemma":0.0027314392,"threshold_uncertainty_score":0.9993261},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7211033,0.019475512,0.011835538,0.14166851,0.010750788,0.0019395776,0.000021024487,0.000037051785,0.09316869],"genre_scores_gemma":[0.98425895,0.000101046986,0.012442447,0.000482722,0.0020652777,0.000037435904,0.000013489073,0.000017505186,0.0005811082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99561065,0.0028397215,0.00048046606,0.00014963884,0.0003846166,0.00053492025],"domain_scores_gemma":[0.99666363,0.00063447363,0.0004698867,0.00010508632,0.0013912097,0.0007357197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015167306,0.00012566101,0.00018711078,0.00016723035,0.00092464266,0.00013634595,0.00019576783,0.00025171036,0.0007843211],"category_scores_gemma":[0.004580249,0.00015695237,0.00014004119,0.00043044044,0.00086657703,0.0005086477,0.0000021982617,0.00032296017,0.0000146267685],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004562162,0.00023085308,0.014891052,0.000028518798,0.00016221104,0.000010476767,0.14642656,0.031343568,0.000015547868,0.6138306,0.0036851617,0.18937087],"study_design_scores_gemma":[0.0016555423,0.000388685,0.018251494,0.00019743697,0.00034959486,0.00012286124,0.29463485,0.011360141,0.000052003037,0.18384695,0.4887384,0.00040205818],"about_ca_topic_score_codex":0.009504493,"about_ca_topic_score_gemma":0.02613408,"teacher_disagreement_score":0.48505324,"about_ca_system_score_codex":0.0010830517,"about_ca_system_score_gemma":0.039945528,"threshold_uncertainty_score":0.9970913},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49269497,0.0002307712,0.000008160439,0.08080969,0.0036654603,0.0016402968,0.000011904419,0.000014712898,0.420924],"genre_scores_gemma":[0.98970413,0.00006933859,0.0001620536,0.0021275992,0.0048734136,0.000025763986,0.000011013301,0.000007490801,0.003019167],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986264,0.0004427075,0.00019193153,0.000057098798,0.00048382638,0.00019801753],"domain_scores_gemma":[0.9991049,0.00007114457,0.00011099361,0.00008299422,0.0003255153,0.00030444967],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002587752,0.000052348172,0.00006989438,0.00006050498,0.0006145365,0.00015115763,0.00021864387,0.000057665056,0.017204586],"category_scores_gemma":[0.00043317114,0.00004057103,0.00006928293,0.00023104736,0.00017711375,0.00013550493,0.0000011246584,0.00016524522,0.00021062067],"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":[0.000004454139,0.00003903308,0.0012856274,8.56036e-7,0.000012726015,0.0000013505855,0.022356864,0.00006770792,1.4945395e-7,0.0054772627,0.05197885,0.91877514],"study_design_scores_gemma":[0.00016172846,0.000093189396,0.0065384107,0.000014901174,0.000024276289,0.0000013263203,0.005587419,0.0002661073,8.0508994e-7,0.0028552401,0.984404,0.00005257745],"about_ca_topic_score_codex":0.0032094107,"about_ca_topic_score_gemma":0.057976786,"teacher_disagreement_score":0.9324252,"about_ca_system_score_codex":0.00042436164,"about_ca_system_score_gemma":0.0020001782,"threshold_uncertainty_score":0.98369384},"labels":[],"label_agreement":null},{"id":"W4367030054","doi":"10.3138/cjpe.0019.012","title":"Évaluation des coûts des services de soutien en santé mentale communautaire","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Activity-based costing; Valuation (finance); Business; Mental health; Agency (philosophy); Contingent valuation; Health services; Environmental health; Psychology; Medicine; Marketing; Sociology; Willingness to pay; Economics; Finance; Psychiatry; Population","score_opus":0.2645309011810223,"score_gpt":0.509113088193697,"score_spread":0.24458218701267476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927083,0.0010649674,0.001251211,0.0011354916,0.00024686332,0.0007062349,0.000008091157,0.000015343589,0.002863453],"genre_scores_gemma":[0.9733421,0.000041867286,0.025803063,0.0003100289,0.00025964328,0.000050851002,0.00002170096,0.000012981931,0.00015777044],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949067,0.0013728429,0.0009645026,0.0001851085,0.0021714238,0.00039941102],"domain_scores_gemma":[0.9958152,0.00033274124,0.00061427633,0.00030266307,0.0024288893,0.0005062354],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024141517,0.00015429345,0.00023536981,0.0006063601,0.00059457624,0.0005895632,0.00066094677,0.000101422316,0.002756646],"category_scores_gemma":[0.001230772,0.00012588323,0.0001344871,0.0006553497,0.0002176228,0.00139932,0.000023174494,0.00021606257,0.00015814819],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014074233,0.000049298265,0.112792976,0.000008290427,0.000024658008,0.0000017458112,0.016544223,0.006895759,0.0001372875,0.00006272184,0.00041184208,0.86305714],"study_design_scores_gemma":[0.0012879454,0.0005248715,0.7011478,0.00014132768,0.00013877843,0.00010865498,0.011490802,0.23908381,0.00062725804,0.023540169,0.021700814,0.00020778111],"about_ca_topic_score_codex":0.0014822128,"about_ca_topic_score_gemma":0.11442116,"teacher_disagreement_score":0.86284935,"about_ca_system_score_codex":0.0013848366,"about_ca_system_score_gemma":0.003877342,"threshold_uncertainty_score":0.998155},"labels":[],"label_agreement":null},{"id":"W4367030058","doi":"10.3138/cjpe.018.015","title":"Irving Rootman, Michael Goodstadt, Brian Hyndman, David V. McQueen, Louise Potvin, Jane Springett, &amp; Erio Ziglio (Éds.) (2001). Evaluation in Health Promotion: Principles and Perspectives.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Sociology; Theology; Political science; Philosophy; Law; Politics","score_opus":0.42290356227939263,"score_gpt":0.49069272073410203,"score_spread":0.0677891584547094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9660669,0.009397428,0.002274774,0.011681104,0.0012175709,0.004810572,0.00001500235,0.00002904573,0.004507588],"genre_scores_gemma":[0.9882125,0.00023538395,0.010389758,0.00020768068,0.0002284357,0.00016341713,0.000029470464,0.000032583797,0.00050077005],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9896738,0.002900552,0.002193163,0.0006863273,0.0037572882,0.00078886567],"domain_scores_gemma":[0.9920356,0.0002486186,0.0017305085,0.0006011106,0.004350318,0.0010338099],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053784993,0.00033360653,0.00058034755,0.001738251,0.0004950681,0.00077758497,0.0004980057,0.00017043679,0.002955517],"category_scores_gemma":[0.009347311,0.00030321203,0.00014662463,0.0016030978,0.00018820382,0.0013489173,0.00003190488,0.0005498256,0.000059837585],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006675189,0.0005394291,0.23465307,0.00007816326,0.00009720448,0.0000218957,0.017350566,0.013806744,0.00015395657,0.003983143,0.0030844102,0.72616464],"study_design_scores_gemma":[0.0053275265,0.0017150438,0.68888736,0.00061567855,0.00018137002,0.00037944946,0.009523974,0.08900853,0.00008597775,0.0130650755,0.19043878,0.00077122636],"about_ca_topic_score_codex":0.0020784303,"about_ca_topic_score_gemma":0.1922245,"teacher_disagreement_score":0.7253934,"about_ca_system_score_codex":0.002422445,"about_ca_system_score_gemma":0.012682974,"threshold_uncertainty_score":0.999942},"labels":[],"label_agreement":null},{"id":"W4367030059","doi":"10.3138/cjpe.25.007","title":"S. Donaldson, C.A. Christie, and M.M. Mark. (2009) <i>What Counts as Credible Evidence in Applied Research and Evaluation Practice?</i> Thousand Oaks, CA: Sage. 265 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SAGE; Psychology; Physics","score_opus":0.3534349116066584,"score_gpt":0.5479246449963839,"score_spread":0.19448973338972553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92413664,0.024746476,0.00013889707,0.01741785,0.002668926,0.0042425985,0.000011423266,0.000013536112,0.02662367],"genre_scores_gemma":[0.99487805,0.0019152904,0.0021605385,0.0002833547,0.00022834846,0.00012970834,0.0000099103945,0.000012206227,0.00038261237],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99361765,0.0008903885,0.00077347783,0.00034192236,0.004023171,0.00035340613],"domain_scores_gemma":[0.9934585,0.0013723738,0.0004905142,0.00030316476,0.0039139134,0.00046149915],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06571472,0.00013203752,0.00022315425,0.0008755207,0.00028645803,0.0013557936,0.00030240943,0.00014672925,0.0025463311],"category_scores_gemma":[0.011137591,0.00010947944,0.000029375513,0.00096495985,0.00025753348,0.001761228,0.000030114601,0.0006690407,0.000113420516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006660221,0.0000447795,0.0072110123,0.0000102335825,0.000012831175,0.000009309807,0.00081082835,0.000111784364,0.00022900364,0.00032957262,0.014652112,0.97651196],"study_design_scores_gemma":[0.003748184,0.0011987307,0.19557875,0.00064512214,0.00023594654,0.00040560318,0.008365675,0.0880501,0.00027726116,0.0468626,0.6541066,0.00052538526],"about_ca_topic_score_codex":0.00063177274,"about_ca_topic_score_gemma":0.023456562,"teacher_disagreement_score":0.97598654,"about_ca_system_score_codex":0.00027789883,"about_ca_system_score_gemma":0.0058688545,"threshold_uncertainty_score":0.99976695},"labels":[],"label_agreement":null},{"id":"W4367030095","doi":"10.3138/cjpe.0015.002","title":"System-Wide Program Assessment with Performance Indicators: Alberta’s Performance Funding Mechanism","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Mechanism (biology); Performance indicator; Business; Performance measurement; Organizational performance; Process management; Political science; Accounting; Marketing","score_opus":0.20148791032238003,"score_gpt":0.46823971684013654,"score_spread":0.26675180651775654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739059,0.00011284697,0.0018422399,0.0010941057,0.00096431124,0.0025052852,0.000002728073,0.000045113036,0.019527454],"genre_scores_gemma":[0.9886471,0.00003861788,0.009887894,0.00014517599,0.00025630338,0.0004289257,0.000020632147,0.000031025847,0.00054432853],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924458,0.0005519852,0.0015224736,0.00043232137,0.004298111,0.000749299],"domain_scores_gemma":[0.99394685,0.00031172528,0.0015977621,0.0005677595,0.0026206013,0.0009552939],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016169483,0.00031377157,0.0004861174,0.0017217543,0.00069709716,0.00092249905,0.000915573,0.00014983602,0.0013926482],"category_scores_gemma":[0.00063822523,0.00022219405,0.00014871775,0.0022635444,0.0001460135,0.0018546673,0.000027283852,0.00048987946,0.00013891803],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042084437,0.000086069005,0.32533944,0.000029722982,0.00005947854,0.000014442751,0.0005966697,0.0025617909,0.000007273199,0.00081401155,0.00037704792,0.67007196],"study_design_scores_gemma":[0.0028680535,0.005275967,0.48031965,0.00068666117,0.00031232665,0.00070948154,0.003966513,0.40407422,0.0001927515,0.00040222326,0.10057018,0.00062197127],"about_ca_topic_score_codex":0.00055615476,"about_ca_topic_score_gemma":0.011009869,"teacher_disagreement_score":0.66945,"about_ca_system_score_codex":0.0015673742,"about_ca_system_score_gemma":0.008131118,"threshold_uncertainty_score":0.99952024},"labels":[],"label_agreement":null},{"id":"W4367030101","doi":"10.3138/cjpe.25.008","title":"D. Russ-Eft &amp; H. Preskill. (2009). <i>Evaluation in Organizations: A Systematic Approach to Enhancing Learning, Performance and Change (2nd ed.)</i> . New York, NY: Basic Books. 552 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Computer science","score_opus":0.22454373486820348,"score_gpt":0.418268263955533,"score_spread":0.19372452908732954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9729846,0.0031541113,0.0058468035,0.0020745306,0.0018192058,0.009756218,0.0000069260886,0.000042651267,0.0043149507],"genre_scores_gemma":[0.9890352,0.00006657011,0.008764241,0.0003389753,0.00041210302,0.00048157116,0.000040345712,0.000033185162,0.0008278236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99298054,0.0011149711,0.0016841526,0.00047477483,0.0032374873,0.0005080933],"domain_scores_gemma":[0.9937376,0.00033220943,0.0011129217,0.0005011147,0.0034493876,0.0008668166],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030770833,0.00027307484,0.0005225988,0.0015257801,0.00037287513,0.0008781349,0.00056361296,0.00018347263,0.0011978867],"category_scores_gemma":[0.011872485,0.00022709683,0.00007607271,0.0019601702,0.00007597923,0.0013102414,0.000036372523,0.00065406266,0.000143622],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000518101,0.00024572245,0.12406837,0.00077770784,0.00008885416,0.0000032451342,0.040118877,0.018757856,0.00086408376,0.00031488534,0.01690185,0.79780674],"study_design_scores_gemma":[0.0055423686,0.0013673847,0.34909844,0.0034444556,0.0007850082,0.00035483847,0.0066752825,0.56046104,0.00045280173,0.0021426985,0.06837698,0.001298656],"about_ca_topic_score_codex":0.0011123689,"about_ca_topic_score_gemma":0.06441633,"teacher_disagreement_score":0.7965081,"about_ca_system_score_codex":0.0004750046,"about_ca_system_score_gemma":0.005689514,"threshold_uncertainty_score":0.9999473},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8318052,0.022171048,0.003916559,0.075679086,0.0059505817,0.0017364668,0.00001938445,0.00003292917,0.05868869],"genre_scores_gemma":[0.9704429,0.000551697,0.026735026,0.000270863,0.0013226407,0.000080403195,0.00001814033,0.000022958106,0.00055537175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99232453,0.005802501,0.00053540315,0.00019396126,0.0005391949,0.0006044318],"domain_scores_gemma":[0.9966572,0.0008725685,0.00048893486,0.00012729614,0.0011089323,0.0007450834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027846007,0.00015522676,0.00021316837,0.00025314945,0.0010548162,0.0001841882,0.0002507776,0.0003260592,0.0003744383],"category_scores_gemma":[0.0068759536,0.00019040254,0.00016637208,0.00065313035,0.0012875055,0.000440703,0.0000030608294,0.00042082003,0.000017639837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005520531,0.00033693475,0.027623296,0.000027637696,0.00021615191,0.000010761941,0.08750984,0.0040808003,0.00006234105,0.5235929,0.0042450456,0.3522888],"study_design_scores_gemma":[0.0027008005,0.00041792163,0.076048665,0.00026351953,0.0006133155,0.00015221626,0.21171747,0.0032925417,0.00014615407,0.18143335,0.5226771,0.00053692],"about_ca_topic_score_codex":0.014636929,"about_ca_topic_score_gemma":0.025750699,"teacher_disagreement_score":0.5184321,"about_ca_system_score_codex":0.0014842328,"about_ca_system_score_gemma":0.067245826,"threshold_uncertainty_score":0.9920268},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9406796,0.0060080867,0.012994117,0.019306563,0.0010020653,0.00083809305,0.000011558045,0.000016897679,0.019143004],"genre_scores_gemma":[0.9930023,0.00020421184,0.0051024505,0.00020967609,0.0005604755,0.00003732537,0.0000034033858,0.000016893124,0.0008632573],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951204,0.0027799252,0.0004563833,0.00017547527,0.00077977654,0.00068800943],"domain_scores_gemma":[0.9972385,0.00034946072,0.00059845555,0.00011056296,0.00091084855,0.00079215626],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0127572715,0.00015221442,0.0002087449,0.00010181276,0.0013811406,0.00034936942,0.0002880128,0.00024517078,0.0002903514],"category_scores_gemma":[0.0035963953,0.00017032487,0.00016036283,0.0006537458,0.0012082579,0.0008583136,0.000006011795,0.00027602862,0.000006200531],"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":[0.000021485816,0.0002200932,0.13858674,0.000031851057,0.00009243179,0.000067346584,0.27499253,0.23079573,0.00006637885,0.060662337,0.012557273,0.2819058],"study_design_scores_gemma":[0.0020928823,0.0006243742,0.26524073,0.0004143234,0.00041834032,0.00017440926,0.14206596,0.14365374,0.0001864323,0.25517333,0.18941729,0.0005382136],"about_ca_topic_score_codex":0.19734752,"about_ca_topic_score_gemma":0.42411664,"teacher_disagreement_score":0.2813676,"about_ca_system_score_codex":0.0033673444,"about_ca_system_score_gemma":0.028571345,"threshold_uncertainty_score":0.99991894},"labels":[],"label_agreement":null},{"id":"W4367030138","doi":"10.3138/cjpe.0015.008","title":"Stakeholder Involvement in Educational Evaluation: Québec’s Commission d’évaluation de l’enseignement collégial","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Stakeholder; Commission; Valuation (finance); Program evaluation; Evaluation methods; Theory of change; Medical education; Psychology; Political science; Pedagogy; Public relations; Management; Business; Medicine; Public administration; Accounting; Engineering; Economics","score_opus":0.47640868414258253,"score_gpt":0.50445403529336,"score_spread":0.028045351150777442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9656986,0.0012161442,0.0011658671,0.016437791,0.0013013855,0.0028378223,0.000006047113,0.000009314757,0.011327034],"genre_scores_gemma":[0.9936074,0.00003390313,0.0045550372,0.00041297392,0.000383003,0.00039366487,0.00005518223,0.000015449305,0.0005433649],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99003845,0.0018574853,0.0017714745,0.00034338547,0.005521838,0.00046737137],"domain_scores_gemma":[0.9919843,0.00045526924,0.0009967377,0.0004084946,0.005559349,0.0005958141],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.045396205,0.00020649614,0.0003133133,0.0013986906,0.00035993205,0.00045450273,0.0005599838,0.00013187692,0.01630167],"category_scores_gemma":[0.0051082894,0.00017827899,0.00013697798,0.001438703,0.00009954572,0.0008339412,0.000020329324,0.00030533288,0.00009033327],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00006111725,0.0002929086,0.21253522,0.000005210889,0.000030385061,0.0000052787655,0.005661942,0.020596309,0.00013339212,0.00031162807,0.014168916,0.7461977],"study_design_scores_gemma":[0.0032534455,0.00059777295,0.7004727,0.00011562596,0.00013858323,0.000066043955,0.0045378474,0.18835282,0.00005947945,0.01879258,0.08335905,0.00025405275],"about_ca_topic_score_codex":0.011728717,"about_ca_topic_score_gemma":0.40398407,"teacher_disagreement_score":0.74594367,"about_ca_system_score_codex":0.0077709667,"about_ca_system_score_gemma":0.04941398,"threshold_uncertainty_score":0.996038},"labels":[],"label_agreement":null},{"id":"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":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91631126,0.001379647,0.00073593354,0.0708916,0.001518095,0.005539321,0.00007301034,0.000021296793,0.0035298197],"genre_scores_gemma":[0.9874917,0.00004169035,0.009735908,0.0013594909,0.00076676346,0.00031865147,0.000017423707,0.000019381503,0.00024896808],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949857,0.001904797,0.0010569027,0.00020576287,0.0012336718,0.00061319553],"domain_scores_gemma":[0.99285746,0.00028404652,0.0013119755,0.0002518049,0.004618875,0.000675843],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01509142,0.0001407743,0.00028547132,0.00058902806,0.00036994202,0.000034171015,0.00023876393,0.0001395376,0.0033269722],"category_scores_gemma":[0.0029390147,0.00012689887,0.00008126259,0.00033069318,0.00009276362,0.00062093465,0.000014512837,0.00039356638,0.0004492848],"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":[0.000042338652,0.00007898098,0.44667387,0.0002807978,0.000057790276,0.0000031572029,0.022393364,0.000339545,0.0001685786,0.00012467559,0.0155562665,0.5142806],"study_design_scores_gemma":[0.0041330266,0.00046112947,0.84950197,0.00036957467,0.0001885482,0.000022971039,0.0020920273,0.022593658,0.000035146073,0.00015785564,0.120238245,0.0002058536],"about_ca_topic_score_codex":0.0023842338,"about_ca_topic_score_gemma":0.10889459,"teacher_disagreement_score":0.5140748,"about_ca_system_score_codex":0.0011610439,"about_ca_system_score_gemma":0.007862759,"threshold_uncertainty_score":0.9977617},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80588233,0.053393118,0.000577817,0.12485374,0.005655225,0.003146363,0.000032196174,0.000025775915,0.006433413],"genre_scores_gemma":[0.9604666,0.0015114854,0.0206361,0.009202754,0.0062508304,0.000086101114,0.00003242724,0.000061003386,0.0017527003],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927965,0.0036948207,0.001366302,0.0002027659,0.0008016662,0.0011379657],"domain_scores_gemma":[0.9933472,0.00044298678,0.00079009257,0.00025892956,0.0025078026,0.0026529392],"candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015382563,0.00022662766,0.0004305991,0.00032481446,0.0010623109,0.000058425037,0.00026984958,0.0010184323,0.0044829827],"category_scores_gemma":[0.004317853,0.00021926746,0.00021167888,0.00061828597,0.00040061417,0.0006052527,0.00001087181,0.0029614398,0.000300273],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010226893,0.00009671176,0.008145991,0.00023256615,0.0000738674,0.000026408135,0.040208,0.00011823022,0.0000063823845,0.0005497431,0.030569248,0.91996264],"study_design_scores_gemma":[0.0024285663,0.0010125639,0.0805772,0.00155167,0.0005065753,0.00012207044,0.015779475,0.0053899474,0.000014640474,0.0031955957,0.8891808,0.00024093228],"about_ca_topic_score_codex":0.012565771,"about_ca_topic_score_gemma":0.14591576,"teacher_disagreement_score":0.91972166,"about_ca_system_score_codex":0.003169371,"about_ca_system_score_gemma":0.02654991,"threshold_uncertainty_score":0.99933875},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98051417,0.0007135993,0.00025428712,0.0032927431,0.00046930934,0.0009266921,0.000008905933,0.0000143151765,0.013805969],"genre_scores_gemma":[0.9961914,0.000029560575,0.0028067813,0.0005678212,0.00016124787,0.000018201987,0.000013095711,0.000013798791,0.00019811234],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99818885,0.00025959272,0.0004564322,0.00013762873,0.0005807356,0.0003767823],"domain_scores_gemma":[0.998039,0.00002397168,0.00022188493,0.0001637874,0.0006181619,0.00093321386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016897613,0.00012652887,0.00022438163,0.00013037697,0.00015566919,0.000048473088,0.00012951363,0.00008265959,0.00032052482],"category_scores_gemma":[0.00044420015,0.000102158716,0.00009916548,0.00033738205,0.00008348329,0.00012058684,0.000003611682,0.00028406468,0.000019465879],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022745984,0.000400885,0.17645663,0.0003106207,0.00028568314,0.0015231348,0.018470561,0.00017861082,0.002283795,0.022323344,0.0030109729,0.7745283],"study_design_scores_gemma":[0.0060079363,0.003910251,0.6112421,0.00075844856,0.00083715783,0.0075854617,0.005998091,0.0009735833,0.002476276,0.01588547,0.3438223,0.00050291984],"about_ca_topic_score_codex":0.0043266304,"about_ca_topic_score_gemma":0.012062779,"teacher_disagreement_score":0.7740254,"about_ca_system_score_codex":0.00079783617,"about_ca_system_score_gemma":0.0025292684,"threshold_uncertainty_score":0.6731314},"labels":[],"label_agreement":null},{"id":"W4367030203","doi":"10.3138/cjpe.0015.001","title":"Editor’s Introduction: Educational Evaluation at the Turn of the Millennium","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Turn (biochemistry); Chemistry","score_opus":0.22207381985994942,"score_gpt":0.5014377426141619,"score_spread":0.2793639227542124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80308044,0.002849556,0.0001211837,0.15534379,0.030789196,0.0026015916,0.000013691947,0.000005565984,0.0051949946],"genre_scores_gemma":[0.9886802,0.000037951173,0.00027899325,0.00027546586,0.008931895,0.0001165413,0.000018986515,0.0000092345645,0.0016507764],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99233204,0.0013128724,0.0010923754,0.00021524602,0.004813798,0.00023367],"domain_scores_gemma":[0.98984045,0.00041105042,0.0013131762,0.0005985985,0.007620358,0.00021639481],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025202177,0.00012450089,0.0001860825,0.00034720582,0.00055169704,0.00020638395,0.00077465054,0.00008087033,0.015097943],"category_scores_gemma":[0.0063573904,0.00006676863,0.00020182846,0.0012403405,0.00026340937,0.0005140139,0.000029974819,0.00024565024,0.00009390362],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032622862,0.0000667955,0.04853712,0.000003112593,0.000045121906,2.412536e-7,0.0012659783,0.013502581,0.00012790658,0.0003510588,0.46075314,0.4753143],"study_design_scores_gemma":[0.0007582235,0.00019096523,0.27521315,0.000027671977,0.00019067488,0.00011183157,0.0013299285,0.019587774,0.00025295693,0.009255975,0.6929712,0.00010965006],"about_ca_topic_score_codex":0.00028872056,"about_ca_topic_score_gemma":0.02053901,"teacher_disagreement_score":0.47520465,"about_ca_system_score_codex":0.0009379199,"about_ca_system_score_gemma":0.008779669,"threshold_uncertainty_score":0.9973336},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9731239,0.0009887237,0.014985749,0.0015733661,0.001167777,0.002199055,0.00026329843,0.00006378362,0.0056343614],"genre_scores_gemma":[0.99652034,0.0000073491424,0.0022349355,0.00017492405,0.00013685189,0.00024807328,0.00059889845,0.000010196445,0.00006845906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99595606,0.00032201098,0.0010363109,0.0002156334,0.0021899296,0.00028002265],"domain_scores_gemma":[0.9930383,0.00015832695,0.0011995853,0.00026713312,0.004856868,0.00047979027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028240364,0.00016331144,0.00022166684,0.0012940065,0.00032186304,0.0006827172,0.0003799936,0.00011046293,0.0004472959],"category_scores_gemma":[0.0010142046,0.00012172332,0.00011265456,0.0014698559,0.00009708176,0.0024639585,0.0000061618684,0.0002164495,0.000053428616],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014263774,0.00010926295,0.015107772,0.000043019532,0.00007681064,0.0000090093035,0.0012450218,0.0034894731,0.000010654335,0.0023296338,0.04226793,0.9351688],"study_design_scores_gemma":[0.004346442,0.0021916989,0.1038048,0.0019347301,0.00047696248,0.0017853138,0.019190533,0.36190492,0.00006215496,0.012576838,0.49071726,0.0010083454],"about_ca_topic_score_codex":0.000901271,"about_ca_topic_score_gemma":0.008185427,"teacher_disagreement_score":0.9341604,"about_ca_system_score_codex":0.00032470463,"about_ca_system_score_gemma":0.0041267485,"threshold_uncertainty_score":0.73206747},"labels":[],"label_agreement":null},{"id":"W4367030207","doi":"10.3138/cjpe.018.004","title":"Contribution de la cartographie de concepts à la modélisation des interventions en situation de crise en protection de la jeunesse","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Brainstorming; Context (archaeology); Elaboration; Structuring; Psychology; Agency (philosophy); Humanities; Sociology; Political science; Computer science; Geography; Philosophy; Social science","score_opus":0.1982564198429033,"score_gpt":0.5171773982803248,"score_spread":0.3189209784374215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76733565,0.00037449074,0.22977602,0.00051431183,0.00017707529,0.0008998602,0.0000070429805,0.000021034279,0.00089450454],"genre_scores_gemma":[0.990026,0.000068111505,0.0093346,0.000064590065,0.00013163999,0.00029131028,0.000020366351,0.000015368134,0.000048019425],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98688996,0.010551731,0.00085234875,0.00021190444,0.0010788123,0.0004152573],"domain_scores_gemma":[0.99525607,0.0011848458,0.00069069216,0.00019790766,0.0021910826,0.00047942248],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05428484,0.0001575222,0.00021620315,0.0008716555,0.0004302007,0.00070670445,0.00025941597,0.00028312168,0.00046864856],"category_scores_gemma":[0.01887705,0.00014834263,0.00024508068,0.00091437326,0.00027895614,0.0009140501,0.000007854512,0.00043133853,0.000012984061],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109305955,0.00040998147,0.18775444,0.000065364315,0.00015158091,0.00002966605,0.037105322,0.10583841,0.00544337,0.016708009,0.001110178,0.6452744],"study_design_scores_gemma":[0.0033755824,0.00075704174,0.5204257,0.00039059366,0.00045925708,0.00071285357,0.0101356115,0.24456824,0.0034721952,0.19594876,0.019384693,0.00036948672],"about_ca_topic_score_codex":0.00120961,"about_ca_topic_score_gemma":0.009832301,"teacher_disagreement_score":0.6449049,"about_ca_system_score_codex":0.0021094924,"about_ca_system_score_gemma":0.0061113434,"threshold_uncertainty_score":0.9995231},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98007244,0.00006767168,0.0023128747,0.012915631,0.00045141793,0.00054676266,0.0000058345995,0.000018036459,0.003609318],"genre_scores_gemma":[0.99111265,0.000035669764,0.008014449,0.00016553752,0.00041145936,0.000055777742,0.000011594711,0.000008602752,0.00018427505],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961205,0.002155943,0.00033023788,0.00013070641,0.00081371656,0.00044889058],"domain_scores_gemma":[0.9979491,0.00033267564,0.00042328,0.00007985323,0.0006168371,0.0005982574],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029988056,0.00008725513,0.00010802765,0.00015916883,0.0005091238,0.00045555487,0.0003060957,0.00022293707,0.00018288312],"category_scores_gemma":[0.010239267,0.000089457,0.000071866794,0.0004655471,0.00034236675,0.0009041088,0.000004550576,0.0003828829,0.0000044412755],"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":[0.000012889447,0.00006736414,0.18525983,0.000008963501,0.000019143601,0.000009076423,0.26976216,0.00025941877,0.0018630227,0.033667002,0.00094568357,0.5081254],"study_design_scores_gemma":[0.00027794312,0.00026192397,0.9218048,0.00003925603,0.0000625476,0.000021080732,0.013776895,0.0015177593,0.00017864238,0.046475563,0.015436877,0.0001467135],"about_ca_topic_score_codex":0.14397416,"about_ca_topic_score_gemma":0.88633895,"teacher_disagreement_score":0.74236476,"about_ca_system_score_codex":0.0014065572,"about_ca_system_score_gemma":0.023671422,"threshold_uncertainty_score":0.99883145},"labels":[],"label_agreement":null},{"id":"W4367030218","doi":"10.3138/cjpe.0014.009","title":"Empowerment Goes Large Scale: The Canada Prenatal Nutrition Experience","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Empowerment; Referral; Scale (ratio); Psychology; Program evaluation; Nursing; Stakeholder; Medical education; Public relations; Medicine; Political science; Economic growth; Economics","score_opus":0.15092984205043414,"score_gpt":0.4754820314681291,"score_spread":0.324552189417695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98716414,0.0006851057,0.00011690439,0.0058760573,0.00092845666,0.0011555289,0.000027955728,0.0000058656565,0.0040399623],"genre_scores_gemma":[0.9979649,0.000028366127,0.0004655759,0.00055129925,0.00021523192,0.00014253787,0.000015989315,0.0000063795515,0.00060969015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99521714,0.0004820122,0.000806788,0.00018989647,0.0029668582,0.00033728115],"domain_scores_gemma":[0.99722636,0.00015502494,0.00037639256,0.000329063,0.001507671,0.00040546266],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0072758747,0.00011625785,0.00016544624,0.00018129952,0.0004690179,0.00042562478,0.00063316827,0.000048047215,0.016290199],"category_scores_gemma":[0.00058996247,0.000072783965,0.000086783926,0.0006347762,0.00009189653,0.00061031344,0.000008635859,0.00019295505,0.000056424495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024303317,0.00008012014,0.012158743,0.000004048663,0.000016451913,0.000009761815,0.0043922393,0.0012361715,0.000008847936,0.00009126502,0.026823329,0.9551547],"study_design_scores_gemma":[0.0013176026,0.0003277271,0.09845378,0.000086180684,0.000049567523,0.000102811835,0.00954131,0.03841596,0.0002579262,0.0018420806,0.84941584,0.0001892411],"about_ca_topic_score_codex":0.0675094,"about_ca_topic_score_gemma":0.91790706,"teacher_disagreement_score":0.9549655,"about_ca_system_score_codex":0.00064115046,"about_ca_system_score_gemma":0.008551554,"threshold_uncertainty_score":0.99706906},"labels":[],"label_agreement":null},{"id":"W4367030226","doi":"10.3138/cjpe.25.003","title":"Pre-Measurement Triangulation: Considerations for Program Evaluation in Human Service Enterprises","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Triangulation; Service (business); Interpretation (philosophy); Computer science; Foundation (evidence); Order (exchange); Management science; Simple (philosophy); Process management; Business; Engineering; Epistemology; Mathematics; Marketing; Political science","score_opus":0.5377527213062439,"score_gpt":0.5605725975894016,"score_spread":0.022819876283157736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9719647,0.0002622204,0.0019123788,0.007452924,0.0023448702,0.01419029,0.000019880084,0.000029847119,0.0018228566],"genre_scores_gemma":[0.98389286,0.0000014100295,0.013111996,0.00026903712,0.00037850733,0.0022470844,0.000047370406,0.000016211103,0.000035527402],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99259895,0.00081814796,0.0017676989,0.00034609917,0.004096091,0.00037298616],"domain_scores_gemma":[0.9831877,0.0004484163,0.0010689083,0.00043754044,0.01443656,0.0004209198],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043001197,0.00019135769,0.000330217,0.0011372808,0.00044914059,0.0008370587,0.00039350518,0.00015758988,0.0034173387],"category_scores_gemma":[0.011389837,0.0001653066,0.00016911849,0.00096417643,0.000077601864,0.0009964562,0.00001199227,0.00034895382,0.00002043779],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050500566,0.00031258832,0.032901764,0.00001622,0.00004687245,0.0000019032796,0.0027712975,0.010220602,0.0014072143,0.0009948506,0.0028052202,0.94847095],"study_design_scores_gemma":[0.0073032477,0.0013528491,0.43991926,0.00013481211,0.00033899606,0.00005110561,0.0013039104,0.4202382,0.0006521096,0.07873759,0.04956065,0.0004072419],"about_ca_topic_score_codex":0.0005879531,"about_ca_topic_score_gemma":0.27724606,"teacher_disagreement_score":0.94806373,"about_ca_system_score_codex":0.00068952213,"about_ca_system_score_gemma":0.009653811,"threshold_uncertainty_score":0.9974937},"labels":[],"label_agreement":null},{"id":"W4367030229","doi":"10.3138/cjpe.0019.010","title":"The Experience of Developing a Package of Instruments to Measure the Critical Characteristics of Community Support Programs for People with a Severe Mental Illness","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Mental Health Association; University of Alberta; University of Toronto; Western University; Centre for Addiction and Mental Health","funders":"","keywords":"Mental illness; Measure (data warehouse); Process (computing); Process management; Program evaluation; Psychology; Computer science; Management science; Mental health; Business; Psychotherapist; Political science; Engineering","score_opus":0.26904403914193825,"score_gpt":0.48578448857306383,"score_spread":0.21674044943112558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926472,0.000029054027,0.0019540477,0.0034964639,0.0002041569,0.0015350675,0.000028169272,0.000001803717,0.000104065366],"genre_scores_gemma":[0.99482137,0.000003882863,0.004847396,0.00009724136,0.00003380157,0.00016465831,0.000010701334,0.0000065632867,0.000014365288],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99631697,0.0005412834,0.0010067107,0.00008487491,0.0018284745,0.00022167728],"domain_scores_gemma":[0.9940515,0.00047621844,0.0007936457,0.00031844294,0.004173037,0.00018713165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011539261,0.00009919221,0.00026996544,0.00014941959,0.00044574193,0.00012740139,0.0006658384,0.000040649757,0.00009193211],"category_scores_gemma":[0.002878663,0.000053600594,0.000081445876,0.0005704242,0.00026960636,0.00032929674,0.000026067157,0.00015463115,0.0000013122424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011078184,0.0000803385,0.04212083,0.0000192478,0.000031013962,1.3000299e-7,0.035074588,0.00003629178,0.000088650835,0.0003382109,0.00017569547,0.92192423],"study_design_scores_gemma":[0.0034319938,0.005531651,0.7756859,0.0006975712,0.00028448945,0.00015524274,0.16001058,0.010717932,0.0069325315,0.0023160402,0.033788193,0.00044784814],"about_ca_topic_score_codex":0.0003065832,"about_ca_topic_score_gemma":0.027409537,"teacher_disagreement_score":0.92147636,"about_ca_system_score_codex":0.00019546201,"about_ca_system_score_gemma":0.003345058,"threshold_uncertainty_score":0.9903377},"labels":[],"label_agreement":null},{"id":"W4367030230","doi":"10.3138/cjpe.25.006","title":"J. A. Morell. (2010). <i>Evaluation in the Face of Uncertainty: Anticipating Surprise and Responding to the Inevitable</i> . New York, NY: Guilford. 303 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Surprise; Face (sociological concept); Psychology; Social psychology; Philosophy; Linguistics","score_opus":0.38195705889810144,"score_gpt":0.489306172726481,"score_spread":0.10734911382837958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97392803,0.0006637206,0.0007040323,0.020397143,0.0009995942,0.0021811966,0.0000066451494,0.000003930155,0.0011157184],"genre_scores_gemma":[0.99683666,0.000018132265,0.002149673,0.00053970126,0.00020968504,0.00007463672,0.000008168595,0.000010208171,0.00015316202],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935129,0.0013944972,0.0012602515,0.0002551799,0.0032211856,0.0003559724],"domain_scores_gemma":[0.99508137,0.0010697863,0.0009144983,0.0005421978,0.0020542343,0.00033789303],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06610746,0.00015427057,0.00027918187,0.0011054416,0.00028150858,0.0005174442,0.0008343755,0.000095962794,0.0005069352],"category_scores_gemma":[0.012837441,0.000089143854,0.00008357279,0.002419371,0.000109398046,0.00049497356,0.000030323272,0.0004913728,0.000017515702],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037721493,0.000029042063,0.035523176,0.000004880024,0.000015345144,0.000001914008,0.012941006,0.02295475,0.00051923376,0.00038866437,0.012334967,0.9152493],"study_design_scores_gemma":[0.0029658242,0.0009919835,0.3857213,0.00024486118,0.00031771752,0.0000879686,0.026523266,0.44269356,0.00036570395,0.012022369,0.12766694,0.00039853007],"about_ca_topic_score_codex":0.0021274297,"about_ca_topic_score_gemma":0.094243295,"teacher_disagreement_score":0.9148508,"about_ca_system_score_codex":0.00017219892,"about_ca_system_score_gemma":0.0048424075,"threshold_uncertainty_score":0.99547786},"labels":[],"label_agreement":null},{"id":"W4367030235","doi":"10.3138/cjpe.0014.004","title":"Facilitating Development of Organizational Productive Capacity: A Role for Empowerment Evaluation","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empowerment; Organization development; Group cohesiveness; Organizational effectiveness; Organizational learning; Knowledge management; Organizational commitment; Psychology; Business; Public relations; Process management; Social psychology; Political science; Economics; Economic growth; Computer science","score_opus":0.3047962368639325,"score_gpt":0.4947043086901009,"score_spread":0.18990807182616842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99087316,0.0002297426,0.0031385068,0.00068915717,0.00038372193,0.0028273228,0.00002414336,0.0000062332215,0.001828019],"genre_scores_gemma":[0.9483567,0.0000016987802,0.050961994,0.00004849101,0.00012589157,0.00024863615,0.000060598955,0.000010661794,0.00018535047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994101,0.00051541824,0.0014706306,0.0002661362,0.0033922687,0.000254538],"domain_scores_gemma":[0.98799336,0.0003028274,0.00087203097,0.00022413654,0.0103426,0.00026506998],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024490627,0.0001370495,0.0002669061,0.0005532634,0.00031624635,0.00015798633,0.00033261138,0.00006951991,0.007293561],"category_scores_gemma":[0.0059314664,0.00011442015,0.000102620514,0.0008208286,0.0000844523,0.0005823103,0.0000066601388,0.00011096023,0.000043792264],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031934043,0.00007329392,0.004001392,0.000008112037,0.00004973735,1.2436803e-7,0.0144508,0.008671862,0.00033484137,0.00014994649,0.000361784,0.9718662],"study_design_scores_gemma":[0.0075542745,0.002367067,0.17106812,0.00031008828,0.00059211155,0.000061121405,0.029871454,0.53698254,0.011335951,0.08645786,0.15255184,0.00084756163],"about_ca_topic_score_codex":0.000073199175,"about_ca_topic_score_gemma":0.0032352887,"teacher_disagreement_score":0.9710186,"about_ca_system_score_codex":0.0007719047,"about_ca_system_score_gemma":0.011963779,"threshold_uncertainty_score":0.99363744},"labels":[],"label_agreement":null},{"id":"W4367030240","doi":"10.3138/cjpe.0019.007","title":"Conducting Evaluation Research with Hard-to-Follow Populations: Adopting a Participant-Centred Approach to Maximize Participant Retention","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Canadian Mental Health Association; University of Ottawa","funders":"","keywords":"Interview; Attrition; Participant observation; Psychology; Applied psychology; Investment (military); Medical education; Social psychology; Medicine; Sociology","score_opus":0.9454488731941052,"score_gpt":0.6050153259743052,"score_spread":0.3404335472198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030240","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782573,0.00043788354,0.0058883256,0.007988398,0.0006114818,0.0050282557,0.000007934869,0.000025360223,0.0017550439],"genre_scores_gemma":[0.90153587,0.000002159079,0.09688655,0.00024129801,0.00040967474,0.0006774125,0.000034161472,0.000024816474,0.00018802812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98607504,0.0029130802,0.0019069131,0.00059225864,0.0075691487,0.00094355136],"domain_scores_gemma":[0.98516935,0.00032835678,0.00086782203,0.00060197245,0.011695554,0.0013369402],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0662783,0.00022522188,0.00044261653,0.0018765283,0.0008201376,0.0011031947,0.00061029044,0.00011308354,0.0011148328],"category_scores_gemma":[0.01599719,0.00017499134,0.00014264799,0.0031038763,0.00009772569,0.0013256603,0.000036449106,0.00044880333,0.00025888465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014496903,0.00017167599,0.012551121,0.000008168469,0.00007135855,0.0000025138363,0.0125244465,0.25771716,0.00034294106,0.00049586577,0.0027249441,0.71324486],"study_design_scores_gemma":[0.0037577676,0.0016555787,0.091112696,0.00036623867,0.00073000765,0.00007911887,0.032848954,0.8421797,0.0003288779,0.0024466796,0.023968862,0.0005255009],"about_ca_topic_score_codex":0.0006463698,"about_ca_topic_score_gemma":0.016878406,"teacher_disagreement_score":0.7127193,"about_ca_system_score_codex":0.0012537441,"about_ca_system_score_gemma":0.0062174303,"threshold_uncertainty_score":0.9999338},"labels":[{"model":"gpt","categories":[],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4367030244","doi":"10.3138/cjpe.0015.012","title":"Reflections on Program Evaluation, 35 Years on","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Program evaluation; Psychology; Statistics; Mathematics","score_opus":0.6401574684201251,"score_gpt":0.6365197505771939,"score_spread":0.0036377178429312096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8817617,0.00034774287,0.00043824752,0.007690133,0.0038181022,0.006744652,0.000012378905,0.00006935975,0.09911762],"genre_scores_gemma":[0.9950123,0.00002361881,0.002540412,0.00071252225,0.00050967024,0.00054245,0.00002774747,0.000019884103,0.0006114027],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99179596,0.0011053646,0.0011370853,0.00035781492,0.005181741,0.000422061],"domain_scores_gemma":[0.9930512,0.00031493354,0.00081308285,0.000534385,0.0046421196,0.0006442788],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02127247,0.00018949174,0.000272568,0.0015034043,0.00040124237,0.0006674807,0.000557304,0.0001316164,0.0064469483],"category_scores_gemma":[0.004653381,0.00015456528,0.00020517726,0.001872531,0.00010685728,0.0005861836,0.00000935938,0.00040260676,0.00063473603],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004446663,0.0001891805,0.0033375816,0.0000010241033,0.000030475743,0.000008942214,0.0007013088,0.0111094015,0.000015982987,0.00080898055,0.009322418,0.97443026],"study_design_scores_gemma":[0.00231496,0.004467501,0.21496075,0.00012147304,0.00019845174,0.00010733374,0.0014881769,0.07536236,0.00005833198,0.018474888,0.68212825,0.00031749197],"about_ca_topic_score_codex":0.00024508918,"about_ca_topic_score_gemma":0.01590385,"teacher_disagreement_score":0.97411275,"about_ca_system_score_codex":0.0010950001,"about_ca_system_score_gemma":0.0062127803,"threshold_uncertainty_score":0.99942106},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9516914,0.006827896,0.000051782805,0.03732284,0.00015817721,0.0030000522,0.00002617633,0.000006047069,0.00091564434],"genre_scores_gemma":[0.9936106,0.00008900729,0.0051952363,0.0005528547,0.00019242223,0.0002877848,0.000039397128,0.000021358828,0.000011328646],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99138033,0.0043703094,0.002994356,0.000265026,0.00043577392,0.00055418053],"domain_scores_gemma":[0.99624354,0.0010941728,0.001537451,0.00025864216,0.00047475917,0.00039142976],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12983155,0.00014394989,0.0006166436,0.0017820612,0.000685472,0.00019154439,0.00022151548,0.000100677076,0.00014939663],"category_scores_gemma":[0.0055224905,0.00016731126,0.00004182666,0.000949488,0.00013830682,0.00091603794,0.000025121417,0.0007334706,0.000019498813],"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":[0.00003521902,0.00015578767,0.86522585,0.0001934892,0.000022118575,3.1142744e-7,0.08641687,0.0039626844,1.760528e-7,0.0015761541,0.00061244745,0.04179886],"study_design_scores_gemma":[0.004953198,0.0012678815,0.7627432,0.0011083682,0.000015783758,0.000046350044,0.1164523,0.089633025,7.738048e-7,0.019728636,0.0036778487,0.00037264757],"about_ca_topic_score_codex":0.06457866,"about_ca_topic_score_gemma":0.6764929,"teacher_disagreement_score":0.6119143,"about_ca_system_score_codex":0.0070611713,"about_ca_system_score_gemma":0.004125391,"threshold_uncertainty_score":0.99675053},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9717522,0.000010519656,0.015262452,0.0040325425,0.00092365214,0.007665483,0.000030054334,0.000020158735,0.00030288866],"genre_scores_gemma":[0.94569606,5.990187e-7,0.048292965,0.0030268512,0.00015830468,0.002665784,0.00013613023,0.00001962415,0.000003678723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9907188,0.0057330322,0.0016882136,0.00016212088,0.0010322897,0.00066554616],"domain_scores_gemma":[0.9919937,0.0014325379,0.0013149482,0.00029060035,0.0042389026,0.0007293029],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.067048974,0.00014260576,0.00025341648,0.0013597956,0.0009757167,0.00007255496,0.0004239771,0.00021871038,0.0006998732],"category_scores_gemma":[0.013814174,0.00013976727,0.00009406769,0.0009803838,0.00009451841,0.00092456216,0.00000925587,0.0013173595,0.0000052330183],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010612652,0.00016626042,0.063457966,0.0005598482,0.000021650876,7.171467e-7,0.04044617,0.0008347797,0.00059419347,0.00032394836,0.00031845915,0.8931699],"study_design_scores_gemma":[0.021833101,0.0033331506,0.29028624,0.001545081,0.00034391496,0.00001555171,0.04569371,0.5848254,0.00039848863,0.02418161,0.026960008,0.00058370864],"about_ca_topic_score_codex":0.010421206,"about_ca_topic_score_gemma":0.6005104,"teacher_disagreement_score":0.8925862,"about_ca_system_score_codex":0.0009875699,"about_ca_system_score_gemma":0.016819326,"threshold_uncertainty_score":0.9961685},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9860648,0.0006710701,0.000007486615,0.006361141,0.00014213625,0.006583677,0.000007979961,0.000010103584,0.00015163435],"genre_scores_gemma":[0.99294907,0.000015479114,0.0062212856,0.00007365385,0.00013455693,0.00053031713,0.000021687894,0.000011858366,0.000042114567],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960881,0.0016009995,0.0005443337,0.00010364692,0.0013491382,0.00031378673],"domain_scores_gemma":[0.99565613,0.00029080972,0.00035424944,0.00058398687,0.0027109608,0.0004038647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066207317,0.00012236115,0.00019695741,0.00012368143,0.00054621877,0.00013913237,0.00024345498,0.000077903474,0.00016025842],"category_scores_gemma":[0.004435526,0.00006805196,0.00021484577,0.00038198472,0.0003294845,0.00023304884,0.00001933786,0.00053322874,0.000010183018],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047301638,0.00041836913,0.030384418,0.000014326963,0.00011588415,0.0000018354234,0.0005329897,0.00024937687,0.0000629415,0.000040290764,0.00042890938,0.96727765],"study_design_scores_gemma":[0.005406899,0.0025018416,0.92333174,0.00018689217,0.00078856444,0.00016633657,0.0004492277,0.03961826,0.00090859033,0.001473796,0.025062822,0.00010504214],"about_ca_topic_score_codex":0.004869162,"about_ca_topic_score_gemma":0.1457333,"teacher_disagreement_score":0.9671726,"about_ca_system_score_codex":0.0012004882,"about_ca_system_score_gemma":0.007850841,"threshold_uncertainty_score":0.9977737},"labels":[],"label_agreement":null},{"id":"W4367030275","doi":"10.3138/cjpe.025.007","title":"Nick L. Smith &amp; Paul R. Brandon (Éds.). (2008). <i>Fundamental Issues in Evaluation</i> . New-York: Guilford, 266 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.35888501749321366,"score_gpt":0.5087863772677234,"score_spread":0.1499013597745097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.963967,0.0046022334,0.0005009831,0.014605898,0.0049885367,0.003424588,0.000024820674,0.000028753733,0.007857138],"genre_scores_gemma":[0.9873266,0.00009050622,0.009245792,0.0005207487,0.0008563195,0.00013261869,0.00007652198,0.000030032033,0.0017208431],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99057615,0.0010462325,0.0019586345,0.000476353,0.005294312,0.0006482903],"domain_scores_gemma":[0.99329424,0.00037589204,0.0011937608,0.0007275805,0.0034126514,0.0009958881],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03643211,0.0002959954,0.0005030139,0.0013447333,0.0003168058,0.0009989737,0.0009913413,0.00022615524,0.017351555],"category_scores_gemma":[0.0062986305,0.0002420595,0.00023112171,0.0015440802,0.00017386787,0.0013333085,0.000031972493,0.00077517855,0.0005646269],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000492524,0.00009465228,0.07073606,0.0000047325548,0.000030442618,0.000005506374,0.0015847434,0.0018280655,0.0002713165,0.00010314123,0.12395574,0.80133635],"study_design_scores_gemma":[0.0059676804,0.000519817,0.16864802,0.00011401982,0.00017668979,0.00012900868,0.0013944908,0.030425167,0.00031029424,0.016317664,0.7755411,0.0004560358],"about_ca_topic_score_codex":0.002705815,"about_ca_topic_score_gemma":0.26385763,"teacher_disagreement_score":0.8008803,"about_ca_system_score_codex":0.00068936,"about_ca_system_score_gemma":0.0145571055,"threshold_uncertainty_score":0.9921959},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90347755,0.0010500615,0.0002622047,0.073546216,0.004511382,0.005137558,0.0002516459,0.00005661897,0.011706739],"genre_scores_gemma":[0.9876043,0.000017187293,0.008622724,0.00033957988,0.0016902301,0.00020139557,0.00025852033,0.0000027765175,0.0012632771],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979398,0.00010121148,0.00049954327,0.00024185826,0.00077784865,0.00043972585],"domain_scores_gemma":[0.99550265,0.0003637683,0.00036433522,0.000106636944,0.0031741883,0.0004884231],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040221508,0.00014084327,0.00023541611,0.00032653107,0.0006872192,0.000248925,0.00044706196,0.00013720967,0.0014202025],"category_scores_gemma":[0.0017681168,0.00006540472,0.00017137411,0.0019374747,0.00017556835,0.00018430963,0.000021530275,0.00038617337,0.000033667126],"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":[0.000022714421,0.00008381446,0.005080859,0.0000045652464,0.00020312787,0.0000010885483,0.00046096646,0.000063306215,0.0030804905,0.001760678,0.3819579,0.6072805],"study_design_scores_gemma":[0.00055203575,0.00031013312,0.13771361,0.0000394062,0.0004671683,0.000007095277,0.004512297,0.0007035378,0.00036015146,0.004309772,0.85076827,0.00025653743],"about_ca_topic_score_codex":0.0027291197,"about_ca_topic_score_gemma":0.10061393,"teacher_disagreement_score":0.60702395,"about_ca_system_score_codex":0.00018974766,"about_ca_system_score_gemma":0.0012991183,"threshold_uncertainty_score":0.99949265},"labels":[],"label_agreement":null},{"id":"W4367030286","doi":"10.3138/cjpe.25.005","title":"Managing Evaluataion: Responding to Common Problems with a 10-Step Process","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Centers for Disease Control and Prevention","keywords":"Conceptualization; Process (computing); Stakeholder; Unit (ring theory); Public sector; Relation (database); Business; Process management; Program evaluation; Knowledge management; Management science; Public relations; Sociology; Psychology; Computer science; Political science; Economics; Public administration","score_opus":0.2596048059938968,"score_gpt":0.5263633695337143,"score_spread":0.26675856353981753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9730007,0.00010122962,0.0021958787,0.009118632,0.0009620164,0.0025225244,0.000005678142,0.000022672068,0.012070672],"genre_scores_gemma":[0.9905291,0.0000013882202,0.007890099,0.00029793865,0.00024456414,0.00018764385,0.000009661892,0.000020295964,0.00081926625],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99387604,0.00047419753,0.0010264233,0.00033522584,0.0038531974,0.00043490672],"domain_scores_gemma":[0.99251676,0.00022950023,0.000794004,0.00049265247,0.0050725886,0.0008945168],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026325282,0.00018619122,0.00031376278,0.0024356206,0.0004008647,0.00089533563,0.0008251159,0.00009134764,0.005681521],"category_scores_gemma":[0.0024423017,0.00013181378,0.00008713549,0.0029440962,0.00009610779,0.0010252096,0.000019432871,0.00045090186,0.00020636305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011400229,0.00004785305,0.026762808,0.000013990936,0.000031232892,0.0000145768145,0.0026821622,0.011171338,0.0002836044,0.00054412783,0.0028816322,0.9554527],"study_design_scores_gemma":[0.0051003485,0.0058612823,0.0959582,0.0007478524,0.0004427897,0.0007180178,0.008277957,0.34018025,0.0011154689,0.032659244,0.50786227,0.0010763302],"about_ca_topic_score_codex":0.00019246005,"about_ca_topic_score_gemma":0.05245799,"teacher_disagreement_score":0.95437634,"about_ca_system_score_codex":0.00027174468,"about_ca_system_score_gemma":0.0056328,"threshold_uncertainty_score":0.99923456},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5765577,0.002829104,0.34449196,0.06420604,0.0020920471,0.00861205,0.000016717357,0.000026347241,0.0011680305],"genre_scores_gemma":[0.89974403,0.000032879543,0.09939233,0.00041014093,0.00021922821,0.0001817804,0.0000111455365,0.000007137501,0.0000013285637],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973828,0.00040677877,0.00042263253,0.00009679987,0.0014777374,0.00021321225],"domain_scores_gemma":[0.99289244,0.00063569105,0.00039835778,0.000089734494,0.0058971033,0.00008668902],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019952245,0.00007318438,0.00009855479,0.00015342853,0.00072062976,0.00015298635,0.00033691394,0.00012538834,0.000055970897],"category_scores_gemma":[0.011702478,0.000050712126,0.00006846978,0.0009059754,0.00015769589,0.00015750088,0.0000038074947,0.00023446203,8.885648e-7],"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":[0.000014212074,0.00013753441,0.008069586,0.00003652204,0.00011162581,7.157874e-7,0.31075588,0.19168942,0.00007358619,0.25461861,0.006100172,0.22839215],"study_design_scores_gemma":[0.0006881121,0.000049854745,0.02755391,0.0000841507,0.00015252287,0.0000027975861,0.019625137,0.3312945,0.000039729723,0.6180697,0.0023170947,0.00012250252],"about_ca_topic_score_codex":0.0030003616,"about_ca_topic_score_gemma":0.063796505,"teacher_disagreement_score":0.3634511,"about_ca_system_score_codex":0.00056489214,"about_ca_system_score_gemma":0.021330522,"threshold_uncertainty_score":0.9966224},"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":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733631,0.009926963,0.000006345106,0.008111097,0.0007214124,0.004762296,0.000013803518,0.0000075984512,0.0030873853],"genre_scores_gemma":[0.9982869,0.00023924583,0.0005220276,0.000406914,0.0001450481,0.00029254812,0.00008690858,0.000013545708,0.000006853146],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99560183,0.0022279243,0.0009286688,0.00012324844,0.00074416364,0.0003741479],"domain_scores_gemma":[0.99808323,0.000042734606,0.00079933007,0.0002999469,0.0005136448,0.00026112093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013167648,0.00013304764,0.00021014872,0.00041797283,0.000251965,0.00003261689,0.00022001991,0.00006343191,0.00031713184],"category_scores_gemma":[0.00000921659,0.0001131378,0.000080791746,0.00039482897,0.00007636256,0.00020639604,0.0000147210285,0.00025475305,0.000009029101],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033258948,0.0002824555,0.0016002316,0.00007891718,0.00007139913,0.000008146509,0.06866314,0.00007726878,5.969784e-7,0.00037568778,0.0008732368,0.92793566],"study_design_scores_gemma":[0.009556823,0.0033486176,0.17014247,0.00033318315,0.000496292,0.0011740775,0.77466744,0.002222246,0.00002145387,0.002077265,0.035664808,0.00029529873],"about_ca_topic_score_codex":0.045143303,"about_ca_topic_score_gemma":0.8120638,"teacher_disagreement_score":0.9276404,"about_ca_system_score_codex":0.0013769009,"about_ca_system_score_gemma":0.0010419192,"threshold_uncertainty_score":0.9612152},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70854896,0.004385716,0.088781625,0.11519211,0.0018486726,0.014205454,0.0019110661,0.000121156976,0.065005235],"genre_scores_gemma":[0.87766296,0.00002042621,0.12089752,0.00011163885,0.00085233455,0.0002016286,0.00008969284,0.00001965876,0.00014413516],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99278665,0.003272829,0.00061603036,0.00037909814,0.0021388396,0.0008065375],"domain_scores_gemma":[0.991225,0.0018447784,0.0003307524,0.0004575688,0.0048883217,0.0012535792],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055141818,0.0001290577,0.00033028628,0.0012548538,0.0020961734,0.0006446068,0.0012058647,0.00013946893,0.0009924623],"category_scores_gemma":[0.020281328,0.00012356792,0.00012741063,0.004539721,0.00073257013,0.00062981516,0.000050420345,0.0009871812,0.00007754158],"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":[0.000033533313,0.0003205774,0.006745246,0.000024916555,0.0005196854,0.00002356862,0.041030418,0.00013991333,0.0025693753,0.06266011,0.0463251,0.83960754],"study_design_scores_gemma":[0.0007893715,0.00085423695,0.034776684,0.00007388092,0.0007344426,0.0000040140085,0.043866016,0.0064896047,0.00009096851,0.03066954,0.8811936,0.00045767336],"about_ca_topic_score_codex":0.038780257,"about_ca_topic_score_gemma":0.68573207,"teacher_disagreement_score":0.8391499,"about_ca_system_score_codex":0.00042643154,"about_ca_system_score_gemma":0.008817819,"threshold_uncertainty_score":0.9999208},"labels":[],"label_agreement":null},{"id":"W4367030299","doi":"10.3138/cjpe.25.004","title":"Jugement crédible en évaluation de programme : définition et conditions requises","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Viewpoints; Argumentation theory; Valuation (finance); Coherence (philosophical gambling strategy); Management science; Psychology; Quality (philosophy); Sociology; Epistemology; Business; Economics; Philosophy; Mathematics; Accounting","score_opus":0.4673144395102768,"score_gpt":0.5733540275195889,"score_spread":0.10603958800931207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367030299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9723673,0.00009800457,0.0039496794,0.00984735,0.0018859629,0.0018995127,0.00002231337,0.000031907988,0.009897961],"genre_scores_gemma":[0.9762732,0.000014002199,0.022259442,0.00051147485,0.0003435128,0.00028458625,0.00009431187,0.000015305319,0.0002042117],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943432,0.0012082848,0.0011312899,0.00025184223,0.0026227126,0.00044262075],"domain_scores_gemma":[0.9935392,0.000547316,0.00085437216,0.00037090958,0.0040573296,0.00063086604],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03927157,0.0001592969,0.0002324731,0.0009845353,0.00034923467,0.0007978073,0.0004824794,0.0001461933,0.006255761],"category_scores_gemma":[0.008533667,0.0001338831,0.00016737898,0.0008430694,0.00012942852,0.0011641069,0.000015954985,0.00048770482,0.00016979803],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021499187,0.00018605267,0.034525752,0.000008167075,0.000050521223,0.000008277112,0.0030876133,0.0033439852,0.002685733,0.012845394,0.00795582,0.93528116],"study_design_scores_gemma":[0.0029814045,0.0015438625,0.44769883,0.000108014036,0.00036734145,0.00023189669,0.0038760283,0.10201637,0.0017033287,0.19874142,0.24025163,0.00047988092],"about_ca_topic_score_codex":0.00043804853,"about_ca_topic_score_gemma":0.033567347,"teacher_disagreement_score":0.9348013,"about_ca_system_score_codex":0.00043195608,"about_ca_system_score_gemma":0.011362536,"threshold_uncertainty_score":0.99981785},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7136883,0.21864893,0.00064394914,0.055899598,0.002916618,0.006943573,0.0003347742,0.000010637423,0.0009136324],"genre_scores_gemma":[0.9360294,0.010361757,0.00678685,0.00062686455,0.0011980217,0.0014653088,0.0007269542,0.00011802796,0.042686854],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923034,0.0025065516,0.0010783375,0.00050288107,0.0022005462,0.0014083209],"domain_scores_gemma":[0.9935787,0.00031869565,0.00037658316,0.0002945028,0.0028548576,0.002576681],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015244012,0.0003892968,0.00074741687,0.0009107196,0.00055907073,0.00023738875,0.0003314304,0.00020964567,0.007187209],"category_scores_gemma":[0.016094267,0.0003982225,0.0002557513,0.0008732348,0.0004743811,0.0005544816,0.00006728539,0.0010457347,0.000052458898],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032061903,0.00044178154,0.0809865,0.0007959464,0.00030063512,0.0017998775,0.003119072,0.000040254687,0.000026234886,0.00007869451,0.05395461,0.85813576],"study_design_scores_gemma":[0.010166297,0.0069328356,0.45973095,0.0031421268,0.0015512843,0.0013080931,0.0064490903,0.01464982,0.000037325983,0.0038663058,0.49164554,0.0005203335],"about_ca_topic_score_codex":0.011342368,"about_ca_topic_score_gemma":0.035093833,"teacher_disagreement_score":0.8576154,"about_ca_system_score_codex":0.0034878764,"about_ca_system_score_gemma":0.0052511734,"threshold_uncertainty_score":0.999847},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8569223,0.00009261272,0.0005338263,0.13808875,0.0010485034,0.0020895393,0.0000075243834,0.000018591545,0.0011983548],"genre_scores_gemma":[0.9944047,0.000003067166,0.0011682138,0.0024030134,0.00061865954,0.00016294449,0.000003927976,0.00000953548,0.0012259753],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968699,0.00029864852,0.00061077886,0.00016815928,0.0017743147,0.00027816248],"domain_scores_gemma":[0.99691683,0.0004870167,0.00028051663,0.00030392234,0.0014851852,0.00052650657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014245923,0.000092131406,0.00012143348,0.00050673436,0.00040567698,0.0007096016,0.00090364064,0.000031916312,0.00025033983],"category_scores_gemma":[0.0069542723,0.0000490379,0.00008426692,0.0010990078,0.000052752763,0.00024332418,0.00004964398,0.00016327962,0.00021173086],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007068462,0.000017869143,0.008854111,9.960122e-7,0.000024534302,0.0000020192056,0.0050117024,0.0016885012,0.00019819768,0.002220683,0.07026987,0.9117044],"study_design_scores_gemma":[0.00012860954,0.00065613247,0.19849277,0.00004424163,0.000040070296,0.000008707607,0.010354482,0.0024171642,0.00051922444,0.0061775013,0.78103065,0.00013047585],"about_ca_topic_score_codex":0.0009870117,"about_ca_topic_score_gemma":0.022023486,"teacher_disagreement_score":0.91157395,"about_ca_system_score_codex":0.0002777694,"about_ca_system_score_gemma":0.0034116153,"threshold_uncertainty_score":0.995822},"labels":[],"label_agreement":null},{"id":"W4384704009","doi":"10.3138/cjpe.75471","title":"Doing the Inner Work for Sustainable Practices","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mindset; Work (physics); Sociology; Grounded theory; Reflective practice; Engineering ethics; Psychology; Epistemology; Public relations; Pedagogy; Qualitative research; Social science; Political science; Engineering","score_opus":0.46181610888955293,"score_gpt":0.5772504504403074,"score_spread":0.1154343415507545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8820776,0.0013972542,0.0061212797,0.08007551,0.0032525163,0.0072574727,0.000007315421,0.000059836628,0.019751236],"genre_scores_gemma":[0.99313676,0.000010167578,0.003010128,0.000319728,0.00036824716,0.00023848843,0.000009206922,0.000009874887,0.0028973925],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967588,0.00045903013,0.0006358381,0.00014147692,0.0016537933,0.00035104807],"domain_scores_gemma":[0.9922365,0.0012785735,0.0012491441,0.00024939547,0.004762447,0.00022394504],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040824447,0.00007791218,0.00013528187,0.0005964659,0.000557767,0.0009785369,0.00051343074,0.000049740353,0.00068641076],"category_scores_gemma":[0.016198318,0.000046130943,0.00010934413,0.002105596,0.00006403236,0.00096344255,0.000014882268,0.00015744929,0.00011262929],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025129328,0.000012424478,0.012464137,0.0000063355915,0.000026973898,0.000006639375,0.0018201679,0.007813207,0.0000052599044,0.0020375447,0.081564344,0.89421785],"study_design_scores_gemma":[0.0005029915,0.00023015057,0.03701074,0.00002204948,0.00006609606,0.000010802344,0.011643618,0.024256555,0.000019027453,0.017247166,0.90891147,0.000079348036],"about_ca_topic_score_codex":0.0002655462,"about_ca_topic_score_gemma":0.0048017683,"teacher_disagreement_score":0.8941385,"about_ca_system_score_codex":0.00023714484,"about_ca_system_score_gemma":0.0050067906,"threshold_uncertainty_score":0.9920887},"labels":[],"label_agreement":null},{"id":"W4384704011","doi":"10.3138/cjpe.74373","title":"Building Capacity With Evaluation Standards and Guidelines in Prince Edward Island: Responding to Academics’ “Call to Action”","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Government (linguistics); Process (computing); Action (physics); Capacity building; Public relations; Political science; Resource (disambiguation); Public administration; Business; Sociology; Computer science; Law","score_opus":0.422866600441089,"score_gpt":0.5731474583533296,"score_spread":0.1502808579122406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798857,0.00009059007,0.0065100095,0.010899602,0.0004885542,0.0017140907,0.000020973466,0.000015102366,0.00037535783],"genre_scores_gemma":[0.9795263,0.0000199499,0.019342907,0.0005025688,0.00021680552,0.00016575595,0.000005412727,0.000014888356,0.00020544491],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99281067,0.00072921644,0.001113736,0.00035510797,0.0046064677,0.000384783],"domain_scores_gemma":[0.99169815,0.00030277975,0.00044231306,0.00023753742,0.00667792,0.0006413167],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.060223598,0.00015124545,0.000276524,0.003738445,0.00022383126,0.00043599968,0.00034455335,0.0001005771,0.00026601102],"category_scores_gemma":[0.01575067,0.00011730407,0.000045479414,0.0041513615,0.000044218927,0.00076202635,0.000029469978,0.00029494896,0.000029477142],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010580921,0.0000073696933,0.05892661,0.000005771832,0.000014442387,0.00000431138,0.0024960667,0.06929574,0.00039665357,0.00020948282,0.0055378554,0.8629999],"study_design_scores_gemma":[0.0025431064,0.0013879014,0.4558022,0.000691182,0.0001217109,0.0000780818,0.0030783932,0.26988432,0.0005465352,0.008216789,0.25719285,0.0004569135],"about_ca_topic_score_codex":0.00047251978,"about_ca_topic_score_gemma":0.084180675,"teacher_disagreement_score":0.862543,"about_ca_system_score_codex":0.0013947533,"about_ca_system_score_gemma":0.0056316215,"threshold_uncertainty_score":0.99902546},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4384704021","doi":"10.3138/cjpe.76349","title":"Sustainability-Ready Evaluation: A Call to Action","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustainability; Nexus (standard); Call to action; Work (physics); Action (physics); Sustainability science; Environmental resource management; Business; Sustainability organizations; Environmental planning; Political science; Computer science; Engineering; Ecology; Marketing; Geography; Economics","score_opus":0.5953134200335379,"score_gpt":0.6226408964927189,"score_spread":0.027327476459180988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9510036,0.00017006502,0.0015477606,0.0339226,0.003051926,0.0048125796,0.000014530288,0.000056953646,0.0054199486],"genre_scores_gemma":[0.99717647,0.000004695412,0.00084401754,0.0003343243,0.00036226446,0.00033836195,0.000039066163,0.000013655992,0.0008871267],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99177986,0.001234329,0.001161482,0.00032362202,0.005053306,0.00044737445],"domain_scores_gemma":[0.9828637,0.00037951415,0.0005603371,0.000467924,0.014895845,0.00083264755],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.05154241,0.00014903475,0.00026682267,0.0018635408,0.0003412631,0.0005726919,0.0005424152,0.000101987025,0.0030658408],"category_scores_gemma":[0.017539142,0.00012189112,0.00014056133,0.0032486992,0.00006601941,0.0008381197,0.000022257871,0.00022728686,0.0008679425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019991377,0.00002565791,0.00940404,0.000005031366,0.00001870472,0.000005427436,0.0015322226,0.025566872,0.000026858921,0.00028393604,0.03765589,0.9254554],"study_design_scores_gemma":[0.001404551,0.0010062333,0.28402156,0.000040159262,0.00017353924,0.00004300146,0.006899802,0.2645583,0.00009120157,0.034435775,0.4070535,0.0002723858],"about_ca_topic_score_codex":0.000763083,"about_ca_topic_score_gemma":0.031059371,"teacher_disagreement_score":0.925183,"about_ca_system_score_codex":0.001943955,"about_ca_system_score_gemma":0.015139469,"threshold_uncertainty_score":0.99991},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99212104,0.0005257704,0.000047547015,0.0003131554,0.000326439,0.0023645824,0.0000040252103,0.000029948977,0.0042674923],"genre_scores_gemma":[0.99664795,0.00027588737,0.0020668963,0.000017347546,0.00078812713,0.000046681947,0.000053321914,0.00001773661,0.000086023596],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99701595,0.0007280343,0.0004139544,0.00018078608,0.0010383697,0.00062291994],"domain_scores_gemma":[0.99643445,0.00012419523,0.00047500772,0.000108763095,0.0022913693,0.00056624046],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.012846383,0.00010881021,0.00015855543,0.0004706832,0.005870278,0.00032261468,0.00016719637,0.00012376008,0.00015200485],"category_scores_gemma":[0.0002160716,0.000090701215,0.000028499004,0.0009404954,0.0001460886,0.0007254213,5.1546976e-7,0.00019784605,0.0000045637967],"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":[0.000010486539,0.000039205817,0.023061853,0.000044823937,0.00003081169,0.0000048558672,0.8049101,0.0001838729,7.631568e-7,0.0022107798,0.000013513094,0.16948888],"study_design_scores_gemma":[0.0031353463,0.003736425,0.13320403,0.0011617763,0.0013007284,0.00012951616,0.59323657,0.013204388,0.00012619136,0.05553032,0.19407831,0.0011564383],"about_ca_topic_score_codex":0.09662145,"about_ca_topic_score_gemma":0.9416002,"teacher_disagreement_score":0.84497875,"about_ca_system_score_codex":0.00057174766,"about_ca_system_score_gemma":0.06133553,"threshold_uncertainty_score":0.995424},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3573177,0.07480315,0.0003454156,0.0352124,0.011113903,0.001631526,0.00032378762,0.000089680056,0.5191625],"genre_scores_gemma":[0.9872375,0.000505272,0.0004190274,0.00013599951,0.004957391,0.000018873508,0.00004141492,0.000026813515,0.00665772],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982658,0.00040621354,0.00041159362,0.000103784725,0.00041028342,0.00040229675],"domain_scores_gemma":[0.9976857,0.00015578754,0.00030650396,0.00011930481,0.0011802155,0.0005525144],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004051792,0.00012308868,0.00018874853,0.0005902698,0.00045259195,0.0007468748,0.00017269659,0.000107535074,0.00450268],"category_scores_gemma":[0.0011512612,0.00012193488,0.00020565704,0.00027817787,0.00028206132,0.00014810302,0.000006509233,0.00026238823,0.00014889376],"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":[0.0000074607487,0.00009704818,0.0015545229,0.000053797627,0.00042384048,0.0003941915,0.009659845,0.0022309374,0.0000039883857,0.31046063,0.03802626,0.63708746],"study_design_scores_gemma":[0.00044688198,0.0002108264,0.00323924,0.000120965895,0.0012980227,0.000043873588,0.0027639773,0.0317155,0.000010549721,0.037427913,0.922566,0.00015623908],"about_ca_topic_score_codex":0.019542458,"about_ca_topic_score_gemma":0.024132023,"teacher_disagreement_score":0.8845397,"about_ca_system_score_codex":0.0004104469,"about_ca_system_score_gemma":0.0036099183,"threshold_uncertainty_score":0.99640733},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91690576,0.003740578,0.000604592,0.041931346,0.003841021,0.0015290111,0.000022899685,0.00014359044,0.03128118],"genre_scores_gemma":[0.99701923,0.00006387133,0.0015878705,0.00014173507,0.0004969593,0.00003317974,0.000015209439,0.0000108112645,0.0006311612],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99800664,0.00051802467,0.00038018296,0.00013337033,0.0006352398,0.0003265581],"domain_scores_gemma":[0.9981095,0.00026721891,0.0002559209,0.000097824566,0.00049187156,0.00077764154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005978892,0.00007929512,0.00021214338,0.00044809713,0.00042596477,0.00018574984,0.00012732214,0.00010934101,0.0002910756],"category_scores_gemma":[0.0029895,0.00007751179,0.000098562945,0.0014061467,0.0001970641,0.00021369831,0.000004046002,0.00020815052,0.000024956638],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002391597,0.00016648496,0.043968804,0.000039845705,0.0009861365,0.000073756586,0.10176383,0.00007617136,0.00008024307,0.009439528,0.5025876,0.34079367],"study_design_scores_gemma":[0.00041921975,0.00022531445,0.0055426806,0.000036095367,0.0012751526,0.000011818642,0.02456095,0.0013178579,0.0000021564508,0.0029338514,0.9634948,0.0001801227],"about_ca_topic_score_codex":0.006631699,"about_ca_topic_score_gemma":0.067202255,"teacher_disagreement_score":0.46090716,"about_ca_system_score_codex":0.00045159148,"about_ca_system_score_gemma":0.0043213186,"threshold_uncertainty_score":0.99998325},"labels":[],"label_agreement":null},{"id":"W4384704143","doi":"10.3138/cjpe.71619","title":"How to Conduct a Metaevaluation?: A Metaevaluation Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Strengths and weaknesses; Computer science; Evaluation methods; Quality (philosophy); Process (computing); Management science; Process management; Psychology; Reliability engineering; Social psychology; Business; Engineering","score_opus":0.718641825237931,"score_gpt":0.625746580813898,"score_spread":0.09289524442403296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704143","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55420166,0.0018467533,0.023782926,0.37212098,0.009968706,0.013501498,0.000069829606,0.00022625091,0.024281377],"genre_scores_gemma":[0.9763773,0.000019533005,0.019804832,0.0013517824,0.00048871886,0.0004087924,0.000038970426,0.000029101804,0.0014809899],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98263407,0.002760812,0.00147262,0.000462598,0.012114012,0.0005559006],"domain_scores_gemma":[0.9665969,0.0014233445,0.0013564886,0.0006158876,0.029018853,0.0009884953],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12004442,0.00023217803,0.00045515018,0.0028329527,0.00041894207,0.0018837444,0.000823913,0.000122231,0.0021467884],"category_scores_gemma":[0.12740064,0.0001829034,0.00025711165,0.0051423684,0.00008354901,0.0028918497,0.00003431151,0.00029869957,0.0012579171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043251348,0.00004935063,0.0007975313,0.0000051211123,0.00013051475,0.00001445862,0.0031129322,0.014965108,0.00046736686,0.0014476829,0.07079294,0.90817374],"study_design_scores_gemma":[0.0015721638,0.0010666269,0.022401962,0.00004507059,0.00060437975,0.00009929321,0.008631141,0.1383503,0.00038205326,0.017059067,0.80945426,0.00033368447],"about_ca_topic_score_codex":0.00030924272,"about_ca_topic_score_gemma":0.008229631,"teacher_disagreement_score":0.9078401,"about_ca_system_score_codex":0.0012490222,"about_ca_system_score_gemma":0.014153463,"threshold_uncertainty_score":0.9995197},"labels":[],"label_agreement":null},{"id":"W4384704152","doi":"10.3138/cjpe.76738","title":"<i>Evaluating and Valuing in Social Research</i> , by Thomas A. Schwandt and Emily F. Gates","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Psychology; Positive economics; Economics","score_opus":0.6880176902655514,"score_gpt":0.6452034549058989,"score_spread":0.04281423535965245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99083525,0.0012206824,0.000024114473,0.0053924355,0.00021360292,0.0006986524,0.0000064799087,0.000009866944,0.0015989349],"genre_scores_gemma":[0.9984538,0.00006906959,0.0009407045,0.00009080755,0.00015196801,0.00005685071,0.000010854784,0.00001058918,0.00021535633],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941303,0.0014985636,0.0008158329,0.0002659169,0.002860298,0.00042910167],"domain_scores_gemma":[0.9962712,0.000866381,0.00032214055,0.0001259876,0.0020696272,0.00034469576],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0672141,0.00010416792,0.00022950665,0.0013083828,0.0005945756,0.00078511453,0.00024968587,0.00008889561,0.00018796284],"category_scores_gemma":[0.0070093935,0.0000865421,0.00004156066,0.0019187593,0.00022004121,0.00070683984,0.00003739398,0.00037445972,0.000025349236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017281935,0.000014229761,0.06854527,0.000009132345,0.000011187213,0.000008082562,0.0041796947,0.00026333862,0.00073262135,0.00046944548,0.015356894,0.9103928],"study_design_scores_gemma":[0.004040427,0.0013412047,0.49473506,0.00026171975,0.00007258492,0.00007078692,0.01913971,0.3130351,0.0003616769,0.10595063,0.0605789,0.0004122088],"about_ca_topic_score_codex":0.00045422564,"about_ca_topic_score_gemma":0.0065515405,"teacher_disagreement_score":0.9099806,"about_ca_system_score_codex":0.00023826433,"about_ca_system_score_gemma":0.002448206,"threshold_uncertainty_score":0.96049935},"labels":[],"label_agreement":null},{"id":"W4384704212","doi":"10.3138/cjpe.77058-fr","title":"Nos racines et nos liens : une célébration de bons remèdes en évaluation autochtone","year":2023,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Forestry; Geography","score_opus":0.385499950579361,"score_gpt":0.5506690169872253,"score_spread":0.16516906640786427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7521996,0.0033995658,0.015069046,0.20550275,0.009386982,0.0049556927,0.000096191616,0.000119789314,0.009270419],"genre_scores_gemma":[0.97978765,0.00055277534,0.011967051,0.0008314942,0.0011220576,0.00023354945,0.00020129398,0.000046862435,0.0052572545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98942494,0.003604267,0.0019702003,0.00045134846,0.0037145314,0.00083468645],"domain_scores_gemma":[0.990989,0.0012274563,0.0014127438,0.0004829973,0.0049380464,0.00094971684],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.05055136,0.00032966494,0.00049111457,0.0018944258,0.000593647,0.0010739495,0.00056919234,0.00036088022,0.0034902352],"category_scores_gemma":[0.010864343,0.00031138473,0.00030160398,0.0037372431,0.00024447075,0.0020937496,0.00003406862,0.000625414,0.00094621093],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003617453,0.00011037563,0.0101724,0.000034565102,0.00009116818,0.000032906704,0.015236776,0.06994353,0.0004475536,0.0034873164,0.022775996,0.87763125],"study_design_scores_gemma":[0.0015553465,0.0010249723,0.25443795,0.00039000754,0.00042003774,0.00013974584,0.004761764,0.6014761,0.00022372125,0.0227195,0.112514764,0.00033613737],"about_ca_topic_score_codex":0.004701063,"about_ca_topic_score_gemma":0.10931039,"teacher_disagreement_score":0.8772951,"about_ca_system_score_codex":0.0014781294,"about_ca_system_score_gemma":0.029573822,"threshold_uncertainty_score":0.99996305},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98935413,0.0003130628,0.0003646178,0.0015102482,0.0018049971,0.004722669,0.000029071454,0.00005391183,0.0018473031],"genre_scores_gemma":[0.99090147,0.0002548748,0.0065784818,0.000072859984,0.0015534582,0.00018705457,0.00022792355,0.00003327287,0.0001906059],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9947671,0.0025807342,0.00058353343,0.00017861054,0.001129648,0.0007603717],"domain_scores_gemma":[0.993994,0.00031034503,0.0009069174,0.0002231419,0.0038344814,0.00073113677],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.013757609,0.00017263507,0.00028893998,0.0009888941,0.009186664,0.00032143213,0.00044488523,0.00019492792,0.00006484987],"category_scores_gemma":[0.00035138492,0.00016639166,0.000114784816,0.0013562738,0.00034202746,0.00073813944,9.933215e-7,0.00041834483,0.0000132089435],"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":[0.000015728408,0.000059348946,0.0029936067,0.00001779505,0.000051512976,0.0000018465928,0.8864986,0.00016026676,2.7691524e-7,0.0067672734,0.00018660809,0.10324718],"study_design_scores_gemma":[0.00045612536,0.0012296512,0.00827183,0.00017487389,0.0001249603,0.0000067605256,0.8634752,0.00065557467,0.000013881668,0.039818253,0.08549767,0.0002752279],"about_ca_topic_score_codex":0.14906543,"about_ca_topic_score_gemma":0.9588248,"teacher_disagreement_score":0.8097594,"about_ca_system_score_codex":0.0021716536,"about_ca_system_score_gemma":0.0845256,"threshold_uncertainty_score":0.9921032},"labels":[],"label_agreement":null},{"id":"W4384704276","doi":"10.3138/cjpe.77058-en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Traditional medicine; Sociology; Political science; Engineering ethics; Environmental ethics; Medicine; Engineering; Philosophy; Biology; Ecology","score_opus":0.32934335382480695,"score_gpt":0.5403537153913232,"score_spread":0.2110103615665162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858684,0.0010982257,0.00016983863,0.006685187,0.0007033188,0.0016580146,0.0000029402163,0.000015153463,0.0037989344],"genre_scores_gemma":[0.9986137,0.00003219508,0.0007581337,0.00010654693,0.0001726894,0.00011274165,0.000032100153,0.000009629282,0.00016227209],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9941622,0.0009974445,0.0012431791,0.00023257753,0.0030641444,0.00030045884],"domain_scores_gemma":[0.9956428,0.0005512476,0.00072445825,0.00021703441,0.0025373697,0.00032712152],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046871148,0.00011712482,0.00024846228,0.002035258,0.00027411798,0.00022019203,0.00025743997,0.00009581783,0.0016097925],"category_scores_gemma":[0.0084395325,0.0000923402,0.00004589754,0.002461729,0.00009253137,0.000781714,0.00001324091,0.0002457252,0.00010251801],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051916527,0.000012593064,0.17173205,0.0000032393382,0.000010070433,0.0000053030994,0.0052356864,0.008269131,0.00004477407,0.00022625795,0.0013764512,0.81307924],"study_design_scores_gemma":[0.0013955714,0.00037706082,0.7174889,0.00010370658,0.00006178742,0.000027149472,0.0035262352,0.2460786,0.000010819034,0.02524394,0.0055812737,0.00010498577],"about_ca_topic_score_codex":0.0010426218,"about_ca_topic_score_gemma":0.06395073,"teacher_disagreement_score":0.8129743,"about_ca_system_score_codex":0.0005371223,"about_ca_system_score_gemma":0.0047000647,"threshold_uncertainty_score":0.9999128},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99537957,0.0001482738,0.00032637347,0.0031667352,0.0001868973,0.000541593,0.000033876364,0.000007923984,0.00020877502],"genre_scores_gemma":[0.9856967,0.000011067102,0.013997864,0.0000923539,0.000037397287,0.00005156948,0.0000082063725,0.000007916213,0.000096967065],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983526,0.00042665825,0.00035621354,0.00016064206,0.0004040375,0.00029983537],"domain_scores_gemma":[0.99895537,0.00013038398,0.00025180672,0.00016836554,0.00014070026,0.00035335834],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003057956,0.000083026745,0.00017280747,0.00008753953,0.00010234818,0.00003134835,0.00016247081,0.0000499677,0.0010030319],"category_scores_gemma":[0.00135357,0.00007632102,0.00006306689,0.00062529783,0.00018969584,0.00012203562,0.00002701372,0.000096767406,0.000041322375],"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":[0.00009043392,0.00009155644,0.028183417,0.000025049087,0.000053819724,0.0000686546,0.08280947,0.021542849,0.043216705,0.000091761925,0.004443096,0.8193832],"study_design_scores_gemma":[0.0008685865,0.00076822087,0.85473204,0.00014790469,0.00020069668,0.000021113763,0.06818352,0.0130795995,0.02156311,0.010175842,0.02993112,0.00032826958],"about_ca_topic_score_codex":0.00509958,"about_ca_topic_score_gemma":0.06308525,"teacher_disagreement_score":0.8265486,"about_ca_system_score_codex":0.00043753756,"about_ca_system_score_gemma":0.00041339162,"threshold_uncertainty_score":0.9999102},"labels":[],"label_agreement":null},{"id":"W4384704291","doi":"10.3138/cjpe.38.1.ed-en","title":"Editor’s Remarks","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Psychology","score_opus":0.3016607384097375,"score_gpt":0.5419447489581198,"score_spread":0.24028401054838233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83711743,0.00097156427,0.002445411,0.03685035,0.06468003,0.0036134229,0.000029206036,0.00013233752,0.05416026],"genre_scores_gemma":[0.9940449,0.000013220605,0.0014438768,0.00020563856,0.0031648087,0.000045330296,0.00001773646,0.000009942429,0.0010545491],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955053,0.000415694,0.0007865304,0.00015167915,0.002868767,0.0002720561],"domain_scores_gemma":[0.9953159,0.00028554566,0.0004931246,0.0002655536,0.0031687526,0.0004710908],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.024627816,0.000083011575,0.00016917981,0.0010701319,0.00019822734,0.0003929544,0.0004595897,0.00007228107,0.0038903803],"category_scores_gemma":[0.005499139,0.00006263263,0.00011801692,0.0016472327,0.00006102372,0.0005616982,0.000011080702,0.00017529621,0.00091196224],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004549832,0.000008382617,0.0116367815,0.000001386721,0.000010852067,0.0000064418723,0.00047632185,0.0016546788,0.000018128467,0.00019120304,0.28842306,0.69756824],"study_design_scores_gemma":[0.0006104685,0.0003107812,0.13341339,0.00003110775,0.000040280895,0.000023838049,0.0013397733,0.07667341,0.000042513147,0.016967505,0.7704299,0.00011702141],"about_ca_topic_score_codex":0.0001839598,"about_ca_topic_score_gemma":0.008594621,"teacher_disagreement_score":0.6974512,"about_ca_system_score_codex":0.00025826498,"about_ca_system_score_gemma":0.0053484077,"threshold_uncertainty_score":0.99986595},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4384704311","doi":"10.3138/cjpe.76031","title":"<i>Ethics for Evaluation. Beyond “Doing No Harm” to “Tackling Bad” and “Doing Good”</i> , par Rob van den Berg, Penny Hawkins et Nicoletta Stame (dir.)","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Harm; Psychology; Social psychology","score_opus":0.2641401555920312,"score_gpt":0.5229258898039616,"score_spread":0.2587857342119304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384704311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86715776,0.003075873,0.03819168,0.05694571,0.0063500074,0.014003333,0.00021312399,0.00014993103,0.013912596],"genre_scores_gemma":[0.95786345,0.00006492747,0.03723099,0.0029563264,0.00058423734,0.00049046596,0.00011357413,0.000054543958,0.0006415057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99134046,0.0014032944,0.0015547534,0.0005524119,0.0044077635,0.00074134395],"domain_scores_gemma":[0.9877919,0.0018444167,0.000951898,0.00046465656,0.00796303,0.0009841194],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07420288,0.0002763988,0.00045331442,0.0014012874,0.0009937779,0.0013808694,0.000640267,0.00020099815,0.0010879221],"category_scores_gemma":[0.011284974,0.00024917178,0.00019850724,0.0016101372,0.00010014703,0.0012606077,0.00006908104,0.00058206444,0.00022214354],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006127976,0.000047873553,0.013453381,0.000039450744,0.00011733918,0.000007984241,0.00725974,0.06465901,0.00053101237,0.0010202473,0.023341576,0.8894611],"study_design_scores_gemma":[0.0035101355,0.0011942405,0.035142157,0.0003487155,0.000488298,0.000045519824,0.0033877064,0.45081273,0.00023982392,0.011923268,0.4923358,0.0005716034],"about_ca_topic_score_codex":0.00035057572,"about_ca_topic_score_gemma":0.028264726,"teacher_disagreement_score":0.8888895,"about_ca_system_score_codex":0.0006603084,"about_ca_system_score_gemma":0.009781825,"threshold_uncertainty_score":0.99999607},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4390063387","doi":"10.3138/cjpe-2023-0009","title":"Employing Mixed-Methods Citation Analysis to Investigate Transnational Influence in Evaluation Theory","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citation; Affordance; Co-citation; Citation analysis; Equity (law); Epistemology; Sociology; Computer science; Management science; Psychology; Political science; Library science; Cognitive psychology; Engineering","score_opus":0.42274354534197994,"score_gpt":0.6040932728385231,"score_spread":0.18134972749654316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741107,0.00009521019,0.018127846,0.005214405,0.00064983143,0.001349468,0.000009885438,0.00001945928,0.0004231458],"genre_scores_gemma":[0.98083174,0.0000034297766,0.018358387,0.00032531604,0.000065609864,0.00027547538,0.000070999675,0.00001190027,0.00005715309],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9888796,0.004398391,0.001618092,0.00037266887,0.004342473,0.00038876932],"domain_scores_gemma":[0.9906521,0.0013819396,0.00068343285,0.00032641902,0.0063880505,0.00056806346],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1153402,0.000161575,0.0003478362,0.007092511,0.00022561442,0.0005020689,0.0005370692,0.000107061176,0.0012389243],"category_scores_gemma":[0.020361125,0.00014278576,0.0001992242,0.012645658,0.000085632644,0.0012173826,0.000015072157,0.00024464444,0.00009881776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013108234,0.000013601996,0.044141717,0.0000023026003,0.00006697612,0.0000019486674,0.0028562618,0.3743249,0.00019753717,0.0021663222,0.00020212555,0.5760132],"study_design_scores_gemma":[0.00047562868,0.00012387718,0.6083519,0.000018085499,0.00025849338,0.0000028862737,0.001555897,0.31773058,0.00010890442,0.07003208,0.0012260213,0.00011567205],"about_ca_topic_score_codex":0.00022070759,"about_ca_topic_score_gemma":0.03098234,"teacher_disagreement_score":0.5758975,"about_ca_system_score_codex":0.0008197234,"about_ca_system_score_gemma":0.005815459,"threshold_uncertainty_score":0.99982065},"labels":[],"label_agreement":null},{"id":"W4390063458","doi":"10.3138/cjpe-2023-0023","title":"The “What” and “Why” of (Un)Ethical Evaluation Practice: A Meta-Narrative Review and Ethical Awareness Framework","year":2023,"lang":"en","type":"review","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; Ontario Council of University Libraries; Wilfrid Laurier University; University of Toronto; University Health Network; Centre for Addiction and Mental Health; The Wilson Centre; York University","funders":"","keywords":"Engineering ethics; Reflexivity; Beneficence; Meta-ethics; Stewardship (theology); Deliberation; Stakeholder; Psychology; Nursing ethics; Sociology; Autonomy; Political science; Public relations; Social science","score_opus":0.7245374058454952,"score_gpt":0.6765867511534138,"score_spread":0.047950654692081374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063458","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015676338,0.96384436,0.0002709942,0.030351868,0.00080589927,0.004594354,0.000017769396,0.000007443311,0.000091650116],"genre_scores_gemma":[0.00023456661,0.9953223,0.0018283941,0.001472348,0.00017558521,0.00087124034,0.000032880194,0.00003080875,0.000031917243],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9756916,0.013654107,0.0034450686,0.00056893565,0.0062390086,0.00040128522],"domain_scores_gemma":[0.9697052,0.013135863,0.0048336037,0.0006778727,0.01102675,0.00062069006],"candidate_categories":["metaresearch","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14897496,0.00041099006,0.0022665304,0.00068806915,0.00074264675,0.0012379948,0.0007608492,0.0010367518,0.0009205521],"category_scores_gemma":[0.10091639,0.00022834259,0.00059230725,0.0020644078,0.0005670407,0.00074323226,0.00007063391,0.002869944,0.000022581977],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006600183,0.000013391867,0.0000038158696,0.0013377118,0.00090109545,0.000004350697,0.0013140698,0.000020934058,1.0421344e-8,0.0016936717,0.0022903793,0.992414],"study_design_scores_gemma":[0.00032924136,0.00045679923,0.000060372764,0.013986586,0.029292688,0.0002645887,0.002744756,0.0026947751,1.6674504e-7,0.032844212,0.9170368,0.00028903282],"about_ca_topic_score_codex":0.00013612826,"about_ca_topic_score_gemma":0.0032374135,"teacher_disagreement_score":0.9921249,"about_ca_system_score_codex":0.00038988102,"about_ca_system_score_gemma":0.017980648,"threshold_uncertainty_score":0.9999927},"labels":[],"label_agreement":null},{"id":"W4390063483","doi":"10.3138/cjpe.75810","title":"Community-Based Evaluation When Localizing Sustainable Development Goals","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre for Community Based Research","funders":"","keywords":"Participatory evaluation; Stakeholder; Sustainable development; Citizen journalism; Key (lock); Process management; Evaluation methods; Sustainable community; Community development; Business; Environmental resource management; Environmental planning; Knowledge management; Management science; Computer science; Political science; Public relations; Public administration; Economics; Engineering; Geography","score_opus":0.5017879788631601,"score_gpt":0.5574306116824358,"score_spread":0.05564263281927573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9719763,0.0004065289,0.0067844614,0.008587378,0.0012574637,0.0036633369,0.0000059261524,0.00007250836,0.0072461087],"genre_scores_gemma":[0.9936293,0.0000022777651,0.004777479,0.00045189794,0.00010996119,0.00024266199,0.00011663345,0.00001765011,0.00065213646],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898707,0.00305211,0.0013817357,0.00020823296,0.00493413,0.0005530938],"domain_scores_gemma":[0.9882078,0.0005560784,0.0008632783,0.0004718197,0.009364788,0.0005361917],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.099131025,0.00016876649,0.00028808884,0.001974496,0.0010445687,0.00077853625,0.0007802155,0.00010889274,0.002730119],"category_scores_gemma":[0.007340849,0.00014157026,0.00012701895,0.0020798394,0.00009787946,0.0008645336,0.000033843502,0.00040426024,0.00039535572],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001963134,0.0000611585,0.013280076,0.000024320274,0.0000387399,0.000012503874,0.0062443274,0.049685504,0.000028149963,0.00037273194,0.02116461,0.9090682],"study_design_scores_gemma":[0.0022889548,0.00049175456,0.08274983,0.0001302984,0.00014787499,0.000013906038,0.019511065,0.42959568,0.00047410524,0.030287223,0.4339945,0.00031479652],"about_ca_topic_score_codex":0.00094399706,"about_ca_topic_score_gemma":0.01424585,"teacher_disagreement_score":0.90875345,"about_ca_system_score_codex":0.0015682804,"about_ca_system_score_gemma":0.021665888,"threshold_uncertainty_score":0.9981815},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9809474,0.0005078463,0.00020345587,0.0033536362,0.00023529808,0.014645616,0.000008291547,0.00001751206,0.00008097297],"genre_scores_gemma":[0.99210715,0.00006502068,0.0015490516,0.000216096,0.0000785785,0.0059290747,0.000036926638,0.000015420437,0.0000026584914],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9971151,0.0007797605,0.00071424234,0.00017380551,0.000528356,0.0006887728],"domain_scores_gemma":[0.9966544,0.00027698008,0.00062321976,0.000102106766,0.0022209894,0.00012232074],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01759181,0.00011561714,0.00021446632,0.00030442822,0.0022131614,0.00006591577,0.0001545816,0.00010449448,0.000017971832],"category_scores_gemma":[0.0013794968,0.000083592924,0.00004339433,0.0005700414,0.00012436893,0.0002018133,0.000022160597,0.00028809634,6.1845105e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039307633,0.000029526784,0.05537734,0.00058422016,0.00010239041,0.0000019993804,0.20926502,0.0039197966,0.000015451611,0.00057785294,0.0001634498,0.72992367],"study_design_scores_gemma":[0.0037319097,0.0010264654,0.19921443,0.00042757535,0.0006179591,0.000018160486,0.5034234,0.26410064,0.00001104379,0.026415823,0.00078899454,0.00022363622],"about_ca_topic_score_codex":0.0035179926,"about_ca_topic_score_gemma":0.31850263,"teacher_disagreement_score":0.7297,"about_ca_system_score_codex":0.0006625681,"about_ca_system_score_gemma":0.00514855,"threshold_uncertainty_score":0.99908584},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841166,0.00062421936,0.000029463275,0.00021608674,0.0019059641,0.005650546,0.00000359573,0.000027748947,0.0074257893],"genre_scores_gemma":[0.99695045,0.00012791513,0.0017821013,0.00002386204,0.0006668074,0.00010959934,0.000017958155,0.00001889184,0.00030243178],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9929413,0.0042785257,0.0007511271,0.00021733054,0.0011441294,0.0006675444],"domain_scores_gemma":[0.99678427,0.00022756723,0.0004849703,0.00019011466,0.0017332939,0.0005797815],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.041137177,0.0001325166,0.00024317748,0.0012178549,0.0036830094,0.00024363777,0.00025597255,0.0001250082,0.0002414934],"category_scores_gemma":[0.00032152684,0.00012475006,0.00007614857,0.0018641975,0.00015467823,0.00034444334,9.75657e-7,0.00029833708,0.000034837754],"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":[0.000006159301,0.0001556106,0.014374342,0.000008916419,0.000023385215,0.00028888852,0.735222,0.00023795984,4.0398118e-7,0.00043798046,0.00009613059,0.24914823],"study_design_scores_gemma":[0.0032165323,0.0013315533,0.024410702,0.0001182227,0.0004856152,0.00064853765,0.6627513,0.003940826,0.000012442142,0.0067328364,0.2958631,0.000488328],"about_ca_topic_score_codex":0.69497544,"about_ca_topic_score_gemma":0.9967214,"teacher_disagreement_score":0.30174595,"about_ca_system_score_codex":0.0025720568,"about_ca_system_score_gemma":0.12102359,"threshold_uncertainty_score":0.9976141},"labels":[],"label_agreement":null},{"id":"W4390063624","doi":"10.3138/cjpe-2023-0024","title":"Arts-Based Evaluation","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Lawson Foundation","keywords":"The arts; Recreation; Arts in education; Painting; Narrative; Psychology; Sociology; Visual arts; Political science; Art","score_opus":0.6412074581239966,"score_gpt":0.6406298731733805,"score_spread":0.0005775849506161057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063624","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96531266,0.00041695553,0.0021009415,0.012025829,0.0033885404,0.0027291789,0.000013664444,0.000057170422,0.013955038],"genre_scores_gemma":[0.99747604,0.0000040349178,0.0015452979,0.0003005405,0.00025249133,0.00014836303,0.000050000726,0.000012174703,0.00021107923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919808,0.0008629073,0.0010698449,0.00023332017,0.005507024,0.00034608413],"domain_scores_gemma":[0.9909841,0.00040689268,0.0007507324,0.00038007647,0.006973712,0.00050452614],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.054079473,0.00012579236,0.00022361515,0.0016933026,0.0002766247,0.00049466913,0.0004985392,0.000088594505,0.007026814],"category_scores_gemma":[0.008443646,0.000099412166,0.00016906457,0.0024111792,0.000079577614,0.0006323497,0.000009040995,0.00018718353,0.0009740839],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001057377,0.000020671412,0.01625752,0.0000024827286,0.000014759703,0.0000048433853,0.00039842387,0.03873305,0.000049316663,0.0002624975,0.016180906,0.92806494],"study_design_scores_gemma":[0.001285175,0.00034764665,0.15001616,0.000035524674,0.00010250969,0.000011224344,0.0007622966,0.7266079,0.00015010068,0.015221345,0.10532564,0.0001344755],"about_ca_topic_score_codex":0.00017954096,"about_ca_topic_score_gemma":0.009371943,"teacher_disagreement_score":0.9279305,"about_ca_system_score_codex":0.00056701485,"about_ca_system_score_gemma":0.01254243,"threshold_uncertainty_score":0.9999086},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"qualitative","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4390063627","doi":"10.3138/cjpe.75803","title":"Contribution Analysis of a Complex System During Disruptions","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Outreach; Occupational safety and health; Agriculture; Business; Coronavirus disease 2019 (COVID-19); Environmental planning; Environmental resource management; Political science; Environmental health; Geography; Environmental science; Medicine","score_opus":0.4378081056136442,"score_gpt":0.5552920873869361,"score_spread":0.11748398177329195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390063627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961111,0.000069354544,0.0013703277,0.0007982436,0.00037478717,0.00056748756,0.000050357685,0.00001837628,0.0006399423],"genre_scores_gemma":[0.99939257,0.0000037859534,0.00032174718,0.000012995054,0.00006571659,0.00003828939,0.00009185193,0.000004674053,0.000068346744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99588466,0.0005055701,0.0011532287,0.000147902,0.0020766642,0.00023198985],"domain_scores_gemma":[0.9935427,0.00022752576,0.0009564211,0.0002627465,0.004701613,0.00030904257],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013125517,0.00008298945,0.00035387537,0.0028479744,0.00024272117,0.00018072531,0.0003085265,0.000054835637,0.0010723589],"category_scores_gemma":[0.0021935909,0.000066387736,0.00027085902,0.0056132358,0.00006902678,0.00036005458,0.000011193618,0.000098211516,0.000077413446],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006425007,0.00009424471,0.4008028,0.00004319039,0.0014484285,0.000026988739,0.003913636,0.21091902,0.0018511481,0.006457801,0.0025825663,0.37179592],"study_design_scores_gemma":[0.0004297599,0.000084715,0.63373005,0.000024767423,0.0005576401,0.000007992104,0.0016553757,0.3613187,0.000065076965,0.00032576686,0.0017474015,0.00005271913],"about_ca_topic_score_codex":0.00036961256,"about_ca_topic_score_gemma":0.013774366,"teacher_disagreement_score":0.37174323,"about_ca_system_score_codex":0.00049583067,"about_ca_system_score_gemma":0.0016034062,"threshold_uncertainty_score":0.9998408},"labels":[],"label_agreement":null},{"id":"W4393862188","doi":"10.3138/cjpe-2024-0012","title":"Strengthening Evaluation Capacity Building Practice Through Competition: The Max Bell School of Public Policy’s Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta; University of Ottawa; Queen's University; McGill University","funders":"","keywords":"Competition (biology); Capacity building; Political science; Architectural engineering; Economics; Engineering; Economic growth","score_opus":0.6298851995534387,"score_gpt":0.5347281576265688,"score_spread":0.09515704192686991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393862188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9290416,0.0061653145,0.00961997,0.03238584,0.0030334846,0.004896387,0.000072160365,0.000047567406,0.014737673],"genre_scores_gemma":[0.9911991,0.00008760161,0.00714907,0.00025829911,0.00093182107,0.0002777748,0.00003381633,0.000026775693,0.000035789966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98209536,0.0063483478,0.0022269466,0.00053060724,0.008238618,0.00056014804],"domain_scores_gemma":[0.97926205,0.0019567003,0.0018024737,0.0007152905,0.01570233,0.0005611286],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10471569,0.00030120192,0.0004276051,0.0013389221,0.0008181958,0.0014472186,0.0007122868,0.00020344794,0.0056290403],"category_scores_gemma":[0.036452033,0.0002191361,0.00030206572,0.00258753,0.00033901332,0.0041589495,0.000040888957,0.0008102994,0.000117928896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024783189,0.00015569296,0.0010447705,0.000050320385,0.00025962916,0.00003555239,0.009822521,0.017223231,0.00015279284,0.025102705,0.0016382027,0.9444898],"study_design_scores_gemma":[0.0019183402,0.00089408545,0.005100744,0.00042652586,0.001362845,0.0024480573,0.013285418,0.8111745,0.00030553274,0.083402,0.07925088,0.00043105625],"about_ca_topic_score_codex":0.004366387,"about_ca_topic_score_gemma":0.024770614,"teacher_disagreement_score":0.9440587,"about_ca_system_score_codex":0.0027867996,"about_ca_system_score_gemma":0.01966661,"threshold_uncertainty_score":0.9995894},"labels":[],"label_agreement":null},{"id":"W4393901164","doi":"10.3138/cjpe-2024-0003","title":"Evaluation Capacity Building: Experiential Learning Through Community–University Collaboratives","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University; Queen's University; University of Alberta","funders":"","keywords":"Experiential learning; Capacity building; Experiential education; Psychology; Sociology; Knowledge management; Mathematics education; Computer science; Political science","score_opus":0.5508950277399596,"score_gpt":0.5316824930199557,"score_spread":0.019212534720003838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98029596,0.0011902438,0.0066042067,0.0013586681,0.001937109,0.0010086922,0.000009614301,0.000031477626,0.0075640273],"genre_scores_gemma":[0.99574685,0.000014763947,0.0037155969,0.000042952677,0.00020695297,0.000018845125,0.000014148915,0.000011045177,0.00022887245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99001247,0.0050769732,0.0006840334,0.00022142747,0.0037377386,0.00026738388],"domain_scores_gemma":[0.9915107,0.00043056795,0.00044815335,0.00027007825,0.007037463,0.00030303572],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03949789,0.00014595901,0.00023136158,0.00076282944,0.00088288856,0.0009812068,0.0005234516,0.000106277665,0.0028551891],"category_scores_gemma":[0.005737506,0.00012693137,0.0001498408,0.0018579625,0.00019754932,0.0020225055,0.000024070567,0.000672362,0.00007038137],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032427055,0.00008303929,0.002886841,0.000016589805,0.00015258472,0.000012947645,0.05123376,0.016491164,0.0009519171,0.004976468,0.00413852,0.91902375],"study_design_scores_gemma":[0.0016039595,0.0010710165,0.010631112,0.00027402127,0.00055673806,0.00006759143,0.064639114,0.47493,0.0011256072,0.026741417,0.4179856,0.00037384385],"about_ca_topic_score_codex":0.00148613,"about_ca_topic_score_gemma":0.016099501,"teacher_disagreement_score":0.9186499,"about_ca_system_score_codex":0.0012847709,"about_ca_system_score_gemma":0.009537692,"threshold_uncertainty_score":0.99805635},"labels":[],"label_agreement":null},{"id":"W4393901296","doi":"10.3138/cjpe-2024-0001","title":"Capturing Evaluation Capacity: Findings from a Mapping of Evaluation Capacity Instruments","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Rubric; Face validity; Construct validity; Content validity; Reliability (semiconductor); Concurrent validity; Construct (python library); Adaptation (eye); Psychology; Computer science; Applied psychology; Internal consistency; Process management; Psychometrics; Engineering; Clinical psychology","score_opus":0.5637636910939985,"score_gpt":0.48089635624878085,"score_spread":0.08286733484521763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98911524,0.0011090428,0.0013924956,0.0011875934,0.0028971399,0.0022242141,0.000054210628,0.000020545971,0.0019995025],"genre_scores_gemma":[0.9949582,0.000013871208,0.0043175225,0.00007930424,0.0003207516,0.00017528831,0.000076873235,0.000022103628,0.000036068657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871926,0.0017209739,0.0020261935,0.00049537676,0.008145583,0.000419322],"domain_scores_gemma":[0.9905832,0.00046081026,0.0009927726,0.00047183462,0.007019793,0.00047158162],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05105589,0.00025836317,0.00046299657,0.0019710467,0.0002745665,0.0008477197,0.00051750476,0.00019533292,0.0056477487],"category_scores_gemma":[0.0066099474,0.00022049698,0.00028345178,0.0017282292,0.00016240498,0.0018629215,0.00002710455,0.00045622565,0.00011388985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015611124,0.000049057482,0.02371707,0.000027558688,0.0001680294,0.0000029137823,0.008715455,0.0048443233,0.0012407531,0.0003259237,0.000995545,0.95989776],"study_design_scores_gemma":[0.0016177904,0.0002958224,0.14744638,0.0006057118,0.0006482531,0.000039019793,0.0025872057,0.7869716,0.0017613715,0.050235398,0.007503207,0.0002881875],"about_ca_topic_score_codex":0.0035476182,"about_ca_topic_score_gemma":0.01496088,"teacher_disagreement_score":0.95960957,"about_ca_system_score_codex":0.0021454855,"about_ca_system_score_gemma":0.009221726,"threshold_uncertainty_score":0.99639505},"labels":[],"label_agreement":null},{"id":"W4393901340","doi":"10.3138/cjpe-2024-0006","title":"Meeting the Challenge: How the City of Kingston Is Working to Propel Evaluation Growth","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Ottawa; Kingston Health Sciences Centre; McGill University; Queen's University","funders":"","keywords":"Regional science; Engineering ethics; Sociology; Engineering","score_opus":0.5229101328012221,"score_gpt":0.5202649908847802,"score_spread":0.00264514191644194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5616208,0.013111694,0.0027483525,0.4002824,0.004952333,0.005462877,0.000010223571,0.000026246018,0.011785111],"genre_scores_gemma":[0.9978519,0.000038875412,0.000794142,0.00044080435,0.0004611375,0.00013636134,0.0000026874277,0.00001259284,0.00026150426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927963,0.0012622287,0.0008545797,0.00026792454,0.00452314,0.00029582588],"domain_scores_gemma":[0.9933619,0.0006118956,0.0006305584,0.00038655216,0.004773546,0.0002355808],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06303442,0.0001385897,0.00020703628,0.0005753449,0.0003785859,0.0010285072,0.00077676715,0.00007436399,0.0010859725],"category_scores_gemma":[0.0063451156,0.00007222768,0.00017655155,0.0017077669,0.00012422614,0.00058143475,0.000030192714,0.0003567265,0.000034626857],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008365625,0.000018293722,0.0032171283,0.00001101453,0.00004447133,0.0000015009758,0.009102309,0.0010009302,0.00004209589,0.0010700936,0.007835598,0.9776482],"study_design_scores_gemma":[0.0009883912,0.0011888491,0.06688341,0.0013299766,0.00076387206,0.00008985088,0.011891291,0.5147994,0.0012511464,0.06844746,0.33195195,0.0004143428],"about_ca_topic_score_codex":0.00057672535,"about_ca_topic_score_gemma":0.009090088,"teacher_disagreement_score":0.9772338,"about_ca_system_score_codex":0.00046726782,"about_ca_system_score_gemma":0.004764993,"threshold_uncertainty_score":0.99982715},"labels":[],"label_agreement":null},{"id":"W4393901348","doi":"10.3138/cjpe-2024-0014","title":"Exploring the Edges: Identifying the Next Generation of Evaluation Capacity Building Research and Practice Through Adjacency","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Adjacency list; Computer science; Data science; Algorithm","score_opus":0.9617855589426995,"score_gpt":0.6449060188564266,"score_spread":0.31687954008627284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9655131,0.0082459655,0.005379184,0.014876242,0.002530932,0.0019101141,0.0000033720448,0.000008431551,0.0015326764],"genre_scores_gemma":[0.99524474,0.0003584793,0.0034231923,0.000082694045,0.00063286716,0.00021269714,0.0000039967076,0.000010612894,0.000030699986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9893242,0.0038933144,0.0010280098,0.00027629852,0.0051873475,0.00029083574],"domain_scores_gemma":[0.9876684,0.0032567258,0.00050612085,0.00037783204,0.00804322,0.0001476765],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.116730005,0.000111451554,0.0001632952,0.00056796387,0.0008444909,0.0019124174,0.00042697706,0.000051586372,0.00032248764],"category_scores_gemma":[0.021393515,0.00006293245,0.00008404123,0.0018015514,0.00029904337,0.0044364245,0.00003294631,0.000519515,0.000018598623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001205139,0.000020025165,0.00028276775,0.000016485114,0.00004767217,0.0000021058556,0.01631584,0.0024683548,0.0018950098,0.005943912,0.0017088364,0.97128695],"study_design_scores_gemma":[0.0010360595,0.0010354796,0.023025084,0.00066337106,0.0006353957,0.00040929695,0.059913803,0.7177952,0.0053872494,0.09536388,0.0944412,0.00029400765],"about_ca_topic_score_codex":0.001181836,"about_ca_topic_score_gemma":0.006214315,"teacher_disagreement_score":0.9709929,"about_ca_system_score_codex":0.00052245625,"about_ca_system_score_gemma":0.0041448097,"threshold_uncertainty_score":0.9991237},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4393901512","doi":"10.3138/cjpe-2024-0002","title":"Evaluation Literacy and Use in Community Organizations: Insights and Implications for Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Australian Government","keywords":"Capacity building; Literacy; Business; Capacity development; Environmental planning; Environmental resource management; Sociology; Economic growth; Economics; Pedagogy; Geography","score_opus":0.43190576373339495,"score_gpt":0.5397514135621242,"score_spread":0.10784564982872924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393901512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98431116,0.0034389442,0.005913343,0.0026030203,0.00045135486,0.0031090658,0.000027004602,0.00001375117,0.00013233542],"genre_scores_gemma":[0.99227345,0.00005980814,0.006960983,0.000105082,0.00010344255,0.0004013668,0.00006688285,0.000015577916,0.000013385233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943124,0.0023666003,0.0010607613,0.00028613556,0.0017515483,0.0002225642],"domain_scores_gemma":[0.9880334,0.0016304437,0.00039600057,0.00031745122,0.009325968,0.0002967067],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04573313,0.00015236171,0.00023151637,0.0014816324,0.00053698407,0.001768249,0.00023724853,0.00011218752,0.00020068516],"category_scores_gemma":[0.018842781,0.000129928,0.000052973923,0.0017324836,0.00011652756,0.0027230964,0.00002134496,0.00033128296,0.0000040381556],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007749859,0.000046387275,0.028604189,0.000023068746,0.00003461379,3.0637315e-7,0.007133137,0.0028402118,0.00026199772,0.004498081,0.00032958068,0.9562207],"study_design_scores_gemma":[0.0009804512,0.00019590711,0.33614224,0.00015020343,0.0002616936,0.000030830903,0.0006250592,0.53201663,0.00004027535,0.12460427,0.004831209,0.00012122314],"about_ca_topic_score_codex":0.000982946,"about_ca_topic_score_gemma":0.03610286,"teacher_disagreement_score":0.95609945,"about_ca_system_score_codex":0.0009485052,"about_ca_system_score_gemma":0.005338861,"threshold_uncertainty_score":0.999268},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4393902965","doi":"10.3138/cjpe-2024-0004","title":"Developing Evaluation Capacity Building Competencies: Participant Reflections From the Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University; University of Waterloo; University of Alberta","funders":"","keywords":"Capacity building; Capacity development; Psychology; Business; Environmental resource management; Environmental science; Economic growth; Economics","score_opus":0.8696201595344439,"score_gpt":0.5799551477667225,"score_spread":0.2896650117677214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393902965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96294004,0.0038030364,0.011957769,0.012635565,0.0043057706,0.0030810076,0.000052217365,0.000046063356,0.0011785572],"genre_scores_gemma":[0.9875508,0.00003870948,0.010811464,0.00024567926,0.00078745786,0.00048854924,0.000036208647,0.000022947486,0.000018216651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98727643,0.0037679966,0.0018075472,0.0005513091,0.006055476,0.0005412483],"domain_scores_gemma":[0.98787445,0.0016900696,0.00082884415,0.00060450804,0.008522372,0.00047978488],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07147564,0.0002795165,0.00038291013,0.0007960739,0.0011957957,0.0016192313,0.00061177433,0.00017222417,0.0032379269],"category_scores_gemma":[0.011263911,0.0001929784,0.00026229236,0.001887365,0.00023062337,0.00156341,0.00003104515,0.00064221845,0.00012304574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012807484,0.000049188322,0.0014419579,0.000013114872,0.00021436698,0.00003771132,0.019247849,0.01597334,0.0002558626,0.004941018,0.0014733707,0.9563394],"study_design_scores_gemma":[0.00086552976,0.0003065201,0.015288252,0.00031970083,0.0011892236,0.00054954726,0.010808274,0.82988656,0.00018078763,0.089586645,0.05068807,0.00033092505],"about_ca_topic_score_codex":0.007024803,"about_ca_topic_score_gemma":0.22620298,"teacher_disagreement_score":0.9560085,"about_ca_system_score_codex":0.0029222893,"about_ca_system_score_gemma":0.014702817,"threshold_uncertainty_score":0.9995875},"labels":[],"label_agreement":null},{"id":"W4393902987","doi":"10.3138/cjpe-2024-0005","title":"Learning From Evaluation Data: Discoveries From the Inaugural Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Alberta; McGill University; Queen's University","funders":"","keywords":"Data science; Computer science","score_opus":0.7100870622061499,"score_gpt":0.544183741665453,"score_spread":0.1659033205406969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393902987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725843,0.00907597,0.0015290293,0.008627242,0.0040326426,0.0023979552,0.00021698045,0.00003087639,0.0015049775],"genre_scores_gemma":[0.9964861,0.00006537492,0.0010233687,0.00012223555,0.0013025751,0.00017812809,0.0007477723,0.00002299766,0.000051422907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9867783,0.0042241137,0.0013997494,0.00063187437,0.0065950435,0.00037091647],"domain_scores_gemma":[0.9913881,0.0018837269,0.00080354855,0.0009767503,0.004570361,0.00037754863],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058051515,0.00025334343,0.00033452516,0.00046488634,0.0007363304,0.0024559663,0.0010609981,0.0001530358,0.008664388],"category_scores_gemma":[0.0134063065,0.00016640764,0.00016847598,0.0010084622,0.00021015006,0.00345421,0.000072610754,0.0007291111,0.00019746566],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018446986,0.000028929388,0.0048581455,0.000003684158,0.00012801259,0.000041398966,0.008711324,0.010382223,0.000025711257,0.0001874857,0.0046105627,0.97100407],"study_design_scores_gemma":[0.0008474298,0.00030129543,0.02700274,0.00014462165,0.0008754138,0.00013132239,0.009872369,0.885741,0.000024251813,0.028960187,0.04588688,0.00021248742],"about_ca_topic_score_codex":0.014338784,"about_ca_topic_score_gemma":0.19765352,"teacher_disagreement_score":0.9707916,"about_ca_system_score_codex":0.001179679,"about_ca_system_score_gemma":0.009957348,"threshold_uncertainty_score":0.99857956},"labels":[],"label_agreement":null},{"id":"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05057317,0.464672,0.0009497221,0.021340702,0.011118138,0.0008553229,0.00019963902,0.000042319283,0.450249],"genre_scores_gemma":[0.9861802,0.0005501595,0.0007108768,0.0001152492,0.00688799,0.000013758612,0.000018807816,0.000027125418,0.005495819],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845433,0.00034482338,0.00040101318,0.00011627339,0.0003633107,0.00032022462],"domain_scores_gemma":[0.998208,0.00015476532,0.00015294504,0.00010000678,0.0008796732,0.00050461094],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003250006,0.00012902537,0.00017032861,0.0004834514,0.0003029116,0.0018076315,0.00014373485,0.00010793925,0.007584417],"category_scores_gemma":[0.0005903254,0.00012072055,0.00023868048,0.00016033753,0.00028207732,0.00020613488,0.0000043850487,0.00034512795,0.000075532334],"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":[0.0000029285186,0.00005189459,0.00014999043,0.000075519834,0.00036211222,0.00036167665,0.0057255942,0.00040153606,0.0000019990418,0.43353823,0.013599313,0.5457292],"study_design_scores_gemma":[0.00018509895,0.00018814643,0.0002984467,0.00030937343,0.0019565758,0.00010666606,0.0011904933,0.04299604,0.00000974888,0.04144871,0.9111786,0.00013208418],"about_ca_topic_score_codex":0.018535849,"about_ca_topic_score_gemma":0.019763736,"teacher_disagreement_score":0.935607,"about_ca_system_score_codex":0.00059272844,"about_ca_system_score_gemma":0.005463777,"threshold_uncertainty_score":0.9992286},"labels":[],"label_agreement":null},{"id":"W4396707487","doi":"10.3138/cjpe-2024-0013","title":"Concluding Remarks: A Bright Future for Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Engineering ethics; Management science; Capacity building; Computer science; Political science; Engineering; Law","score_opus":0.4634754320822916,"score_gpt":0.5450116204168327,"score_spread":0.08153618833454113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396707487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8842792,0.010270531,0.05553475,0.019739559,0.01683417,0.007507346,0.00007108438,0.00007293783,0.0056904387],"genre_scores_gemma":[0.98267025,0.00001714282,0.015043898,0.0001753322,0.0016694748,0.00024645796,0.000025075295,0.000019079831,0.00013327277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940431,0.0007384848,0.0011660373,0.00034935714,0.003340472,0.00036251018],"domain_scores_gemma":[0.99210423,0.0006291146,0.0005422503,0.00028104984,0.006000883,0.00044244464],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.048242357,0.00016873184,0.0002859178,0.0010963595,0.00038767303,0.0013069318,0.00044110997,0.00013795367,0.0023525523],"category_scores_gemma":[0.004999172,0.00012818984,0.0002700766,0.00112419,0.00007861318,0.0012900677,0.000010419978,0.00028572217,0.000042578326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015452457,0.000013603873,0.0010523342,0.000020929472,0.00005660998,0.0000030156991,0.0014038712,0.0020999021,0.00017531023,0.0040172916,0.01357733,0.97756433],"study_design_scores_gemma":[0.0010514162,0.00030706023,0.00738551,0.00020380263,0.0002937847,0.00007712246,0.001096774,0.5994358,0.00028637718,0.048805684,0.34087327,0.00018340163],"about_ca_topic_score_codex":0.0001628309,"about_ca_topic_score_gemma":0.0063441354,"teacher_disagreement_score":0.97738093,"about_ca_system_score_codex":0.001214637,"about_ca_system_score_gemma":0.008695615,"threshold_uncertainty_score":0.9997298},"labels":[],"label_agreement":null},{"id":"W4396707874","doi":"10.3138/cjpe-2024-0011","title":"The Science and Practice of Evaluation Capacity Building","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Capacity building; Architectural engineering; Political science; Engineering","score_opus":0.5353283803429555,"score_gpt":0.5759095146980391,"score_spread":0.04058113435508359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396707874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95738083,0.0077659893,0.001934958,0.016334267,0.003201207,0.0019187945,0.0000059448635,0.00001172041,0.011446261],"genre_scores_gemma":[0.99522144,0.000042983,0.004493799,0.00006605001,0.00011430831,0.000031832555,5.9813294e-7,0.000004673658,0.00002430116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99187714,0.0009609808,0.00082280964,0.00020758707,0.0059053404,0.00022615468],"domain_scores_gemma":[0.9839262,0.0019633577,0.0005465417,0.0002442768,0.013043033,0.00027663462],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1488352,0.00007851487,0.00012755427,0.00071108754,0.00052526343,0.001299487,0.0003779135,0.0000392904,0.0002104704],"category_scores_gemma":[0.05493576,0.00004814404,0.000053422937,0.0018096846,0.00056800066,0.0018308095,0.000018213954,0.00019106145,0.000010488993],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009186798,0.000008628673,0.00038292498,0.000004771448,0.000016726952,0.0000012329784,0.0014021927,0.00088872894,0.0006823216,0.0063347835,0.00086990104,0.9893986],"study_design_scores_gemma":[0.00048439353,0.0004916078,0.021534728,0.00014729038,0.00029061333,0.0002826749,0.0041117296,0.7523365,0.0009838135,0.04317458,0.17603013,0.0001319397],"about_ca_topic_score_codex":0.00033211434,"about_ca_topic_score_gemma":0.0022900393,"teacher_disagreement_score":0.98926663,"about_ca_system_score_codex":0.0006180029,"about_ca_system_score_gemma":0.01473612,"threshold_uncertainty_score":0.99973726},"labels":[],"label_agreement":null},{"id":"W4396708036","doi":"10.3138/cjpe.38.3.ed-en","title":"Editor’s Remarks","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Philosophy","score_opus":0.23986684550211407,"score_gpt":0.53726516308728,"score_spread":0.29739831758516594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396708036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40802038,0.031316463,0.02977652,0.08365179,0.2535668,0.0070697684,0.00006807716,0.00023124731,0.18629895],"genre_scores_gemma":[0.991924,0.000014370662,0.0025319273,0.00016733223,0.0044750264,0.00003175822,0.0000074488485,0.000009975775,0.000838153],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99599636,0.00034867862,0.0007634437,0.0001712244,0.0025084005,0.00021189549],"domain_scores_gemma":[0.99652624,0.00028781785,0.00023191837,0.00021919417,0.0023077265,0.00042709245],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019522728,0.00008729533,0.00015133605,0.00085658184,0.00012858829,0.0010298449,0.0003767322,0.00007261011,0.0068802848],"category_scores_gemma":[0.0026851979,0.00006194687,0.00013877731,0.0009012755,0.00006105189,0.00081044494,0.0000071524605,0.00023540495,0.00043046143],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029673306,0.000007654344,0.0016723007,0.0000036012727,0.00001651454,0.000010607311,0.0004852689,0.00046249697,0.000015470963,0.00071727793,0.181378,0.81522787],"study_design_scores_gemma":[0.00020631256,0.00024171131,0.009716845,0.00007642375,0.00005493559,0.00005469574,0.00047021595,0.092491984,0.000034297074,0.016600339,0.8799663,0.00008593234],"about_ca_topic_score_codex":0.00017835973,"about_ca_topic_score_gemma":0.007082405,"teacher_disagreement_score":0.8151419,"about_ca_system_score_codex":0.0003860287,"about_ca_system_score_gemma":0.008402396,"threshold_uncertainty_score":0.997219},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83453274,0.0073802825,0.09954596,0.05292638,0.0035112114,0.0017650569,0.000022600203,0.0002477889,0.000067974244],"genre_scores_gemma":[0.9720712,0.000037843896,0.027379671,0.00023901189,0.00009478789,0.00004437626,0.000016502545,0.000016654913,0.00009998799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979547,0.00055107725,0.00037336562,0.0003665603,0.00045036254,0.00030389032],"domain_scores_gemma":[0.9980288,0.00025127825,0.00017939032,0.00047010643,0.00076882396,0.0003015726],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005570021,0.00012577097,0.00018228582,0.0013365202,0.00018815514,0.0022011825,0.0010193976,0.00008991817,0.000023195604],"category_scores_gemma":[0.002809517,0.000121236706,0.0000401694,0.002527513,0.000045734076,0.0027987866,0.00008493662,0.00035112226,0.000051874642],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016164972,0.000024622193,0.00028365885,0.000011379544,0.000054343596,0.00010256085,0.0014256899,0.00026483313,0.0007737768,0.000019546022,0.0050804866,0.99179745],"study_design_scores_gemma":[0.0034511595,0.005704609,0.035460234,0.005482951,0.00036867618,0.004115339,0.0045155096,0.55680716,0.027637463,0.019667247,0.33527464,0.0015150302],"about_ca_topic_score_codex":0.0007795158,"about_ca_topic_score_gemma":0.015725767,"teacher_disagreement_score":0.9902824,"about_ca_system_score_codex":0.0006923992,"about_ca_system_score_gemma":0.0066190767,"threshold_uncertainty_score":0.9990125},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10929291,0.09271572,0.0779949,0.0474545,0.14830656,0.011808351,0.0001353151,0.00094362197,0.5113481],"genre_scores_gemma":[0.98203087,0.000040584615,0.006418641,0.00028521268,0.0093506025,0.0004657902,0.00002084511,0.00004018341,0.0013472887],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917567,0.00008299899,0.00025929476,0.00011265073,0.0001956072,0.00017380608],"domain_scores_gemma":[0.9992282,0.000029543844,0.00008173259,0.00015956737,0.00026680023,0.00023416695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012363311,0.0000673835,0.000080580765,0.0002739962,0.00005771118,0.00011616117,0.00014861856,0.000089417954,0.0035687913],"category_scores_gemma":[0.000026279356,0.00006015285,0.000085710235,0.00028837472,0.00004296717,0.000094130315,0.0000011540161,0.00020206966,0.00009029229],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031158434,0.000016323012,0.000098224846,0.000003293385,0.00003751283,0.000010159436,0.00042897632,0.0000019066805,0.000049788585,0.0062112235,0.3570422,0.6360973],"study_design_scores_gemma":[0.00014780786,0.00019978598,0.0025500273,0.00006161685,0.00005266554,0.00009150518,0.00010086127,0.00057367474,0.000018825187,0.009334254,0.9867994,0.00006955113],"about_ca_topic_score_codex":0.00047388513,"about_ca_topic_score_gemma":0.0016654596,"teacher_disagreement_score":0.87273794,"about_ca_system_score_codex":0.00016970086,"about_ca_system_score_gemma":0.00079966534,"threshold_uncertainty_score":0.9973421},"labels":[],"label_agreement":null},{"id":"W4401363452","doi":"10.3138/cjpe.39.1.rr-en","title":"Roots and Relations: Celebrating Good Medicine in Indigenous Evaluation","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Engineering ethics; Traditional medicine; Sociology; History; Anthropology; Medicine; Engineering; Biology; Ecology","score_opus":0.27093444104940484,"score_gpt":0.5361930289587907,"score_spread":0.2652585879093859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9633284,0.013666122,0.00096954807,0.010101052,0.0016477577,0.0022198802,0.000004527486,0.000018532115,0.008044182],"genre_scores_gemma":[0.9980743,0.000037075813,0.0012797036,0.000097878146,0.00024569602,0.00009156017,0.000017323357,0.000010403612,0.00014606418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99468344,0.00086291175,0.0012094696,0.00025526705,0.0027436218,0.0002452929],"domain_scores_gemma":[0.99659127,0.0005525803,0.00039711528,0.00018632469,0.001970099,0.00030258516],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03907019,0.00012194851,0.00022733015,0.0017073682,0.00019393348,0.00047445117,0.00021966282,0.00009615277,0.0025375937],"category_scores_gemma":[0.004763488,0.00009153673,0.000052224324,0.0015247625,0.000092554976,0.0010447956,0.000009362625,0.00031109626,0.00005654545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004005096,0.000012702478,0.04446691,0.000007525721,0.000015257189,0.000008552444,0.0057650534,0.0032582579,0.000042759853,0.00070559216,0.00096419815,0.9447492],"study_design_scores_gemma":[0.0012188304,0.0006398524,0.3752596,0.00043947485,0.0001644779,0.000109367465,0.0031793304,0.54462606,0.000018909897,0.05145658,0.022717379,0.00017011493],"about_ca_topic_score_codex":0.0010093543,"about_ca_topic_score_gemma":0.054856278,"teacher_disagreement_score":0.94457906,"about_ca_system_score_codex":0.00073940115,"about_ca_system_score_gemma":0.0067357277,"threshold_uncertainty_score":0.99889517},"labels":[],"label_agreement":null},{"id":"W4401363543","doi":"10.3138/cjpe-2023-0021","title":"Breaking the Mould? Expanding our Conceptualization of Evaluator Competencies","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Conceptualization; Psychology; Engineering ethics; Sociology; Computer science; Engineering; Artificial intelligence","score_opus":0.40402035861867575,"score_gpt":0.5589097674439346,"score_spread":0.15488940882525887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9558064,0.00813821,0.013606777,0.010137781,0.005654345,0.0022067358,0.00002594653,0.000036866037,0.0043869503],"genre_scores_gemma":[0.9982228,0.00001763726,0.0011611439,0.00011547873,0.0002787496,0.000036810983,0.000008188823,0.000010786032,0.0001484004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948405,0.00078209117,0.001113961,0.00017910906,0.0028615983,0.00022272299],"domain_scores_gemma":[0.9953874,0.00040762027,0.0006356931,0.0002594069,0.0031040753,0.0002058579],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020877294,0.00011679464,0.00023100486,0.0006766078,0.00024511895,0.0006441518,0.00050740794,0.00006605505,0.0011073576],"category_scores_gemma":[0.0029150282,0.0000711175,0.00016725856,0.0012240978,0.00011075696,0.0007439646,0.000015313482,0.00020236221,0.00004446034],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011155339,0.000020368267,0.010338623,0.000020432775,0.000073972966,0.0000052788914,0.009593023,0.009002294,0.00058323547,0.0065380284,0.00611918,0.9576944],"study_design_scores_gemma":[0.0011276344,0.00084529014,0.04374561,0.00062838424,0.00046275376,0.00017007384,0.046133924,0.75823677,0.0014929437,0.024363505,0.12246422,0.0003288928],"about_ca_topic_score_codex":0.00032597163,"about_ca_topic_score_gemma":0.0039175176,"teacher_disagreement_score":0.9573655,"about_ca_system_score_codex":0.00033430345,"about_ca_system_score_gemma":0.0055391826,"threshold_uncertainty_score":0.99980575},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6919555,0.14630005,0.0053333933,0.08977929,0.047286928,0.0054745344,0.000013744906,0.00008576633,0.013770798],"genre_scores_gemma":[0.9758137,0.0003215394,0.016423857,0.0013565378,0.004822754,0.00006765379,0.000012780334,0.000032013668,0.0011491799],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99922085,0.00008381136,0.00025583926,0.000086291926,0.00019243108,0.00016076861],"domain_scores_gemma":[0.9993996,0.000047528672,0.00005908174,0.000071744376,0.00020293111,0.00021912712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001251067,0.000062819556,0.00015307139,0.0004006853,0.00003303159,0.000022570948,0.000058888487,0.00008575672,0.00055939006],"category_scores_gemma":[0.00022471746,0.000051373092,0.000062709965,0.00027706625,0.00008194063,0.00018251209,0.0000013609305,0.00027670045,0.00001676912],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084375155,0.00006534711,0.007488953,0.00006935868,0.00013116251,0.0012965103,0.0019507825,0.00022276455,0.00024796717,0.0009427362,0.034925867,0.9525742],"study_design_scores_gemma":[0.0018863907,0.0012741025,0.011583549,0.00047867827,0.00021192234,0.0016535355,0.00024365808,0.009964154,0.00014305726,0.0086524645,0.9637984,0.00011008079],"about_ca_topic_score_codex":0.00018570178,"about_ca_topic_score_gemma":0.0047496273,"teacher_disagreement_score":0.9524641,"about_ca_system_score_codex":0.00066996884,"about_ca_system_score_gemma":0.0032698952,"threshold_uncertainty_score":0.61249286},"labels":[],"label_agreement":null},{"id":"W4401363915","doi":"10.3138/cjpe-2024-0008","title":"Nora F. Murphy Johnson &amp; A. Rafael Johnson (2021). <i>Creative Evaluation and Engagement Essentials (Vol. 1)</i>","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Art; Art history","score_opus":0.3043823667836116,"score_gpt":0.5217967985992583,"score_spread":0.21741443181564674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9108886,0.03215453,0.013079768,0.0098992,0.009351686,0.006986124,0.000072331015,0.000067737164,0.017499993],"genre_scores_gemma":[0.9930037,0.00047522137,0.004320862,0.00023415194,0.0008333015,0.00026851965,0.00007920684,0.00002972985,0.0007553037],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99031967,0.002331931,0.0014888176,0.0005436799,0.004867529,0.00044836162],"domain_scores_gemma":[0.99062127,0.00060234894,0.00071168196,0.0004293353,0.0069733034,0.00066203874],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05000189,0.00027439988,0.00041821276,0.0016199852,0.000454755,0.0019088483,0.00043237742,0.00014797234,0.012995031],"category_scores_gemma":[0.006777088,0.00021719735,0.00020694171,0.0015372413,0.0001715705,0.0015098441,0.00003497474,0.00045770855,0.0003831525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024096964,0.000047222453,0.0017392363,0.000020262334,0.0001093917,0.000008595059,0.0027187064,0.0020124502,0.00025641854,0.00037836115,0.038050815,0.9546344],"study_design_scores_gemma":[0.0016079256,0.0006087543,0.025916506,0.00033624037,0.00075830705,0.000055843164,0.0016573318,0.18287408,0.0004261805,0.01706526,0.7682866,0.0004069687],"about_ca_topic_score_codex":0.00092215516,"about_ca_topic_score_gemma":0.014221024,"teacher_disagreement_score":0.95422745,"about_ca_system_score_codex":0.00092166674,"about_ca_system_score_gemma":0.007992235,"threshold_uncertainty_score":0.99912727},"labels":[],"label_agreement":null},{"id":"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98749566,0.00046993626,0.000013667488,0.00082240684,0.0007854472,0.0016655913,0.0000068375602,0.0000069487887,0.008733525],"genre_scores_gemma":[0.99960065,0.000040859522,0.000056528505,0.000007777189,0.000113009075,0.0000030981168,0.000005546581,0.0000047336152,0.00016778361],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919939,0.0065551735,0.00030912764,0.00007783617,0.0007586347,0.00030532188],"domain_scores_gemma":[0.9973019,0.00087667676,0.0001468274,0.00017730398,0.0012566204,0.00024070016],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.03370007,0.00005468118,0.00012640878,0.000554095,0.0035962667,0.00011729664,0.00037656506,0.0000892188,0.00006468159],"category_scores_gemma":[0.00012657918,0.00004018218,0.000050462746,0.0009881211,0.0004978076,0.00013107904,5.1730046e-7,0.0007181766,0.00000618805],"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":[0.00003148035,0.00020644264,0.0029323413,0.00014216636,0.000028455965,0.000012983042,0.84507954,0.0018210836,0.0000015146667,0.14548422,0.00019540008,0.004064367],"study_design_scores_gemma":[0.0008535769,0.0022451547,0.018222054,0.00187935,0.00013542711,0.000013420543,0.26017278,0.007180137,0.000083172235,0.02996145,0.67892206,0.00033140893],"about_ca_topic_score_codex":0.7329605,"about_ca_topic_score_gemma":0.98413545,"teacher_disagreement_score":0.6787267,"about_ca_system_score_codex":0.002149796,"about_ca_system_score_gemma":0.099388555,"threshold_uncertainty_score":0.9977009},"labels":[],"label_agreement":null},{"id":"W4401363971","doi":"10.3138/cjpe-2024-0126","title":"Reinhard Stockmann, Wolfgang Meyer, &amp; Laszlo Szentmarjay. (Eds.) (2022). <i>The Institutionalisation of Evaluation in the Americas</i>","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Institutionalisation; Political science; Sociology; Humanities; Philosophy; Law","score_opus":0.31244695241803505,"score_gpt":0.5200390598074937,"score_spread":0.2075921073894586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9310779,0.01853623,0.005760088,0.028611612,0.0044370415,0.0054322397,0.00004225591,0.000026718786,0.0060759173],"genre_scores_gemma":[0.9979202,0.00010943092,0.00072880543,0.00046917432,0.00031863636,0.00023997614,0.00006008405,0.00001110781,0.00014258498],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901634,0.0023500656,0.0014860987,0.00028398298,0.0054253936,0.00029107626],"domain_scores_gemma":[0.9945388,0.00091505767,0.00075621123,0.0004920117,0.0031308045,0.00016713492],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.053720083,0.00016338163,0.0002565108,0.0010059107,0.00028711578,0.00062561204,0.00069462106,0.00009170949,0.002058992],"category_scores_gemma":[0.0054448918,0.000095454896,0.00019715508,0.0026552575,0.00024972882,0.0009735943,0.00001818433,0.00043854193,0.00011193437],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001906672,0.000052809854,0.0044223866,0.000013672497,0.000041972897,0.0000057328257,0.0043979175,0.021103822,0.00013391243,0.0025661485,0.017370516,0.949872],"study_design_scores_gemma":[0.0011904619,0.00041871765,0.085209064,0.00028387722,0.00037668977,0.00016329785,0.003099465,0.21034686,0.00012893825,0.036737062,0.66178983,0.00025571277],"about_ca_topic_score_codex":0.00093154114,"about_ca_topic_score_gemma":0.029435609,"teacher_disagreement_score":0.9496163,"about_ca_system_score_codex":0.00067845284,"about_ca_system_score_gemma":0.008181767,"threshold_uncertainty_score":0.99885327},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4401363982","doi":"10.3138/cjpe-2023-0025","title":"E-Eval: Learnings from a Community-Based Evaluation Capacity Building Initiative","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Concordia University of Edmonton; University of Alberta","funders":"","keywords":"Capacity building; Geography; Forestry; Political science","score_opus":0.6622962955102082,"score_gpt":0.5664147753741403,"score_spread":0.09588152013606788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401363982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97849685,0.00084223214,0.010966413,0.003471186,0.0019187639,0.0013608694,0.000042111125,0.00004100137,0.002860566],"genre_scores_gemma":[0.9914756,0.0000041651047,0.007441659,0.00052370556,0.00030020188,0.0001184968,0.000086713546,0.000020755753,0.000028708217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9889382,0.004841674,0.0011792794,0.00027821766,0.0044324393,0.00033019515],"domain_scores_gemma":[0.99100435,0.0017975147,0.0007019207,0.00041305987,0.005601824,0.0004813388],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05627129,0.00019658037,0.0003152913,0.0013424868,0.0005847486,0.0014055566,0.0006446693,0.00013868831,0.0049282513],"category_scores_gemma":[0.008720417,0.00016080371,0.00022630443,0.0014721156,0.00016823426,0.0013183252,0.00001826127,0.0009795686,0.00017931525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021243073,0.000054164233,0.0070004077,0.000013971942,0.00008634123,0.0000069833304,0.007055054,0.018911455,0.0002930355,0.00046718298,0.0034402232,0.96264994],"study_design_scores_gemma":[0.0011727574,0.00062375667,0.044756267,0.00035386955,0.0003835688,0.000017132543,0.0034093459,0.82541806,0.0005444987,0.052909646,0.07016111,0.00025001206],"about_ca_topic_score_codex":0.0031258613,"about_ca_topic_score_gemma":0.019666402,"teacher_disagreement_score":0.9623999,"about_ca_system_score_codex":0.0013422393,"about_ca_system_score_gemma":0.011958282,"threshold_uncertainty_score":0.9996311},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9484782,0.008074141,0.000012595665,0.027970128,0.01068498,0.0027838964,0.00003534567,0.000021702483,0.0019389964],"genre_scores_gemma":[0.99641156,0.00032097884,0.0005310492,0.001698241,0.00063174684,0.0001488011,0.000045854136,0.000027514061,0.00018425989],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972431,0.0005981535,0.0010643428,0.00015130287,0.00045332004,0.0004897739],"domain_scores_gemma":[0.99848753,0.00023665986,0.00029585027,0.00017145985,0.00045386318,0.0003546637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043697874,0.000111542715,0.00035919173,0.0010543684,0.0000746373,0.000063376996,0.00020973982,0.0001778511,0.00070162944],"category_scores_gemma":[0.00040366498,0.000106469204,0.000083083374,0.00063856755,0.000039401642,0.0006132598,0.000016357282,0.00076067675,0.000012604348],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071724564,0.00009959639,0.11007804,0.0010170231,0.00007586277,0.00025075473,0.040510807,0.00011862063,0.000044365403,0.00130255,0.06770693,0.7787237],"study_design_scores_gemma":[0.00413137,0.0008738941,0.6123571,0.0042049354,0.00016327361,0.00002386798,0.025353933,0.0017243939,0.000021036118,0.009125582,0.3416557,0.00036496503],"about_ca_topic_score_codex":0.012113452,"about_ca_topic_score_gemma":0.503571,"teacher_disagreement_score":0.77835876,"about_ca_system_score_codex":0.0025355858,"about_ca_system_score_gemma":0.021807795,"threshold_uncertainty_score":0.994465},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7758736,0.036593452,0.005087701,0.10214232,0.022128193,0.0066779554,0.000062369436,0.0001264096,0.051308013],"genre_scores_gemma":[0.9715685,0.005805511,0.0075037195,0.00019257348,0.005100659,0.000049857004,0.00012620044,0.000051361407,0.009601598],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99423444,0.0027497418,0.0009095178,0.00028964216,0.0010508217,0.00076581864],"domain_scores_gemma":[0.9962263,0.000386442,0.0004808493,0.0001795765,0.0018654023,0.0008613989],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.014987378,0.00022989509,0.00028198204,0.00067567994,0.0024533023,0.0006205676,0.00023368844,0.00040310234,0.0007342752],"category_scores_gemma":[0.00029711486,0.00021841713,0.00019242257,0.0013815,0.00035554692,0.0012515055,9.383732e-7,0.0005689803,0.00012556279],"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":[0.000011813944,0.00015163168,0.0004484032,0.00018594044,0.00011618271,0.00003007011,0.55951655,0.0017325487,0.000023157363,0.14464186,0.0025363169,0.29060552],"study_design_scores_gemma":[0.0004356348,0.00076755695,0.012460978,0.0010164827,0.0007700232,0.00015399295,0.009233961,0.032990087,0.00007715354,0.02758792,0.91416174,0.00034443833],"about_ca_topic_score_codex":0.32402238,"about_ca_topic_score_gemma":0.97503906,"teacher_disagreement_score":0.91162544,"about_ca_system_score_codex":0.0032313217,"about_ca_system_score_gemma":0.1914979,"threshold_uncertainty_score":0.99884534},"labels":[],"label_agreement":null},{"id":"W4401364631","doi":"10.3138/cjpe-2023-0020","title":"Developing an Evaluation Training Program for Community-Based Organizations: A Participatory Curriculum Development Approach","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Training (meteorology); Curriculum; Citizen journalism; Curriculum development; Medical education; Sociology; Computer science; Political science; Pedagogy; Geography; Medicine","score_opus":0.6931025557856326,"score_gpt":0.5773742074883836,"score_spread":0.11572834829724898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7084437,0.0011849356,0.27510384,0.0019614985,0.002198257,0.009618494,0.00001820668,0.00016873781,0.0013023025],"genre_scores_gemma":[0.8272568,0.0000015378249,0.17023078,0.00020879303,0.00018953273,0.001731904,0.000333898,0.000028542512,0.00001824298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99277306,0.0021085937,0.0014686016,0.00031981972,0.0028740305,0.00045588397],"domain_scores_gemma":[0.98927474,0.00044421406,0.0005383983,0.00036290078,0.008857516,0.00052221684],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.053629883,0.00021555634,0.00030908862,0.0012049073,0.0009272837,0.0014585787,0.00062299427,0.0001303319,0.000428193],"category_scores_gemma":[0.0049893777,0.00017703553,0.000115730574,0.0022500749,0.000103337436,0.0011926523,0.000014056768,0.00038915878,0.00002720965],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068038366,0.00016715586,0.0022323441,0.000051852796,0.00005413679,0.0000010420893,0.010105342,0.0150132,0.000012065604,0.001544409,0.0005076145,0.970304],"study_design_scores_gemma":[0.0009354303,0.0006090317,0.005005686,0.00019934379,0.00022176141,0.00002121013,0.009867447,0.8951361,0.00012356331,0.0072043864,0.08040471,0.0002713188],"about_ca_topic_score_codex":0.000134473,"about_ca_topic_score_gemma":0.0066735526,"teacher_disagreement_score":0.9700327,"about_ca_system_score_codex":0.0014823256,"about_ca_system_score_gemma":0.04093181,"threshold_uncertainty_score":0.999578},"labels":[],"label_agreement":null},{"id":"W4401364750","doi":"10.3138/cjpe-2023-0047","title":"Expert Panels in Evaluation: An Update From the Field Using the DATA Model","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Canada; Agriculture and Agri-Food Canada; University of Prince Edward Island","funders":"","keywords":"Field (mathematics); Computer science; Data science; Mathematics","score_opus":0.7706233405746606,"score_gpt":0.6311445631645073,"score_spread":0.13947877741015335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85417444,0.0124906255,0.037636425,0.0864676,0.004574502,0.0034177962,0.000112659756,0.00002377352,0.0011021608],"genre_scores_gemma":[0.9938583,0.000041475716,0.0035113576,0.0019259651,0.0005167878,0.00004710441,0.00006803881,0.000010309581,0.000020681397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99426967,0.0013752173,0.0008683562,0.0003137165,0.002940367,0.00023266386],"domain_scores_gemma":[0.99613523,0.0010787928,0.0002852363,0.0009917762,0.0013085838,0.00020035187],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.037724517,0.00011802684,0.0001586325,0.00028840126,0.0002810685,0.001400119,0.0016001563,0.00007364102,0.0026808265],"category_scores_gemma":[0.0038226338,0.00006206725,0.00006713003,0.0008583246,0.000075286225,0.0017538992,0.00004812617,0.00034507984,0.00003330539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009043076,0.0000151084405,0.0014663325,8.1242854e-7,0.000021690077,0.000003995698,0.004290626,0.063283935,0.000030857827,0.00021624433,0.009654232,0.9210071],"study_design_scores_gemma":[0.00027289218,0.00006756321,0.0036943015,0.000067200315,0.00008571979,0.000012461629,0.0025782906,0.94654477,0.00002617278,0.02103949,0.02553062,0.000080531914],"about_ca_topic_score_codex":0.0033009548,"about_ca_topic_score_gemma":0.061384503,"teacher_disagreement_score":0.9209266,"about_ca_system_score_codex":0.00034305025,"about_ca_system_score_gemma":0.009094842,"threshold_uncertainty_score":0.99963653},"labels":[],"label_agreement":null},{"id":"W4401364911","doi":"10.3138/cjpe-2024-0023","title":"Marthe Hurteau &amp; Thomas Archibald (Eds.). (2023). <i>Practical Wisdom for an Ethical Evaluation Practice</i> .","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Philosophy; Environmental ethics; Engineering ethics; Engineering","score_opus":0.4952909679291251,"score_gpt":0.6140363416331979,"score_spread":0.11874537370407279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401364911","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1650718,0.02062413,0.21269801,0.47024062,0.029418632,0.02751974,0.00032413495,0.0003136494,0.073789276],"genre_scores_gemma":[0.9105394,0.000099902594,0.08251535,0.0029311504,0.0020391752,0.0007439676,0.00023622818,0.000061595405,0.0008332102],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98744816,0.0035619454,0.001660511,0.000574232,0.006197195,0.00055795314],"domain_scores_gemma":[0.98492134,0.0037015392,0.00078388996,0.00060558267,0.008983868,0.0010037941],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09691397,0.00025474108,0.00038157514,0.000984504,0.00047154844,0.0021390563,0.0005670024,0.00035360674,0.0031737764],"category_scores_gemma":[0.038688753,0.000196477,0.00030117124,0.001250417,0.0002248244,0.0026623916,0.000021732327,0.0011287981,0.00034007253],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012671061,0.00011211114,0.00021232662,0.000016074231,0.00009174035,0.00000994376,0.0017277424,0.0022223764,0.00010995125,0.0056116143,0.06956732,0.92019206],"study_design_scores_gemma":[0.00087423716,0.0010123844,0.0010628615,0.00008188403,0.0004996216,0.00026493717,0.0010594773,0.2771444,0.000025913225,0.045309864,0.6724683,0.0001961156],"about_ca_topic_score_codex":0.00037655936,"about_ca_topic_score_gemma":0.026456768,"teacher_disagreement_score":0.91999596,"about_ca_system_score_codex":0.00069715164,"about_ca_system_score_gemma":0.021535395,"threshold_uncertainty_score":0.99889684},"labels":[],"label_agreement":null},{"id":"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05057317,0.464672,0.0009497221,0.021340702,0.011118138,0.0008553229,0.00019963902,0.000042319283,0.450249],"genre_scores_gemma":[0.9861802,0.0005501595,0.0007108768,0.0001152492,0.00688799,0.000013758612,0.000018807816,0.000027125418,0.005495819],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845433,0.00034482338,0.00040101318,0.00011627339,0.0003633107,0.00032022462],"domain_scores_gemma":[0.998208,0.00015476532,0.00015294504,0.00010000678,0.0008796732,0.00050461094],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003250006,0.00012902537,0.00017032861,0.0004834514,0.0003029116,0.0018076315,0.00014373485,0.00010793925,0.007584417],"category_scores_gemma":[0.0005903254,0.00012072055,0.00023868048,0.00016033753,0.00028207732,0.00020613488,0.0000043850487,0.00034512795,0.000075532334],"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":[0.0000029285186,0.00005189459,0.00014999043,0.000075519834,0.00036211222,0.00036167665,0.0057255942,0.00040153606,0.0000019990418,0.43353823,0.013599313,0.5457292],"study_design_scores_gemma":[0.00018509895,0.00018814643,0.0002984467,0.00030937343,0.0019565758,0.00010666606,0.0011904933,0.04299604,0.00000974888,0.04144871,0.9111786,0.00013208418],"about_ca_topic_score_codex":0.018535849,"about_ca_topic_score_gemma":0.019763736,"teacher_disagreement_score":0.935607,"about_ca_system_score_codex":0.00059272844,"about_ca_system_score_gemma":0.005463777,"threshold_uncertainty_score":0.9992286},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7132883,0.13509537,0.005097711,0.0813193,0.046368703,0.0053013205,0.00001266202,0.00008280055,0.013433852],"genre_scores_gemma":[0.9774324,0.00027945745,0.015567039,0.0011829257,0.0044670356,0.00006274179,0.000011070334,0.000028658389,0.00096863107],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99923444,0.000081999235,0.00025140398,0.000084902415,0.00018858541,0.00015864547],"domain_scores_gemma":[0.9994091,0.00004723729,0.0000575714,0.00007072482,0.00019883926,0.00021656019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001232908,0.00006172165,0.0001501401,0.00039927682,0.000032444696,0.000021890619,0.00005782508,0.000083552106,0.0005445798],"category_scores_gemma":[0.0002246681,0.00005045497,0.00006206086,0.00027205833,0.00007898229,0.00017804804,0.0000013501448,0.0002727813,0.000015612106],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007240496,0.000059244256,0.006757493,0.000060832477,0.00011428942,0.0010905988,0.0018635824,0.0002106859,0.00020376178,0.00077384996,0.026396988,0.96239626],"study_design_scores_gemma":[0.0018055582,0.001286789,0.012721211,0.00047135135,0.00020454467,0.0015373945,0.00024746708,0.010157748,0.00013106165,0.008520597,0.9628096,0.00010665371],"about_ca_topic_score_codex":0.00017537051,"about_ca_topic_score_gemma":0.00499641,"teacher_disagreement_score":0.96228963,"about_ca_system_score_codex":0.00066938024,"about_ca_system_score_gemma":0.00327769,"threshold_uncertainty_score":0.59627676},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77748835,0.0007842749,0.21959484,0.0012569919,0.00032641098,0.00039785024,0.00010528471,0.000018598172,0.00002738898],"genre_scores_gemma":[0.8729567,0.0000015306528,0.12686577,0.000055618257,0.00003201654,0.000015099471,0.000032355692,0.000007980646,0.000032912307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946348,0.0021369471,0.0012304494,0.0005085007,0.0011843294,0.00030494315],"domain_scores_gemma":[0.99639654,0.00065609737,0.0003637268,0.00079323,0.0012958905,0.00049449207],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03421565,0.0001408887,0.00051958096,0.010362779,0.00012944998,0.00066397357,0.0008410709,0.00014080884,0.00058779866],"category_scores_gemma":[0.0064322515,0.00011695967,0.00029951453,0.017618343,0.00007187408,0.00069351954,0.000054570963,0.00034116697,0.000030905812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031811465,0.00010163068,0.1004682,0.0000073338124,0.0031381086,0.0049440227,0.018718388,0.04075062,0.000095781994,0.0015857089,0.00096049736,0.8291979],"study_design_scores_gemma":[0.00037705057,0.00013498034,0.07844426,0.000045291697,0.009473613,0.0006418297,0.025759596,0.87559545,0.000021107211,0.006771467,0.0024907212,0.0002446517],"about_ca_topic_score_codex":0.008145534,"about_ca_topic_score_gemma":0.38039958,"teacher_disagreement_score":0.8348448,"about_ca_system_score_codex":0.0004324467,"about_ca_system_score_gemma":0.002085022,"threshold_uncertainty_score":0.99845934},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64041436,0.0029967795,0.00045869613,0.2961797,0.047425978,0.0015754921,0.00002523104,0.000089372916,0.010834376],"genre_scores_gemma":[0.96291596,0.00082870584,0.0021591561,0.00023936284,0.030318866,0.000106911204,0.00014453832,0.000028037675,0.003258447],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952829,0.002870308,0.0005656594,0.00022817601,0.000597073,0.00045588028],"domain_scores_gemma":[0.99624884,0.0007005335,0.00055244315,0.00012385835,0.0019241231,0.00045019315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018355545,0.0001523869,0.00020977182,0.0005283065,0.0006994454,0.00020106946,0.0001854137,0.0003075763,0.0006414373],"category_scores_gemma":[0.0056099463,0.00017130177,0.00014926572,0.0014795173,0.0007900311,0.0007681897,0.0000057077027,0.00047995226,0.0001293933],"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":[0.000011188106,0.00016798446,0.009328964,0.00007360305,0.00020851972,0.0000091814745,0.1414967,0.003996422,0.000085476066,0.07610049,0.10423476,0.66428673],"study_design_scores_gemma":[0.00056194037,0.00037222155,0.06968478,0.00014733696,0.0002996043,0.000085654545,0.06890753,0.0022077542,0.000012336709,0.011648019,0.84582776,0.00024507858],"about_ca_topic_score_codex":0.005423056,"about_ca_topic_score_gemma":0.037570223,"teacher_disagreement_score":0.741593,"about_ca_system_score_codex":0.00072624517,"about_ca_system_score_gemma":0.0072944215,"threshold_uncertainty_score":0.9983333},"labels":[],"label_agreement":null},{"id":"W4405365784","doi":"10.3138/cjpe.76851","title":"Veronica G. Thomas and Patricia B. Campbell (2021). <i>Evaluation in today’s world: Respecting diversity, improving quality, and promoting usability</i>","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diversity (politics); Usability; Quality (philosophy); Sociology; Library science; Computer science; Philosophy; Anthropology; Epistemology; Human–computer interaction","score_opus":0.3843085190255128,"score_gpt":0.5217906207117903,"score_spread":0.1374821016862775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928129,0.0006125193,0.000054140186,0.003166204,0.00044690754,0.0015192932,0.000004755029,0.000013314818,0.0013699825],"genre_scores_gemma":[0.9987467,0.000029690753,0.0008597363,0.00007933294,0.00014016459,0.00004007328,0.000008582292,0.000009823285,0.000085928514],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99310833,0.0018763165,0.0012965145,0.00042298643,0.002878156,0.00041768412],"domain_scores_gemma":[0.9954674,0.001050706,0.0009055187,0.0002707716,0.0019176144,0.0003879886],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07861734,0.00015297087,0.00032090902,0.0017051494,0.00060851016,0.0005908658,0.00031923022,0.0000850016,0.0003402686],"category_scores_gemma":[0.012235839,0.00013561004,0.000069800735,0.0023945302,0.00011682094,0.0009692717,0.00017562648,0.0003362116,0.00001643965],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012279833,0.000017690507,0.3766063,0.000014321147,0.000008042904,0.0000043066634,0.003832413,0.00061573467,0.00006370031,0.00011263625,0.00016614006,0.6185464],"study_design_scores_gemma":[0.0016826236,0.00028214345,0.7919185,0.00010084595,0.00008684169,0.000016389311,0.0046178126,0.18109009,0.000044997865,0.018140938,0.0018186732,0.00020011413],"about_ca_topic_score_codex":0.0029036514,"about_ca_topic_score_gemma":0.1590468,"teacher_disagreement_score":0.61834633,"about_ca_system_score_codex":0.0008252806,"about_ca_system_score_gemma":0.0033967993,"threshold_uncertainty_score":0.9960845},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98681563,0.00022773436,0.00032369397,0.0093314145,0.0004191989,0.0011659357,0.000016723778,0.000041454394,0.0016582118],"genre_scores_gemma":[0.99327475,0.000036277383,0.005723204,0.00022411818,0.00017953738,0.0001813515,0.00015216917,0.000025920572,0.00020268279],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964605,0.0016290605,0.0005804176,0.00022698389,0.0005931825,0.00050984655],"domain_scores_gemma":[0.9972033,0.00021182952,0.00027495538,0.00024443265,0.0015581227,0.00050737394],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010186324,0.00014628652,0.00018871321,0.00046029026,0.0002627078,0.00019092427,0.00025033043,0.00026919736,0.002143631],"category_scores_gemma":[0.0009473297,0.00014226497,0.0000716532,0.0015207897,0.000120078075,0.00032731192,0.000011719005,0.00037377037,0.0002523679],"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":[0.0001298553,0.00019915834,0.27355275,0.00008861616,0.00018766071,0.00009029594,0.059333656,0.00039197653,0.0032989588,0.00077462307,0.0064676693,0.6554848],"study_design_scores_gemma":[0.0019258917,0.00079513976,0.87200344,0.00011419694,0.00016275115,0.00006853463,0.07325613,0.005606901,0.0024699604,0.03911295,0.0042186016,0.0002654807],"about_ca_topic_score_codex":0.0152432015,"about_ca_topic_score_gemma":0.14795005,"teacher_disagreement_score":0.6552193,"about_ca_system_score_codex":0.0015766735,"about_ca_system_score_gemma":0.0070373756,"threshold_uncertainty_score":0.99876857},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858605,0.00066372525,0.000008584224,0.0070580128,0.00023343346,0.0015401104,0.0000043344908,0.00000800086,0.004623262],"genre_scores_gemma":[0.99842733,0.000032344873,0.000054369924,0.000026387752,0.00017728817,0.00009532485,0.000012089988,0.000006785985,0.0011680904],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796605,0.000640421,0.0003130371,0.000076068136,0.00079237233,0.00021205697],"domain_scores_gemma":[0.9977151,0.00017376714,0.00017623084,0.00014914428,0.0017123214,0.00007344925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0086110635,0.000060290946,0.00008676373,0.00020383149,0.0006666029,0.00018237194,0.00024042832,0.000030822684,0.00018142819],"category_scores_gemma":[0.00089119317,0.00003433731,0.000052146424,0.00020511086,0.00045847928,0.00024022107,0.00003504684,0.00017513832,0.0000062654963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025493278,0.000017174574,0.0023403869,0.00007509586,0.00009913519,0.0000013851899,0.1250546,0.022177977,0.000028331964,0.089284115,0.012122229,0.74877405],"study_design_scores_gemma":[0.0003397291,0.00012679616,0.005865527,0.00005853715,0.000092633534,0.000002233218,0.010501625,0.8326242,0.000008483755,0.11922402,0.031106262,0.000049935785],"about_ca_topic_score_codex":0.0012282928,"about_ca_topic_score_gemma":0.05777172,"teacher_disagreement_score":0.81044626,"about_ca_system_score_codex":0.00010283192,"about_ca_system_score_gemma":0.0005519414,"threshold_uncertainty_score":0.9594215},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9777495,0.00059694576,0.00042688206,0.004082836,0.00040043725,0.002350129,0.00000315319,0.000057148412,0.0143329315],"genre_scores_gemma":[0.99288845,0.00007692577,0.0064059705,0.000086014574,0.000165251,0.00010998258,0.000066587374,0.000016795633,0.00018399283],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99119425,0.005722846,0.0005496695,0.00013692015,0.0020774743,0.00031884923],"domain_scores_gemma":[0.99309874,0.001156455,0.0010682346,0.000116672876,0.004164838,0.00039508005],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040637586,0.00011404892,0.0002109137,0.0008478644,0.0011242696,0.0002822139,0.00026283629,0.00012012885,0.00018928526],"category_scores_gemma":[0.026479898,0.00012620584,0.000061463994,0.0008655876,0.00024453728,0.0010786013,0.000020106543,0.00055544253,0.000020463212],"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":[0.000050512346,0.00008804231,0.025215518,0.00003219169,0.0001507427,0.0000021037222,0.5285392,0.06640501,0.000037067628,0.002223805,0.0004788709,0.37677693],"study_design_scores_gemma":[0.0022314584,0.0013365358,0.12741882,0.00023420915,0.0010341856,0.000052775085,0.59165996,0.11263426,0.000024910018,0.0021497074,0.16077828,0.0004449197],"about_ca_topic_score_codex":0.018958744,"about_ca_topic_score_gemma":0.01894029,"teacher_disagreement_score":0.376332,"about_ca_system_score_codex":0.00059251365,"about_ca_system_score_gemma":0.0064524254,"threshold_uncertainty_score":0.9991801},"labels":[],"label_agreement":null},{"id":"W4405365972","doi":"10.3138/cjpe.76834","title":"Gail Vallance Barrington &amp; Beverly Triana-Tremain. (2022). <i>Evaluation time: A practical guide for evaluation</i>","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Environmental science","score_opus":0.4077939034852666,"score_gpt":0.576833651242932,"score_spread":0.16903974775766534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81174207,0.0035356625,0.025616355,0.07760708,0.012914771,0.03773558,0.00027707094,0.00034235316,0.030229082],"genre_scores_gemma":[0.95800245,0.000095656535,0.027078645,0.0017669647,0.002136348,0.0033981404,0.0009610782,0.00012365812,0.0064370455],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98373646,0.0027147431,0.0024872315,0.0006835185,0.009570373,0.000807666],"domain_scores_gemma":[0.9779643,0.0019289101,0.0018540778,0.0007975938,0.016558964,0.00089615467],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.12750241,0.00032402013,0.00058321,0.001727806,0.0006571253,0.0009484202,0.0007808233,0.000238205,0.0096024675],"category_scores_gemma":[0.04797655,0.0002807167,0.00040440942,0.00277029,0.00013850817,0.0015330835,0.000033640626,0.00038315795,0.0013282644],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012570343,0.000069594294,0.0018949875,0.000012469026,0.00010230653,0.000003935464,0.0009954749,0.014130671,0.00028575462,0.0003464018,0.2737108,0.7083219],"study_design_scores_gemma":[0.004726415,0.00064827077,0.013579928,0.0000637884,0.0005629666,0.000051010935,0.00079221005,0.5570961,0.0000747299,0.02260119,0.39948946,0.00031393132],"about_ca_topic_score_codex":0.00024959305,"about_ca_topic_score_gemma":0.012447807,"teacher_disagreement_score":0.708008,"about_ca_system_score_codex":0.001778877,"about_ca_system_score_gemma":0.024835592,"threshold_uncertainty_score":0.9999645},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3573177,0.07480315,0.0003454156,0.0352124,0.011113903,0.001631526,0.00032378762,0.000089680056,0.5191625],"genre_scores_gemma":[0.9872375,0.000505272,0.0004190274,0.00013599951,0.004957391,0.000018873508,0.00004141492,0.000026813515,0.00665772],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982658,0.00040621354,0.00041159362,0.000103784725,0.00041028342,0.00040229675],"domain_scores_gemma":[0.9976857,0.00015578754,0.00030650396,0.00011930481,0.0011802155,0.0005525144],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004051792,0.00012308868,0.00018874853,0.0005902698,0.00045259195,0.0007468748,0.00017269659,0.000107535074,0.00450268],"category_scores_gemma":[0.0011512612,0.00012193488,0.00020565704,0.00027817787,0.00028206132,0.00014810302,0.000006509233,0.00026238823,0.00014889376],"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":[0.0000074607487,0.00009704818,0.0015545229,0.000053797627,0.00042384048,0.0003941915,0.009659845,0.0022309374,0.0000039883857,0.31046063,0.03802626,0.63708746],"study_design_scores_gemma":[0.00044688198,0.0002108264,0.00323924,0.000120965895,0.0012980227,0.000043873588,0.0027639773,0.0317155,0.000010549721,0.037427913,0.922566,0.00015623908],"about_ca_topic_score_codex":0.019542458,"about_ca_topic_score_gemma":0.024132023,"teacher_disagreement_score":0.8845397,"about_ca_system_score_codex":0.0004104469,"about_ca_system_score_gemma":0.0036099183,"threshold_uncertainty_score":0.99640733},"labels":[],"label_agreement":null},{"id":"W4405366000","doi":"10.3138/cjpe-2023-0011","title":"When we say evaluation, it isn’t the same thing","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sociology; Computer science","score_opus":0.5162236582112425,"score_gpt":0.5551123995560459,"score_spread":0.03888874134480336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366000","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39471072,0.0037541883,0.0026594154,0.5453715,0.009123754,0.007657325,0.000033182718,0.000112718604,0.036577243],"genre_scores_gemma":[0.9927279,0.000067421635,0.0013997488,0.002078971,0.00063285505,0.0002142577,0.000032658096,0.00002096427,0.0028252224],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.990172,0.0017622599,0.0012893107,0.00027663622,0.0060614115,0.00043832595],"domain_scores_gemma":[0.9915784,0.0008549698,0.0009217213,0.00054639013,0.0056623803,0.0004361093],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.07333303,0.00016152431,0.00025166108,0.0009754174,0.00065800495,0.000977325,0.0009983879,0.00009847059,0.012458819],"category_scores_gemma":[0.009676247,0.00010147099,0.00019298618,0.0018061794,0.00013127543,0.00096768903,0.000029714312,0.00035055078,0.0010146267],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067732653,0.000012666391,0.004104524,0.0000025900283,0.000033478496,0.000003047554,0.0077784294,0.010509758,0.000018263476,0.0004230048,0.18906865,0.7880388],"study_design_scores_gemma":[0.0009510927,0.00025391494,0.04707082,0.00008079245,0.00018813474,0.000038546477,0.0101824775,0.38251233,0.000034427034,0.0789678,0.47953853,0.0001811185],"about_ca_topic_score_codex":0.0005210097,"about_ca_topic_score_gemma":0.027597908,"teacher_disagreement_score":0.7878577,"about_ca_system_score_codex":0.0006170236,"about_ca_system_score_gemma":0.009163156,"threshold_uncertainty_score":0.9997632},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836797,0.00007410504,0.000008206049,0.015409619,0.00029124395,0.00039085778,0.0000070220385,0.000013561098,0.00012564598],"genre_scores_gemma":[0.9986601,0.0000070087813,0.00014103389,0.00003795578,0.0008785902,0.000025031408,0.00008234254,5.709028e-7,0.00016735008],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992785,0.0001475752,0.00013307425,0.00010113332,0.00017911679,0.00016059737],"domain_scores_gemma":[0.9993285,0.000037802693,0.00005554111,0.000021837912,0.0003083687,0.00024797604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013775202,0.000042213134,0.00005899181,0.0001011032,0.00017210131,0.00006052901,0.000062348474,0.00006056889,0.000223688],"category_scores_gemma":[0.00055366784,0.000019937897,0.000023595168,0.00063265674,0.000026661386,0.00008900957,0.0000068065888,0.00010756414,0.000042167583],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001363194,0.000009427496,0.021173855,0.0000016683304,0.000016914004,0.0000096603535,0.00010657781,0.00026118956,0.09311415,0.00004532606,0.031120768,0.8541268],"study_design_scores_gemma":[0.00010161675,0.00059232255,0.81170607,0.000010208969,0.000019883895,0.00010703506,0.0001554971,0.0012089286,0.00031634347,0.00044260782,0.18527201,0.00006747558],"about_ca_topic_score_codex":0.0006622072,"about_ca_topic_score_gemma":0.044246655,"teacher_disagreement_score":0.85405934,"about_ca_system_score_codex":0.0000820324,"about_ca_system_score_gemma":0.00011023865,"threshold_uncertainty_score":0.97319335},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5203267,0.0061254418,0.013844666,0.044975378,0.0810602,0.01303333,0.00012520196,0.0011673528,0.31934172],"genre_scores_gemma":[0.9836332,0.000046715086,0.0045651775,0.0004368789,0.00825575,0.00083293323,0.00006240646,0.000050129216,0.0021168138],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908847,0.00009896715,0.00026664627,0.00009950254,0.00022343028,0.00022297466],"domain_scores_gemma":[0.99897563,0.000029475143,0.00017472997,0.00019368416,0.00036778848,0.00025870802],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001570721,0.00006404202,0.00009014008,0.00034214518,0.00008927755,0.000044104243,0.0001815432,0.000089023575,0.0020108484],"category_scores_gemma":[0.000054293174,0.00006081981,0.000072829294,0.00052821136,0.00004295263,0.00006525079,0.0000017872532,0.0001500907,0.00019131367],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047206795,0.000017634686,0.0006872406,0.0000012426443,0.000024262406,0.000006072632,0.00041474478,0.0000067771916,0.00005762277,0.0016248913,0.5019671,0.49518773],"study_design_scores_gemma":[0.00039169585,0.00022897626,0.03365488,0.00002226041,0.000034223354,0.000035264362,0.00025708237,0.00040908507,0.000020787946,0.008447721,0.9564135,0.00008448932],"about_ca_topic_score_codex":0.0004930989,"about_ca_topic_score_gemma":0.0020426016,"teacher_disagreement_score":0.49510324,"about_ca_system_score_codex":0.000113372174,"about_ca_system_score_gemma":0.00050674536,"threshold_uncertainty_score":0.9989014},"labels":[],"label_agreement":null},{"id":"W4405366177","doi":"10.3138/cjpe-2023-0012","title":"Examining Youth Sector Stakeholders’ Experiences in an Online Program Evaluation Certificate","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"York University; Youth Research and Evaluation eXchange; Brock University","funders":"","keywords":"Certificate; Business; Public relations; Political science; Computer science","score_opus":0.9339822613619181,"score_gpt":0.581308825436659,"score_spread":0.3526734359252591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99436516,0.00018516122,0.00007188006,0.0007213355,0.0012342961,0.0029245382,0.000018489025,0.000050089246,0.00042906235],"genre_scores_gemma":[0.9968215,0.000009124609,0.0018019546,0.00008396574,0.00025823835,0.0007197795,0.00022569502,0.000020601448,0.00005913871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911465,0.0016459336,0.0016183223,0.00047178377,0.0045535145,0.0005639161],"domain_scores_gemma":[0.994144,0.00023507273,0.000937588,0.00047295756,0.003571895,0.0006384538],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03396134,0.0002106657,0.00034876,0.0020779548,0.00026852,0.0008795586,0.00074401964,0.00013211228,0.0022671022],"category_scores_gemma":[0.0037836994,0.00017155163,0.00010360034,0.0032890085,0.00014559661,0.0016508942,0.000019361501,0.00031996475,0.00008056897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019853222,0.00012726535,0.04696091,0.0000034843733,0.000011588325,0.0000079043675,0.036784373,0.009406613,0.00006583357,0.00001208567,0.00031089052,0.9062892],"study_design_scores_gemma":[0.0013383396,0.0012869802,0.34067336,0.00007755812,0.000074939715,0.000010026845,0.16984648,0.48259002,0.00007376269,0.0012093225,0.0025844418,0.00023475292],"about_ca_topic_score_codex":0.0005627401,"about_ca_topic_score_gemma":0.05345097,"teacher_disagreement_score":0.90605444,"about_ca_system_score_codex":0.00065632217,"about_ca_system_score_gemma":0.006035719,"threshold_uncertainty_score":0.99959916},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"incentives","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W4406258567","doi":"10.3138/cjpe-2023-0055","title":"Reporting Lines of Inquiry: Documenting Evaluations and Making Values Explicit","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Documentation; Set (abstract data type); Dimension (graph theory); Key (lock); Computer science; Value (mathematics); Quality (philosophy); Action (physics); Psychology; Epistemology; Mathematics","score_opus":0.5936105233649892,"score_gpt":0.6283661788620908,"score_spread":0.03475565549710158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406258567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98439884,0.004273318,0.0045954194,0.0021129567,0.0017188098,0.00080930017,0.0000037837115,0.000019225816,0.002068337],"genre_scores_gemma":[0.9916321,0.000024234017,0.0077498304,0.00005559577,0.0003582699,0.0000390474,0.000005728642,0.000011868346,0.00012330142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941642,0.00045155216,0.0026558603,0.0002511565,0.0022430727,0.00023415816],"domain_scores_gemma":[0.9936929,0.00051213265,0.0022832386,0.00023777418,0.0030606794,0.00021329444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040812105,0.00012135005,0.00030452682,0.0011090161,0.00022749983,0.0007961701,0.0002454239,0.00006776542,0.0008959249],"category_scores_gemma":[0.013578381,0.00009413398,0.000138138,0.0010404431,0.00009911454,0.0010401335,0.000023204273,0.00019331016,0.000014064643],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004593414,0.000013129312,0.028001122,0.000030422038,0.00004933264,0.000008807215,0.0067251744,0.0022061495,0.00032938772,0.0012600109,0.0010415476,0.9603303],"study_design_scores_gemma":[0.00087458506,0.00073296204,0.14195865,0.0014983455,0.0006006826,0.00033854146,0.015767418,0.7182884,0.0009851777,0.08503619,0.03353383,0.0003851976],"about_ca_topic_score_codex":0.00015745926,"about_ca_topic_score_gemma":0.0018170113,"teacher_disagreement_score":0.95994514,"about_ca_system_score_codex":0.00019785012,"about_ca_system_score_gemma":0.003921776,"threshold_uncertainty_score":0.99473065},"labels":[],"label_agreement":null},{"id":"W4406258628","doi":"10.3138/cjpe-2024-0028","title":"Theory-of-Change Visuals: Using Diagrams, Metaphors, and Symbols to Communicate Complex Ideas and Get Buy-In","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Context (archaeology); Creativity; Field (mathematics); Stakeholder; Dynamism; Sociology; Epistemology; Psychology; Public relations; Social psychology","score_opus":0.7625487198627899,"score_gpt":0.6027241267009266,"score_spread":0.15982459316186337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406258628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865531,0.009220324,0.00073662115,0.0019400335,0.00027621802,0.0010583024,0.000015255159,0.0000057910997,0.00019437273],"genre_scores_gemma":[0.9951955,0.000105600986,0.004388324,0.00018541771,0.00005853069,0.000036272308,0.000006055744,0.000009608833,0.000014693316],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99680185,0.0009875986,0.000814714,0.00018318859,0.0010040639,0.00020859574],"domain_scores_gemma":[0.99782026,0.00056078495,0.00026807698,0.00022548936,0.00074450433,0.00038087828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021275569,0.00011295491,0.00029790407,0.001015876,0.00011541519,0.00037238584,0.0002758356,0.00005524092,0.0003508228],"category_scores_gemma":[0.0012149533,0.000086980814,0.000059164184,0.00084596046,0.00012441793,0.0005545152,0.000036771762,0.00017213506,0.000007535834],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017690752,0.000021164817,0.050326135,0.000020880329,0.00003627016,0.000007879108,0.005503331,0.0002630645,0.0001466035,0.004007802,0.00018841155,0.93946075],"study_design_scores_gemma":[0.0009725943,0.0008421758,0.50719684,0.0006556051,0.0002688285,0.00012381462,0.0064683002,0.3801218,0.000111569716,0.08026316,0.022660244,0.0003150806],"about_ca_topic_score_codex":0.0011806024,"about_ca_topic_score_gemma":0.018701218,"teacher_disagreement_score":0.9391457,"about_ca_system_score_codex":0.00017076611,"about_ca_system_score_gemma":0.0010110842,"threshold_uncertainty_score":0.99920493},"labels":[],"label_agreement":null},{"id":"W4406259049","doi":"10.3138/cjpe-2024-0034","title":"Old Knowledge, New Tools: Applying an Indigenous Approach to Social Network Analysis","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indigenous; Honour; Traditional knowledge; Social network analysis; Work (physics); Indigenous education; Value (mathematics); Scale (ratio); Process (computing); Sociology; Data science; Computer science; Geography; Social science; Engineering; Cartography; Archaeology; Ecology; Social capital","score_opus":0.42867378272941575,"score_gpt":0.5489013155159965,"score_spread":0.12022753278658077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406259049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78234386,0.006904803,0.1626492,0.0030559285,0.0052362112,0.006688591,0.000046831334,0.00013358537,0.032940965],"genre_scores_gemma":[0.9843445,0.000005103349,0.012466848,0.00024402769,0.0018629646,0.00013891341,0.000050176597,0.000017819233,0.00086967304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99546605,0.0006369331,0.0010112056,0.00036321976,0.0020699482,0.00045261052],"domain_scores_gemma":[0.99658996,0.00019548029,0.00031416758,0.00028496498,0.0016355809,0.0009798201],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01873785,0.00016286015,0.00036884996,0.0017901931,0.00046678883,0.0023157685,0.0006529238,0.0001164243,0.000965435],"category_scores_gemma":[0.0005779562,0.00013101142,0.0002952832,0.0056986366,0.000040691477,0.001078311,0.000018298662,0.0002940687,0.00017422305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076220617,0.000040356997,0.003577185,0.0000047412072,0.0001967181,0.0000032164944,0.015846886,0.043007474,0.0000035199494,0.0009041082,0.008115009,0.92829317],"study_design_scores_gemma":[0.0006209069,0.0007420038,0.097292565,0.00006337745,0.0017069508,0.00003958484,0.005903044,0.51652044,0.000009858559,0.014607765,0.36201945,0.00047406473],"about_ca_topic_score_codex":0.000909454,"about_ca_topic_score_gemma":0.038442884,"teacher_disagreement_score":0.9278191,"about_ca_system_score_codex":0.00064653717,"about_ca_system_score_gemma":0.009474202,"threshold_uncertainty_score":0.99994785},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9161735,0.051982544,0.0032218692,0.0021269028,0.0019616138,0.014794252,0.00030717632,0.0000724458,0.009359677],"genre_scores_gemma":[0.983707,0.005377271,0.0087044975,0.00013109883,0.001069876,0.00017905419,0.000353349,0.00005364998,0.00042421854],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973808,0.0004320588,0.0004534595,0.00033301895,0.00083047734,0.00057016866],"domain_scores_gemma":[0.9977377,0.0002486169,0.00025233385,0.00023349462,0.0009870271,0.00054081454],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.007712019,0.000160127,0.00021568059,0.00030068264,0.0047961134,0.00063690083,0.00030788177,0.00016482495,0.00010233294],"category_scores_gemma":[0.000102180864,0.00013321127,0.000035398753,0.00044579702,0.00034139992,0.0010487105,0.0000022030015,0.00023696129,0.000003945938],"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":[0.00001778654,0.000063370215,0.0013474984,0.00014977397,0.00017280012,0.000007524403,0.6129703,0.000017278258,0.0000018551135,0.018698312,0.0012163658,0.36533716],"study_design_scores_gemma":[0.00072087726,0.0007517437,0.00049261353,0.0002768651,0.00071863824,0.00010570301,0.017474128,0.0012837276,0.000012575309,0.03929158,0.93855286,0.0003186766],"about_ca_topic_score_codex":0.122358076,"about_ca_topic_score_gemma":0.8686197,"teacher_disagreement_score":0.9373365,"about_ca_system_score_codex":0.00073783105,"about_ca_system_score_gemma":0.08465907,"threshold_uncertainty_score":0.9964995},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2132297,0.108868875,0.005069687,0.53786176,0.025384739,0.018424168,0.000057040495,0.000303515,0.090800524],"genre_scores_gemma":[0.9896309,0.00037177425,0.00036821855,0.0042562075,0.0025762902,0.0006946726,0.000034758832,0.000046895228,0.0020202862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956807,0.0012616616,0.0011023242,0.00021769817,0.0011495061,0.00058810326],"domain_scores_gemma":[0.9958693,0.0007259235,0.0005115662,0.0003595631,0.002122268,0.0004113721],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021291314,0.0001799885,0.00029409557,0.00042181255,0.0016857673,0.0001359451,0.00045914963,0.0001625975,0.001470423],"category_scores_gemma":[0.0020131976,0.00009971373,0.0001528725,0.0006921629,0.00014020802,0.00044514122,0.000031713236,0.0014454313,0.00005279514],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001771281,0.000011192451,0.002733043,0.00011779664,0.00014186362,0.000007952358,0.026830237,0.0021261114,0.00003194366,0.002915741,0.12176468,0.8433017],"study_design_scores_gemma":[0.00108791,0.00019360751,0.0134330895,0.0012673963,0.0012258551,0.000067402536,0.0069678156,0.5350874,0.0000029152322,0.021018941,0.41945854,0.00018912883],"about_ca_topic_score_codex":0.0031968332,"about_ca_topic_score_gemma":0.0583102,"teacher_disagreement_score":0.8431126,"about_ca_system_score_codex":0.0024405124,"about_ca_system_score_gemma":0.01333466,"threshold_uncertainty_score":0.9996139},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9792086,0.001860165,0.00042530222,0.0006797659,0.00088104396,0.0069226716,0.0000028600389,0.00006284353,0.009956768],"genre_scores_gemma":[0.98018926,0.0000048154916,0.016012453,0.000051503674,0.0003336977,0.0029749996,0.000007944518,0.000037706137,0.00038760938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98312,0.011205018,0.00093025086,0.00038931737,0.0033251436,0.0010302351],"domain_scores_gemma":[0.9939232,0.0009936349,0.00033773214,0.00022373491,0.0033810553,0.0011406433],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08581575,0.00021805154,0.0003718014,0.0010672209,0.0005181684,0.0006918692,0.00039525636,0.00022394466,0.0013171489],"category_scores_gemma":[0.020560803,0.0002201088,0.00019525974,0.0021223626,0.00031149032,0.0008266553,0.000019262672,0.0008485021,0.00006254906],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000059367965,0.00014014833,0.03258326,0.000026193653,0.000120570774,0.000055441596,0.12403541,0.0012086813,0.00019003691,0.00028811613,0.00015185733,0.8411409],"study_design_scores_gemma":[0.005299705,0.007340012,0.18351026,0.0020640474,0.0024185565,0.00006900639,0.050045285,0.5175599,0.0010456595,0.08398346,0.14520305,0.0014610704],"about_ca_topic_score_codex":0.2634236,"about_ca_topic_score_gemma":0.9861609,"teacher_disagreement_score":0.83967984,"about_ca_system_score_codex":0.01494113,"about_ca_system_score_gemma":0.11311284,"threshold_uncertainty_score":0.99959576},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.767519,0.08193115,0.009607874,0.1247096,0.003993922,0.0043375883,0.00015163569,0.0001088045,0.007640424],"genre_scores_gemma":[0.98492795,0.0023286114,0.010394717,0.00015352968,0.0007719461,0.00051336875,0.00020075268,0.000034580637,0.0006745222],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938997,0.003118588,0.0007708033,0.0002646229,0.0008874966,0.001058784],"domain_scores_gemma":[0.9965126,0.00025564857,0.0004260321,0.00017191526,0.0016244766,0.0010093339],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011430089,0.00026988884,0.00025422242,0.00033910654,0.0027107052,0.0007288737,0.0003108145,0.0002499858,0.0011854486],"category_scores_gemma":[0.0010753245,0.0002773781,0.00022804544,0.0009655451,0.0006936464,0.00097089744,0.000011087685,0.0005136196,0.000026431195],"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":[0.000010710229,0.00034651358,0.006634698,0.000183202,0.00037250697,0.000018507413,0.46268326,0.0064482065,0.000022274255,0.02067476,0.011822112,0.49078324],"study_design_scores_gemma":[0.0011941198,0.0011616711,0.103385545,0.0027310627,0.002020222,0.0000990596,0.2564698,0.09581804,0.00040048928,0.19551708,0.34045482,0.0007481287],"about_ca_topic_score_codex":0.026641726,"about_ca_topic_score_gemma":0.31201613,"teacher_disagreement_score":0.49003512,"about_ca_system_score_codex":0.0076636523,"about_ca_system_score_gemma":0.031438936,"threshold_uncertainty_score":0.9999678},"labels":[],"label_agreement":null},{"id":"W4406530370","doi":"10.3138/cjpe-2023-0026","title":"Foundations for a Utopia: Can Evaluation Contribute to Achieving a Better World, and How?","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique; Government of Canada; Government of Nova Scotia; University of Victoria","funders":"","keywords":"Utopia; Environmental ethics; Sociology; Aesthetics; Philosophy; History; Art history","score_opus":0.3634329391642527,"score_gpt":0.5449652074120074,"score_spread":0.1815322682477547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406530370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.717147,0.0023239607,0.04402025,0.22217576,0.0041250554,0.008504917,0.00012884384,0.000041723906,0.0015324806],"genre_scores_gemma":[0.98960626,0.000005663176,0.007821445,0.000729493,0.00046842903,0.00052504597,0.00004641149,0.0000146184575,0.0007826587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99633235,0.00045582338,0.0006277838,0.0002950932,0.0019840428,0.00030491975],"domain_scores_gemma":[0.99425524,0.00065772736,0.00028064556,0.0002160038,0.004069536,0.00052084395],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.023293313,0.00013597486,0.00022565745,0.0014766917,0.00033211295,0.0020677848,0.00025271214,0.000058584803,0.0007355592],"category_scores_gemma":[0.0054092463,0.00010839052,0.00012512812,0.001144543,0.000054568445,0.00077617017,0.000013934773,0.00017108601,0.0000249409],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009956641,0.000009384688,0.004378081,0.00001078007,0.000046241308,0.0000017996325,0.0011118958,0.0008333951,0.0000633444,0.0019408737,0.009918071,0.98167616],"study_design_scores_gemma":[0.0011651579,0.00056959,0.04421614,0.0002036288,0.00039698562,0.000040546325,0.0005930098,0.37943763,0.000049478327,0.020539109,0.5525705,0.00021817548],"about_ca_topic_score_codex":0.00015014329,"about_ca_topic_score_gemma":0.056852706,"teacher_disagreement_score":0.981458,"about_ca_system_score_codex":0.00070046494,"about_ca_system_score_gemma":0.005546898,"threshold_uncertainty_score":0.9989682},"labels":[],"label_agreement":null},{"id":"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94022244,0.0021711853,0.032248758,0.011078931,0.007079005,0.0047530932,0.0002592183,0.00009348745,0.002093908],"genre_scores_gemma":[0.9889286,0.000004640706,0.005989571,0.00088125106,0.0035120049,0.00017851451,0.00041597598,0.000031595242,0.000057856312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998593,0.00001575254,0.0004063961,0.00027008192,0.00041742425,0.0002973475],"domain_scores_gemma":[0.9982857,0.00008097956,0.00014614504,0.00023828699,0.0011402046,0.00010866013],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001427676,0.00014955786,0.00018344379,0.00052356644,0.00013163089,0.0012416426,0.00032801574,0.00005538514,0.0011424948],"category_scores_gemma":[0.001268832,0.00013124403,0.0000960165,0.00068539707,0.000043990967,0.0022383106,0.00003305802,0.00012890331,0.00033838578],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003912346,0.000030112798,0.0020360718,0.00017328393,0.000050028935,0.00001937419,0.000098620134,0.000066225024,0.00023207504,0.001001419,0.040211484,0.9560422],"study_design_scores_gemma":[0.00033823692,0.00009613314,0.009080617,0.00087954366,0.00042360486,0.000011045966,0.0003777491,0.06911074,0.00024426187,0.0066632894,0.91248786,0.0002869211],"about_ca_topic_score_codex":0.015054979,"about_ca_topic_score_gemma":0.03216313,"teacher_disagreement_score":0.95575523,"about_ca_system_score_codex":0.00012438519,"about_ca_system_score_gemma":0.0010585997,"threshold_uncertainty_score":0.99979514},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06448379,0.05444958,0.041206006,0.3938293,0.08064762,0.0070922384,0.00004942641,0.00024529404,0.35799673],"genre_scores_gemma":[0.942887,0.00026347564,0.036309525,0.00015323253,0.01888595,0.00006471543,0.00000794952,0.000025533456,0.0014026026],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99638957,0.0021478585,0.00021568475,0.00007666123,0.0009076933,0.00026254027],"domain_scores_gemma":[0.9976292,0.00048707836,0.00006166364,0.000053886353,0.001220634,0.0005474913],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032167014,0.00004480235,0.00008180016,0.00028013455,0.0002960207,0.00038698257,0.00014803329,0.000094631156,0.0007605463],"category_scores_gemma":[0.007086122,0.00003882744,0.00007947243,0.00045674047,0.00037701707,0.00032089592,0.0000027375638,0.00036548052,0.000025710606],"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":[0.0000020665148,0.0000058666337,0.00013329477,0.000018109482,0.00002603359,0.00002489542,0.019082855,0.000007763456,0.000013053421,0.028963171,0.037731424,0.91399145],"study_design_scores_gemma":[0.000067198045,0.0001269388,0.0004026235,0.0001249227,0.000028861794,0.0000035768526,0.004670227,0.00091460434,0.000008975083,0.059674043,0.93392515,0.00005289186],"about_ca_topic_score_codex":0.007815633,"about_ca_topic_score_gemma":0.055390414,"teacher_disagreement_score":0.9139386,"about_ca_system_score_codex":0.0005480635,"about_ca_system_score_gemma":0.0125109805,"threshold_uncertainty_score":0.9987914},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3037101,0.16239224,0.005858798,0.26908353,0.12014577,0.0040983125,0.00015245049,0.0001280585,0.13443074],"genre_scores_gemma":[0.9583705,0.00080754183,0.0010660561,0.0003075229,0.018210966,0.00018671947,0.0001153547,0.00008404951,0.020851284],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935075,0.003726267,0.0009264767,0.0005103196,0.0006709781,0.0006584529],"domain_scores_gemma":[0.9968227,0.0002764933,0.00034916002,0.00039095577,0.0014514548,0.00070922094],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013840141,0.00027295764,0.00039524777,0.0016891807,0.00021021678,0.0006332957,0.00026947027,0.00055304973,0.00876406],"category_scores_gemma":[0.0006118802,0.00026934023,0.00039260578,0.0015776173,0.00034938566,0.00057460205,0.000008177249,0.0015571683,0.00064222194],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007715961,0.0001968612,0.0015223471,0.00009004654,0.0005380019,0.00028647136,0.0038472258,0.0003860138,0.0001977388,0.002746302,0.25222385,0.737888],"study_design_scores_gemma":[0.0009349388,0.0011572539,0.01632026,0.0003234738,0.0009317895,0.0033456215,0.00084357883,0.005655924,0.00001670785,0.0023352264,0.96789867,0.00023657284],"about_ca_topic_score_codex":0.0019173333,"about_ca_topic_score_gemma":0.014989829,"teacher_disagreement_score":0.7376514,"about_ca_system_score_codex":0.0006224147,"about_ca_system_score_gemma":0.003550819,"threshold_uncertainty_score":0.99997586},"labels":[],"label_agreement":null},{"id":"W4406938302","doi":"10.3138/cjpe-2023-0005","title":"Developing a Community of Practice (CoP) on Monitoring, Evaluation, and Learning (MEL) in a Global Network of Women’s Funds","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Psychology; Medical education; Medicine","score_opus":0.38552297080082165,"score_gpt":0.5674184361961859,"score_spread":0.18189546539536428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406938302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99380505,0.0018477984,0.0004663667,0.0010091962,0.0007050244,0.0006227441,0.0000024427115,0.000005562159,0.001535791],"genre_scores_gemma":[0.9952029,0.000044972297,0.0045040883,0.00004950567,0.000112568756,0.00006055999,0.0000036988042,0.0000066960856,0.000015031281],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99299806,0.0029925075,0.0011605272,0.00015585676,0.0024006213,0.00029242338],"domain_scores_gemma":[0.993818,0.0012186441,0.00078994414,0.00019818827,0.0037390504,0.00023621746],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.073799334,0.00011359618,0.00029080742,0.00045683255,0.00019808782,0.00024044448,0.0002820306,0.0000798697,0.00023876433],"category_scores_gemma":[0.013937587,0.0000965249,0.00005853851,0.0015946944,0.000090994996,0.0006960363,0.00002285661,0.0005281995,0.0000055390983],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049072303,0.000040335228,0.1232374,0.00002984125,0.000050109258,0.0000030098095,0.010353641,0.035653032,0.000007856139,0.001337135,0.00012589534,0.82911265],"study_design_scores_gemma":[0.0016006187,0.0020958008,0.7582463,0.0013374927,0.00017595496,0.00006139445,0.030509073,0.1520023,0.000059142654,0.029682469,0.024004938,0.00022452652],"about_ca_topic_score_codex":0.0018581988,"about_ca_topic_score_gemma":0.008033517,"teacher_disagreement_score":0.8288881,"about_ca_system_score_codex":0.002438691,"about_ca_system_score_gemma":0.008855318,"threshold_uncertainty_score":0.9967635},"labels":[],"label_agreement":null},{"id":"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05057317,0.464672,0.0009497221,0.021340702,0.011118138,0.0008553229,0.00019963902,0.000042319283,0.450249],"genre_scores_gemma":[0.9861802,0.0005501595,0.0007108768,0.0001152492,0.00688799,0.000013758612,0.000018807816,0.000027125418,0.005495819],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845433,0.00034482338,0.00040101318,0.00011627339,0.0003633107,0.00032022462],"domain_scores_gemma":[0.998208,0.00015476532,0.00015294504,0.00010000678,0.0008796732,0.00050461094],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003250006,0.00012902537,0.00017032861,0.0004834514,0.0003029116,0.0018076315,0.00014373485,0.00010793925,0.007584417],"category_scores_gemma":[0.0005903254,0.00012072055,0.00023868048,0.00016033753,0.00028207732,0.00020613488,0.0000043850487,0.00034512795,0.000075532334],"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":[0.0000029285186,0.00005189459,0.00014999043,0.000075519834,0.00036211222,0.00036167665,0.0057255942,0.00040153606,0.0000019990418,0.43353823,0.013599313,0.5457292],"study_design_scores_gemma":[0.00018509895,0.00018814643,0.0002984467,0.00030937343,0.0019565758,0.00010666606,0.0011904933,0.04299604,0.00000974888,0.04144871,0.9111786,0.00013208418],"about_ca_topic_score_codex":0.018535849,"about_ca_topic_score_gemma":0.019763736,"teacher_disagreement_score":0.935607,"about_ca_system_score_codex":0.00059272844,"about_ca_system_score_gemma":0.005463777,"threshold_uncertainty_score":0.9992286},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9408412,0.0010925033,0.000039305134,0.056836624,0.0005855414,0.00043412065,0.0000068315944,0.000009004618,0.00015485646],"genre_scores_gemma":[0.9981455,0.000008578624,0.000095967036,0.000053396096,0.0015171106,0.0000233665,0.000025854548,4.4985333e-7,0.00012978389],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993922,0.00015551111,0.00010634882,0.000086845015,0.0001502439,0.00010886807],"domain_scores_gemma":[0.99957055,0.000047359266,0.000025421868,0.000020265194,0.00019499536,0.00014142798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014197271,0.000035975685,0.00003886372,0.000047152254,0.00016594454,0.00014638752,0.00006602722,0.00004341328,0.00020868224],"category_scores_gemma":[0.0002979059,0.000012466262,0.000024757956,0.00035272416,0.00002817911,0.00008611525,0.0000047876097,0.00014237175,0.000024714187],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047969343,0.000004051617,0.001740388,0.0000014910685,0.000015946227,0.0000051037073,0.000102925595,0.00010167493,0.017578753,0.00012759653,0.026160663,0.95415664],"study_design_scores_gemma":[0.000037296104,0.00045905236,0.19181074,0.000020187537,0.000035489014,0.00028532467,0.00012262125,0.0028131192,0.00015570055,0.00047634883,0.8037328,0.00005129979],"about_ca_topic_score_codex":0.0005521024,"about_ca_topic_score_gemma":0.050909717,"teacher_disagreement_score":0.9541053,"about_ca_system_score_codex":0.00008288156,"about_ca_system_score_gemma":0.0001413248,"threshold_uncertainty_score":0.9664087},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9843034,0.0026031218,0.00006872561,0.000232702,0.0022618156,0.002035848,0.000006304243,0.00008618112,0.008401888],"genre_scores_gemma":[0.9962936,0.000089398585,0.0010918416,0.000034821955,0.002108821,0.000020854404,0.000049208993,0.000023360657,0.0002880919],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961692,0.001916167,0.00052694965,0.00019585424,0.00064227247,0.000549524],"domain_scores_gemma":[0.9979502,0.0003555863,0.00042538607,0.00012140763,0.0006438566,0.0005035577],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.011369281,0.00013205278,0.00017179805,0.00027067857,0.006128151,0.00094603875,0.00032547605,0.00015505773,0.00017130403],"category_scores_gemma":[0.0001574318,0.00009443141,0.00008542427,0.00039962825,0.00038255553,0.0005630459,6.1542045e-7,0.00068285567,0.000024480156],"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":[0.000005979878,0.000023477174,0.008669923,0.000011912085,0.00005169653,0.00001285941,0.6777192,0.000048165344,0.0000017413385,0.011719681,0.000016600257,0.3017188],"study_design_scores_gemma":[0.00040430017,0.0007502004,0.0059528938,0.00048542916,0.000328335,0.00011381269,0.45433044,0.0022442292,0.000077181,0.011293263,0.5236468,0.00037313573],"about_ca_topic_score_codex":0.23129603,"about_ca_topic_score_gemma":0.9251081,"teacher_disagreement_score":0.693812,"about_ca_system_score_codex":0.00069267326,"about_ca_system_score_gemma":0.060012627,"threshold_uncertainty_score":0.9951657},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9136749,0.041140303,0.0066975043,0.012725775,0.0024425122,0.020275185,0.000005838852,0.00010915101,0.0029288277],"genre_scores_gemma":[0.99444884,0.00011821232,0.002970303,0.000083010826,0.00079370895,0.0015189851,0.00003727491,0.000015015524,0.000014623805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981044,0.00015741638,0.000762544,0.0002140268,0.00052194134,0.00023965973],"domain_scores_gemma":[0.99792707,0.0001000135,0.00012260587,0.00014596192,0.0012682511,0.0004360718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025914293,0.00011119403,0.00017602515,0.00077186537,0.000112902184,0.00018060657,0.00007493397,0.00012419025,0.00024538767],"category_scores_gemma":[0.0005135114,0.00010136998,0.00006022086,0.00092878775,0.00012536728,0.0002628101,0.000004283943,0.0003411872,0.000034363617],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014186203,0.00009124168,0.0014974201,0.000080380276,0.000018829134,0.00001381166,0.0020071715,0.0001538201,0.000026870515,0.002323081,0.00009632573,0.99367684],"study_design_scores_gemma":[0.00014575804,0.0031199849,0.019898297,0.0017617147,0.0010210113,0.0007385932,0.009234947,0.6076361,0.0023961237,0.22231948,0.13122237,0.0005056609],"about_ca_topic_score_codex":0.0011729734,"about_ca_topic_score_gemma":0.019550467,"teacher_disagreement_score":0.9931712,"about_ca_system_score_codex":0.0006808758,"about_ca_system_score_gemma":0.006275863,"threshold_uncertainty_score":0.99935764},"labels":[],"label_agreement":null},{"id":"W4413187217","doi":"10.3138/cjpe-2023-0049","title":"Intersections between Participatory Evaluation and Social Pedagogy When Assessing Socio-Educational Projects","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citizen journalism; Sociology; Pedagogy; Political science","score_opus":0.6169192173815058,"score_gpt":0.6321641301355303,"score_spread":0.015244912754024509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187217","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9706464,0.00047179312,0.001970258,0.020331942,0.0012467687,0.001279122,0.000007505727,0.000010018838,0.0040361867],"genre_scores_gemma":[0.9975872,0.0000026646392,0.0012540207,0.00026505225,0.00041930852,0.00018584295,0.000033209264,0.000008069058,0.0002446204],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949975,0.0013848365,0.0010271409,0.00023920552,0.0020622169,0.00028907164],"domain_scores_gemma":[0.9936443,0.0005380952,0.00071454607,0.0001774415,0.0046935263,0.00023207262],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021630757,0.00013890454,0.00026982953,0.0011603484,0.0007430469,0.00080244994,0.00028872068,0.00012741127,0.0017661565],"category_scores_gemma":[0.003484142,0.00012230249,0.00011553731,0.0006359327,0.00019391128,0.0010936111,0.000022007694,0.0002833565,0.000022822556],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061403593,0.000037010275,0.2397014,0.000009685707,0.00006575686,3.207793e-7,0.008351111,0.00014864156,0.000026068257,0.0010606787,0.0050905156,0.74550265],"study_design_scores_gemma":[0.0012483108,0.00018033128,0.8688912,0.00007902546,0.00050087506,0.000010640826,0.01894887,0.02736717,0.000039107406,0.06317215,0.019385623,0.00017671978],"about_ca_topic_score_codex":0.00042610307,"about_ca_topic_score_gemma":0.008804557,"teacher_disagreement_score":0.7453259,"about_ca_system_score_codex":0.000976082,"about_ca_system_score_gemma":0.019733518,"threshold_uncertainty_score":0.99914634},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96236503,0.009231402,0.0033301613,0.010883818,0.0056409035,0.006969994,0.00020818698,0.000029171319,0.0013413499],"genre_scores_gemma":[0.98878294,0.0011352578,0.005033911,0.0014269103,0.0007736052,0.00061649375,0.0010211779,0.000042764354,0.0011669147],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98944837,0.0056919944,0.0023217883,0.0003823499,0.0010544588,0.0011010347],"domain_scores_gemma":[0.99501973,0.0005919073,0.001526412,0.0003167785,0.0015716816,0.00097347086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011649142,0.00036839303,0.0004992465,0.0008234847,0.001180297,0.00013471582,0.0003481515,0.0005130896,0.00032458495],"category_scores_gemma":[0.00080383744,0.00039911756,0.00019829006,0.00089187187,0.000111439964,0.00080515415,0.000036229445,0.0008691837,0.000048739366],"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":[0.00032268598,0.001013369,0.2645887,0.003947868,0.0003137657,0.000058542813,0.14268504,0.0019863187,0.0007325123,0.0024810326,0.03162655,0.5502436],"study_design_scores_gemma":[0.010888614,0.0034608638,0.72821385,0.010606512,0.0026901127,0.00008975283,0.10283657,0.03598089,0.0033061528,0.016304899,0.08461389,0.0010078878],"about_ca_topic_score_codex":0.2340645,"about_ca_topic_score_gemma":0.63972837,"teacher_disagreement_score":0.5492357,"about_ca_system_score_codex":0.0065167323,"about_ca_system_score_gemma":0.026299369,"threshold_uncertainty_score":0.99984604},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31963092,0.049301185,0.0072977254,0.2801693,0.072646104,0.004297162,0.00007726652,0.000056618024,0.26652372],"genre_scores_gemma":[0.9511408,0.0005518323,0.001469999,0.00086544326,0.00771219,0.00022892853,0.00009743303,0.000047938905,0.037885424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930005,0.004389789,0.000998121,0.00044976512,0.0005237427,0.0006380793],"domain_scores_gemma":[0.99587107,0.00025499915,0.0005991898,0.00047455094,0.0022789133,0.00052130944],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012549992,0.00025957206,0.0004552534,0.0018443885,0.0002913801,0.00030214974,0.00033006535,0.00058234064,0.0044842865],"category_scores_gemma":[0.001076662,0.00026996562,0.00033578268,0.0017521203,0.000383796,0.00037581468,0.00001083899,0.0012997927,0.0001827523],"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":[0.00015816836,0.00036023176,0.009643346,0.000054393484,0.00054489245,0.000064625485,0.0017993958,0.0004757537,0.00016633971,0.0036374466,0.2583362,0.7247592],"study_design_scores_gemma":[0.0021552492,0.00081176695,0.07629865,0.00022908625,0.0009207685,0.0006732675,0.0010172884,0.0016358151,0.000026559603,0.0031273314,0.91290265,0.00020155344],"about_ca_topic_score_codex":0.0024742372,"about_ca_topic_score_gemma":0.023770433,"teacher_disagreement_score":0.72455764,"about_ca_system_score_codex":0.0006241162,"about_ca_system_score_gemma":0.003996843,"threshold_uncertainty_score":0.99997526},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9341413,0.00032950166,0.000052734245,0.064248346,0.0003702779,0.00049150793,0.0000036097188,0.0000041258672,0.0003586169],"genre_scores_gemma":[0.99892306,0.0000051152433,0.000119440505,0.00014095297,0.0005473914,0.00002584702,0.000019249404,2.2377023e-7,0.00021873455],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99940413,0.00018403646,0.00011483701,0.00007600906,0.00011575269,0.00010520565],"domain_scores_gemma":[0.9994717,0.00004334387,0.000044780438,0.000024844401,0.00031280864,0.00010251221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012798568,0.00003414097,0.00004504706,0.00005171031,0.00023316825,0.00006751358,0.000081602935,0.000045816287,0.000103010905],"category_scores_gemma":[0.0005369903,0.000012496387,0.000021020604,0.0003940349,0.000031139556,0.000055066237,0.000006444439,0.00011799466,0.0000066762054],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011561529,0.000008673429,0.013663249,0.0000010009196,0.000018412013,0.0000012244943,0.000052774303,0.00014375286,0.0167606,0.00019475393,0.030255169,0.93888885],"study_design_scores_gemma":[0.000071584975,0.00025364404,0.5672895,0.000011251597,0.000028153294,0.000042786392,0.00012011246,0.00061206607,0.00020251432,0.0005216728,0.43081203,0.00003473697],"about_ca_topic_score_codex":0.00071797514,"about_ca_topic_score_gemma":0.08051687,"teacher_disagreement_score":0.9388541,"about_ca_system_score_codex":0.00008316833,"about_ca_system_score_gemma":0.00015938806,"threshold_uncertainty_score":0.9362613},"labels":[],"label_agreement":null},{"id":"W4413187250","doi":"10.3138/cjpe-2024-0045","title":"L’utilisation des évaluations par l’analyse thématique : le cas d’Anciens Combattants Canada (ACC)","year":2025,"lang":"fr","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Political science","score_opus":0.2822294590102694,"score_gpt":0.49894638162417587,"score_spread":0.21671692261390646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87621385,0.015172091,0.011255077,0.059695482,0.010451124,0.0035899943,0.00015848574,0.00002379537,0.02344013],"genre_scores_gemma":[0.9902142,0.0001890461,0.005489838,0.00086343935,0.00023125585,0.00012334913,0.00006173429,0.000020364047,0.0028067597],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9908357,0.0023334078,0.0023424379,0.0004462927,0.003159671,0.0008824595],"domain_scores_gemma":[0.9862507,0.00083712325,0.0014119504,0.0006131818,0.009826603,0.0010604673],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024183003,0.00035026885,0.00060063455,0.0013946505,0.0013398494,0.00089348725,0.0008603703,0.0002549122,0.0041201264],"category_scores_gemma":[0.008693611,0.00033579394,0.00027403864,0.0031848683,0.0005386932,0.0015844054,0.000035139914,0.0005838741,0.000054302032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00002213324,0.00014599465,0.072323866,0.00005158739,0.00022016658,0.00002350318,0.0029658098,0.021886934,0.00004084082,0.0038767636,0.029534345,0.86890805],"study_design_scores_gemma":[0.0023636557,0.00039260503,0.46575478,0.0006933845,0.0010211713,0.00009838182,0.01036627,0.30743465,0.00067815796,0.037834156,0.17289995,0.0004628461],"about_ca_topic_score_codex":0.6397611,"about_ca_topic_score_gemma":0.99472404,"teacher_disagreement_score":0.8684452,"about_ca_system_score_codex":0.0057840315,"about_ca_system_score_gemma":0.17567328,"threshold_uncertainty_score":0.99996024},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050177857,0.12004379,0.0011292131,0.020917665,0.0058068275,0.00083577016,0.00008665031,0.000015767617,0.80098647],"genre_scores_gemma":[0.98604065,0.00033120997,0.00093705324,0.00033643143,0.0024161777,0.000015879763,0.000014345209,0.000013313024,0.0098949615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984657,0.00041417434,0.000435285,0.00010084418,0.00027517517,0.00030881152],"domain_scores_gemma":[0.9976387,0.00014168482,0.00027973382,0.00012424107,0.0014575985,0.0003580467],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029104266,0.00012196842,0.0001994766,0.00053335656,0.00043636255,0.00079144095,0.00018030585,0.00011435107,0.0035865307],"category_scores_gemma":[0.001110354,0.000121034194,0.00020044054,0.00018024881,0.0003131167,0.00012839865,0.0000060021903,0.0002818771,0.000018513758],"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":[0.0000064415276,0.00010055485,0.00117406,0.000042437136,0.00036219571,0.000067619316,0.0024185204,0.00050055026,0.0000016247428,0.52687,0.013558682,0.4548973],"study_design_scores_gemma":[0.00050954404,0.00013695024,0.0019293261,0.00022779283,0.0020869444,0.000019179266,0.0015846686,0.011988283,0.00001769831,0.06113912,0.920241,0.00011949767],"about_ca_topic_score_codex":0.024542287,"about_ca_topic_score_gemma":0.032973174,"teacher_disagreement_score":0.9358628,"about_ca_system_score_codex":0.0005944243,"about_ca_system_score_gemma":0.0062418114,"threshold_uncertainty_score":0.99939185},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28603026,0.010579904,0.45351174,0.028062176,0.007894981,0.039332613,0.000043156793,0.00007470974,0.17447044],"genre_scores_gemma":[0.96315354,0.00015878765,0.035318483,0.000039717037,0.0003461715,0.000111182344,0.000016464686,0.000011810284,0.000843861],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939147,0.0039602113,0.00062409404,0.0001555017,0.0008919961,0.0004534906],"domain_scores_gemma":[0.99348515,0.0019953009,0.0004675789,0.00018826973,0.0036521484,0.0002115594],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.053023532,0.00007984122,0.00016755956,0.00060774374,0.0052586757,0.00016661285,0.000322612,0.00013231802,0.000090468464],"category_scores_gemma":[0.0014862764,0.000060377497,0.0001064437,0.0009757206,0.00038376704,0.00021591526,7.846596e-7,0.00019269572,7.272018e-7],"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":[0.00017483548,0.00016293525,0.0012426487,0.0002526691,0.00013978362,6.214312e-7,0.47265047,0.00290146,0.00007051258,0.34794354,0.0024772051,0.1719833],"study_design_scores_gemma":[0.001538634,0.0016864784,0.00077752676,0.00080367905,0.00036294336,0.0000026995212,0.0791771,0.048532102,0.00081731897,0.2262115,0.6398571,0.00023292744],"about_ca_topic_score_codex":0.039260253,"about_ca_topic_score_gemma":0.8566139,"teacher_disagreement_score":0.8173536,"about_ca_system_score_codex":0.0024326383,"about_ca_system_score_gemma":0.13186662,"threshold_uncertainty_score":0.99603635},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9094424,0.00039830664,0.030065903,0.012174605,0.001535465,0.015456878,0.000025592974,0.00009915753,0.030801684],"genre_scores_gemma":[0.96658784,0.0000045206243,0.031017313,0.0012072849,0.00026376886,0.00071492133,0.00004554565,0.00002171324,0.00013709316],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99057966,0.005745878,0.0012401744,0.0003050629,0.001374916,0.0007542856],"domain_scores_gemma":[0.99354357,0.00041009777,0.0011884121,0.00029934762,0.003769129,0.00078942406],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.030673292,0.00018162583,0.00031362215,0.0006603108,0.0014527807,0.0001266148,0.00035172552,0.00017226036,0.00028706496],"category_scores_gemma":[0.004730347,0.00015648403,0.000050326726,0.0012279509,0.0000790845,0.0011693763,0.000010496368,0.0007720902,0.000022883944],"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":[0.00020320246,0.0001588152,0.24441321,0.00043678528,0.00020998664,0.000013301153,0.103311464,0.0031674951,0.0005263461,0.0041055027,0.019861592,0.6235923],"study_design_scores_gemma":[0.012813819,0.0025865785,0.6582147,0.0018460096,0.0009178768,0.000052390762,0.17649993,0.110855766,0.00016682253,0.007758995,0.027532676,0.0007544167],"about_ca_topic_score_codex":0.0014273983,"about_ca_topic_score_gemma":0.010986769,"teacher_disagreement_score":0.6228379,"about_ca_system_score_codex":0.0024601403,"about_ca_system_score_gemma":0.03100191,"threshold_uncertainty_score":0.9998472},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075466186,0.013292986,0.06314017,0.032062393,0.050507247,0.007899911,0.000037163085,0.00021947952,0.75737447],"genre_scores_gemma":[0.9811696,0.00002767972,0.010333788,0.0011082701,0.0035628807,0.0006556725,0.000018424884,0.000022270167,0.0031014155],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992077,0.00010091569,0.00028365408,0.00009644303,0.00014426796,0.00016701741],"domain_scores_gemma":[0.99898916,0.000026569296,0.00015825256,0.00020237661,0.0004628874,0.00016077344],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010952586,0.00006339858,0.00009572302,0.0003051757,0.00008577587,0.000047077367,0.00019025455,0.00009521441,0.0015678322],"category_scores_gemma":[0.000052230003,0.00006032213,0.0000708057,0.00032832762,0.000048322512,0.000055769167,0.0000016346604,0.00016241666,0.000019662066],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007779222,0.000035487912,0.0009773591,0.000001849196,0.000039706727,0.0000017179799,0.00017598007,0.000002552522,0.000042054176,0.009075065,0.38661394,0.6030265],"study_design_scores_gemma":[0.0004458107,0.00014092984,0.019101357,0.000043873708,0.000056755372,0.00001411564,0.00013920876,0.00013604085,0.000036077046,0.014636209,0.96518743,0.00006220003],"about_ca_topic_score_codex":0.0006424345,"about_ca_topic_score_gemma":0.002944906,"teacher_disagreement_score":0.9057034,"about_ca_system_score_codex":0.0001704405,"about_ca_system_score_gemma":0.0009181842,"threshold_uncertainty_score":0.9993449},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9869401,0.000378486,0.00039651972,0.0050558974,0.0004957604,0.0045617875,0.0000048750535,0.000034862165,0.0021317129],"genre_scores_gemma":[0.98084074,0.0000043027853,0.018291589,0.00043171828,0.00006319006,0.00014169536,0.00009106189,0.000006632696,0.00012904666],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948384,0.0020322707,0.0007065767,0.00023474103,0.0017096674,0.00047831706],"domain_scores_gemma":[0.9935034,0.00005361256,0.00042470935,0.00021599093,0.004798264,0.001004003],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032085754,0.0001151972,0.00021647807,0.00088942,0.00083653576,0.00026883025,0.00037946866,0.00012725106,0.00016515334],"category_scores_gemma":[0.002539682,0.00012599981,0.000064752625,0.0013204584,0.00012064703,0.0008509667,0.000017092902,0.0001857856,0.00000605217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000026144508,0.00018718782,0.03730009,0.0000071275135,0.000039196268,7.040747e-7,0.055513065,0.00024022619,0.0000016706987,0.0006790383,0.0003970598,0.9056085],"study_design_scores_gemma":[0.0015059877,0.0010284391,0.7521959,0.00017534013,0.00020366184,0.0000028294407,0.018628916,0.0018478272,0.00003534667,0.0056167594,0.2184407,0.00031828068],"about_ca_topic_score_codex":0.0092405435,"about_ca_topic_score_gemma":0.4613651,"teacher_disagreement_score":0.9052902,"about_ca_system_score_codex":0.004658916,"about_ca_system_score_gemma":0.06899621,"threshold_uncertainty_score":0.999162},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97709525,0.0006678797,0.000021351503,0.00032900958,0.00045808672,0.013377532,0.0000054291345,0.000006779096,0.008038699],"genre_scores_gemma":[0.99686664,0.00010027356,0.0020625119,0.000048460985,0.00019569928,0.0005929834,0.00004732758,0.000007607535,0.00007849935],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99594,0.0018380682,0.0007543451,0.0001356577,0.0008722893,0.00045958365],"domain_scores_gemma":[0.99714583,0.00022928548,0.000471168,0.00014661191,0.0018694618,0.0001376381],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.029643929,0.000072564624,0.0002184279,0.00032954072,0.0020393191,0.00051399047,0.00042928557,0.00014982373,0.000027410511],"category_scores_gemma":[0.0003794044,0.000066424574,0.00008874438,0.0011627845,0.00020150638,0.00036908532,4.910189e-7,0.0002434638,2.6109512e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010299874,0.00023035586,0.005512937,0.00003727902,0.000016404516,5.10756e-7,0.2863242,0.00013376435,1.0500934e-7,0.00032640077,0.00005414341,0.7073536],"study_design_scores_gemma":[0.0061165867,0.0013785062,0.49062446,0.0006566163,0.00064967014,0.000033516342,0.3598724,0.016086591,0.0000068164704,0.030014388,0.09418958,0.00037087072],"about_ca_topic_score_codex":0.74463344,"about_ca_topic_score_gemma":0.9995997,"teacher_disagreement_score":0.70698273,"about_ca_system_score_codex":0.0013513516,"about_ca_system_score_gemma":0.08764683,"threshold_uncertainty_score":0.9992599},"labels":[],"label_agreement":null},{"id":"W4413187340","doi":"10.3138/cjpe-2024-0033","title":"How Do Municipal Policy- and Decision-Makers Evaluate the Impact of Their Policies? Insights from the City of Regina in Saskatchewan, Canada","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Public Health Ontario; Saskatchewan Health; University of Toronto; Saskatchewan Science Centre; Saskatchewan Health Authority; University of Regina","funders":"","keywords":"Political science; Public administration; Environmental planning; Geography","score_opus":0.14757668733566243,"score_gpt":0.46834605433322624,"score_spread":0.3207693669975638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413187340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98309153,0.0018196774,0.00009874452,0.013414725,0.0002552608,0.00082250475,0.000044040633,0.0000013565394,0.00045216366],"genre_scores_gemma":[0.99934196,0.000037894955,0.00022398388,0.00023319048,0.00007338077,0.000020124022,0.000004670258,0.00000559609,0.000059172315],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99584854,0.0009910073,0.00081249117,0.00018944961,0.0018948518,0.0002636565],"domain_scores_gemma":[0.9934709,0.002653825,0.0008148784,0.0005984735,0.002239528,0.00022237159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009110388,0.00016492316,0.00039174382,0.0006222581,0.00021061847,0.0002973393,0.0008814285,0.00007889596,0.00009873582],"category_scores_gemma":[0.0055570803,0.00007902788,0.00015992133,0.001846644,0.00030715144,0.00033328633,0.000046332985,0.00028903692,3.2995882e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009694368,0.000035081186,0.15224439,0.0000038184858,0.00014883284,0.0000022784736,0.011405907,0.0056861723,0.00009139842,0.00056507403,0.005140622,0.8245795],"study_design_scores_gemma":[0.0013111164,0.00027243025,0.8774469,0.00021054602,0.00008282829,0.0000074408863,0.036929622,0.027703106,0.00013434408,0.049050435,0.006742307,0.000108923196],"about_ca_topic_score_codex":0.7857941,"about_ca_topic_score_gemma":0.9923807,"teacher_disagreement_score":0.8244706,"about_ca_system_score_codex":0.00095374015,"about_ca_system_score_gemma":0.032310564,"threshold_uncertainty_score":0.97317535},"labels":[],"label_agreement":null},{"id":"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942528,0.00024184432,0.0008894622,0.0009473439,0.00044621064,0.001390247,0.0000062568206,0.000021179623,0.0018046439],"genre_scores_gemma":[0.9879944,0.0000144349915,0.011212652,0.000056250003,0.000070224385,0.00015641632,0.000041795487,0.0000057582265,0.00044810117],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984397,0.00018329729,0.0005417445,0.00005559034,0.00052306626,0.00025659503],"domain_scores_gemma":[0.9981068,0.000032763568,0.00024944564,0.0000865508,0.0013042488,0.0002202199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002193599,0.00009262099,0.00018705864,0.00040572428,0.00055864104,0.00009833624,0.00021066424,0.000058699352,0.00014814749],"category_scores_gemma":[0.00015643735,0.00009151542,0.00007428584,0.0004969346,0.0001648256,0.00020742812,0.0000032693015,0.0001076086,0.0000027398169],"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":[0.000010268573,0.0000547263,0.012129397,0.000020795487,0.000066189925,0.000002233849,0.52081156,0.000034935805,0.00000793555,0.0011817784,0.003555563,0.46212465],"study_design_scores_gemma":[0.00079050084,0.00057810365,0.32854757,0.0002997455,0.00024332186,0.0000012142838,0.09991131,0.00011604649,0.000121636804,0.0012940894,0.56787205,0.00022441852],"about_ca_topic_score_codex":0.043897416,"about_ca_topic_score_gemma":0.8949311,"teacher_disagreement_score":0.8510336,"about_ca_system_score_codex":0.00032939677,"about_ca_system_score_gemma":0.005192834,"threshold_uncertainty_score":0.96246934},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99029636,0.0032393488,0.000008574925,0.00068210956,0.00016739253,0.004713914,0.00001443152,0.0000014529992,0.00087642635],"genre_scores_gemma":[0.9991357,0.00033201798,0.0002823905,0.00003565324,0.00012741782,0.0000438571,0.000011979133,0.000005042272,0.000025969264],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99122953,0.0052953768,0.0010993676,0.00014643837,0.0018155065,0.00041379101],"domain_scores_gemma":[0.99480015,0.0011405187,0.0010580854,0.00015288284,0.0027614848,0.00008685084],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.06673625,0.000063980544,0.00026862163,0.0002491317,0.0019542144,0.00010872912,0.00034223768,0.00010747537,0.0000027888973],"category_scores_gemma":[0.00052666303,0.000054445474,0.000027605302,0.0009857563,0.0004181273,0.00023802742,0.0000032310384,0.00037083172,1.3260733e-8],"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":[0.000026157506,0.00016761801,0.09734269,0.00041631705,0.000041400068,0.000003151247,0.77871,0.0021382133,4.380208e-7,0.009283036,0.00005372774,0.11181727],"study_design_scores_gemma":[0.0020538236,0.0008011655,0.8074416,0.0015889342,0.0001692758,0.000057074627,0.16290395,0.008397495,0.0000046219952,0.011394822,0.005031744,0.00015551354],"about_ca_topic_score_codex":0.98853683,"about_ca_topic_score_gemma":0.9999024,"teacher_disagreement_score":0.71009886,"about_ca_system_score_codex":0.0012667006,"about_ca_system_score_gemma":0.11659404,"threshold_uncertainty_score":0.9993451},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9406905,0.0044162897,0.0036651115,0.013195901,0.0012353505,0.0016267595,0.00015340142,0.000017923776,0.034998715],"genre_scores_gemma":[0.9880184,0.0004891997,0.005889811,0.00086941855,0.00029475283,0.00014322676,0.00014535847,0.00003900357,0.0041108257],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9860413,0.010693268,0.0010019572,0.00049952674,0.00063823373,0.0011256901],"domain_scores_gemma":[0.9946976,0.0015180756,0.0008013189,0.00035545343,0.0018752491,0.0007523516],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018134536,0.00036599755,0.0005927317,0.0011249663,0.00036620194,0.00036627584,0.00053085975,0.00062584557,0.001082514],"category_scores_gemma":[0.00068016216,0.00038746485,0.00027346364,0.0013109022,0.0005203607,0.00057542,0.00002577479,0.0011081777,0.000041886982],"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":[0.00036227063,0.0007862528,0.31722328,0.00036398057,0.0014837853,0.0004598352,0.1654997,0.0013657792,0.00058922544,0.0020704984,0.012324589,0.49747083],"study_design_scores_gemma":[0.004301712,0.0012119465,0.9115853,0.0014966989,0.0013453697,0.0014075405,0.02115967,0.019554561,0.0004675083,0.007990466,0.029012082,0.000467174],"about_ca_topic_score_codex":0.04450032,"about_ca_topic_score_gemma":0.28037438,"teacher_disagreement_score":0.594362,"about_ca_system_score_codex":0.0014005176,"about_ca_system_score_gemma":0.017991524,"threshold_uncertainty_score":0.9998577},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98835516,0.0019191345,0.0027978274,0.00027877715,0.0015415592,0.0009110159,0.000029980638,0.0000073500196,0.004159181],"genre_scores_gemma":[0.996366,0.000011966576,0.0032117083,0.00010320126,0.00018997806,0.000046268673,0.0000056055796,0.000007412723,0.000057863108],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987706,0.000061931016,0.00074604584,0.00017067466,0.000054689586,0.00019605804],"domain_scores_gemma":[0.99894637,0.0000372685,0.00047383283,0.00016432418,0.00025702224,0.00012117762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029117148,0.00008985316,0.00024422127,0.0005337653,0.00017989938,0.00013956509,0.00013614974,0.00005280937,0.00025361462],"category_scores_gemma":[0.0006041184,0.0001048216,0.00008825093,0.0003903999,0.000029154618,0.00021623826,0.000008571704,0.00016688093,0.000028971755],"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":[0.000007694623,0.000062508865,0.36916333,0.0000052786677,0.000087413864,0.0003961936,0.0008502792,0.00012343997,3.118614e-7,0.0026807897,0.00052682357,0.6260959],"study_design_scores_gemma":[0.013825219,0.0021726126,0.3405865,0.00044954036,0.00084324187,0.0008912781,0.0433037,0.19835916,0.00003561554,0.16267501,0.23541279,0.0014453273],"about_ca_topic_score_codex":0.04339919,"about_ca_topic_score_gemma":0.060150545,"teacher_disagreement_score":0.6246506,"about_ca_system_score_codex":0.0003182919,"about_ca_system_score_gemma":0.0005187483,"threshold_uncertainty_score":0.9629709},"labels":[],"label_agreement":null},{"id":"W4413972820","doi":"10.3138/cjpe-2024-0044","title":"Taking Stock of Contribution Analysis: Reflecting on the Past to Inform the Future","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stock (firearms); Geography; Data science; Computer science; Archaeology","score_opus":0.3492271650557068,"score_gpt":0.5756301893170004,"score_spread":0.2264030242612936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413972820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9126993,0.000391384,0.0062774774,0.069487266,0.0012884745,0.001942702,0.000008454934,0.0000067617852,0.007898168],"genre_scores_gemma":[0.9983015,0.0000027059789,0.00028022396,0.0010641196,0.00018457179,0.000052719588,0.000004502814,0.000002483946,0.00010718631],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964629,0.00055464264,0.00088353216,0.000120385695,0.0017851924,0.00019335838],"domain_scores_gemma":[0.9938703,0.0006107359,0.0010677687,0.00034056837,0.0039775944,0.00013301596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022468805,0.00008774139,0.00021009531,0.0009797168,0.000529152,0.00033689785,0.0005611293,0.000054125285,0.00084192696],"category_scores_gemma":[0.0047879107,0.00004384513,0.00018164012,0.0043530115,0.000050216287,0.00022450503,0.000014659737,0.00024331042,0.000013492657],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034028333,0.000016421807,0.045759566,0.0000019918202,0.00019499905,4.2516754e-7,0.0015382663,0.017768698,0.00002720332,0.007050478,0.0030586538,0.9245493],"study_design_scores_gemma":[0.0006649877,0.00061380805,0.7900304,0.00011679416,0.000778223,0.0000047028893,0.0093473885,0.07934085,0.00026586477,0.006740878,0.111971036,0.0001250397],"about_ca_topic_score_codex":0.00020439536,"about_ca_topic_score_gemma":0.027797602,"teacher_disagreement_score":0.92442423,"about_ca_system_score_codex":0.00037181677,"about_ca_system_score_gemma":0.0022807717,"threshold_uncertainty_score":0.98994255},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955839,0.00087739265,0.00014057591,0.00061679067,0.0013404839,0.0010864728,0.0000021690748,0.0000015200045,0.00035070773],"genre_scores_gemma":[0.9985282,0.000008369994,0.0011562019,0.00002356178,0.00016301633,0.000052987623,0.0000029325586,0.0000056435115,0.00005910895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99575484,0.00047237854,0.0016933264,0.00012792752,0.0017672394,0.00018429554],"domain_scores_gemma":[0.99552286,0.0003093847,0.0013992718,0.00023834479,0.002264174,0.00026595435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012261347,0.00008603389,0.00036297354,0.0011457498,0.00003830417,0.000092401,0.0004479513,0.000050959967,0.00028752675],"category_scores_gemma":[0.005816371,0.00006633748,0.000111901405,0.0010330222,0.00006732433,0.0004697507,0.000009429882,0.00013637297,0.000006611624],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013906492,0.00020838501,0.9505356,0.00037001964,0.00006379027,0.0000029276478,0.0047159344,0.0007688257,0.0003358633,0.0004640937,0.0018096667,0.040711008],"study_design_scores_gemma":[0.0014215022,0.0011750775,0.9218672,0.0047347005,0.00026207053,0.00004883312,0.046215538,0.0043750578,0.0006013688,0.018259412,0.00081470545,0.0002245636],"about_ca_topic_score_codex":0.0007502328,"about_ca_topic_score_gemma":0.0035099715,"teacher_disagreement_score":0.041499604,"about_ca_system_score_codex":0.0004018026,"about_ca_system_score_gemma":0.0058343103,"threshold_uncertainty_score":0.9998017},"labels":[],"label_agreement":null},{"id":"W56576167","doi":"10.3138/cjpe.017.003","title":"Evaluation and Municipal Urban Planning: Practice and Prospects","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Government (linguistics); Urban planning; Local government; Scale (ratio); Environmental planning; Evaluation methods; Comprehensive planning; Public administration; Process management; Management science; Business; Environmental resource management; Political science; Geography; Engineering; Economics; Civil engineering","score_opus":0.4565580453517729,"score_gpt":0.5429851099364679,"score_spread":0.08642706458469496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W56576167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95949346,0.013549857,0.0001663078,0.0069856863,0.0007053656,0.0020354562,0.0000036610213,0.000012100489,0.01704811],"genre_scores_gemma":[0.99652284,0.00005484248,0.0027629249,0.00026002334,0.00018140346,0.00005704878,0.0000033977994,0.000008620876,0.00014886764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99441063,0.0010439958,0.00072903815,0.00023795824,0.0033353372,0.00024304788],"domain_scores_gemma":[0.99364436,0.00044657133,0.00073610846,0.00022902609,0.0044462495,0.00049768965],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030606369,0.00012313134,0.00019981015,0.0005718962,0.0002937187,0.0006621281,0.00020980531,0.00008070521,0.0015034799],"category_scores_gemma":[0.013263645,0.00009852379,0.000042449217,0.00052864425,0.00012347968,0.0013532476,0.000015403974,0.00022532212,0.00002842157],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001473712,0.000048612215,0.03453352,0.0000039248,0.000041045223,0.000008731161,0.009659731,0.0009590867,0.000016304624,0.00044429774,0.005266649,0.94900334],"study_design_scores_gemma":[0.0021628817,0.0010761272,0.10549274,0.00007714018,0.00044734712,0.00032571136,0.005060625,0.7262611,0.000022390066,0.007008261,0.15184978,0.000215947],"about_ca_topic_score_codex":0.00017477515,"about_ca_topic_score_gemma":0.0019102982,"teacher_disagreement_score":0.9487874,"about_ca_system_score_codex":0.00028837036,"about_ca_system_score_gemma":0.0012476535,"threshold_uncertainty_score":0.99940926},"labels":[],"label_agreement":null},{"id":"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03460146,0.0010270005,0.0013019195,0.93168104,0.010994016,0.0022823988,0.000006067002,0.00001773664,0.01808835],"genre_scores_gemma":[0.52337575,0.00057226204,0.064417794,0.0039852075,0.3901819,0.0003926184,0.000019987727,0.00005574937,0.01699873],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99597836,0.0026352387,0.00019704724,0.00007725416,0.0008561082,0.00025600602],"domain_scores_gemma":[0.99791783,0.00016872867,0.00007119231,0.00009322287,0.001266001,0.00048301904],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026229821,0.00004280328,0.00007263349,0.000121348254,0.0006090635,0.00019013832,0.00021670261,0.000058262223,0.0048202276],"category_scores_gemma":[0.005364032,0.00003110134,0.000046081106,0.00046347216,0.0002595529,0.00020503587,0.0000019875588,0.0002599533,0.0001401291],"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":[0.000005208558,0.000006024127,0.000041159066,0.0000012714155,0.000007377338,6.586925e-7,0.016855728,0.00015665912,0.0000035779035,0.0011987486,0.20237587,0.7793477],"study_design_scores_gemma":[0.00007457406,0.00016111143,0.0006627068,0.000008897352,0.000014654445,0.0000015811086,0.0050325957,0.000117971686,0.000008500333,0.0053594965,0.9885191,0.000038835125],"about_ca_topic_score_codex":0.012323761,"about_ca_topic_score_gemma":0.11611453,"teacher_disagreement_score":0.9276959,"about_ca_system_score_codex":0.0003832735,"about_ca_system_score_gemma":0.0033914356,"threshold_uncertainty_score":0.9960895},"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":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99032587,0.00043444068,0.0019924792,0.006014579,0.00031982837,0.0008104693,0.000019702702,0.00000326706,0.000079339945],"genre_scores_gemma":[0.9958049,0.0000036910476,0.0035376367,0.0005863696,0.000044615634,0.000007678327,0.000007440222,0.0000031389004,0.000004528088],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9927831,0.0020657636,0.0023151864,0.00030909132,0.0022229352,0.00030392388],"domain_scores_gemma":[0.99167997,0.00042167038,0.0012591962,0.00051019934,0.0057282215,0.00040077462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027292889,0.00013759766,0.0006513182,0.00091777404,0.00008740794,0.00013167862,0.000530112,0.00014258098,0.00038701922],"category_scores_gemma":[0.008222813,0.00010495899,0.00026248355,0.0028616334,0.00013020425,0.00035298106,0.000011368311,0.0003265235,0.000002550136],"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":[0.0001624962,0.0003029451,0.60624385,0.000017731072,0.00018842574,0.000005916031,0.013161607,0.055061467,0.00025220288,0.00064432085,0.000100017554,0.323859],"study_design_scores_gemma":[0.0005272082,0.0004706623,0.9306127,0.00014855628,0.00031212138,0.0000017084544,0.008429754,0.036908094,0.00007278523,0.022185057,0.00020549935,0.00012584343],"about_ca_topic_score_codex":0.03617253,"about_ca_topic_score_gemma":0.24625814,"teacher_disagreement_score":0.32436883,"about_ca_system_score_codex":0.00087317865,"about_ca_system_score_gemma":0.0018240806,"threshold_uncertainty_score":0.98440695},"labels":[],"label_agreement":null},{"id":"W78612901","doi":"10.3138/cjpe.0017.008","title":"Defining the Benefits, Outputs, and Knowledge Elements of Program Evaluation","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Process (computing); Program evaluation; Process management; Knowledge management; Raising (metalworking); Evaluation methods; Participatory evaluation; Management science; Business; Computer science; Public relations; Political science; Engineering; Public administration","score_opus":0.346987607917928,"score_gpt":0.5305338923085439,"score_spread":0.18354628439061588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W78612901","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94770753,0.024931505,0.000561145,0.0018539011,0.0018482679,0.0067156157,0.000019136412,0.000018117227,0.016344769],"genre_scores_gemma":[0.9930192,0.00005444529,0.0064223777,0.000073009214,0.00006763705,0.0002640497,0.000014027944,0.00001153107,0.00007372675],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9936026,0.00156633,0.0014093552,0.0002461287,0.0028498932,0.00032572413],"domain_scores_gemma":[0.9922829,0.0004021617,0.0012240364,0.00034914925,0.0053987796,0.00034292968],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04448366,0.00015779128,0.00027928167,0.00058184995,0.0003407967,0.000375414,0.0004045528,0.00008772751,0.0011496536],"category_scores_gemma":[0.00643301,0.000104826984,0.00011863988,0.0009913787,0.00015424803,0.0005308649,0.000016667096,0.0002205635,0.000033273467],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007350692,0.00007023135,0.045613274,0.0000058373125,0.00003566897,3.3829792e-7,0.0013801428,0.0008310687,0.000006568809,0.008150543,0.0009284835,0.9429705],"study_design_scores_gemma":[0.0051182224,0.0026864705,0.42422885,0.00029336545,0.0008486578,0.000114211405,0.008548507,0.20863533,0.0006921472,0.029311545,0.31903172,0.0004909678],"about_ca_topic_score_codex":0.0001407305,"about_ca_topic_score_gemma":0.010888319,"teacher_disagreement_score":0.94247955,"about_ca_system_score_codex":0.00029775812,"about_ca_system_score_gemma":0.006744636,"threshold_uncertainty_score":0.9997634},"labels":[],"label_agreement":null},{"id":"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97468764,0.0013995873,0.00097919,0.0018053891,0.0015034124,0.0082158595,0.000019145997,0.000036253918,0.011353513],"genre_scores_gemma":[0.993634,0.0000047432204,0.003191314,0.00026685916,0.00043315126,0.002180799,0.000048577807,0.0000343708,0.00020622846],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934617,0.0017892551,0.0009820595,0.00031838942,0.002850034,0.00059851754],"domain_scores_gemma":[0.99465173,0.00029964783,0.0008212996,0.00034442058,0.0034927423,0.00039016156],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017290484,0.00027246337,0.00032369207,0.00077739847,0.00040257152,0.00020119749,0.0004885135,0.00025674183,0.0024268108],"category_scores_gemma":[0.0031700784,0.00021047956,0.00018781086,0.000676733,0.000101871,0.0001452944,0.0000117915915,0.0005570619,0.00010100956],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007034007,0.00019555549,0.02233886,0.000028058657,0.00021120372,0.0000025666213,0.031716876,0.002982261,0.000028758772,0.003260536,0.0011120096,0.93805295],"study_design_scores_gemma":[0.0052490765,0.0028037431,0.8248347,0.0010205063,0.0015192326,0.00019481851,0.03899578,0.022968767,0.0001684835,0.03928679,0.061735805,0.0012222839],"about_ca_topic_score_codex":0.00050355354,"about_ca_topic_score_gemma":0.014973186,"teacher_disagreement_score":0.9368307,"about_ca_system_score_codex":0.0007465408,"about_ca_system_score_gemma":0.0046047955,"threshold_uncertainty_score":0.9984851},"labels":[],"label_agreement":null}]}