{"meta":{"query_hash":"24b6424d1b26","filters":{"venue":"American Journal of Evaluation"},"cohort_total":60,"direct_labels_cover":1,"predictions_cover":60,"exported":60,"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/24b6424d1b26","api":"https://metacan.xera.ac/api/v1/cohort?venue=American+Journal+of+Evaluation"},"results":[{"id":"W1965824013","doi":"10.1177/1098214013478142","title":"The Case for Participatory Evaluation in an Era of Accountability","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":165,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accountability; Technocracy; Citizen journalism; Participatory evaluation; Context (archaeology); Participatory GIS; Public sector; Sociology; Politics; Public administration; Public relations; Government (linguistics); Social accounting; Political science; Business; Accounting; Law","score_opus":0.3658990701241563,"score_gpt":0.5819220676204166,"score_spread":0.21602299749626036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965824013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956147,0.00010957475,0.0012915941,0.001679054,0.0002966348,0.0008882008,0.0000025109907,0.0000018029875,0.00011589483],"genre_scores_gemma":[0.9986309,0.000011099897,0.0009842381,0.00012726316,0.00008269704,0.00015102219,0.000002187676,0.0000053179797,0.000005267404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99331063,0.0022231645,0.0014915783,0.00015018921,0.0026553317,0.0001690883],"domain_scores_gemma":[0.98764414,0.0025079807,0.0017769705,0.00041052172,0.007575229,0.0000851332],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.061524533,0.00008670531,0.00026805632,0.00017315483,0.00013880213,0.00013956577,0.00028528282,0.000025744705,0.00085244473],"category_scores_gemma":[0.0064954823,0.000051667073,0.00010185917,0.0006170449,0.0002068225,0.0012213981,0.000018501709,0.00014855116,0.000014559758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009059246,0.00009918122,0.03286157,0.0000015467712,0.00001130706,4.0646654e-7,0.0024718784,0.009100755,0.0004589886,0.00007705129,0.0002700547,0.95455664],"study_design_scores_gemma":[0.0011461996,0.0011114717,0.35569516,0.00001653843,0.000077552715,0.00004219375,0.02528007,0.5954453,0.00029707165,0.020622417,0.00018571394,0.00008033651],"about_ca_topic_score_codex":0.0001816407,"about_ca_topic_score_gemma":0.0008789924,"teacher_disagreement_score":0.95447636,"about_ca_system_score_codex":0.00022916561,"about_ca_system_score_gemma":0.0010467374,"threshold_uncertainty_score":0.966358},"labels":[],"label_agreement":null},{"id":"W1975564755","doi":"10.1177/1098214013477235","title":"Understanding Dimensions of Organizational Evaluation Capacity","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; École Nationale d'Administration Publique","funders":"Australian Government","keywords":"Dimension (graph theory); Capacity building; Government (linguistics); Knowledge management; Organization development; Business; Organizational learning; Process management; Computer science; Economics; Economic growth","score_opus":0.5129125946126178,"score_gpt":0.4844682783398096,"score_spread":0.028444316272808245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975564755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9566416,0.000042039355,0.038054843,0.0020623284,0.00045433588,0.0004082503,0.0000030512288,0.0000047843837,0.002328777],"genre_scores_gemma":[0.995521,0.000019256106,0.004124605,0.0001777771,0.00009882332,0.000009666234,0.0000067658902,0.000008409908,0.000033716857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99075204,0.0012754337,0.0013202219,0.00017663519,0.0063333036,0.00014234446],"domain_scores_gemma":[0.98663145,0.0010338967,0.0023680418,0.00028099393,0.009570603,0.000115013914],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019100176,0.000109466746,0.00033167662,0.00057141506,0.00013476444,0.00009478243,0.00026150365,0.00003310406,0.008698439],"category_scores_gemma":[0.006523244,0.00007107978,0.00011202178,0.0014964523,0.00021009058,0.0009792264,0.000032897566,0.00013830882,0.00012090871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016246365,0.0007334481,0.27357244,0.00001296341,0.0004161826,0.000001011216,0.010865044,0.1709167,0.04356529,0.017433697,0.02258581,0.45973495],"study_design_scores_gemma":[0.0017692255,0.0009835371,0.28060743,0.00006787218,0.00028520636,0.000049696868,0.013046647,0.49726197,0.001848736,0.20356487,0.00029099974,0.00022379073],"about_ca_topic_score_codex":0.000037106725,"about_ca_topic_score_gemma":0.000016391039,"teacher_disagreement_score":0.45951116,"about_ca_system_score_codex":0.0004922193,"about_ca_system_score_gemma":0.0011243908,"threshold_uncertainty_score":0.99220777},"labels":[],"label_agreement":null},{"id":"W1989835141","doi":"10.1177/1098214009349865","title":"A Review and Synthesis of Current Research on Cross-Cultural Evaluation","year":2009,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Construct (python library); Context (archaeology); Indigenous; Sociology; Empirical research; Management science; Knowledge management; Engineering ethics; Epistemology; Computer science; Ecology","score_opus":0.7361957222054291,"score_gpt":0.7346471200265722,"score_spread":0.0015486021788568838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989835141","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006474273,0.99580795,0.000023927025,0.00040834807,0.0003158376,0.0014421426,0.000015109212,0.0000030890442,0.0013361668],"genre_scores_gemma":[0.0037736408,0.9955565,0.00018416313,0.000104879124,0.00022217826,0.00010277998,0.000015173022,0.000015455222,0.000025268659],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.974152,0.010589377,0.0034207408,0.000498248,0.011056174,0.00028344482],"domain_scores_gemma":[0.9716466,0.005050879,0.006201261,0.0006613212,0.016266141,0.00017378197],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.119118944,0.00031750574,0.0023654136,0.001395263,0.00017104753,0.000255148,0.00070117053,0.00008867722,0.0009152797],"category_scores_gemma":[0.030492466,0.00018881568,0.00056124775,0.0025435768,0.0005078126,0.0006769135,0.00006806621,0.0007822441,0.00009445599],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018082517,0.0001043053,0.0000175072,0.0011218422,0.00005718975,3.051532e-7,0.00007649527,0.000053970612,2.7859338e-7,0.000068130015,0.0031394823,0.99534243],"study_design_scores_gemma":[0.00060135114,0.0021459023,0.001269944,0.067504644,0.0044620824,0.00011218164,0.00035773753,0.0013266862,0.0000042626402,0.0023553323,0.91949034,0.00036950945],"about_ca_topic_score_codex":0.0000047880785,"about_ca_topic_score_gemma":0.0000028743723,"teacher_disagreement_score":0.9949729,"about_ca_system_score_codex":0.0006106913,"about_ca_system_score_gemma":0.0033277047,"threshold_uncertainty_score":0.99999803},"labels":[],"label_agreement":null},{"id":"W2000821194","doi":"10.1177/1098214009340580","title":"Toward Accurate Measurement of Participation","year":2009,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Conceptualization; Operationalization; Citizen journalism; Stakeholder; Field (mathematics); Participatory evaluation; Psychology; Sociology; Management science; Computer science; Epistemology; Political science; Public relations; Social science; Artificial intelligence; Engineering; Mathematics","score_opus":0.4707113104953488,"score_gpt":0.5611236037354239,"score_spread":0.0904122932400751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000821194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9687301,0.00011325674,0.023991514,0.0044177147,0.0002842521,0.00016361472,9.294852e-7,0.0000036718122,0.0022949525],"genre_scores_gemma":[0.997949,0.00002591848,0.0016215859,0.00029512044,0.00008811981,0.0000025748463,9.071384e-7,0.0000026861821,0.0000140914435],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99210656,0.00072857545,0.0012656611,0.00012088566,0.0056584855,0.00011981544],"domain_scores_gemma":[0.99155825,0.00021921631,0.0022732755,0.00021740118,0.0056480416,0.00008381377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022764243,0.00007913479,0.00029481115,0.00031337788,0.00004212512,0.00005270194,0.00023129226,0.000016949884,0.0006678664],"category_scores_gemma":[0.0038803685,0.000054786356,0.00011648862,0.00075172225,0.000063422376,0.00054921187,0.000009329701,0.00008661609,0.000031692336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012537371,0.00012052605,0.0038210345,0.0000010150106,0.00002256329,5.35994e-7,0.0014296273,0.013686885,0.0063871103,0.00027914476,0.0008410622,0.97328514],"study_design_scores_gemma":[0.0016253154,0.004344353,0.8773189,0.00007562724,0.00019720322,0.000019647188,0.0033618144,0.07993228,0.010647767,0.020523945,0.0017755845,0.00017756462],"about_ca_topic_score_codex":0.00000507098,"about_ca_topic_score_gemma":0.0000050247854,"teacher_disagreement_score":0.9731076,"about_ca_system_score_codex":0.00015023707,"about_ca_system_score_gemma":0.000623695,"threshold_uncertainty_score":0.7889678},"labels":[],"label_agreement":null},{"id":"W2014357589","doi":"10.1177/1098214011405311","title":"Legislator Uses of Public Performance Reports","year":2011,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Public Policy and Administration Research","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Accountability; Legislator; Government (linguistics); Performance measurement; Dual (grammatical number); Key (lock); Public relations; Business; Public administration; Accounting; Political science; Computer science; Computer security; Marketing; Law; Legislation","score_opus":0.2353065547670905,"score_gpt":0.4390290283376902,"score_spread":0.2037224735705997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014357589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9582841,0.00003806822,0.00015404413,0.0011349285,0.00013826732,0.00007830625,6.5142757e-7,0.0000042940374,0.04016737],"genre_scores_gemma":[0.99898404,0.000073319636,0.00058781274,0.000057150406,0.00015576584,0.0000026513492,5.769373e-7,0.0000030321253,0.00013564544],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99779075,0.0005307609,0.0004094205,0.00006208854,0.0010454308,0.00016151968],"domain_scores_gemma":[0.9976074,0.00008352325,0.00092305226,0.0001025064,0.0011441415,0.00013938882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007472538,0.00004047832,0.00013067012,0.00018137053,0.000118128504,0.000028184695,0.00013037192,0.000019828567,0.00065010315],"category_scores_gemma":[0.002281778,0.00003490921,0.000054147597,0.0004537871,0.0004890444,0.0006615245,0.000010154004,0.00008984668,0.0000030957192],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009301938,0.00042346612,0.2680101,0.000012925618,0.00013442987,0.000020340598,0.036550455,0.000018997885,0.0010043788,0.019423243,0.0018631011,0.67244554],"study_design_scores_gemma":[0.000758535,0.003274263,0.89126754,0.000101562495,0.00011829005,0.00019203186,0.028382104,0.00062858075,0.0052715237,0.00788349,0.061791368,0.0003307034],"about_ca_topic_score_codex":0.00048399522,"about_ca_topic_score_gemma":0.000092764036,"teacher_disagreement_score":0.67211485,"about_ca_system_score_codex":0.00006747455,"about_ca_system_score_gemma":0.002133624,"threshold_uncertainty_score":0.7118174},"labels":[],"label_agreement":null},{"id":"W2032438539","doi":"10.1177/1098214009349792","title":"Exploring the Intervention— Context Interface","year":2009,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"","keywords":"Sociotechnical system; Context (archaeology); Adaptation (eye); Workaround; Process (computing); Knowledge management; Computer science; Social network analysis; Psychology; Social media; World Wide Web","score_opus":0.8024925403175549,"score_gpt":0.7139293653214512,"score_spread":0.08856317499610367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032438539","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9495773,0.00004164516,0.008279584,0.04007573,0.0007812098,0.00037307027,0.0000015925627,0.000009338962,0.0008605498],"genre_scores_gemma":[0.9889599,0.000031636842,0.00044523083,0.010141052,0.00031918933,0.000028576545,4.2471734e-7,0.000004924675,0.000069039066],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99549913,0.0024056288,0.0010232867,0.00008710184,0.0007262776,0.0002585693],"domain_scores_gemma":[0.99611026,0.0011396968,0.0014675725,0.00016493416,0.0010043253,0.00011322402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010635684,0.000069017806,0.00017947971,0.00014843362,0.0003621348,0.000014002434,0.00021084989,0.000010684144,0.00047355346],"category_scores_gemma":[0.003088569,0.000045211567,0.000069592104,0.0004552,0.000095092466,0.00054701563,0.000020414935,0.00037604946,0.00011484547],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006350529,0.000019906945,0.0015290704,0.0000054974284,0.000012385929,5.3444245e-7,0.027013648,0.000093097166,0.00040704134,0.0003994392,0.004646824,0.96580905],"study_design_scores_gemma":[0.0037865052,0.0038523288,0.68265355,0.00073063816,0.0001363461,0.00005436165,0.21425362,0.0021143712,0.0006359386,0.003600823,0.08792953,0.000252009],"about_ca_topic_score_codex":0.00010039798,"about_ca_topic_score_gemma":0.000050845225,"teacher_disagreement_score":0.96555704,"about_ca_system_score_codex":0.00032730348,"about_ca_system_score_gemma":0.00046622302,"threshold_uncertainty_score":0.51850784},"labels":[],"label_agreement":null},{"id":"W2033993956","doi":"10.1177/1098214013478146","title":"The Practice of Evaluation in Public Sector Contexts","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accountability; Public sector; Citizen journalism; Perception; Diversity (politics); Reflection (computer programming); Sociology; Evaluation methods; Public relations; Public administration; Political science; Psychology; Law; Computer science; Engineering","score_opus":0.1817166479435985,"score_gpt":0.51942008015783,"score_spread":0.3377034322142315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033993956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97212,0.00043598315,0.0011405452,0.017486684,0.00055047934,0.0006908134,9.514484e-7,0.000002723555,0.007571862],"genre_scores_gemma":[0.9983479,0.00008907158,0.0009407014,0.00041278443,0.00009871848,0.00004284217,0.0000017484974,0.0000061286964,0.00006013187],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98749596,0.003961464,0.0016684426,0.00016980339,0.0065120957,0.00019225692],"domain_scores_gemma":[0.97932833,0.0047503426,0.0033365218,0.0003734613,0.012122161,0.000089158566],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06268525,0.000098610064,0.00029143182,0.00043930142,0.00011427155,0.00025047082,0.00037114418,0.00002844849,0.002327336],"category_scores_gemma":[0.032873448,0.00005761548,0.000102010235,0.0013538031,0.0002034815,0.0019695333,0.000033228793,0.00020410874,0.00011834496],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006828456,0.00009669466,0.011006985,8.342536e-7,0.000032473556,3.1818197e-7,0.0012923105,0.0025527477,0.0006450415,0.0005639796,0.0020630984,0.98167723],"study_design_scores_gemma":[0.002801644,0.0016322384,0.63223195,0.000057240315,0.00014998727,0.00007358374,0.026250636,0.2905151,0.00038661022,0.02760956,0.01809752,0.00019390104],"about_ca_topic_score_codex":0.00009459017,"about_ca_topic_score_gemma":0.000106536565,"teacher_disagreement_score":0.98148334,"about_ca_system_score_codex":0.000271745,"about_ca_system_score_gemma":0.001478455,"threshold_uncertainty_score":0.9985847},"labels":[],"label_agreement":null},{"id":"W2034211783","doi":"10.1177/1098214015578731","title":"Merging Developmental and Feminist Evaluation to Monitor and Evaluate Transformative Social Change","year":2015,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transformative learning; Theory of change; Sociology; Social transformation; Social change; Monitoring and evaluation; Participatory evaluation; Program evaluation; Political science; Pedagogy; Social science; Public administration; Law","score_opus":0.3677671345545405,"score_gpt":0.5374349974415299,"score_spread":0.16966786288698937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034211783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906209,0.0001968032,0.0017134985,0.004661172,0.00035727108,0.00062530825,0.0000056199497,0.000005908513,0.0018134789],"genre_scores_gemma":[0.9946082,0.000024608471,0.0043730927,0.0006233861,0.00028034672,0.000057411846,0.000004205081,0.000009586924,0.000019168345],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99220496,0.0012557354,0.00094469794,0.0002393816,0.005139417,0.0002157785],"domain_scores_gemma":[0.995243,0.0003213944,0.00088919763,0.000095510295,0.0031651244,0.00028578535],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0361091,0.00015816375,0.000366566,0.00051963225,0.00025250917,0.00021573067,0.00016896486,0.000033693403,0.0001909915],"category_scores_gemma":[0.0020282117,0.0001214128,0.00005309286,0.0007771955,0.0001595601,0.001257684,0.000053221393,0.000139413,0.000036310776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001647859,0.00002686885,0.0047893524,0.0000017755115,0.000032034717,5.922293e-7,0.054496527,0.00021518565,0.00025670003,0.000075000244,0.00048524406,0.9394559],"study_design_scores_gemma":[0.0073336973,0.0035089871,0.57467043,0.00012984598,0.0005970101,0.00029118257,0.1838822,0.210718,0.00092770724,0.010000648,0.007269978,0.0006703087],"about_ca_topic_score_codex":0.00002910627,"about_ca_topic_score_gemma":0.000025879377,"teacher_disagreement_score":0.9387856,"about_ca_system_score_codex":0.00040713567,"about_ca_system_score_gemma":0.0007350713,"threshold_uncertainty_score":0.9925285},"labels":[],"label_agreement":null},{"id":"W2034409422","doi":"10.1177/1098214008316655","title":"Cross-Disciplinarization: A New Talisman for Evaluation?","year":2008,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Cross disciplinary; Discipline; Field (mathematics); Engineering ethics; Face (sociological concept); Management science; Sociology; Interdisciplinarity; Computer science; Data science; Social science; Engineering","score_opus":0.2784832306773482,"score_gpt":0.5746443419319662,"score_spread":0.296161111254618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034409422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9142166,0.00018608893,0.07712578,0.0042868354,0.0010192038,0.000773086,0.000006413502,0.0000108085815,0.0023751978],"genre_scores_gemma":[0.98802143,0.000027241089,0.009464083,0.0004095201,0.00075621414,0.00003797961,0.00002224966,0.000014573466,0.0012467095],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99093884,0.0007187479,0.00154122,0.00029946747,0.0062841857,0.00021750951],"domain_scores_gemma":[0.9870718,0.00094527146,0.0022966063,0.0004118052,0.009064811,0.00020966772],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023306796,0.00015399737,0.00039792486,0.00052014575,0.00040211825,0.00019233969,0.00045764088,0.000043096705,0.0038206666],"category_scores_gemma":[0.0067837834,0.00011593144,0.00024662254,0.0012631351,0.00023248154,0.0011876657,0.000038829898,0.00012997248,0.00009066455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044467382,0.00017789096,0.06797379,0.0000031691068,0.000096904194,0.000002322555,0.0065493565,0.11399089,0.0004107434,0.0008017536,0.023995185,0.78555334],"study_design_scores_gemma":[0.0075156293,0.0024559938,0.47174972,0.000039662245,0.00030045718,0.00030630452,0.0027254412,0.44972783,0.00054305897,0.045573555,0.01869688,0.00036546827],"about_ca_topic_score_codex":0.00001476363,"about_ca_topic_score_gemma":0.00001845535,"teacher_disagreement_score":0.78518784,"about_ca_system_score_codex":0.0002781866,"about_ca_system_score_gemma":0.0036542148,"threshold_uncertainty_score":0.99709},"labels":[],"label_agreement":null},{"id":"W2041989608","doi":"10.1177/1098214013487426","title":"The Complexity of Institutionalizing Evaluation as a Best Practice in North American Quitlines","year":2013,"lang":"en","type":"article","venue":"American Journal of 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":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Centers for Disease Control and Prevention; National Institutes of Health","keywords":"Quitline; Thematic analysis; Institutionalisation; Qualitative research; Process (computing); Best practice; Process management; Program evaluation; Management science; Computer science; Psychology; Medicine; Sociology; Business; Intervention (counseling); Political science; Nursing; Engineering","score_opus":0.6067356275386427,"score_gpt":0.6851844173352069,"score_spread":0.07844878979656411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041989608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9654668,0.0000737228,0.0004252884,0.030609071,0.00031235148,0.001339524,0.000005983791,0.0000049785695,0.0017623119],"genre_scores_gemma":[0.992133,0.00015252325,0.0035815777,0.0037181107,0.00021231947,0.00017615884,0.0000047019666,0.000009007064,0.00001255656],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98967874,0.0058414326,0.0017880454,0.00015409543,0.002158295,0.0003793934],"domain_scores_gemma":[0.9839295,0.004897101,0.0046248906,0.0002467892,0.006140335,0.00016138633],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01721756,0.00011117327,0.00032604026,0.0002915785,0.0005253807,0.000022238117,0.0002587803,0.000020364692,0.00023650719],"category_scores_gemma":[0.030548653,0.00008077572,0.000052100208,0.0016896318,0.0011480583,0.000874975,0.00004828702,0.00041763877,0.0001296727],"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":[0.00042400378,0.00035485695,0.23702629,0.00006720696,0.000111237525,0.0000022721435,0.039285436,0.0041367435,0.00088485645,0.0065050754,0.0041982373,0.7070038],"study_design_scores_gemma":[0.001827351,0.0012780281,0.90142804,0.00015460813,0.00013175046,0.000023989254,0.07088831,0.01230932,0.000027837305,0.0018673877,0.00990788,0.00015547143],"about_ca_topic_score_codex":0.00990547,"about_ca_topic_score_gemma":0.0051114103,"teacher_disagreement_score":0.7068483,"about_ca_system_score_codex":0.0007219593,"about_ca_system_score_gemma":0.004567523,"threshold_uncertainty_score":0.99668765},"labels":[],"label_agreement":null},{"id":"W2043887666","doi":"10.1177/1098214005278752","title":"Is Sustainability Possible? A Review and Commentary on Empirical Studies of Program Sustainability","year":2005,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":715,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustainability; Champion; Sustainability organizations; Empirical research; Program evaluation; Sustainability science; Social sustainability; Business; Environmental resource management; Political science; Economics; Public administration","score_opus":0.712236943529094,"score_gpt":0.7821963698676211,"score_spread":0.06995942633852714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043887666","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":[0.0010691484,0.9065609,0.0000144668575,0.08415609,0.00014749337,0.007934865,0.000053299525,0.00001333975,0.000050375358],"genre_scores_gemma":[0.00042964937,0.9710518,0.00074565836,0.026782027,0.0002950489,0.00063440774,0.000009899251,0.00002503453,0.00002645341],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9804281,0.012806425,0.0042795343,0.0004183346,0.0014595721,0.0006080463],"domain_scores_gemma":[0.9776227,0.0065362733,0.0073942486,0.00056773674,0.007539903,0.0003391728],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.026656913,0.00037523915,0.0032619978,0.0004796003,0.00037700968,0.000009837236,0.00032104301,0.000117335316,0.00023351176],"category_scores_gemma":[0.021490786,0.00026373786,0.00036149332,0.0014723823,0.0008869134,0.000253531,0.0001664211,0.0011388519,0.0000061689652],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00002120301,0.00011817476,0.00080955937,0.054377254,0.00012569649,0.0000011446872,0.0036266071,6.281363e-7,3.8368606e-9,0.0000073423143,0.034619655,0.90629274],"study_design_scores_gemma":[0.00053593447,0.0024190964,0.0011562214,0.02110073,0.002321351,0.000018601733,0.01036001,0.0000103013035,4.468605e-8,0.0005915622,0.96127546,0.0002106915],"about_ca_topic_score_codex":0.00008780414,"about_ca_topic_score_gemma":0.000022440689,"teacher_disagreement_score":0.92665577,"about_ca_system_score_codex":0.005004627,"about_ca_system_score_gemma":0.010604755,"threshold_uncertainty_score":0.99998146},"labels":[],"label_agreement":null},{"id":"W2046660743","doi":"10.1177/1098214008327931","title":"Do Self-Assessments Work to Detect Workshop Success?","year":2009,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Self-assessment; Applied psychology; Psychology; Work (physics); Multilevel model; Self-report study; Computer science; Social psychology; Machine learning; Engineering","score_opus":0.042287017239091264,"score_gpt":0.41814185392178405,"score_spread":0.37585483668269276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046660743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900874,0.0001599507,0.0027958893,0.0009434809,0.00059759535,0.0003137962,3.8423966e-7,0.000024426585,0.0050770896],"genre_scores_gemma":[0.99152553,0.00001577766,0.0070656072,0.00075946277,0.00041321627,0.000015332125,0.0000049037485,0.000013756155,0.00018643535],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99735737,0.0004807336,0.00061215454,0.00019742225,0.0010710306,0.00028130872],"domain_scores_gemma":[0.9981852,0.00012806026,0.00071706955,0.00023158056,0.0005798217,0.00015827485],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036644107,0.00015592844,0.00028042455,0.0004410008,0.00010464407,0.00007990584,0.00023102497,0.000048199367,0.0018904039],"category_scores_gemma":[0.00012359316,0.00013853353,0.000091104805,0.0009472864,0.00002691745,0.00022028551,0.000013235659,0.00023361285,0.00030346442],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004027112,0.00008794501,0.017942583,0.0000011153385,0.00009869032,0.0000060831226,0.006167089,0.0009088446,0.00011241355,0.00003234247,0.0047055352,0.96953464],"study_design_scores_gemma":[0.0012789005,0.0019110253,0.9890778,0.000100733676,0.00017898894,0.00003951945,0.0015943747,0.0002845741,0.00007587009,0.0005906018,0.004612552,0.00025504988],"about_ca_topic_score_codex":0.0000027809126,"about_ca_topic_score_gemma":0.0000021107069,"teacher_disagreement_score":0.9711352,"about_ca_system_score_codex":0.00025832662,"about_ca_system_score_gemma":0.00017704174,"threshold_uncertainty_score":0.999022},"labels":[],"label_agreement":null},{"id":"W2053636313","doi":"10.1177/1098214008319012","title":"The Case of Top Beginnings and the Missing Child Outcomes","year":2008,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Early Childhood Education and Development","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Formative assessment; Work (physics); Set (abstract data type); Foundation (evidence); Program evaluation; Political science; Public relations; Psychology; Management science; Engineering ethics; Pedagogy; Public administration; Engineering; Computer science","score_opus":0.023099755106382413,"score_gpt":0.35318993430323464,"score_spread":0.33009017919685224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053636313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94648975,0.00051944255,0.00007108781,0.05005257,0.00016661602,0.00009683864,1.2706506e-7,0.0000019812364,0.0026015674],"genre_scores_gemma":[0.998488,0.00035185882,0.00054112467,0.00045841775,0.00009206703,0.0000012117247,1.0678125e-7,0.000002186112,0.00006500069],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988278,0.00044220776,0.0002449153,0.000040461695,0.00036667488,0.00007789685],"domain_scores_gemma":[0.99851644,0.0005241152,0.00050806405,0.000061752515,0.00034053382,0.000049115268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036611424,0.00003727869,0.00011242823,0.00003861925,0.000826071,0.00003117353,0.00007402409,0.0000090661315,0.000021708447],"category_scores_gemma":[0.0013386386,0.000019302372,0.00004413148,0.00017869775,0.0009799998,0.000098455654,0.0000082256365,0.00008146348,7.276377e-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":[0.00005418669,0.000034353197,0.061406128,0.0000012026418,0.00009047982,0.0000131402085,0.2815614,0.000039468374,0.0000051378065,0.005965742,0.0012164941,0.64961225],"study_design_scores_gemma":[0.002036853,0.00019752274,0.8093101,0.00006144543,0.00015123314,0.00165083,0.16799022,0.00022594054,0.000057988706,0.007139148,0.011026138,0.00015261017],"about_ca_topic_score_codex":0.0008325885,"about_ca_topic_score_gemma":0.00009514526,"teacher_disagreement_score":0.74790394,"about_ca_system_score_codex":0.00004086736,"about_ca_system_score_gemma":0.0005435438,"threshold_uncertainty_score":0.63535535},"labels":[],"label_agreement":null},{"id":"W2060998986","doi":"10.1177/1098214006287990","title":"Developing a Stakeholder-Driven Anticipated Timeline of Impact for Evaluation of Social Programs","year":2006,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Timeline; Stakeholder; Stakeholder engagement; Stakeholder analysis; Program evaluation; Process (computing); Process management; Computer science; Management science; Public relations; Business; Political science; Engineering; Geography","score_opus":0.47865420615752025,"score_gpt":0.5785712379293496,"score_spread":0.09991703177182937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060998986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9750329,0.00006220213,0.023281967,0.00054291636,0.00015083069,0.0007138599,0.000012302985,0.0000041292283,0.00019886985],"genre_scores_gemma":[0.99098086,0.000004071643,0.008737455,0.000024588204,0.00016325204,0.000024024748,0.000039240298,0.000010516149,0.000015975616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915067,0.0010452102,0.0019206788,0.00017679506,0.0051600276,0.00019057855],"domain_scores_gemma":[0.98145366,0.00047792355,0.0042222543,0.00017658323,0.013625381,0.000044217726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028006349,0.00013172964,0.0005466081,0.00052132254,0.00012835425,0.000042784985,0.00025583315,0.000041653977,0.0003828456],"category_scores_gemma":[0.002031491,0.000095023126,0.00025459388,0.0012270785,0.0001685483,0.00042526668,0.000026498827,0.00008671324,0.0000034508635],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004521639,0.00036109058,0.047313873,0.000015322712,0.00016487931,2.3594384e-7,0.0025454697,0.07432165,0.007035482,0.00059364265,0.00057103887,0.86662513],"study_design_scores_gemma":[0.0042958404,0.0022164392,0.4510524,0.000093024064,0.000552861,0.000010034279,0.0024288946,0.5255904,0.0034334825,0.009895286,0.00025708653,0.00017426064],"about_ca_topic_score_codex":0.00005968901,"about_ca_topic_score_gemma":0.000038966522,"teacher_disagreement_score":0.8664509,"about_ca_system_score_codex":0.00032186395,"about_ca_system_score_gemma":0.0021784722,"threshold_uncertainty_score":0.9706498},"labels":[],"label_agreement":null},{"id":"W2061653962","doi":"10.1177/1098214007307942","title":"Evaluations That Consider the Cost of Educational Programs","year":2007,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"School Choice and Performance","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Program evaluation; Cost effectiveness; Set (abstract data type); Cost–benefit analysis; Computer science; Cost estimate; Macro; Program Design Language; Actuarial science; Cost contingency; Management science; Relevant cost; Risk analysis (engineering); Economics; Business","score_opus":0.10349334241685199,"score_gpt":0.4664295884873363,"score_spread":0.3629362460704843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061653962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795229,0.00029589917,0.0006346142,0.011010407,0.00042815658,0.00034109462,8.4677697e-7,0.0000027347721,0.0077633373],"genre_scores_gemma":[0.9982579,0.00007113709,0.0006680286,0.00026141535,0.00062126794,0.0000084746025,0.0000027349533,0.000003892304,0.00010515474],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977714,0.00038965527,0.0003402059,0.000059341677,0.0012911316,0.00014826533],"domain_scores_gemma":[0.99673665,0.00088170485,0.0007971375,0.000103807,0.0014064234,0.000074295065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009862582,0.000051057417,0.00011511921,0.00009527585,0.0003807295,0.00002578492,0.0001558457,0.00002090853,0.000588064],"category_scores_gemma":[0.0013694757,0.00003581063,0.000071816314,0.0004836786,0.0005402757,0.00028773633,0.000009886938,0.00012694357,0.0000114391805],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006858729,0.00013816837,0.32266822,0.0000028015572,0.00006664988,2.8199474e-7,0.022286255,0.00036109833,0.00013253401,0.0032802962,0.0020999184,0.64889514],"study_design_scores_gemma":[0.0006068033,0.0003806707,0.9327306,0.00007622007,0.00023310623,0.000022290647,0.03947637,0.00036012402,0.000352046,0.006327555,0.019309198,0.00012497482],"about_ca_topic_score_codex":0.00039187053,"about_ca_topic_score_gemma":0.0011987477,"teacher_disagreement_score":0.6487702,"about_ca_system_score_codex":0.00013294036,"about_ca_system_score_gemma":0.0011631501,"threshold_uncertainty_score":0.64388883},"labels":[],"label_agreement":null},{"id":"W2063290014","doi":"10.1177/1098214012464426","title":"Improving Program Results Through the Use of Predictive Operational Performance Indicators","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Employment and Social Development Canada; Carleton University","funders":"","keywords":"Accountability; Context (archaeology); Performance indicator; Program evaluation; Process management; Quality (philosophy); Computer science; Risk analysis (engineering); Term (time); Operations management; Environmental economics; Business; Engineering; Marketing; Economics; Political science; Public administration","score_opus":0.1859485882753664,"score_gpt":0.471487866355326,"score_spread":0.2855392780799596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063290014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917656,0.00003234569,0.0037504886,0.0026396515,0.00026787614,0.0006962406,0.0000074979316,0.000006514174,0.0008337753],"genre_scores_gemma":[0.9884297,0.000035141427,0.010901447,0.00035183175,0.00013397021,0.000053229025,0.000006847192,0.000006287286,0.00008151281],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99375075,0.00078341673,0.0013920763,0.00017833758,0.0037432348,0.00015215827],"domain_scores_gemma":[0.9920714,0.0011549816,0.0027179765,0.0003344838,0.0036561033,0.00006507713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007876904,0.00010793762,0.0002530985,0.00026584635,0.00017495704,0.00023050507,0.00039019893,0.000028125589,0.00046987322],"category_scores_gemma":[0.004184056,0.00005809321,0.000103965474,0.0011644142,0.00035204558,0.0024634404,0.00004899225,0.00020851442,0.000049033075],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000139515,0.00010553405,0.019569164,0.0000017014543,0.000041867326,1.3238049e-7,0.002950251,0.036148403,0.00021982669,0.00006828856,0.0030057437,0.93774956],"study_design_scores_gemma":[0.00089162536,0.0025731148,0.48575088,0.000036836635,0.00007080796,0.000019537018,0.0035522669,0.4999062,0.0006189755,0.00045218258,0.006026628,0.000100932484],"about_ca_topic_score_codex":0.00010486869,"about_ca_topic_score_gemma":0.0000065964937,"teacher_disagreement_score":0.93764865,"about_ca_system_score_codex":0.00010478024,"about_ca_system_score_gemma":0.0008794796,"threshold_uncertainty_score":0.51447827},"labels":[],"label_agreement":null},{"id":"W2063748659","doi":"10.1016/s1098-2140(00)00090-4","title":"Planning for community-based evaluation","year":2000,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Global Health Research","funders":"","keywords":"Management science; Program evaluation; Set (abstract data type); Unit (ring theory); Process (computing); Conflict resolution; Evaluation methods; Process management; Computer science; Psychology; Sociology; Political science; Business; Engineering; Mathematics education","score_opus":0.355370496696108,"score_gpt":0.5926022913441982,"score_spread":0.2372317946480902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063748659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97119504,0.0000836268,0.021226972,0.0020041321,0.00029903871,0.0005212631,0.0000054459224,0.000007950127,0.0046565332],"genre_scores_gemma":[0.9918718,0.0000048603206,0.006567748,0.0011978636,0.00017642937,0.000042391548,0.000026928317,0.000009950096,0.00010203072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9909324,0.003138678,0.0011117165,0.00014423732,0.0044991253,0.00017383517],"domain_scores_gemma":[0.99139667,0.002398506,0.0012933873,0.00038363825,0.004428474,0.00009931434],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.062370263,0.000115685485,0.00031484058,0.00041459184,0.0003348171,0.0001538117,0.00040411297,0.000030891046,0.0047241133],"category_scores_gemma":[0.0032913194,0.00008755118,0.0001753835,0.000762441,0.00011680328,0.000566063,0.000009255357,0.0002414249,0.0000750351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021897495,0.000075713375,0.0026774323,0.0000016634191,0.000018585042,1.6175443e-7,0.0011870371,0.19519553,0.00016251094,0.000024981127,0.0018481534,0.7985893],"study_design_scores_gemma":[0.003456121,0.0024610232,0.05898298,0.000072969604,0.0002517479,0.00001941933,0.0047213444,0.8889052,0.00042753326,0.015081334,0.025429545,0.00019076462],"about_ca_topic_score_codex":0.0000148748995,"about_ca_topic_score_gemma":0.000009231274,"teacher_disagreement_score":0.7983985,"about_ca_system_score_codex":0.00022742034,"about_ca_system_score_gemma":0.0011802013,"threshold_uncertainty_score":0.9961857},"labels":[],"label_agreement":null},{"id":"W2063922189","doi":"10.1177/1098214007304536","title":"Analysis of Thin Online Interview Data","year":2007,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Focus Groups and Qualitative Methods","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Meaning (existential); Computer science; Context (archaeology); Qualitative property; Perception; Data collection; Semantics (computer science); Data science; Qualitative analysis; Qualitative research; Psychology; Sociology; Machine learning","score_opus":0.34668716451748016,"score_gpt":0.5830954045773991,"score_spread":0.2364082400599189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063922189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8404301,0.0008390259,0.1549185,0.0016661023,0.00020415863,0.00008444699,0.00002256175,0.0000035344376,0.0018315527],"genre_scores_gemma":[0.96197635,0.0001388582,0.037544668,0.00014629321,0.00014442783,1.6045122e-7,0.000019472285,0.00000319298,0.000026603662],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99581903,0.0025121411,0.000583844,0.00009028961,0.00088517653,0.000109493114],"domain_scores_gemma":[0.9968578,0.000854468,0.0011457263,0.00019894406,0.0008732802,0.00006975556],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.047295433,0.000047185502,0.00032166232,0.00035137078,0.00005708563,0.000011518928,0.00031583678,0.000016271682,0.00029714397],"category_scores_gemma":[0.0031136665,0.000037683294,0.00011732063,0.0017252839,0.00032679117,0.00023867446,0.00003201472,0.00009599188,9.4024074e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029204723,0.00008836927,0.00443787,0.0000023150312,0.0004575696,9.978604e-7,0.01716785,0.00017854829,0.00014319303,0.00096971926,0.00010883227,0.9764155],"study_design_scores_gemma":[0.00096150645,0.001807382,0.64805734,0.00018075638,0.00835973,0.0000043704763,0.27467299,0.03169628,0.0001824466,0.0053745485,0.028350923,0.00035175806],"about_ca_topic_score_codex":0.00095286925,"about_ca_topic_score_gemma":0.0023492528,"teacher_disagreement_score":0.9760638,"about_ca_system_score_codex":0.00008049388,"about_ca_system_score_gemma":0.0001971631,"threshold_uncertainty_score":0.98100984},"labels":[],"label_agreement":null},{"id":"W2070663696","doi":"10.1177/1098214010371817","title":"A Realist Evaluation Approach to Unpacking the Impacts of the Sentencing Guidelines","year":2010,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Criminal Justice and Corrections Analysis","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Unpacking; Prison; Sentencing guidelines; Work (physics); Psychological intervention; Resource (disambiguation); Impact evaluation; Key (lock); Control (management); Linkage (software); Public economics; Sociology; Management science; Criminology; Political science; Psychology; Economics; Computer science; Computer security","score_opus":0.08324908097625391,"score_gpt":0.42450876934372395,"score_spread":0.34125968836747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070663696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895496,0.000051639494,0.002959836,0.00471064,0.0005060761,0.00024267563,8.667907e-7,0.000003022035,0.001975665],"genre_scores_gemma":[0.99754256,0.000027257209,0.0015542577,0.00032165807,0.0005284036,0.000007264075,8.1372536e-7,0.000004714115,0.000013078526],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9969135,0.0008024083,0.0004519253,0.00008779858,0.0016166456,0.00012772862],"domain_scores_gemma":[0.9949748,0.00020521194,0.00089751626,0.00020698798,0.0036489149,0.00006655276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012089445,0.00006300175,0.00014923874,0.00013071453,0.00041809495,0.00005863825,0.00026148642,0.000021324415,0.000048108086],"category_scores_gemma":[0.007399987,0.000035610436,0.00015271168,0.0011693111,0.00022175761,0.00015642426,0.0000230033,0.00018317603,0.000001401843],"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":[0.00004225816,0.000076831326,0.0047798306,0.0000046395585,0.0000891664,1.5244566e-7,0.057148304,0.016881917,0.010670683,0.0005185712,0.0012195712,0.9085681],"study_design_scores_gemma":[0.000277478,0.00017459894,0.02731835,0.00009325664,0.0023026755,0.000033134023,0.91678905,0.050244745,0.0005406819,0.00079287554,0.0013040967,0.00012903492],"about_ca_topic_score_codex":0.016276613,"about_ca_topic_score_gemma":0.016274588,"teacher_disagreement_score":0.90843904,"about_ca_system_score_codex":0.0001420252,"about_ca_system_score_gemma":0.00082216517,"threshold_uncertainty_score":0.9902741},"labels":[],"label_agreement":null},{"id":"W2073141549","doi":"10.1177/1098214007312630","title":"Using Self-Assessments to Detect Workshop Success","year":2008,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Communication in Education and Healthcare","field":"Psychology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of British Columbia; University of Calgary; University of Saskatchewan","funders":"","keywords":"Psychology; Reliability (semiconductor); Applied psychology; Program evaluation; Scale (ratio); Gold standard (test); Medical education; Medicine; Statistics","score_opus":0.2077316628935172,"score_gpt":0.5490251839928058,"score_spread":0.34129352109928857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073141549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9857823,0.00025269503,0.008492531,0.0022114539,0.0008913256,0.0002034763,8.087782e-7,0.000014807773,0.002150582],"genre_scores_gemma":[0.96268255,0.00005365141,0.036121268,0.0008218822,0.00021840564,0.000014502432,0.0000017856105,0.00001329922,0.00007263539],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99800915,0.00073190965,0.0004989687,0.00011424418,0.000488513,0.00015724688],"domain_scores_gemma":[0.9976409,0.00020108488,0.00068376865,0.0003474801,0.0009653667,0.00016141549],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012687766,0.00008134867,0.00019118657,0.00028561344,0.0001696018,0.000015622976,0.00022863435,0.00002892061,0.0010050489],"category_scores_gemma":[0.00014141333,0.00008006016,0.00006282853,0.00062320847,0.00005125233,0.00012253158,0.000023114617,0.0002065507,0.000057311485],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037024045,0.00052747567,0.12719113,0.000009405673,0.00028556012,0.000012894304,0.04010272,0.0020579891,0.0007823758,0.00036244633,0.009171954,0.81912583],"study_design_scores_gemma":[0.0014053333,0.0010578701,0.9662002,0.00009833491,0.0001793525,0.0008461799,0.01669606,0.0019086668,0.00008593634,0.00041719523,0.010807339,0.0002975349],"about_ca_topic_score_codex":0.0001360689,"about_ca_topic_score_gemma":0.000019999019,"teacher_disagreement_score":0.83900905,"about_ca_system_score_codex":0.00034940752,"about_ca_system_score_gemma":0.00055021857,"threshold_uncertainty_score":0.99990815},"labels":[],"label_agreement":null},{"id":"W2093411079","doi":"10.1177/1098214010379038","title":"Evaluating the Science of Discovery in Complex Health Systems","year":2010,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Interdisciplinary Research and Collaboration","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Nutrasource; University of Toronto","funders":"","keywords":"Process (computing); Discipline; Plan (archaeology); Data science; Work (physics); Engineering ethics; Computer science; Scientific discovery; Management science; Logic model; Translational science; Health science; Sociology; Psychology; Engineering; Medicine; Social science; Medical education","score_opus":0.2891501171514995,"score_gpt":0.5838757997116935,"score_spread":0.29472568256019394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093411079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931541,0.00006698093,0.0014008785,0.004161816,0.00047615214,0.00028209522,0.0000033183487,0.0000010885534,0.0004535561],"genre_scores_gemma":[0.9989868,0.0000028837378,0.0007855728,0.000039619248,0.0001379861,0.000005630632,7.9893783e-7,0.0000031106567,0.00003762724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919734,0.0013601972,0.0011282403,0.0001674273,0.005164202,0.00020651807],"domain_scores_gemma":[0.99297965,0.0009800481,0.001875296,0.0003475477,0.0037350187,0.00008243678],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.064352244,0.000061911094,0.00027263767,0.00056643004,0.00021472652,0.00029895382,0.0006991006,0.000010950119,0.000054961318],"category_scores_gemma":[0.008036617,0.000034110053,0.00005625509,0.0028832408,0.0007915532,0.0009887591,0.00008535916,0.00026431866,0.0000059907484],"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":[0.00069345307,0.00021746678,0.011639638,0.000009503089,0.000021104606,0.0000026684882,0.009029349,0.066237785,0.32772973,0.005509307,0.0017186839,0.5771913],"study_design_scores_gemma":[0.0008620449,0.0053997384,0.28584674,0.00008056198,0.000013504347,0.000090441,0.037044443,0.6593426,0.0010063297,0.010106144,0.00009830137,0.000109136745],"about_ca_topic_score_codex":0.00010528691,"about_ca_topic_score_gemma":0.00023268718,"teacher_disagreement_score":0.59310484,"about_ca_system_score_codex":0.00015067562,"about_ca_system_score_gemma":0.0029537734,"threshold_uncertainty_score":0.96344626},"labels":[],"label_agreement":null},{"id":"W2097114336","doi":"10.1177/1098214010378355","title":"Evaluating Capacity Building for Policy Research Organizations","year":2010,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"International Development and Aid","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Capacity building; Legislation; Business; Key (lock); Corporate governance; Process management; Program evaluation; Public relations; Economics; Political science; Computer science; Economic growth; Public administration; Computer security; Finance","score_opus":0.1885404601512432,"score_gpt":0.5539368367300723,"score_spread":0.3653963765788291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097114336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9784132,0.000006151732,0.0032790212,0.013417323,0.00057061634,0.00026529937,0.0000020764217,0.0000075623298,0.004038746],"genre_scores_gemma":[0.9574761,0.000007701443,0.04051429,0.000095373034,0.0017347703,0.000010349001,0.0000026012087,0.000008272698,0.00015057172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99740416,0.00049359235,0.00029491636,0.000088983135,0.0015099713,0.00020839242],"domain_scores_gemma":[0.9914264,0.00068198633,0.000363452,0.00006311892,0.0073796855,0.000085346735],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01534924,0.000048093883,0.00010313298,0.00039336298,0.0006467111,0.000090339694,0.00020153656,0.000029624354,0.00019430304],"category_scores_gemma":[0.022477698,0.00004563512,0.000043313143,0.0010837571,0.0003441089,0.00029918842,0.00001676745,0.00024720444,0.000007865389],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005991491,0.000102769205,0.0054155975,0.000004985573,0.00007596561,5.79263e-7,0.023287699,0.0005769378,0.104698285,0.60427487,0.0018621107,0.25964028],"study_design_scores_gemma":[0.0035938546,0.0023387508,0.07458399,0.00023583099,0.00024224927,0.000057302408,0.024464702,0.026024876,0.017324794,0.7783831,0.07193263,0.0008179234],"about_ca_topic_score_codex":0.0005829831,"about_ca_topic_score_gemma":0.00033890994,"teacher_disagreement_score":0.25882235,"about_ca_system_score_codex":0.00031621955,"about_ca_system_score_gemma":0.0026354166,"threshold_uncertainty_score":0.9857564},"labels":[],"label_agreement":null},{"id":"W2102960304","doi":"10.1177/1098214012464037","title":"Arguments for a Common Set of Principles for Collaborative Inquiry in Evaluation","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Carleton University; University of Ottawa","funders":"","keywords":"Logic model; Set (abstract data type); Context (archaeology); Field (mathematics); Stakeholder; Program evaluation; Management science; Engineering ethics; Sociology; Computer science; Epistemology; Knowledge management; Public relations; Political science; Social science; Public administration; Engineering","score_opus":0.39253977170837995,"score_gpt":0.5662179449091042,"score_spread":0.1736781732007242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102960304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98558354,0.00010209202,0.009325097,0.0017711198,0.00040965484,0.0024858536,0.000019871648,0.0000021983183,0.00030059542],"genre_scores_gemma":[0.9892596,0.000018280763,0.009960947,0.0001531373,0.00013121401,0.0004107251,0.000026212156,0.00000874278,0.000031140153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993849,0.0010684364,0.001714679,0.00020198018,0.0029942351,0.00017166209],"domain_scores_gemma":[0.98529494,0.00197222,0.003016125,0.00024871496,0.009396606,0.00007141837],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029864952,0.00011819261,0.00047374985,0.00058552413,0.000069994974,0.00008531129,0.00028771613,0.000037085436,0.00050511287],"category_scores_gemma":[0.0061370325,0.00008853722,0.0001253126,0.0009930803,0.0001350084,0.00086500513,0.000024477664,0.00008149468,0.000011689032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004938131,0.00019034835,0.04199456,0.000013982809,0.00008054135,9.910812e-8,0.011389159,0.051619925,0.002236897,0.0005150211,0.003115026,0.8883506],"study_design_scores_gemma":[0.005472619,0.0034739124,0.26173934,0.000110695095,0.00017055609,0.0000045470642,0.03310417,0.6547024,0.002050935,0.036493763,0.0024909147,0.00018615049],"about_ca_topic_score_codex":0.000023156561,"about_ca_topic_score_gemma":0.00007633395,"teacher_disagreement_score":0.88816446,"about_ca_system_score_codex":0.00029252126,"about_ca_system_score_gemma":0.0012717171,"threshold_uncertainty_score":0.9989582},"labels":[],"label_agreement":null},{"id":"W2120292430","doi":"10.1177/1098214012440030","title":"A New Realistic Evaluation Analysis Method","year":2012,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":144,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Health Research Board","keywords":"Coding (social sciences); Computer science; Qualitative research; Qualitative analysis; Narrative; Management science; Context (archaeology); Evaluation methods; Data science; Psychology; Sociology; Social science; Engineering","score_opus":0.29742318158161135,"score_gpt":0.6135208376358036,"score_spread":0.3160976560541922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120292430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2729564,0.00047320683,0.7160211,0.0023298915,0.0008939134,0.00034561535,0.0000034624757,0.00000912737,0.0069672633],"genre_scores_gemma":[0.9390099,0.000018102959,0.059850387,0.00033082452,0.0005459119,0.000008960162,0.000012333111,0.000007946536,0.00021565447],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98620427,0.0036090617,0.0014516233,0.00021308832,0.008253094,0.0002688432],"domain_scores_gemma":[0.9905058,0.0015396079,0.0026389742,0.00047343184,0.004504244,0.0003379342],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.08044642,0.00014157471,0.000533049,0.0013237938,0.00010950227,0.00014717273,0.00035287274,0.00003633859,0.009592068],"category_scores_gemma":[0.008161817,0.00010074926,0.00034325197,0.004146119,0.000052745836,0.0011957019,0.000031590032,0.00017001606,0.00015889762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056471803,0.000053866766,0.039207507,5.0199844e-7,0.00028522318,2.033798e-7,0.0017722686,0.043084387,0.00016589371,0.00038730152,0.0038795734,0.9111068],"study_design_scores_gemma":[0.0010173871,0.00045864744,0.53329664,0.0000112399775,0.004213882,0.00004073945,0.0032798636,0.44310302,0.00015972738,0.009809973,0.004422669,0.00018623992],"about_ca_topic_score_codex":0.00011767673,"about_ca_topic_score_gemma":0.000052354808,"teacher_disagreement_score":0.91092056,"about_ca_system_score_codex":0.00037985574,"about_ca_system_score_gemma":0.0013892109,"threshold_uncertainty_score":0.9913133},"labels":[],"label_agreement":null},{"id":"W2140628270","doi":"10.1177/1098214014532166","title":"How Analogue Research Can Advance Descriptive Evaluation Theory","year":2014,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpersonal communication; Frame (networking); Computer science; Management science; Accountability; Evaluation methods; Epistemology; Psychology; Social psychology; Political science","score_opus":0.3507628690464508,"score_gpt":0.5660418537784816,"score_spread":0.21527898473203078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140628270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9120359,0.00032604244,0.067234166,0.011547325,0.0009122904,0.00064081606,0.0000052131795,0.0000102750755,0.007288008],"genre_scores_gemma":[0.9956565,0.0000432569,0.0031110814,0.00034695634,0.00041944554,0.00003445047,0.000009024697,0.000013549981,0.00036573078],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9736034,0.012856439,0.0010029294,0.00037559037,0.01181072,0.0003508941],"domain_scores_gemma":[0.9778165,0.003449526,0.0017511661,0.00058841193,0.016192803,0.00020159551],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16305058,0.00015598346,0.00041681246,0.0010700745,0.0003130811,0.00042164233,0.00061805925,0.000044879085,0.0008065109],"category_scores_gemma":[0.034939047,0.0001113944,0.00015164564,0.0021306393,0.000456819,0.0011465694,0.00005744426,0.00044316752,0.000071104885],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014223078,0.000058432386,0.0035215092,0.0000012766269,0.00003330616,6.2869026e-7,0.0026022254,0.0064878063,0.00095811253,0.004125887,0.0015502726,0.98051834],"study_design_scores_gemma":[0.0028320681,0.004219403,0.14805347,0.000113558555,0.00026536357,0.000072556824,0.052338794,0.34884262,0.0018248559,0.41952598,0.021515062,0.0003962717],"about_ca_topic_score_codex":0.000024098523,"about_ca_topic_score_gemma":0.00014303891,"teacher_disagreement_score":0.980122,"about_ca_system_score_codex":0.0006674662,"about_ca_system_score_gemma":0.0016091487,"threshold_uncertainty_score":0.97319007},"labels":[],"label_agreement":null},{"id":"W2147607381","doi":"10.1177/1098214007309280","title":"The Evaluation of Large Research Initiatives","year":2008,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":144,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Program evaluation; Agency (philosophy); Government (linguistics); Work (physics); Political science; Management science; Public relations; Public administration; Sociology; Engineering; Social science","score_opus":0.8816684527440397,"score_gpt":0.727468180018336,"score_spread":0.1542002727257037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147607381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891057,0.0018344495,0.0014390178,0.001238122,0.00030901583,0.00028124353,0.000004714444,0.0000014889597,0.005786228],"genre_scores_gemma":[0.9986893,0.0007605782,0.000323713,0.000024756588,0.00012224352,0.000008076996,8.201211e-7,0.000005414658,0.00006509508],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.93062854,0.009501756,0.0015933621,0.0002975611,0.05746344,0.0005153461],"domain_scores_gemma":[0.9140736,0.014790451,0.0016002763,0.00050079974,0.06885068,0.00018422763],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.36563444,0.000073522344,0.00027716334,0.020573715,0.00061591074,0.00027043626,0.0012337404,0.00003090312,0.0003782494],"category_scores_gemma":[0.22491363,0.000040009807,0.00015105197,0.09118454,0.0009350633,0.0007370567,0.00017447442,0.00037241325,0.00004785818],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012983666,0.00022031344,0.05034644,8.969214e-7,0.000052820465,0.0000036381098,0.002031767,0.00086236105,0.00090451457,0.0008260244,0.008424918,0.93619645],"study_design_scores_gemma":[0.0013213335,0.001622692,0.8919392,0.000016467882,0.00003838969,0.00005981162,0.010143766,0.065817125,0.0014151023,0.023506483,0.004031598,0.00008802626],"about_ca_topic_score_codex":0.000025234429,"about_ca_topic_score_gemma":0.000011306279,"teacher_disagreement_score":0.93610847,"about_ca_system_score_codex":0.00027434313,"about_ca_system_score_gemma":0.0022186744,"threshold_uncertainty_score":0.9905273},"labels":[],"label_agreement":null},{"id":"W2149719915","doi":"10.1177/1098214008325023","title":"An Assessment of the Theoretical Underpinnings of Practical Participatory Evaluation","year":2008,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Context (archaeology); Process (computing); Citizen journalism; Key (lock); Management science; Participatory action research; Knowledge management; Empirical research; Action (physics); Computer science; Epistemology; Psychology; Sociology; Engineering","score_opus":0.36844893795092876,"score_gpt":0.6248471033074683,"score_spread":0.25639816535653953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149719915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98149073,0.000031573632,0.013610761,0.0024161558,0.0003237666,0.00032163633,0.0000021530177,0.0000026822338,0.0018005405],"genre_scores_gemma":[0.9947462,0.000019502751,0.004898443,0.00022399008,0.0000836296,0.0000115048415,0.00000169863,0.00000774221,0.0000072674625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9849417,0.0044905725,0.0016997985,0.0001763577,0.008526938,0.00016458913],"domain_scores_gemma":[0.98865235,0.0014654833,0.0033602405,0.0005662707,0.0058382675,0.000117376825],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03925495,0.00011468368,0.0004232621,0.00025957252,0.00013436508,0.000028677747,0.00041794972,0.00004117019,0.0020681585],"category_scores_gemma":[0.006563201,0.000067684785,0.0001947159,0.000962702,0.0011591988,0.00067592826,0.000042855077,0.00024272942,0.000005732771],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004904929,0.0018145251,0.5240415,0.000012317576,0.00025527197,0.0000031477127,0.013053106,0.08304765,0.01791772,0.05378032,0.0018608829,0.3037231],"study_design_scores_gemma":[0.00083759765,0.0014297705,0.63061154,0.000033861055,0.00023298239,0.00006556228,0.004369862,0.34352988,0.0019356196,0.016793266,0.00007942671,0.00008065625],"about_ca_topic_score_codex":0.000009599368,"about_ca_topic_score_gemma":0.00000506154,"teacher_disagreement_score":0.30364245,"about_ca_system_score_codex":0.00019915319,"about_ca_system_score_gemma":0.003895509,"threshold_uncertainty_score":0.9988441},"labels":[],"label_agreement":null},{"id":"W2156859842","doi":"10.1177/1098214014535658","title":"The Ethical Tipping Points of Evaluators in Conflict Zones","year":2014,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Development Research Centre","funders":"","keywords":"Affect (linguistics); Section (typography); Ethical issues; Face (sociological concept); Psychology; Engineering ethics; Conflict of interest; Sociology; Social psychology; Public relations; Political science; Law; Social science; Computer science","score_opus":0.17093914735823218,"score_gpt":0.5305063413621447,"score_spread":0.3595671940039125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156859842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824148,0.00011507779,0.005631241,0.00953013,0.00043741133,0.0001641932,5.41453e-7,0.0000024067506,0.0017042385],"genre_scores_gemma":[0.997949,0.00006562105,0.0012230847,0.0006066838,0.000109936365,0.000004964359,5.781604e-7,0.0000054510124,0.00003465832],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99025714,0.003298657,0.0015510487,0.00015422425,0.0045698606,0.00016905447],"domain_scores_gemma":[0.98979723,0.004575419,0.002650918,0.00032687577,0.002571414,0.00007811784],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.066231444,0.00009237957,0.00035338348,0.00035607076,0.00010738301,0.000081087404,0.0004307726,0.000048909333,0.0003315472],"category_scores_gemma":[0.02091448,0.00005319772,0.00012258843,0.000918387,0.0003102502,0.00024442092,0.00003661621,0.00037275304,0.00003740172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016457368,0.00005105074,0.04854803,0.0000020903417,0.000027967986,3.9387817e-7,0.0022453647,0.0075888275,0.0006303901,0.0030107512,0.00093381363,0.9367967],"study_design_scores_gemma":[0.001973331,0.0016602199,0.62253845,0.0001215376,0.00007932783,0.00003361523,0.007795542,0.31858924,0.0006269467,0.034579743,0.01182913,0.00017288617],"about_ca_topic_score_codex":0.000023085135,"about_ca_topic_score_gemma":0.00006439133,"teacher_disagreement_score":0.9366239,"about_ca_system_score_codex":0.00009960783,"about_ca_system_score_gemma":0.0005958839,"threshold_uncertainty_score":0.98733276},"labels":[],"label_agreement":null},{"id":"W2169058265","doi":"10.1177/1098214009354774","title":"Bibliometrics as a Performance Measurement Tool for Research Evaluation: The Case of Research Funded by the National Cancer Institute of Canada","year":2010,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":157,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; Canadian Partnership Against Cancer; Canadian Cancer Society","funders":"National Cancer Institute","keywords":"Bibliometrics; Documentation; Management science; Medical education; Medicine; Library science; Computer science; Engineering","score_opus":0.8412037386951862,"score_gpt":0.6852424986880619,"score_spread":0.1559612400071243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169058265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98805255,0.0010688794,0.00040047418,0.0072782896,0.0009979452,0.0011638785,0.000058386144,0.0000010829192,0.0009785158],"genre_scores_gemma":[0.9987945,0.00021741693,0.00038606263,0.00007804685,0.00026496523,0.00012534331,0.000001919392,0.000008879927,0.00012284651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.92335457,0.0031440994,0.001804564,0.00042780384,0.07057135,0.0006976436],"domain_scores_gemma":[0.8123634,0.015151732,0.00150251,0.0005794502,0.1701824,0.0002205035],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.45272475,0.00011645762,0.00033998647,0.05198887,0.00089619326,0.00051786576,0.0021179891,0.00005729633,0.00043851434],"category_scores_gemma":[0.28436464,0.00006109954,0.00013465388,0.27616403,0.0014385205,0.000660463,0.00023992226,0.0009501457,0.0000030362287],"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":[0.0003175146,0.00020700159,0.0071733887,0.000017104281,0.00011817386,0.0000041833077,0.00047641055,0.0030652578,0.0077913282,0.0005833893,0.13014525,0.850101],"study_design_scores_gemma":[0.007698217,0.008209094,0.20627739,0.00022821143,0.00030785662,0.0012185388,0.017935544,0.5235799,0.043585524,0.041519895,0.14872758,0.00071224605],"about_ca_topic_score_codex":0.05011414,"about_ca_topic_score_gemma":0.044885606,"teacher_disagreement_score":0.8493888,"about_ca_system_score_codex":0.0011645157,"about_ca_system_score_gemma":0.020326532,"threshold_uncertainty_score":0.9852273},"labels":[],"label_agreement":null},{"id":"W2253092986","doi":"10.1177/1098214015615230","title":"Introducing Evidence-Based Principles to Guide Collaborative Approaches to Evaluation","year":2015,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University; Queen's University","funders":"","keywords":"Variety (cybernetics); Set (abstract data type); Context (archaeology); Computer science; Management science; Knowledge management; Psychology; Data science; Engineering; Artificial intelligence","score_opus":0.7348226152021603,"score_gpt":0.5424577550404095,"score_spread":0.1923648601617508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253092986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8650076,0.0003391762,0.0882647,0.040641308,0.0009562429,0.0015117911,0.000004499857,0.000013522587,0.0032611636],"genre_scores_gemma":[0.9325728,0.0000070909223,0.065023445,0.001676617,0.000465706,0.000093213544,0.0000046557716,0.0000130273775,0.00014345403],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98455256,0.0032861084,0.0016761733,0.0004574558,0.009769458,0.0002582335],"domain_scores_gemma":[0.9818253,0.0014139055,0.0017572227,0.00060114166,0.013891285,0.0005111447],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09005673,0.00018905998,0.00047942105,0.0010615874,0.00013032948,0.0003426085,0.00057880464,0.000034292363,0.000530261],"category_scores_gemma":[0.055608306,0.00013941419,0.00010441913,0.0035294641,0.000089748515,0.0012254459,0.00007743132,0.0001580605,0.00029790687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027098923,0.000050352206,0.005213894,0.00000105605,0.000020652811,5.1653024e-7,0.0047440515,0.5909342,0.0003893224,0.00013705666,0.0059569688,0.3922809],"study_design_scores_gemma":[0.0023764346,0.0063497913,0.066634975,0.0003442035,0.0003282595,0.000022335802,0.03759166,0.84164125,0.0040908605,0.0033573965,0.036771405,0.00049144577],"about_ca_topic_score_codex":0.00003400631,"about_ca_topic_score_gemma":0.00008961079,"teacher_disagreement_score":0.39178947,"about_ca_system_score_codex":0.0013159086,"about_ca_system_score_gemma":0.0073426478,"threshold_uncertainty_score":0.9982848},"labels":[],"label_agreement":null},{"id":"W2318178033","doi":"10.1177/1098214013503698","title":"Managing Tensions Between Evaluation and Research","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Temporality; Psychological intervention; Software deployment; Process (computing); Management science; Psychology; Sociology; Engineering ethics; Computer science; Epistemology","score_opus":0.47772656074020564,"score_gpt":0.6157514516411698,"score_spread":0.1380248909009642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318178033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802135,0.0001993876,0.0021741558,0.011756685,0.0002013404,0.0005508481,8.9548826e-7,0.0000049271616,0.004898242],"genre_scores_gemma":[0.9969881,0.000068875335,0.002331134,0.00019337679,0.00024846595,0.000028509889,0.0000033859014,0.00000810423,0.00013005408],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9870958,0.0031166677,0.0010039213,0.00024547332,0.008301758,0.00023641392],"domain_scores_gemma":[0.9841439,0.002339619,0.00093663693,0.00033900575,0.012052897,0.00018791875],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0714384,0.00009767957,0.00029961075,0.0010077792,0.00028249988,0.000345456,0.0002885809,0.000030883384,0.0026489745],"category_scores_gemma":[0.007943246,0.000068043286,0.000069343405,0.0014503445,0.0002749547,0.0011634958,0.00007774925,0.0003136753,0.00029543543],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009274296,0.000017721432,0.03604556,8.460693e-7,0.000020698044,2.9884407e-7,0.00085281115,0.00094839314,0.0004935671,0.00010987002,0.0026778397,0.95882314],"study_design_scores_gemma":[0.00074205676,0.00070182025,0.7268568,0.000042068714,0.00010182883,0.000025218918,0.009414387,0.16749005,0.00012892406,0.09252984,0.0018573366,0.00010962672],"about_ca_topic_score_codex":0.000083956744,"about_ca_topic_score_gemma":0.000010992133,"teacher_disagreement_score":0.9587135,"about_ca_system_score_codex":0.00020514267,"about_ca_system_score_gemma":0.0006851025,"threshold_uncertainty_score":0.99826276},"labels":[],"label_agreement":null},{"id":"W2319861733","doi":"10.1177/1098214014542100","title":"Insights on Using Developmental Evaluation for Innovating","year":2014,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Conceptualization; Process (computing); Knowledge management; Process management; Rendering (computer graphics); Computer science; Psychology; Management science; Business; Engineering; Artificial intelligence","score_opus":0.35735194148799976,"score_gpt":0.5543062644225002,"score_spread":0.19695432293450044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319861733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9296078,0.000018883096,0.06633253,0.00050017354,0.0005733205,0.00041749162,9.793494e-7,0.000004641747,0.0025441882],"genre_scores_gemma":[0.9637597,0.0000015765262,0.03519446,0.00067376293,0.00031543098,0.00001922778,0.0000066798875,0.000010521649,0.00001860453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924273,0.0010994474,0.0012667668,0.00022748491,0.0048246393,0.00015435019],"domain_scores_gemma":[0.99017936,0.001384525,0.0021653955,0.0001898382,0.0060057556,0.000075152464],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029487727,0.00012712482,0.00031081293,0.00067634234,0.00022378459,0.00013952403,0.00024986066,0.00003009329,0.0003482328],"category_scores_gemma":[0.010658501,0.00009235309,0.0001019309,0.0010812924,0.00007460052,0.00058750797,0.00002170007,0.00012430077,0.00003358059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010116811,0.00004927513,0.0023402951,0.0000013822068,0.000024886182,8.615216e-8,0.000983902,0.034103595,0.0039117057,0.0009134166,0.000354244,0.957216],"study_design_scores_gemma":[0.0017467113,0.0012711562,0.023804335,0.00005997321,0.00008945526,0.00001832487,0.0027847898,0.9470034,0.0016494895,0.018363886,0.003052178,0.0001562494],"about_ca_topic_score_codex":0.000005514293,"about_ca_topic_score_gemma":0.000009420181,"teacher_disagreement_score":0.9570598,"about_ca_system_score_codex":0.00055104593,"about_ca_system_score_gemma":0.0013538746,"threshold_uncertainty_score":0.9993466},"labels":[],"label_agreement":null},{"id":"W2520519417","doi":"10.1177/1098214016668401","title":"Introducing Reflexivity to Evaluation Practice","year":2016,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reflexivity; Action (physics); Psychology; Thematic analysis; Action research; Engineering ethics; Action plan; Competence (human resources); Sociology; Qualitative research; Pedagogy; Social psychology; Social science","score_opus":0.27423114310164076,"score_gpt":0.5920985262212245,"score_spread":0.31786738311958374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520519417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.854856,0.00007019765,0.07263486,0.063474126,0.0012167996,0.00052083674,0.0000027060346,0.000010444642,0.007214026],"genre_scores_gemma":[0.9784046,0.000024374136,0.019235848,0.001618274,0.0005298529,0.00001915708,9.498153e-7,0.000009457117,0.00015751865],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9863702,0.0033564335,0.001315626,0.00033978443,0.008401768,0.00021619529],"domain_scores_gemma":[0.98238623,0.002962429,0.0022346552,0.00054672675,0.011668981,0.00020096652],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.090552494,0.0001257669,0.00032590612,0.0006271381,0.00012232487,0.00014762046,0.00038687454,0.000027271557,0.00290052],"category_scores_gemma":[0.06624832,0.00007161531,0.00011355462,0.001342331,0.000092781534,0.0018785786,0.000054722095,0.00012443413,0.0005750011],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022500106,0.00005731218,0.0015911344,3.925302e-7,0.000026427197,7.1038596e-7,0.0009156074,0.0042401706,0.007446389,0.00022066446,0.0042161453,0.98106],"study_design_scores_gemma":[0.01141051,0.014073159,0.46234757,0.0005768739,0.0016930517,0.00068141916,0.027281988,0.101581424,0.014888053,0.07719248,0.28682002,0.0014534465],"about_ca_topic_score_codex":0.00001592721,"about_ca_topic_score_gemma":0.00002255696,"teacher_disagreement_score":0.9796066,"about_ca_system_score_codex":0.0006600155,"about_ca_system_score_gemma":0.0013744475,"threshold_uncertainty_score":0.998011},"labels":[],"label_agreement":null},{"id":"W2800401326","doi":"10.1177/1098214018765698","title":"Outcomes and Impacts of Development Interventions","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":120,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"International Fund for Agricultural Development; Consortium of International Agricultural Research Centers; Centre for International Forestry Research; Canada Research Chairs; United Nations Development Programme","keywords":"CLARITY; Psychological intervention; Consistency (knowledge bases); Outcome (game theory); Accountability; Confusion; Management science; Psychology; Computer science; Sociology; Political science; Economics","score_opus":0.2737634216383244,"score_gpt":0.5787112819025034,"score_spread":0.304947860264179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800401326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99097604,0.0000636114,0.006919491,0.0010627599,0.00022952331,0.0000828946,8.281481e-7,0.0000017187499,0.00066312455],"genre_scores_gemma":[0.99255407,0.000013506447,0.0071610655,0.00015662558,0.00004617428,0.0000017148126,6.7665894e-7,0.0000028493553,0.00006332814],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99667937,0.00032731696,0.0010154138,0.00009055112,0.0018050603,0.00008226833],"domain_scores_gemma":[0.9954387,0.00035768538,0.0015249758,0.00014170352,0.0024612339,0.00007569888],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011818907,0.00006126443,0.00024832212,0.00034753414,0.000067655004,0.000043317494,0.00014963512,0.00001190632,0.0010169207],"category_scores_gemma":[0.00220232,0.000039332393,0.000090562506,0.00042057206,0.0002053173,0.00046221333,0.000033248245,0.000054540607,0.00003021261],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042912277,0.00006814596,0.25180614,0.0000027702313,0.000056657536,2.2020177e-7,0.002524343,0.00004020466,0.00048378002,0.00023233889,0.0004708661,0.74427164],"study_design_scores_gemma":[0.00054136215,0.0009014718,0.99006087,0.00006337133,0.00004447654,0.000014693979,0.002282281,0.002044455,0.0012246512,0.001731304,0.0010384527,0.000052634045],"about_ca_topic_score_codex":0.000007969195,"about_ca_topic_score_gemma":0.00003772479,"teacher_disagreement_score":0.744219,"about_ca_system_score_codex":0.000056297216,"about_ca_system_score_gemma":0.0005211114,"threshold_uncertainty_score":0.9998963},"labels":[],"label_agreement":null},{"id":"W2802781340","doi":"10.1177/1098214018763553","title":"Evaluating Social Innovations","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Variety (cybernetics); Psychological intervention; Management science; Conceptual framework; Computer science; Knowledge management; Sociology; Engineering ethics; Psychology; Social science; Economics; Engineering","score_opus":0.4567176324915049,"score_gpt":0.6367359267377268,"score_spread":0.18001829424622195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802781340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9731865,0.000018389845,0.0129062645,0.0048571792,0.00072452927,0.00014329681,0.0000017995858,0.0000075781595,0.008154453],"genre_scores_gemma":[0.9889687,0.0000024358178,0.008880067,0.0008206981,0.0011505797,0.000005978549,0.0000026032603,0.000007642472,0.00016131654],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.992362,0.0010343203,0.001291858,0.0001798744,0.004962357,0.0001695766],"domain_scores_gemma":[0.9859452,0.0005964832,0.0022153198,0.00022726557,0.010950129,0.000065588356],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.032424934,0.00009744492,0.00027721564,0.00058837526,0.00034786362,0.00016175439,0.00035065945,0.000026425563,0.003952151],"category_scores_gemma":[0.0066091036,0.00007178003,0.000111762034,0.0022922105,0.00033091032,0.0006909236,0.000039206978,0.00015895585,0.0003063791],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063171734,0.00004459918,0.004868916,4.280241e-7,0.000026935952,3.2161535e-7,0.0025068521,0.0004301437,0.0023995347,0.0011696892,0.0044741505,0.9840153],"study_design_scores_gemma":[0.0033168541,0.0072653242,0.5896171,0.00005132813,0.00028828564,0.00012563792,0.016700009,0.2807485,0.00214496,0.07520051,0.024069246,0.0004722529],"about_ca_topic_score_codex":0.000007162983,"about_ca_topic_score_gemma":0.000013964075,"teacher_disagreement_score":0.983543,"about_ca_system_score_codex":0.00016530743,"about_ca_system_score_gemma":0.0011202603,"threshold_uncertainty_score":0.9969584},"labels":[],"label_agreement":null},{"id":"W2884500380","doi":"10.1177/1098214018778809","title":"The Need for Analysts in Social Impact Measurement","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Program evaluation; Management science; Actuarial science; Applied psychology; Business; Political science; Economics; Public administration","score_opus":0.3492754177554118,"score_gpt":0.5984297125613699,"score_spread":0.24915429480595808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884500380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825596,0.0000785483,0.009103552,0.0063927914,0.00042405372,0.00030053587,0.0000015806925,0.000002129564,0.0011371803],"genre_scores_gemma":[0.9987721,0.000008117022,0.00046643423,0.00019099044,0.0005188208,0.0000116195115,6.2582535e-7,0.0000042044526,0.000027121496],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9942046,0.0007885481,0.0008783338,0.000112105656,0.0038493369,0.00016707985],"domain_scores_gemma":[0.9922832,0.00063762075,0.0012663141,0.00015721563,0.00560306,0.000052554948],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.047754526,0.000073518335,0.00022041409,0.00030005377,0.00028536434,0.00015123816,0.00029292883,0.000016201937,0.0002514507],"category_scores_gemma":[0.004443418,0.00003869888,0.00017157225,0.00097531825,0.00017239495,0.00028773514,0.000014413486,0.00008366511,0.000023197994],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043145442,0.00004743732,0.020313036,4.2812712e-7,0.000059421127,1.7618686e-7,0.0018366065,0.0010424188,0.0009110133,0.00017119928,0.009870947,0.9653159],"study_design_scores_gemma":[0.0021561254,0.0027265467,0.82544327,0.000020247358,0.00010150379,0.00000992085,0.007832703,0.13037603,0.00036275308,0.022662073,0.00817663,0.00013217433],"about_ca_topic_score_codex":0.000020014191,"about_ca_topic_score_gemma":0.00023436811,"teacher_disagreement_score":0.9651837,"about_ca_system_score_codex":0.00042002788,"about_ca_system_score_gemma":0.0009987229,"threshold_uncertainty_score":0.9805371},"labels":[],"label_agreement":null},{"id":"W2884511286","doi":"10.1177/1098214018781506","title":"Making Space for Adaptive Learning","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa","keywords":"Interrogation; Space (punctuation); Mediation; Psychology; Social learning; Process (computing); Social psychology; Computer science; Sociology; Pedagogy; Political science; Social science","score_opus":0.3892532860461554,"score_gpt":0.5842406175819069,"score_spread":0.19498733153575154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884511286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6728446,0.000060985865,0.31558532,0.0027838687,0.0007353945,0.00027406475,0.0000012162302,0.000007709418,0.0077068293],"genre_scores_gemma":[0.9772994,0.0000054157163,0.021568973,0.00028941,0.00056692166,0.000006874215,7.289678e-7,0.0000069746748,0.00025530256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99622047,0.00060048053,0.00063758745,0.00014947429,0.0022483296,0.00014364207],"domain_scores_gemma":[0.9922931,0.0010215396,0.0016316983,0.00014638147,0.0048502604,0.00005701714],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017975984,0.00007641927,0.00022485429,0.00030752667,0.00019062601,0.000105700485,0.00021513333,0.00001770097,0.000992467],"category_scores_gemma":[0.0051589063,0.00005486158,0.000111979025,0.00061109714,0.00016542766,0.00046495566,0.000021593487,0.00011867804,0.00009168536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029874736,0.000025989464,0.00678361,6.5574176e-7,0.000033264285,3.5590148e-7,0.0026591653,0.006485262,0.0006516275,0.0010979362,0.0024663252,0.9794971],"study_design_scores_gemma":[0.0019537557,0.010361776,0.07185193,0.00009561897,0.00017347884,0.00006289627,0.025596743,0.79883415,0.0013004179,0.028900327,0.060602874,0.00026603736],"about_ca_topic_score_codex":0.0000031952209,"about_ca_topic_score_gemma":0.000012210108,"teacher_disagreement_score":0.979231,"about_ca_system_score_codex":0.0001222234,"about_ca_system_score_gemma":0.0004932402,"threshold_uncertainty_score":0.9999208},"labels":[],"label_agreement":null},{"id":"W2901688885","doi":"10.1177/1098214018796319","title":"Honoring Lived Experience: Life Histories as a Realist Evaluation Method","year":2018,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of British Columbia; Impact; St. Michael's Hospital","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Lived experience; Context (archaeology); Set (abstract data type); Psychology; Indigenous; Sociology; Epistemology; Computer science; History; Psychotherapist","score_opus":0.365242125327843,"score_gpt":0.5972764607902662,"score_spread":0.2320343354624232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901688885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9412824,0.00022063652,0.041305788,0.0026121202,0.0020413834,0.0004106675,0.0000017064361,0.000015982596,0.012109328],"genre_scores_gemma":[0.97877294,0.000029210303,0.019077454,0.0008598754,0.0009621045,0.000039688497,0.000004570396,0.000013610221,0.00024054649],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871544,0.0027854333,0.0016004019,0.00038106355,0.0078237755,0.00025492083],"domain_scores_gemma":[0.9846693,0.0010605569,0.0028508175,0.00055696804,0.010598964,0.00026334843],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04510768,0.00018251284,0.00047010163,0.00061655336,0.0003340753,0.00026575255,0.00052797364,0.000048155405,0.0064059496],"category_scores_gemma":[0.020226767,0.00013850529,0.00017148687,0.0014595479,0.0003943392,0.0012161782,0.000058379395,0.00019820487,0.00022215524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003641899,0.00009501248,0.009795102,0.000001919874,0.00006848305,0.0000016070768,0.039443724,0.0029291546,0.0027423848,0.0005268288,0.00399789,0.9400337],"study_design_scores_gemma":[0.0050085704,0.008353051,0.22183608,0.00015478441,0.00082241715,0.00028563317,0.14142163,0.5060673,0.006270869,0.046609193,0.062226076,0.0009444193],"about_ca_topic_score_codex":0.00015616823,"about_ca_topic_score_gemma":0.00005856277,"teacher_disagreement_score":0.9390893,"about_ca_system_score_codex":0.0006580432,"about_ca_system_score_gemma":0.0026842689,"threshold_uncertainty_score":0.9945023},"labels":[],"label_agreement":null},{"id":"W2936658129","doi":"10.1177/1098214019835821","title":"Research and Evaluation With Community-Based Projects: Approaches, Considerations, and Strategies","year":2019,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Public Health Agency of Canada","keywords":"Context (archaeology); Management science; Program evaluation; Engineering ethics; Psychology; Process management; Political science; Business; Engineering","score_opus":0.8556213530259436,"score_gpt":0.7057655941049885,"score_spread":0.14985575892095504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936658129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9894729,0.000059818452,0.0005152438,0.006036582,0.00006340104,0.0018167812,0.000005466168,0.00000736429,0.0020224394],"genre_scores_gemma":[0.9931628,0.00001275029,0.0049634306,0.0016388512,0.00006224233,0.00012163028,0.0000096858585,0.000010726582,0.000017868082],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9846673,0.012540993,0.0006768224,0.00014901679,0.0016582843,0.00030758625],"domain_scores_gemma":[0.99051577,0.0050895633,0.000873381,0.00023134761,0.003142004,0.00014791903],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.043148335,0.00009298832,0.0002417993,0.0004457354,0.00091686705,0.0000672196,0.00007754718,0.000039435086,0.0001820404],"category_scores_gemma":[0.0013962159,0.000071154325,0.000010985927,0.00057957,0.00047645834,0.00059636374,0.000033317552,0.0008745446,0.00001241418],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017858999,0.000519597,0.5181473,0.0017885566,0.00023863219,0.0000053470417,0.29538804,0.008283526,0.003805611,0.020541538,0.006999356,0.1424966],"study_design_scores_gemma":[0.008760233,0.008783492,0.30456725,0.00079192064,0.00015657459,0.00008101807,0.6168603,0.044743422,0.000112807335,0.012932197,0.0019028161,0.00030798535],"about_ca_topic_score_codex":0.00048118975,"about_ca_topic_score_gemma":0.00039260206,"teacher_disagreement_score":0.32147226,"about_ca_system_score_codex":0.00032108102,"about_ca_system_score_gemma":0.0064957864,"threshold_uncertainty_score":0.99913645},"labels":[],"label_agreement":null},{"id":"W2971517022","doi":"10.1177/1098214019866260","title":"Evaluations in the English-Speaking Commonwealth Caribbean Region: Lessons From the Field","year":2019,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Commonwealth; Pride; Nexus (standard); Face (sociological concept); Public relations; Political science; Sociology; Psychology; Social psychology; Social science; Law","score_opus":0.20495958925068822,"score_gpt":0.5292134531119421,"score_spread":0.3242538638612539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971517022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91273504,0.00020971148,0.0020967936,0.07606922,0.00084254274,0.0005031081,0.0000036836068,0.000004821316,0.0075350897],"genre_scores_gemma":[0.9932316,0.000050197083,0.00031372087,0.0059343935,0.0004095969,0.000014655533,0.000006444624,0.0000065048325,0.00003286759],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9907645,0.0036130566,0.0010746862,0.00021558342,0.0041422704,0.00018991041],"domain_scores_gemma":[0.9852945,0.01037187,0.0015503844,0.0007366632,0.001993438,0.000053126903],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.029395761,0.00011813524,0.00030202253,0.00021120647,0.00020477705,0.00026032544,0.0009626947,0.000033797016,0.0011200215],"category_scores_gemma":[0.0074388906,0.000059264818,0.00014723004,0.0012770247,0.00010055754,0.00057333196,0.000048243448,0.00046522776,0.00008212418],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001102214,0.00010131536,0.21321988,0.0000010753503,0.000043170163,0.00000269485,0.048313692,0.014094652,0.000044233064,0.0017990483,0.014594885,0.7076751],"study_design_scores_gemma":[0.0014319227,0.0009020899,0.8187229,0.00009469385,0.00012729222,0.000025974019,0.08027123,0.05187843,0.000037389083,0.011557493,0.034782104,0.0001684932],"about_ca_topic_score_codex":0.00038360927,"about_ca_topic_score_gemma":0.0009055299,"teacher_disagreement_score":0.70750666,"about_ca_system_score_codex":0.0001541922,"about_ca_system_score_gemma":0.0008171258,"threshold_uncertainty_score":0.9997931},"labels":[],"label_agreement":null},{"id":"W3035076565","doi":"10.1177/1098214020908211","title":"The Role of Intuition in Evaluative Judgment and Decision","year":2020,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Intuition; Psychology; Epistemology; Social psychology; Management science; Cognitive science","score_opus":0.117224265564639,"score_gpt":0.4903323073651327,"score_spread":0.37310804180049373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035076565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895865,0.0006045569,0.005347468,0.0034064255,0.00010905882,0.00022522177,0.0000013720303,0.0000014408243,0.00071796356],"genre_scores_gemma":[0.9975567,0.00022027636,0.0019050192,0.00024877334,0.000056629186,0.00000615874,7.153767e-7,0.0000036588071,0.0000020723571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99465907,0.0008213959,0.001103019,0.00014682273,0.003168671,0.0001010189],"domain_scores_gemma":[0.9948945,0.0018401344,0.0014139205,0.00014526462,0.0016216435,0.00008451859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017182862,0.00007543248,0.00025517697,0.00019015084,0.00007531082,0.00006790161,0.00022471823,0.000017360966,0.00021832598],"category_scores_gemma":[0.004969893,0.000044119635,0.000062386716,0.0008267024,0.00016568601,0.0003705403,0.0000460855,0.00013735265,0.000012833995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024849098,0.000023171644,0.013352024,5.5664515e-7,0.0000107484375,2.4589627e-7,0.0028819425,0.0041808784,0.0012110658,0.00043584962,0.00011694158,0.9775381],"study_design_scores_gemma":[0.001935175,0.0029676268,0.28627208,0.00007812794,0.00007302203,0.000013945601,0.03204533,0.5063393,0.0021438664,0.16524488,0.0027605975,0.00012604451],"about_ca_topic_score_codex":0.000010767681,"about_ca_topic_score_gemma":0.00002768371,"teacher_disagreement_score":0.97741205,"about_ca_system_score_codex":0.00009049195,"about_ca_system_score_gemma":0.00038825124,"threshold_uncertainty_score":0.5955272},"labels":[],"label_agreement":null},{"id":"W3035271094","doi":"10.1177/1098214019899164","title":"Talking Circles: A Culturally Responsive Evaluation Practice","year":2020,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stollery Children's Hospital","funders":"","keywords":"Privilege (computing); Indigenous; Invisibility; Sociology; Power (physics); Stakeholder; Culturally appropriate; Power structure; Psychology; Pedagogy; Social psychology; Public relations; Computer science; Ethnography; Political science; Medicine; Computer security; Artificial intelligence","score_opus":0.22132405977411476,"score_gpt":0.5437861279564394,"score_spread":0.3224620681823247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035271094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90099776,0.0003314499,0.011353708,0.07834337,0.0006390774,0.0007078856,0.000003856951,0.00001746488,0.007605411],"genre_scores_gemma":[0.9849212,0.00005047859,0.008025411,0.006504564,0.00043968868,0.000014222038,0.000006130718,0.000010836416,0.000027451466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9848098,0.0040964973,0.0014770775,0.00032121682,0.009099884,0.00019548845],"domain_scores_gemma":[0.9803633,0.0022893916,0.0034564643,0.00028398054,0.013378401,0.0002284458],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038181048,0.00014796545,0.00038671505,0.0003095923,0.00016546244,0.0002918189,0.0004399312,0.000036146146,0.001908107],"category_scores_gemma":[0.0607248,0.00010905984,0.0001774028,0.0017139709,0.00013011711,0.0021489752,0.000050400457,0.0002899696,0.00026714616],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000684661,0.00006716159,0.0010840201,0.0000020564248,0.000087109125,0.000006539016,0.0133393975,0.02047441,0.004021595,0.00017788357,0.006290049,0.9537651],"study_design_scores_gemma":[0.0053762817,0.006109191,0.11051746,0.00013709613,0.0012465992,0.000427697,0.13663293,0.6473782,0.00122866,0.008371631,0.08194409,0.00063015585],"about_ca_topic_score_codex":0.0000105194795,"about_ca_topic_score_gemma":0.0000060557268,"teacher_disagreement_score":0.95313495,"about_ca_system_score_codex":0.0003153653,"about_ca_system_score_gemma":0.001976588,"threshold_uncertainty_score":0.9990043},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3127477413","doi":"10.1177/1098214020927785","title":"Photo-Based Evaluation: A Method for Participatory Evaluation With Adolescents","year":2021,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Participatory Visual Research Methods","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Participatory evaluation; Transformative learning; Visual methods; Program evaluation; Citizen journalism; Participatory action research; Health promotion; Promotion (chess); Process (computing); Psychology; Youth engagement; Applied psychology; Visual research; Positive Youth Development; Medical education; Evaluation methods; Computer science; Pedagogy; Public relations; Sociology; Public health; Medicine; Nursing; Political science; Developmental psychology; Politics; Social science; Engineering","score_opus":0.6163707543039818,"score_gpt":0.6992086103214732,"score_spread":0.08283785601749138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127477413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77456826,0.00051540596,0.21924306,0.0017037723,0.0004518203,0.002076337,0.000006921427,0.000019327914,0.0014150835],"genre_scores_gemma":[0.9383117,0.000008432097,0.060411666,0.00041867013,0.00036398013,0.0004285024,0.000010450934,0.000023506664,0.000023070554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9743284,0.01827384,0.00067150913,0.00028635355,0.0059442534,0.0004956253],"domain_scores_gemma":[0.98434174,0.0013485505,0.0010416468,0.00029767628,0.012600193,0.00037018638],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08496554,0.00015760961,0.0004085266,0.00023982406,0.0003993198,0.00011326482,0.00021137731,0.000060831695,0.0010738161],"category_scores_gemma":[0.02263942,0.00014206472,0.00017571678,0.0011268769,0.0004109561,0.00042662854,0.000017062528,0.00022393928,0.000007794176],"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":[0.001204725,0.0006302402,0.012022779,0.000040059676,0.0002485381,0.000008535641,0.010569199,0.023627892,0.0070357644,0.0003850641,0.0005886643,0.94363856],"study_design_scores_gemma":[0.010038081,0.0029950477,0.04790047,0.000625626,0.0032447593,0.000018752893,0.02629644,0.87711406,0.018831909,0.005230049,0.007135433,0.00056937255],"about_ca_topic_score_codex":0.00011083819,"about_ca_topic_score_gemma":0.00036927918,"teacher_disagreement_score":0.94306916,"about_ca_system_score_codex":0.001261894,"about_ca_system_score_gemma":0.014118048,"threshold_uncertainty_score":0.99983937},"labels":[],"label_agreement":null},{"id":"W3178131540","doi":"10.1177/1098214020940409","title":"Reviewing Health Service and Program Evaluations in Indigenous Contexts: A Systematic Review","year":2021,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health; Public Health Ontario; University of Toronto; St. Michael's Hospital","funders":"Ontario Ministry of Health and Long-Term Care","keywords":"Indigenous; Reciprocity (cultural anthropology); Public relations; Sociology; Service (business); Management science; Psychology; Political science; Business; Social science; Engineering; Marketing; Ecology","score_opus":0.07921618690179015,"score_gpt":0.4988806023287977,"score_spread":0.41966441542700755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178131540","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":[0.00003926699,0.98752636,0.000013448791,0.00072687294,0.0003521251,0.010925381,0.000005466955,0.00001289168,0.00039817096],"genre_scores_gemma":[0.000012060357,0.99828726,0.00064950075,0.00043410118,0.000291697,0.00017357619,0.000058296602,0.00002930479,0.00006420879],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9797377,0.015010219,0.002952988,0.0003035789,0.001519495,0.00047599862],"domain_scores_gemma":[0.9899327,0.0007829016,0.0061868345,0.0003265427,0.0024839255,0.0002871058],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.03291468,0.00029578176,0.0038616785,0.0004660833,0.0014788116,0.000109697015,0.00030498323,0.00011296825,0.00005230489],"category_scores_gemma":[0.0006448454,0.00022008944,0.00032466117,0.0023569237,0.00015764098,0.0002900007,0.0000031979778,0.00052195083,0.000013117658],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[5.5589504e-7,0.00010714918,0.0000012925763,0.33368227,0.00008165288,0.000002300135,0.067477286,3.5788605e-7,4.9464677e-10,0.00023522515,0.00002213109,0.59838974],"study_design_scores_gemma":[0.00008984207,0.00020488052,0.000004169867,0.5798957,0.0018860763,0.000102502156,0.002296819,0.0000019251065,2.0415336e-9,0.000033976656,0.41533095,0.00015316904],"about_ca_topic_score_codex":0.010800643,"about_ca_topic_score_gemma":0.100594886,"teacher_disagreement_score":0.5982366,"about_ca_system_score_codex":0.0020511413,"about_ca_system_score_gemma":0.09866263,"threshold_uncertainty_score":0.9998211},"labels":[],"label_agreement":null},{"id":"W3183879452","doi":"10.1177/10982140211007573","title":"Understanding Evaluation Policy and Organizational Capacity for Evaluation: An Interview Study","year":2021,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accountability; Context (archaeology); Thematic analysis; Organizational performance; Organizational learning; Capacity building; Conceptual framework; Knowledge management; Management science; Sociology; Psychology; Public relations; Political science; Qualitative research; Computer science; Social science; Economics","score_opus":0.6422351798637937,"score_gpt":0.5788854004605903,"score_spread":0.06334977940320341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183879452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9289254,0.00021879184,0.06434616,0.0037875467,0.0005458596,0.0012783456,0.000012206977,0.000008135012,0.00087753776],"genre_scores_gemma":[0.9942707,0.000030198571,0.0045951298,0.00048678622,0.00046170337,0.00005993485,0.000046733625,0.000016317446,0.000032516156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9855019,0.0053408956,0.001399178,0.00042684833,0.00713083,0.00020034786],"domain_scores_gemma":[0.98027533,0.0012708709,0.001666459,0.00040592122,0.016198924,0.0001824943],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07109134,0.00017498694,0.00044430798,0.00062928384,0.00032558385,0.00040682437,0.00026237557,0.00004136195,0.002225097],"category_scores_gemma":[0.019001095,0.00014403401,0.000107876156,0.0018955696,0.00013831281,0.0012880213,0.000055840268,0.00015008295,0.000010086316],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013870298,0.00075069687,0.030161984,0.000010130127,0.0002319331,0.0000014179823,0.009007017,0.018402869,0.00082093134,0.005143231,0.0005524355,0.93477863],"study_design_scores_gemma":[0.0076018395,0.0033439617,0.14990686,0.000076334494,0.0011011251,0.00017041886,0.056350306,0.6142021,0.0002460723,0.16563192,0.0010140868,0.0003550002],"about_ca_topic_score_codex":0.00001622955,"about_ca_topic_score_gemma":0.00022119076,"teacher_disagreement_score":0.9344236,"about_ca_system_score_codex":0.0012694029,"about_ca_system_score_gemma":0.0047642333,"threshold_uncertainty_score":0.998687},"labels":[],"label_agreement":null},{"id":"W3202036368","doi":"10.1177/1098214021997574","title":"Cocreating an Evaluation Approach for a Healthy Relationships Program With Community Partners: Lessons Learned and Recommendations","year":2021,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Community Health and Development","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Public Health Agency of Canada","keywords":"Community-based participatory research; Participatory action research; Flexibility (engineering); Mental health; Context (archaeology); Program evaluation; Psychology; Process (computing); Medical education; Applied psychology; Sociology; Medicine; Political science; Computer science; Psychiatry","score_opus":0.5453551764340937,"score_gpt":0.6032116774600894,"score_spread":0.05785650102599571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202036368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9518748,0.00030070246,0.02050515,0.02163405,0.00014652027,0.0034291898,0.000017314655,0.000045817167,0.0020464452],"genre_scores_gemma":[0.82589823,0.00013169428,0.17144972,0.0008784857,0.00011148747,0.0007945376,0.00068811193,0.000022379627,0.000025329891],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9831783,0.014673404,0.00094069453,0.00017531823,0.0006870017,0.00034527617],"domain_scores_gemma":[0.99097335,0.0027972597,0.0014570274,0.00038476527,0.004069026,0.00031858782],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.02323759,0.00014678262,0.00038742757,0.00019989701,0.0030590398,0.000039382747,0.00011493515,0.000077277655,0.000062335384],"category_scores_gemma":[0.0038518182,0.00012923565,0.000045410445,0.00060619257,0.00012649441,0.000394597,0.00005006216,0.0014259898,0.0000015304139],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071532966,0.0007659087,0.021456663,0.00018128505,0.000086840664,3.8023376e-7,0.026993662,0.00079220755,0.000027454436,0.000814146,0.00049573736,0.9476704],"study_design_scores_gemma":[0.011815714,0.008786632,0.22390755,0.0010999772,0.00095497683,0.00012623536,0.5677167,0.16818187,0.000021190877,0.009198497,0.0076455474,0.0005450739],"about_ca_topic_score_codex":0.00024885984,"about_ca_topic_score_gemma":0.0013076785,"teacher_disagreement_score":0.9471253,"about_ca_system_score_codex":0.00055802986,"about_ca_system_score_gemma":0.0048836456,"threshold_uncertainty_score":0.99823886},"labels":[],"label_agreement":null},{"id":"W3203032688","doi":"10.1177/10982140211009971","title":"Book Review: <i>Scaling Impact: Innovation for the Public Good</i> by Robert McLean &amp; John Gargani.","year":2021,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"University-Industry-Government Innovation Models","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Sociology; Scaling; Psychology; Management; Economics; Mathematics","score_opus":0.032573228569346045,"score_gpt":0.2951786650114992,"score_spread":0.2626054364421532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203032688","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":[0.28964987,0.048256595,0.31539184,0.33000112,0.0021324328,0.0029225522,0.000052185525,0.00012521983,0.011468199],"genre_scores_gemma":[0.8215511,0.0020640967,0.0015766595,0.16932626,0.0024342497,0.00002529614,0.00046408034,0.00008542109,0.0024728708],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979224,0.00006345781,0.00063888874,0.00016581868,0.0009995706,0.00020983678],"domain_scores_gemma":[0.993817,0.00014501318,0.0018904533,0.00023392006,0.0038971836,0.000016431146],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002929609,0.00014734264,0.0002599896,0.00022059867,0.00024511706,0.00024150543,0.00022424427,0.00005003394,0.0013939291],"category_scores_gemma":[0.0013910643,0.000117530435,0.00012599518,0.0021939625,0.000060191833,0.0019918755,0.00006365744,0.00030562052,0.000020346217],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038100985,0.000097218115,0.0014346377,0.000063200605,0.00016279341,0.0000013715922,0.00003180031,0.00048795412,0.0033176902,0.0022696315,0.9420226,0.05007301],"study_design_scores_gemma":[0.0007681933,0.00003809685,0.000805516,0.00021264206,0.00038327154,0.000020012212,0.00041831715,0.0059322384,0.00022862795,0.00034538042,0.99067056,0.00017713255],"about_ca_topic_score_codex":0.00002993135,"about_ca_topic_score_gemma":0.0000061157484,"teacher_disagreement_score":0.5319012,"about_ca_system_score_codex":0.0004112497,"about_ca_system_score_gemma":0.00026850204,"threshold_uncertainty_score":0.99951893},"labels":[],"label_agreement":null},{"id":"W3208939115","doi":"10.1177/1098214020936769","title":"The Use of Evaluability Assessments in Improving Future Evaluations: A Scoping Review of 10 Years of Literature (2008–2018)","year":2021,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Ambiguity; Psychology; Engineering ethics; Equity (law); Relevance (law); Management science; Political science; Engineering; Computer science","score_opus":0.36142971211574515,"score_gpt":0.6078438813411042,"score_spread":0.24641416922535908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208939115","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009881364,0.99584,0.00024222938,0.00018988179,0.0006852604,0.0019522804,0.000043352764,0.0000019784043,0.00005688611],"genre_scores_gemma":[0.0003083153,0.9953063,0.003974634,0.000062267725,0.00015160312,0.00006913425,0.00005179028,0.000021527148,0.000054398246],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9744276,0.01011017,0.0068402165,0.00047947204,0.007875055,0.00026748597],"domain_scores_gemma":[0.9659846,0.0064841877,0.015390501,0.0012499319,0.010794957,0.00009581108],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06344813,0.00032834813,0.0031116481,0.00087057456,0.00007778259,0.00014513855,0.0008925869,0.00015082397,0.00086246803],"category_scores_gemma":[0.029408274,0.00021049095,0.0009969742,0.0045597735,0.0003184494,0.0008796083,0.00015141127,0.000626304,0.0000051793727],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024954143,0.00010677148,0.000095097384,0.008238254,0.00010957144,0.0000011066107,0.00023233781,0.00023318951,0.0000044521294,0.00001877128,0.00039886317,0.99053663],"study_design_scores_gemma":[0.0012176703,0.0016504569,0.0028988319,0.85312825,0.003162652,0.00008665565,0.0013164841,0.004767446,0.000010773536,0.0004746058,0.13079187,0.00049430144],"about_ca_topic_score_codex":0.000017595657,"about_ca_topic_score_gemma":0.000030167857,"teacher_disagreement_score":0.9900423,"about_ca_system_score_codex":0.0004433475,"about_ca_system_score_gemma":0.010661864,"threshold_uncertainty_score":0.9949468},"labels":[],"label_agreement":null},{"id":"W4235318396","doi":"10.1177/109821400002100306","title":"Planning for Community-based Evaluation","year":2000,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Program evaluation; Unit (ring theory); Management science; Set (abstract data type); Process (computing); Conflict resolution; Process management; Psychology; Computer science; Sociology; Political science; Business; Engineering; Mathematics education; Social science","score_opus":0.355370496696108,"score_gpt":0.5926022913441982,"score_spread":0.2372317946480902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235318396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97119504,0.0000836268,0.021226972,0.0020041321,0.00029903871,0.0005212631,0.0000054459224,0.000007950127,0.0046565332],"genre_scores_gemma":[0.9918718,0.0000048603206,0.006567748,0.0011978636,0.00017642937,0.000042391548,0.000026928317,0.000009950096,0.00010203072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9909324,0.003138678,0.0011117165,0.00014423732,0.0044991253,0.00017383517],"domain_scores_gemma":[0.99139667,0.002398506,0.0012933873,0.00038363825,0.004428474,0.00009931434],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.062370263,0.000115685485,0.00031484058,0.00041459184,0.0003348171,0.0001538117,0.00040411297,0.000030891046,0.0047241133],"category_scores_gemma":[0.0032913194,0.00008755118,0.0001753835,0.000762441,0.00011680328,0.000566063,0.000009255357,0.0002414249,0.0000750351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021897495,0.000075713375,0.0026774323,0.0000016634191,0.000018585042,1.6175443e-7,0.0011870371,0.19519553,0.00016251094,0.000024981127,0.0018481534,0.7985893],"study_design_scores_gemma":[0.003456121,0.0024610232,0.05898298,0.000072969604,0.0002517479,0.00001941933,0.0047213444,0.8889052,0.00042753326,0.015081334,0.025429545,0.00019076462],"about_ca_topic_score_codex":0.0000148748995,"about_ca_topic_score_gemma":0.000009231274,"teacher_disagreement_score":0.7983985,"about_ca_system_score_codex":0.00022742034,"about_ca_system_score_gemma":0.0011802013,"threshold_uncertainty_score":0.9961857},"labels":[],"label_agreement":null},{"id":"W4236526761","doi":"10.1177/109821400002100304","title":"Legal and Ethical Issues in Evaluating Abortion Services","year":2000,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Confidentiality; Abortion; Context (archaeology); Legal service; Ethical issues; Business; Public relations; Internet privacy; Engineering ethics; Law; Political science; Computer science; Engineering","score_opus":0.11986276787814307,"score_gpt":0.5591065619368589,"score_spread":0.43924379405871583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236526761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900986,0.00029406013,0.00013273272,0.0070406115,0.00012900411,0.00014175198,8.290036e-7,0.000004485951,0.0021579326],"genre_scores_gemma":[0.9958149,0.00022006543,0.002666073,0.0010056356,0.00015101218,0.000005525077,0.00000213859,0.0000057686198,0.00012886756],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99332285,0.0015464184,0.0011669644,0.00021043532,0.0035984619,0.00015485342],"domain_scores_gemma":[0.9970525,0.000620799,0.0008187489,0.00018516563,0.0012329656,0.000089848225],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028836446,0.00010239531,0.00032052954,0.00037089852,0.00008690719,0.00020345238,0.0002030708,0.000056470504,0.0034034504],"category_scores_gemma":[0.0010801823,0.00007547455,0.000058909394,0.00082935125,0.00012034892,0.000678344,0.000017605038,0.0003634765,0.00006821895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013182109,0.000028506809,0.025376137,0.000002332999,0.000008594177,0.000001953618,0.0021715008,0.008551056,0.00044560916,0.00019826027,0.00010491324,0.9629793],"study_design_scores_gemma":[0.0014024104,0.0014003959,0.6300365,0.0001092374,0.00005771734,0.000088531335,0.0054929946,0.34554273,0.00014483111,0.009715995,0.0058488324,0.00015985852],"about_ca_topic_score_codex":0.00015605641,"about_ca_topic_score_gemma":0.00017521145,"teacher_disagreement_score":0.96281946,"about_ca_system_score_codex":0.00009328346,"about_ca_system_score_gemma":0.00037113752,"threshold_uncertainty_score":0.9994194},"labels":[],"label_agreement":null},{"id":"W4238820305","doi":"10.1177/109821400402500311","title":"Commentary: Minimizing Evaluation Misuse as Principled Practice","year":2004,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Management science; Computer science; Sociology; Economics","score_opus":0.19120246854867498,"score_gpt":0.5583508310794473,"score_spread":0.3671483625307723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238820305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9330601,0.00020381455,0.0043454445,0.054929424,0.00081259495,0.00060164335,0.0000019138458,0.0000110252195,0.0060340166],"genre_scores_gemma":[0.97375345,0.00007298121,0.018394893,0.007387835,0.0003086499,0.000022560187,0.000011185489,0.000013761724,0.0000346817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9862009,0.0024696267,0.0016136105,0.0003046525,0.009169579,0.00024161076],"domain_scores_gemma":[0.9867216,0.0016192786,0.0033486057,0.00047206273,0.007644819,0.00019364081],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051461488,0.00017284995,0.00039581637,0.0005592022,0.00021796525,0.00025514423,0.00045484534,0.000039214156,0.0018916872],"category_scores_gemma":[0.018853717,0.0001326994,0.0001753346,0.0012355205,0.00015325366,0.0019820663,0.000054701195,0.00027211942,0.0002943819],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077350944,0.0005899616,0.0033749198,0.0000032379733,0.00020190436,0.000012634153,0.008346802,0.104409344,0.0021595808,0.00091072614,0.005471374,0.873746],"study_design_scores_gemma":[0.04039069,0.016870826,0.15368918,0.0006496352,0.0043280437,0.0022360699,0.15548147,0.24369287,0.010188259,0.13898733,0.2315634,0.0019222284],"about_ca_topic_score_codex":0.00010625873,"about_ca_topic_score_gemma":0.000040216244,"teacher_disagreement_score":0.8718238,"about_ca_system_score_codex":0.00094122894,"about_ca_system_score_gemma":0.0022422622,"threshold_uncertainty_score":0.9990207},"labels":[],"label_agreement":null},{"id":"W4244203368","doi":"10.1177/109821400302400106","title":"A Comparison of Three Retrospective Self-reporting Methods of Measuring Change in Instructional Practice","year":2003,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":221,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Satisficing; Psychology; Recall; Retrospective cohort study; Attitude change; Cognition; Behavior change; Intervention (counseling); Social psychology; Applied psychology; Cognitive psychology; Medicine; Computer science","score_opus":0.5729309612507211,"score_gpt":0.5646686413581473,"score_spread":0.008262319892573755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244203368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99300456,0.0007905214,0.0014983182,0.00018718607,0.0004817647,0.00018205862,9.1264656e-7,0.0000043153495,0.0038503413],"genre_scores_gemma":[0.9344466,0.000014883654,0.06542398,0.000030390729,0.0000624457,0.000014355376,3.3679547e-7,0.000005668105,0.0000013776678],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99649954,0.0012942707,0.0013936564,0.000139223,0.0005424889,0.00013079305],"domain_scores_gemma":[0.99283326,0.00031111817,0.005721438,0.00010652035,0.0009920405,0.000035612622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00784766,0.000091148475,0.00054251647,0.00015883056,0.000032386502,0.000003636201,0.00006924453,0.00004249406,0.00022304892],"category_scores_gemma":[0.0026176511,0.000073697774,0.00010109269,0.00056273333,0.00012890955,0.00015007937,0.000011391027,0.00027842514,0.0000011730787],"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":[0.00019227054,0.0005332357,0.7114393,0.000003934733,0.00014441895,0.000003798731,0.0054937666,0.000026396841,0.001226619,0.00079644116,0.000010253244,0.28012958],"study_design_scores_gemma":[0.00066412654,0.0012259871,0.99095505,0.000042242253,0.00019704769,0.0001251501,0.0046962295,0.00004913415,0.00051598967,0.0013325172,0.0001253023,0.00007123447],"about_ca_topic_score_codex":0.00025497464,"about_ca_topic_score_gemma":0.000032054326,"teacher_disagreement_score":0.28005832,"about_ca_system_score_codex":0.00012502963,"about_ca_system_score_gemma":0.000046506997,"threshold_uncertainty_score":0.3133762},"labels":[],"label_agreement":null},{"id":"W4283033908","doi":"10.1177/10982140211056913","title":"Developing Evaluation Approaches for an Anti-Human Trafficking Housing Program","year":2022,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Migration, Health and Trauma","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Formative assessment; Protocol (science); Program evaluation; Evaluation methods; Human trafficking; Public relations; Best practice; Psychology; Process management; Political science; Engineering ethics; Business; Medicine; Engineering; Public administration; Pedagogy; Alternative medicine","score_opus":0.2469876266596626,"score_gpt":0.4708132701818361,"score_spread":0.22382564352217352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283033908","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9838761,0.00026459052,0.01294465,0.0004796814,0.0005585575,0.0015036743,0.000004034421,0.000031260046,0.00033743994],"genre_scores_gemma":[0.9874447,0.0000024579374,0.011383234,0.00018288133,0.00037977417,0.0004636763,0.000107573636,0.00002834615,0.0000073456295],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9963183,0.0014581183,0.0007075237,0.00024030698,0.0009937383,0.0002820482],"domain_scores_gemma":[0.99768686,0.000112929985,0.001233874,0.00017659899,0.0006912638,0.00009848588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0091452645,0.00012625,0.00027028372,0.00032532454,0.0006186764,0.000048926173,0.00015350225,0.000028044218,0.00028991885],"category_scores_gemma":[0.00014004245,0.00012948875,0.0000989467,0.00046899286,0.00006212645,0.0002483322,0.000012743561,0.0002176558,0.000001652178],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013806013,0.00032449025,0.0022705155,0.000012049674,0.000073955554,8.1230183e-7,0.0153601505,0.013756451,0.00010870512,0.0012690349,0.00025751695,0.9664283],"study_design_scores_gemma":[0.010960424,0.020919403,0.45634565,0.00011091176,0.0014966192,0.0005351222,0.1519966,0.3402092,0.00017238884,0.008686041,0.00754875,0.0010189149],"about_ca_topic_score_codex":0.000064146756,"about_ca_topic_score_gemma":0.000082167266,"teacher_disagreement_score":0.96540934,"about_ca_system_score_codex":0.00046716348,"about_ca_system_score_gemma":0.00068376586,"threshold_uncertainty_score":0.52803975},"labels":[],"label_agreement":null},{"id":"W4308916752","doi":"10.1177/10982140211008978","title":"A Comparison of Fidelity Implementation Frameworks Used in the Field of Early Intervention","year":2022,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Family and Disability Support Research","field":"Psychology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Fidelity; Conceptualization; Conceptual framework; Intervention (counseling); Field (mathematics); Management science; Computer science; Quality (philosophy); Knowledge management; Psychology; Sociology; Engineering; Social science","score_opus":0.11013994599000954,"score_gpt":0.5610765366306308,"score_spread":0.4509365906406213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308916752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9967793,0.00008981136,0.0016100244,0.00092559506,0.00014808652,0.0002487543,0.000009177549,0.0000010217547,0.00018820545],"genre_scores_gemma":[0.99967396,9.1163264e-7,0.0001246411,0.00013404537,0.00002054053,0.00002710252,0.000013375452,0.000002965088,0.0000024804542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961308,0.0020735895,0.0007975657,0.0000798006,0.00082039577,0.00009781494],"domain_scores_gemma":[0.9978563,0.00081228005,0.0008958104,0.00017193906,0.00024555653,0.000018122815],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006381253,0.000045165176,0.0002101671,0.00016389016,0.000035214987,0.0000063573452,0.00018353517,0.00002531905,0.0030564377],"category_scores_gemma":[0.00035781716,0.00003708737,0.00011835182,0.00044436488,0.00008398093,0.000078928795,0.000028596058,0.00046328083,0.0000011495748],"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":[0.0005312542,0.0006061941,0.74808514,0.000007817671,0.000039566876,9.242504e-7,0.020133847,0.00039044002,0.00057378237,0.00020918695,0.000895183,0.22852664],"study_design_scores_gemma":[0.0007616846,0.004294024,0.82599264,0.000012676596,0.000040114275,0.00000447481,0.16668093,0.00042481563,0.0002437519,0.0014729521,0.00004039301,0.00003151946],"about_ca_topic_score_codex":0.002274933,"about_ca_topic_score_gemma":0.00019131508,"teacher_disagreement_score":0.22849512,"about_ca_system_score_codex":0.00007140228,"about_ca_system_score_gemma":0.00007454569,"threshold_uncertainty_score":0.9978549},"labels":[],"label_agreement":null},{"id":"W4313250641","doi":"10.1177/10982140221106991","title":"Laying a Solid Foundation for the Next Generation of Evaluation Capacity Building: Findings from an Integrative Review","year":2022,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Scholarship; Foundation (evidence); Capacity building; Engineering ethics; Political science; Management science; Sociology; Public relations; Economics; Engineering; Law","score_opus":0.5281446215139854,"score_gpt":0.552257622583783,"score_spread":0.024113001069797524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313250641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9015306,0.0010050958,0.091588184,0.004145938,0.00058545027,0.0010573332,0.000018860452,0.0000041551,0.000064366504],"genre_scores_gemma":[0.9906204,0.00035422455,0.0072691115,0.0011984244,0.00025343217,0.00021709272,0.000065730135,0.0000100610305,0.000011526881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9903591,0.0032482874,0.0014041963,0.00025772,0.0045760903,0.00015458134],"domain_scores_gemma":[0.99026376,0.001888515,0.0028500063,0.0003619502,0.004568974,0.00006678513],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.053027164,0.0001311702,0.00040036225,0.00028917496,0.0005215689,0.00014869412,0.0004154313,0.000020804539,0.0024085203],"category_scores_gemma":[0.007583005,0.00008701489,0.00019574142,0.00095813203,0.00011778886,0.0011637158,0.000045877347,0.00023967409,0.000003464331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016091141,0.00013380888,0.0024619761,0.000009684613,0.000107082764,1.5612969e-7,0.007180661,0.06890283,0.03453159,0.0005519745,0.0024434708,0.88351583],"study_design_scores_gemma":[0.0008514303,0.0014067297,0.011631107,0.00012776762,0.0005299873,0.00001784637,0.011140413,0.95993745,0.0017130144,0.010845466,0.0016759424,0.00012285398],"about_ca_topic_score_codex":0.00010360429,"about_ca_topic_score_gemma":0.00004166746,"teacher_disagreement_score":0.8910346,"about_ca_system_score_codex":0.00069016573,"about_ca_system_score_gemma":0.0013960135,"threshold_uncertainty_score":0.9985034},"labels":[],"label_agreement":null},{"id":"W4313466224","doi":"10.1177/10982140221079837","title":"Translating Evaluation Policy Into Practice in Government Organizations","year":2022,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Government (linguistics); Policy analysis; Program evaluation; Key (lock); Public policy; Public relations; Evaluation methods; Process management; Business; Public administration; Management science; Political science; Computer science; Economics; Engineering; Computer security","score_opus":0.09400042012462564,"score_gpt":0.5279233762509515,"score_spread":0.4339229561263259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313466224","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9314688,0.00041277302,0.013296736,0.034870066,0.0007694929,0.00094148115,0.000008784366,0.00001104278,0.018220866],"genre_scores_gemma":[0.9923508,0.000025554054,0.006435518,0.00094679795,0.00013041295,0.00004843658,0.000006740344,0.000011838256,0.000043864016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9837594,0.004192274,0.0014390487,0.00023535646,0.010200328,0.00017361563],"domain_scores_gemma":[0.99285966,0.0011798219,0.0022917863,0.0002898601,0.003293045,0.00008583108],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047903053,0.00010933651,0.00026165403,0.0006095027,0.00028858028,0.00008953561,0.0003813397,0.000016148193,0.004845102],"category_scores_gemma":[0.021136971,0.00009665039,0.0000745884,0.0044887555,0.00006463617,0.0010613967,0.00006947502,0.00029845658,0.000025305146],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010941513,0.00021265438,0.007536105,7.48746e-7,0.000024920484,0.0000018660446,0.021180239,0.16030169,0.00053743785,0.00071653136,0.00028031258,0.80909806],"study_design_scores_gemma":[0.004807677,0.0032193826,0.11871657,0.000036161142,0.0004126973,0.00027090378,0.19723642,0.61028856,0.0003141711,0.039136793,0.025105545,0.000455151],"about_ca_topic_score_codex":0.00017893511,"about_ca_topic_score_gemma":0.00011838045,"teacher_disagreement_score":0.8086429,"about_ca_system_score_codex":0.0019494032,"about_ca_system_score_gemma":0.0035748784,"threshold_uncertainty_score":0.9960646},"labels":[],"label_agreement":null},{"id":"W4392775921","doi":"10.1177/10982140241234841","title":"Mapping Evaluation Use: A Scoping Review of Extant Literature (2005–2022)","year":2024,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Extant taxon; Program evaluation; Management science; Evaluation methods; Psychology; Sociology; Political science; Engineering; Public administration","score_opus":0.39634967058603965,"score_gpt":0.6096230452322937,"score_spread":0.21327337464625407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392775921","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047225232,0.99410397,0.00076650654,0.0005753961,0.0015928156,0.00248639,0.00003457269,0.00000987375,0.00038323013],"genre_scores_gemma":[0.00007774415,0.9972134,0.0014383523,0.00033727786,0.0004686073,0.00012360937,0.00010418015,0.000042311916,0.0001944651],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.97617716,0.0058172015,0.0057619554,0.0006198691,0.011292386,0.00033141996],"domain_scores_gemma":[0.9775426,0.0020879463,0.010425425,0.0008989124,0.008858827,0.00018633748],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08210161,0.0004954277,0.003228513,0.0022347497,0.000099798395,0.00047345928,0.00079279626,0.00015114101,0.003571033],"category_scores_gemma":[0.013857627,0.00031171687,0.0012804766,0.0053604445,0.00015733393,0.0012461083,0.00012556795,0.00084522355,0.0001614961],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069015305,0.000032559125,0.000004615372,0.02486003,0.00017081601,0.0000046671103,0.0003594472,0.000053113843,0.0000017470636,0.000021729977,0.0040309858,0.9704534],"study_design_scores_gemma":[0.00022872418,0.00028628894,0.000022891936,0.7237769,0.0032567356,0.0002522659,0.00023331163,0.0031331268,8.0390106e-7,0.00042631428,0.2681032,0.0002794889],"about_ca_topic_score_codex":0.0000038114915,"about_ca_topic_score_gemma":0.000007560161,"teacher_disagreement_score":0.9701739,"about_ca_system_score_codex":0.0007985375,"about_ca_system_score_gemma":0.009483951,"threshold_uncertainty_score":0.9999335},"labels":[],"label_agreement":null},{"id":"W4401375525","doi":"10.1177/10982140241270011","title":"Book Review: Policy Evaluation in the Era of COVID-19","year":2024,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Centre for Disease Control","funders":"","keywords":"Pearl; Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Political science; Virology; Geography; Medicine","score_opus":0.19986347767528487,"score_gpt":0.5871476618453196,"score_spread":0.38728418417003474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401375525","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.147267,0.39099473,0.008882572,0.44158393,0.0012565148,0.002534146,0.000016120302,0.000017927816,0.0074470644],"genre_scores_gemma":[0.94870603,0.01298112,0.00027504427,0.03755402,0.00029484404,0.000044276916,0.000008122796,0.000008253793,0.00012831758],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98712826,0.003899792,0.0016113508,0.0002059854,0.007007598,0.00014701393],"domain_scores_gemma":[0.99414986,0.002147844,0.0012427684,0.00038906094,0.001976645,0.000093823655],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07934207,0.00010844768,0.0003560693,0.0006793414,0.000063066655,0.00011397709,0.00048620315,0.000023782306,0.006224033],"category_scores_gemma":[0.016094755,0.00006176788,0.00018127974,0.0029069297,0.00015809,0.0007257789,0.000023649984,0.00030117904,0.00009106063],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003727634,0.00005679907,0.0006570757,0.000046171263,0.000026230953,0.0000028385537,0.0039832266,0.0081918705,0.00009626506,0.0004368124,0.20840982,0.7780556],"study_design_scores_gemma":[0.0014924032,0.0015590324,0.03590489,0.0014058675,0.00050510524,0.0002480333,0.0067783226,0.24626489,0.00008886047,0.02553803,0.6799645,0.00025006186],"about_ca_topic_score_codex":0.000059734746,"about_ca_topic_score_gemma":0.000021887328,"teacher_disagreement_score":0.801439,"about_ca_system_score_codex":0.0004844193,"about_ca_system_score_gemma":0.0061335247,"threshold_uncertainty_score":0.99950075},"labels":[],"label_agreement":null},{"id":"W4403692227","doi":"10.1177/10982140241287936","title":"Streamlining Complex Intervention Evaluation Through Participatory Systems Mapping and Contribution Analysis: A Comprehensive Framework for Actionable Complexity Evaluation","year":2024,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Participatory evaluation; Intervention (counseling); Citizen journalism; Computer science; Management science; Evaluation methods; Program evaluation; Process management; Risk analysis (engineering); Engineering; Sociology; Business; Political science; Psychology; Public administration; Reliability engineering; Social science","score_opus":0.5525892727434512,"score_gpt":0.5892092362444481,"score_spread":0.036619963500996944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403692227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5252204,0.0022279348,0.46916083,0.0009638118,0.0010321555,0.0012569363,0.000031125925,0.000021597109,0.00008522534],"genre_scores_gemma":[0.98815924,0.00007054201,0.010712041,0.00012984178,0.00039199376,0.00028109137,0.00022754313,0.000016250282,0.000011478663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.987675,0.0037417067,0.0021299892,0.0005419746,0.0056056078,0.0003057007],"domain_scores_gemma":[0.9825975,0.003146724,0.0023491066,0.0003612688,0.011415599,0.00012985153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04410046,0.00024276678,0.00076903345,0.0010585159,0.0003693887,0.00076493726,0.00022009882,0.00009306822,0.0008826406],"category_scores_gemma":[0.0057014143,0.00020110687,0.00041470834,0.0024398416,0.00025375743,0.0016452558,0.000045239103,0.00029316783,0.000021396983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045175847,0.000253033,0.010289513,0.00009045735,0.002610592,0.0000015599466,0.006749615,0.30554366,0.001062126,0.022520877,0.001399612,0.6490272],"study_design_scores_gemma":[0.0012560256,0.00057254,0.06698834,0.00026774203,0.0028552958,0.000019858564,0.0135461325,0.8376714,0.000042319614,0.0748289,0.0017752161,0.00017621028],"about_ca_topic_score_codex":0.00008411087,"about_ca_topic_score_gemma":0.000047255995,"teacher_disagreement_score":0.648851,"about_ca_system_score_codex":0.0009504101,"about_ca_system_score_gemma":0.00088062085,"threshold_uncertainty_score":0.9842997},"labels":[],"label_agreement":null},{"id":"W4413360974","doi":"10.1177/10982140251355140","title":"Theory-Practice Connections in Collaborative Approaches to Evaluation: A Systematic Review of Practice","year":2025,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Systematic review; Management science; Psychology; Evaluation methods; Program evaluation; Peer evaluation; Computer science; Engineering ethics; MEDLINE; Political science; Higher education; Engineering","score_opus":0.31953432024649814,"score_gpt":0.545800497569362,"score_spread":0.22626617732286386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413360974","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0806444,0.1044661,0.14920712,0.3967833,0.0038976045,0.025021022,0.000044010336,0.00003942833,0.23989704],"genre_scores_gemma":[0.97854435,0.0015357384,0.012710321,0.0066717463,0.000053798987,0.00031402492,0.00000451559,0.000008658731,0.00015685736],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97634304,0.014846642,0.0028717134,0.00029137635,0.005487799,0.00015945702],"domain_scores_gemma":[0.965926,0.01338631,0.004552295,0.00056731293,0.015479848,0.00008822717],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13738212,0.00014470372,0.00088759314,0.0010114486,0.00009388689,0.00010160088,0.00041884193,0.000032444863,0.00052454544],"category_scores_gemma":[0.21781065,0.00010444481,0.00013212927,0.006078054,0.00011413006,0.0013545203,0.000048775306,0.00021844589,0.000042805776],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039892998,0.0038562182,0.001801657,0.028361477,0.0027845749,0.000016966682,0.058190223,0.118970685,0.0004553052,0.20682012,0.019400695,0.55535275],"study_design_scores_gemma":[0.0075313547,0.006215972,0.011332629,0.19292821,0.014364318,0.00039571963,0.56356835,0.120796084,0.00070350646,0.06838824,0.012769241,0.0010063997],"about_ca_topic_score_codex":0.000015595484,"about_ca_topic_score_gemma":0.000026999356,"teacher_disagreement_score":0.8978999,"about_ca_system_score_codex":0.0005038938,"about_ca_system_score_gemma":0.0034736386,"threshold_uncertainty_score":0.88824666},"labels":[],"label_agreement":null}]}