{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":60,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":60,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"24b6424d1b26","filters":{"venue":"American Journal of Evaluation"}},"results":[{"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Mary Ann Scheirer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.712236943529094,"gpt":0.7821963698676211,"spread":0.06995942633852714,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02665691,0.0003752391,0.003261998,0.0004796003,0.0003770097,0.000009837236,0.000321043,0.0001173353,0.0002335118],"category_scores_gemma":[0.02149079,0.0002637379,0.0003614933,0.001472382,0.0008869134,0.000253531,0.0001664211,0.001138852,0.000006168965],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.005004627,"about_ca_system_score_gemma":0.01060476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008780414,"about_ca_topic_score_gemma":0.00002244069,"domain_scores_codex":[0.9804281,0.01280642,0.004279534,0.0004183346,0.001459572,0.0006080463],"domain_scores_gemma":[0.9776227,0.006536273,0.007394249,0.0005677367,0.007539903,0.0003391728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002120301,0.0001181748,0.0008095594,0.05437725,0.0001256965,0.000001144687,0.003626607,6.281363e-7,3.836861e-9,0.000007342314,0.03461966,0.9062927],"study_design_scores_gemma":[0.0005359345,0.002419096,0.001156221,0.02110073,0.002321351,0.00001860173,0.01036001,0.0000103013,4.468605e-8,0.0005915622,0.9612755,0.0002106915],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001069148,0.9065609,0.00001446686,0.08415609,0.0001474934,0.007934865,0.00005329953,0.00001333975,0.00005037536],"genre_scores_gemma":[0.0004296494,0.9710518,0.0007456584,0.02678203,0.0002950489,0.0006344077,0.000009899251,0.00002503453,0.00002645341],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9266558,"threshold_uncertainty_score":0.9999815,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Tony C. M. Lam","is_ca":true},{"name":"Priscilla Bengo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5729309612507211,"gpt":0.5646686413581473,"spread":0.008262319892573755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00784766,0.00009114847,0.0005425165,0.0001588306,0.0000323865,0.000003636201,0.00006924453,0.00004249406,0.0002230489],"category_scores_gemma":[0.002617651,0.00007369777,0.0001010927,0.0005627333,0.0001289096,0.0001500794,0.00001139103,0.0002784251,0.000001173079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001250296,"about_ca_system_score_gemma":0.000046507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002549746,"about_ca_topic_score_gemma":0.00003205433,"domain_scores_codex":[0.9964995,0.001294271,0.001393656,0.000139223,0.0005424889,0.0001307931],"domain_scores_gemma":[0.9928333,0.0003111182,0.005721438,0.0001065203,0.0009920405,0.00003561262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001922705,0.0005332357,0.7114393,0.000003934733,0.000144419,0.000003798731,0.005493767,0.00002639684,0.001226619,0.0007964412,0.00001025324,0.2801296],"study_design_scores_gemma":[0.0006641265,0.001225987,0.9909551,0.00004224225,0.0001970477,0.0001251501,0.004696229,0.00004913415,0.0005159897,0.001332517,0.0001253023,0.00007123447],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930046,0.0007905214,0.001498318,0.0001871861,0.0004817647,0.0001820586,9.126466e-7,0.00000431535,0.003850341],"genre_scores_gemma":[0.9344466,0.00001488365,0.06542398,0.00003039073,0.0000624457,0.00001435538,3.367955e-7,0.000005668105,0.000001377668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2800583,"threshold_uncertainty_score":0.3133762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965824013","doi":"10.1177/1098214013478142","title":"The Case for Participatory Evaluation in an Era of Accountability","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jill Anne Chouinard","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3658990701241563,"gpt":0.5819220676204166,"spread":0.2160229974962604,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06152453,0.00008670531,0.0002680563,0.0001731548,0.0001388021,0.0001395658,0.0002852828,0.0000257447,0.0008524447],"category_scores_gemma":[0.006495482,0.00005166707,0.0001018592,0.0006170449,0.0002068225,0.001221398,0.00001850171,0.0001485512,0.00001455976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002291656,"about_ca_system_score_gemma":0.001046737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001816407,"about_ca_topic_score_gemma":0.0008789924,"domain_scores_codex":[0.9933106,0.002223165,0.001491578,0.0001501892,0.002655332,0.0001690883],"domain_scores_gemma":[0.9876441,0.002507981,0.00177697,0.0004105217,0.007575229,0.0000851332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009059246,0.00009918122,0.03286157,0.000001546771,0.00001130706,4.064665e-7,0.002471878,0.009100755,0.0004589886,0.00007705129,0.0002700547,0.9545566],"study_design_scores_gemma":[0.0011462,0.001111472,0.3556952,0.00001653843,0.00007755272,0.00004219375,0.02528007,0.5954453,0.0002970716,0.02062242,0.0001857139,0.00008033651],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956147,0.0001095748,0.001291594,0.001679054,0.0002966348,0.0008882008,0.000002510991,0.000001802988,0.0001158948],"genre_scores_gemma":[0.9986309,0.0000110999,0.0009842381,0.0001272632,0.00008269704,0.0001510222,0.000002187676,0.00000531798,0.000005267404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9544764,"threshold_uncertainty_score":0.966358,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"David Campbell","is_ca":false},{"name":"Michelle Picard-Aitken","is_ca":false},{"name":"Grégoire Côté","is_ca":false},{"name":"Julie Caruso","is_ca":false},{"name":"Rodolfo Valentim","is_ca":true},{"name":"Stuart Edmonds","is_ca":true},{"name":"Gregory Thomas Williams","is_ca":true},{"name":"Benoît Macaluso","is_ca":true},{"name":"Jean-Pierre Robitaille","is_ca":true},{"name":"Nicolas Bastien","is_ca":true},{"name":"Marie-Claude Laframboise","is_ca":true},{"name":"Louis-Michel Lebeau","is_ca":true},{"name":"Philippe Mirabel","is_ca":true},{"name":"Vincent Larivière","is_ca":true},{"name":"Éric Archambault","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8412037386951862,"gpt":0.6852424986880619,"spread":0.1559612400071243,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.4527248,0.0001164576,0.0003399865,0.05198887,0.0008961933,0.0005178658,0.002117989,0.00005729633,0.0004385143],"category_scores_gemma":[0.2843646,0.00006109954,0.0001346539,0.276164,0.00143852,0.000660463,0.0002399223,0.0009501457,0.000003036229],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001164516,"about_ca_system_score_gemma":0.02032653,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05011414,"about_ca_topic_score_gemma":0.04488561,"domain_scores_codex":[0.9233546,0.003144099,0.001804564,0.0004278038,0.07057135,0.0006976436],"domain_scores_gemma":[0.8123634,0.01515173,0.00150251,0.0005794502,0.1701824,0.0002205035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003175146,0.0002070016,0.007173389,0.00001710428,0.0001181739,0.000004183308,0.0004764106,0.003065258,0.007791328,0.0005833893,0.1301453,0.850101],"study_design_scores_gemma":[0.007698217,0.008209094,0.2062774,0.0002282114,0.0003078566,0.001218539,0.01793554,0.5235799,0.04358552,0.0415199,0.1487276,0.0007122461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9880525,0.001068879,0.0004004742,0.00727829,0.0009979452,0.001163878,0.00005838614,0.000001082919,0.0009785158],"genre_scores_gemma":[0.9987945,0.0002174169,0.0003860626,0.00007804685,0.0002649652,0.0001253433,0.000001919392,0.000008879927,0.0001228465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8493888,"threshold_uncertainty_score":0.9852273,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"William M. K. Trochim","is_ca":false},{"name":"Stephen E. Marcus","is_ca":false},{"name":"Louise C. Mâsse","is_ca":true},{"name":"Richard P. Moser","is_ca":false},{"name":"Patrick C. Weld","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8816684527440397,"gpt":0.727468180018336,"spread":0.1542002727257037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.3656344,0.00007352234,0.0002771633,0.02057371,0.0006159107,0.0002704363,0.00123374,0.00003090312,0.0003782494],"category_scores_gemma":[0.2249136,0.00004000981,0.000151052,0.09118454,0.0009350633,0.0007370567,0.0001744744,0.0003724133,0.00004785818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002743431,"about_ca_system_score_gemma":0.002218674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002523443,"about_ca_topic_score_gemma":0.00001130628,"domain_scores_codex":[0.9306285,0.009501756,0.001593362,0.0002975611,0.05746344,0.0005153461],"domain_scores_gemma":[0.9140736,0.01479045,0.001600276,0.0005007997,0.06885068,0.0001842276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001298367,0.0002203134,0.05034644,8.969214e-7,0.00005282047,0.00000363811,0.002031767,0.000862361,0.0009045146,0.0008260244,0.008424918,0.9361964],"study_design_scores_gemma":[0.001321333,0.001622692,0.8919392,0.00001646788,0.00003838969,0.00005981162,0.01014377,0.06581713,0.001415102,0.02350648,0.004031598,0.00008802626],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9891057,0.001834449,0.001439018,0.001238122,0.0003090158,0.0002812435,0.000004714444,0.00000148896,0.005786228],"genre_scores_gemma":[0.9986893,0.0007605782,0.000323713,0.00002475659,0.0001222435,0.000008076996,8.201211e-7,0.000005414658,0.00006509508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9361085,"threshold_uncertainty_score":0.9905273,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Suzanne F. Jackson","is_ca":true},{"name":"Gillian Kolla","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2974231815816114,"gpt":0.6135208376358036,"spread":0.3160976560541922,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.08044642,0.0001415747,0.000533049,0.001323794,0.0001095023,0.0001471727,0.0003528727,0.00003633859,0.009592068],"category_scores_gemma":[0.008161817,0.0001007493,0.000343252,0.004146119,0.00005274584,0.001195702,0.00003159003,0.0001700161,0.0001588976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003798557,"about_ca_system_score_gemma":0.001389211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001176767,"about_ca_topic_score_gemma":0.00005235481,"domain_scores_codex":[0.9862043,0.003609062,0.001451623,0.0002130883,0.008253094,0.0002688432],"domain_scores_gemma":[0.9905058,0.001539608,0.002638974,0.0004734318,0.004504244,0.0003379342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000564718,0.00005386677,0.03920751,5.019984e-7,0.0002852232,2.033798e-7,0.001772269,0.04308439,0.0001658937,0.0003873015,0.003879573,0.9111068],"study_design_scores_gemma":[0.001017387,0.0004586474,0.5332966,0.00001123998,0.004213882,0.00004073945,0.003279864,0.443103,0.0001597274,0.009809973,0.004422669,0.0001862399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2729564,0.0004732068,0.7160211,0.002329892,0.0008939134,0.0003456153,0.000003462476,0.00000912737,0.006967263],"genre_scores_gemma":[0.9390099,0.00001810296,0.05985039,0.0003308245,0.0005459119,0.000008960162,0.00001233311,0.000007946536,0.0002156545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9109206,"threshold_uncertainty_score":0.9913133,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"B. Belcher","is_ca":true},{"name":"Markus Palenberg","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2737634216383244,"gpt":0.5787112819025034,"spread":0.304947860264179,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01181891,0.00006126443,0.0002483221,0.0003475341,0.000067655,0.00004331749,0.0001496351,0.00001190632,0.001016921],"category_scores_gemma":[0.00220232,0.00003933239,0.00009056251,0.0004205721,0.0002053173,0.0004622133,0.00003324825,0.00005454061,0.00003021261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005629722,"about_ca_system_score_gemma":0.0005211114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007969195,"about_ca_topic_score_gemma":0.00003772479,"domain_scores_codex":[0.9966794,0.000327317,0.001015414,0.00009055112,0.00180506,0.00008226833],"domain_scores_gemma":[0.9954387,0.0003576854,0.001524976,0.0001417035,0.002461234,0.00007569888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004291228,0.00006814596,0.2518061,0.000002770231,0.00005665754,2.202018e-7,0.002524343,0.00004020466,0.00048378,0.0002323389,0.0004708661,0.7442716],"study_design_scores_gemma":[0.0005413622,0.0009014718,0.9900609,0.00006337133,0.00004447654,0.00001469398,0.002282281,0.002044455,0.001224651,0.001731304,0.001038453,0.00005263404],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990976,0.0000636114,0.006919491,0.00106276,0.0002295233,0.0000828946,8.281481e-7,0.00000171875,0.0006631245],"genre_scores_gemma":[0.9925541,0.00001350645,0.007161065,0.0001566256,0.00004617428,0.000001714813,6.766589e-7,0.000002849355,0.00006332814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.744219,"threshold_uncertainty_score":0.9998963,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Isabelle Bourgeois","is_ca":true},{"name":"J. Bradley Cousins","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5129125946126178,"gpt":0.4844682783398096,"spread":0.02844431627280825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01910018,0.0001094667,0.0003316766,0.0005714151,0.0001347644,0.00009478243,0.0002615037,0.00003310406,0.008698439],"category_scores_gemma":[0.006523244,0.00007107978,0.0001120218,0.001496452,0.0002100906,0.0009792264,0.00003289757,0.0001383088,0.0001209087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004922193,"about_ca_system_score_gemma":0.001124391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003710673,"about_ca_topic_score_gemma":0.00001639104,"domain_scores_codex":[0.990752,0.001275434,0.001320222,0.0001766352,0.006333304,0.0001423445],"domain_scores_gemma":[0.9866315,0.001033897,0.002368042,0.0002809939,0.009570603,0.0001150139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001624636,0.0007334481,0.2735724,0.00001296341,0.0004161826,0.000001011216,0.01086504,0.1709167,0.04356529,0.0174337,0.02258581,0.4597349],"study_design_scores_gemma":[0.001769225,0.0009835371,0.2806074,0.00006787218,0.0002852064,0.00004969687,0.01304665,0.497262,0.001848736,0.2035649,0.0002909997,0.0002237907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9566416,0.00004203936,0.03805484,0.002062328,0.0004543359,0.0004082503,0.000003051229,0.000004784384,0.002328777],"genre_scores_gemma":[0.995521,0.00001925611,0.004124605,0.0001777771,0.00009882332,0.000009666234,0.00000676589,0.000008409908,0.00003371686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4595112,"threshold_uncertainty_score":0.9922078,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"J. Bradley Cousins","is_ca":true},{"name":"Elizabeth Whitmore","is_ca":true},{"name":"Lyn M. Shulha","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3925397717083799,"gpt":0.5662179449091042,"spread":0.1736781732007242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02986495,0.0001181926,0.0004737499,0.0005855241,0.00006999497,0.00008531129,0.0002877161,0.00003708544,0.0005051129],"category_scores_gemma":[0.006137033,0.00008853722,0.0001253126,0.0009930803,0.0001350084,0.0008650051,0.00002447766,0.00008149468,0.00001168903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002925213,"about_ca_system_score_gemma":0.001271717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002315656,"about_ca_topic_score_gemma":0.00007633395,"domain_scores_codex":[0.993849,0.001068436,0.001714679,0.0002019802,0.002994235,0.0001716621],"domain_scores_gemma":[0.9852949,0.00197222,0.003016125,0.000248715,0.009396606,0.00007141837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004938131,0.0001903483,0.04199456,0.00001398281,0.00008054135,9.910812e-8,0.01138916,0.05161992,0.002236897,0.0005150211,0.003115026,0.8883506],"study_design_scores_gemma":[0.005472619,0.003473912,0.2617393,0.0001106951,0.0001705561,0.000004547064,0.03310417,0.6547024,0.002050935,0.03649376,0.002490915,0.0001861505],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9855835,0.000102092,0.009325097,0.00177112,0.0004096548,0.002485854,0.00001987165,0.000002198318,0.0003005954],"genre_scores_gemma":[0.9892596,0.00001828076,0.009960947,0.0001531373,0.000131214,0.0004107251,0.00002621216,0.00000874278,0.00003114015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8881645,"threshold_uncertainty_score":0.9989582,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Lyn M. Shulha","is_ca":true},{"name":"Elizabeth Whitmore","is_ca":true},{"name":"J. Bradley Cousins","is_ca":true},{"name":"Nathalie Gilbert","is_ca":true},{"name":"Hind Al Hudib","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7348226152021603,"gpt":0.5424577550404095,"spread":0.1923648601617508,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09005673,0.00018906,0.0004794211,0.001061587,0.0001303295,0.0003426085,0.0005788046,0.00003429236,0.000530261],"category_scores_gemma":[0.05560831,0.0001394142,0.0001044191,0.003529464,0.00008974852,0.001225446,0.00007743132,0.0001580605,0.0002979069],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001315909,"about_ca_system_score_gemma":0.007342648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003400631,"about_ca_topic_score_gemma":0.00008961079,"domain_scores_codex":[0.9845526,0.003286108,0.001676173,0.0004574558,0.009769458,0.0002582335],"domain_scores_gemma":[0.9818253,0.001413906,0.001757223,0.0006011417,0.01389129,0.0005111447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002709892,0.00005035221,0.005213894,0.00000105605,0.00002065281,5.165302e-7,0.004744051,0.5909342,0.0003893224,0.0001370567,0.005956969,0.3922809],"study_design_scores_gemma":[0.002376435,0.006349791,0.06663498,0.0003442035,0.0003282595,0.0000223358,0.03759166,0.8416412,0.00409086,0.003357396,0.03677141,0.0004914458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8650076,0.0003391762,0.0882647,0.04064131,0.0009562429,0.001511791,0.000004499857,0.00001352259,0.003261164],"genre_scores_gemma":[0.9325728,0.000007090922,0.06502344,0.001676617,0.000465706,0.00009321354,0.000004655772,0.00001302738,0.000143454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3917895,"threshold_uncertainty_score":0.9982848,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jill Anne Chouinard","is_ca":true},{"name":"J. Bradley Cousins","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7361957222054291,"gpt":0.7346471200265722,"spread":0.001548602178856884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1191189,0.0003175057,0.002365414,0.001395263,0.0001710475,0.000255148,0.0007011705,0.00008867722,0.0009152797],"category_scores_gemma":[0.03049247,0.0001888157,0.0005612478,0.002543577,0.0005078126,0.0006769135,0.00006806621,0.0007822441,0.00009445599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006106913,"about_ca_system_score_gemma":0.003327705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004788079,"about_ca_topic_score_gemma":0.000002874372,"domain_scores_codex":[0.974152,0.01058938,0.003420741,0.000498248,0.01105617,0.0002834448],"domain_scores_gemma":[0.9716466,0.005050879,0.006201261,0.0006613212,0.01626614,0.000173782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001808252,0.0001043053,0.0000175072,0.001121842,0.00005718975,3.051532e-7,0.00007649527,0.00005397061,2.785934e-7,0.00006813002,0.003139482,0.9953424],"study_design_scores_gemma":[0.0006013511,0.002145902,0.001269944,0.06750464,0.004462082,0.0001121816,0.0003577375,0.001326686,0.00000426264,0.002355332,0.9194903,0.0003695094],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0006474273,0.9958079,0.00002392702,0.0004083481,0.0003158376,0.001442143,0.00001510921,0.000003089044,0.001336167],"genre_scores_gemma":[0.003773641,0.9955565,0.0001841631,0.0001048791,0.0002221783,0.00010278,0.00001517302,0.00001545522,0.00002526866],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9949729,"threshold_uncertainty_score":0.999998,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Pierre‐Marc Daigneault","is_ca":true},{"name":"Steve Jacob","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4707113104953488,"gpt":0.5611236037354239,"spread":0.0904122932400751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02276424,0.00007913479,0.0002948112,0.0003133779,0.00004212512,0.00005270194,0.0002312923,0.00001694988,0.0006678664],"category_scores_gemma":[0.003880369,0.00005478636,0.0001164886,0.0007517223,0.00006342238,0.0005492119,0.000009329701,0.00008661609,0.00003169234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001502371,"about_ca_system_score_gemma":0.000623695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000507098,"about_ca_topic_score_gemma":0.000005024785,"domain_scores_codex":[0.9921066,0.0007285755,0.001265661,0.0001208857,0.005658485,0.0001198154],"domain_scores_gemma":[0.9915583,0.0002192163,0.002273276,0.0002174012,0.005648042,0.00008381377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001253737,0.000120526,0.003821034,0.000001015011,0.00002256329,5.35994e-7,0.001429627,0.01368689,0.00638711,0.0002791448,0.0008410622,0.9732851],"study_design_scores_gemma":[0.001625315,0.004344353,0.8773189,0.00007562724,0.0001972032,0.00001964719,0.003361814,0.07993228,0.01064777,0.02052394,0.001775585,0.0001775646],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9687301,0.0001132567,0.02399151,0.004417715,0.0002842521,0.0001636147,9.294852e-7,0.000003671812,0.002294953],"genre_scores_gemma":[0.997949,0.00002591848,0.001621586,0.0002951204,0.00008811981,0.000002574846,9.071384e-7,0.000002686182,0.00001409144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9731076,"threshold_uncertainty_score":0.7889678,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Martha A. Brown","is_ca":false},{"name":"Sherri Di Lallo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2213240597741148,"gpt":0.5437861279564394,"spread":0.3224620681823247,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03818105,0.0001479654,0.0003867151,0.0003095923,0.0001654624,0.0002918189,0.0004399312,0.00003614615,0.001908107],"category_scores_gemma":[0.0607248,0.0001090598,0.0001774028,0.001713971,0.0001301171,0.002148975,0.00005040046,0.0002899696,0.0002671462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003153653,"about_ca_system_score_gemma":0.001976588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001051948,"about_ca_topic_score_gemma":0.000006055727,"domain_scores_codex":[0.9848098,0.004096497,0.001477077,0.0003212168,0.009099884,0.0001954885],"domain_scores_gemma":[0.9803633,0.002289392,0.003456464,0.0002839805,0.0133784,0.0002284458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000684661,0.00006716159,0.00108402,0.000002056425,0.00008710913,0.000006539016,0.0133394,0.02047441,0.004021595,0.0001778836,0.006290049,0.9537651],"study_design_scores_gemma":[0.005376282,0.006109191,0.1105175,0.0001370961,0.001246599,0.000427697,0.1366329,0.6473782,0.00122866,0.008371631,0.08194409,0.0006301558],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9009978,0.0003314499,0.01135371,0.07834337,0.0006390774,0.0007078856,0.000003856951,0.00001746488,0.007605411],"genre_scores_gemma":[0.9849212,0.00005047859,0.008025411,0.006504564,0.0004396887,0.00001422204,0.000006130718,0.00001083642,0.00002745147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.953135,"threshold_uncertainty_score":0.9990043,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Pernelle Smits","is_ca":true},{"name":"François Champagne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3684489379509288,"gpt":0.6248471033074683,"spread":0.2563981653565395,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03925495,0.0001146837,0.0004232621,0.0002595725,0.0001343651,0.00002867775,0.0004179497,0.00004117019,0.002068158],"category_scores_gemma":[0.006563201,0.00006768478,0.0001947159,0.000962702,0.001159199,0.0006759283,0.00004285508,0.0002427294,0.000005732771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001991532,"about_ca_system_score_gemma":0.003895509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009599368,"about_ca_topic_score_gemma":0.00000506154,"domain_scores_codex":[0.9849417,0.004490572,0.001699799,0.0001763577,0.008526938,0.0001645891],"domain_scores_gemma":[0.9886523,0.001465483,0.00336024,0.0005662707,0.005838268,0.0001173768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004904929,0.001814525,0.5240415,0.00001231758,0.000255272,0.000003147713,0.01305311,0.08304765,0.01791772,0.05378032,0.001860883,0.3037231],"study_design_scores_gemma":[0.0008375976,0.00142977,0.6306115,0.00003386106,0.0002329824,0.00006556228,0.004369862,0.3435299,0.00193562,0.01679327,0.00007942671,0.00008065625],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9814907,0.00003157363,0.01361076,0.002416156,0.0003237666,0.0003216363,0.000002153018,0.000002682234,0.00180054],"genre_scores_gemma":[0.9947462,0.00001950275,0.004898443,0.0002239901,0.0000836296,0.00001150484,0.00000169863,0.00000774221,0.000007267462],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3036425,"threshold_uncertainty_score":0.9988441,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Marcel D’Eon","is_ca":true},{"name":"Leslie Sadownik","is_ca":true},{"name":"Alexandra Harrison","is_ca":true},{"name":"Jill Nation","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2077316628935172,"gpt":0.5490251839928058,"spread":0.3412935210992886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001268777,0.00008134867,0.0001911866,0.0002856134,0.0001696018,0.00001562298,0.0002286344,0.00002892061,0.001005049],"category_scores_gemma":[0.0001414133,0.00008006016,0.00006282853,0.0006232085,0.00005125233,0.0001225316,0.00002311462,0.0002065507,0.00005731148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003494075,"about_ca_system_score_gemma":0.0005502186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001360689,"about_ca_topic_score_gemma":0.00001999902,"domain_scores_codex":[0.9980091,0.0007319096,0.0004989687,0.0001142442,0.000488513,0.0001572469],"domain_scores_gemma":[0.9976409,0.0002010849,0.0006837687,0.0003474801,0.0009653667,0.0001614155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003702405,0.0005274757,0.1271911,0.000009405673,0.0002855601,0.0000128943,0.04010272,0.002057989,0.0007823758,0.0003624463,0.009171954,0.8191258],"study_design_scores_gemma":[0.001405333,0.00105787,0.9662002,0.00009833491,0.0001793525,0.0008461799,0.01669606,0.001908667,0.00008593634,0.0004171952,0.01080734,0.0002975349],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9857823,0.000252695,0.008492531,0.002211454,0.0008913256,0.0002034763,8.087782e-7,0.00001480777,0.002150582],"genre_scores_gemma":[0.9626825,0.00005365141,0.03612127,0.0008218822,0.0002184056,0.00001450243,0.00000178561,0.00001329922,0.00007263539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.839009,"threshold_uncertainty_score":0.9999081,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Isabelle Bourgeois","is_ca":true},{"name":"Sebastian Lemire","is_ca":false},{"name":"Leslie A. Fierro","is_ca":true},{"name":"Ann Marie Castleman","is_ca":false},{"name":"Minji Cho","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5281446215139854,"gpt":0.552257622583783,"spread":0.02411300106979752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05302716,0.0001311702,0.0004003622,0.000289175,0.0005215689,0.0001486941,0.0004154313,0.00002080454,0.00240852],"category_scores_gemma":[0.007583005,0.00008701489,0.0001957414,0.000958132,0.0001177889,0.001163716,0.00004587735,0.0002396741,0.000003464331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006901657,"about_ca_system_score_gemma":0.001396014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001036043,"about_ca_topic_score_gemma":0.00004166746,"domain_scores_codex":[0.9903591,0.003248287,0.001404196,0.00025772,0.00457609,0.0001545813],"domain_scores_gemma":[0.9902638,0.001888515,0.002850006,0.0003619502,0.004568974,0.00006678513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001609114,0.0001338089,0.002461976,0.000009684613,0.0001070828,1.561297e-7,0.007180661,0.06890283,0.03453159,0.0005519745,0.002443471,0.8835158],"study_design_scores_gemma":[0.0008514303,0.00140673,0.01163111,0.0001277676,0.0005299873,0.00001784637,0.01114041,0.9599375,0.001713014,0.01084547,0.001675942,0.000122854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9015306,0.001005096,0.09158818,0.004145938,0.0005854503,0.001057333,0.00001886045,0.0000041551,0.0000643665],"genre_scores_gemma":[0.9906204,0.0003542246,0.007269111,0.001198424,0.0002534322,0.0002170927,0.00006573014,0.00001006103,0.00001152688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8910346,"threshold_uncertainty_score":0.9985034,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Lynda Rey","is_ca":true},{"name":"Marie‐Claude Tremblay","is_ca":true},{"name":"Astrid Brousselle","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4777265607402056,"gpt":0.6157514516411698,"spread":0.1380248909009642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0714384,0.00009767957,0.0002996108,0.001007779,0.0002824999,0.000345456,0.0002885809,0.00003088338,0.002648975],"category_scores_gemma":[0.007943246,0.00006804329,0.0000693434,0.001450344,0.0002749547,0.001163496,0.00007774925,0.0003136753,0.0002954354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002051427,"about_ca_system_score_gemma":0.0006851025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008395674,"about_ca_topic_score_gemma":0.00001099213,"domain_scores_codex":[0.9870958,0.003116668,0.001003921,0.0002454733,0.008301758,0.0002364139],"domain_scores_gemma":[0.9841439,0.002339619,0.0009366369,0.0003390058,0.0120529,0.0001879187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000009274296,0.00001772143,0.03604556,8.460693e-7,0.00002069804,2.988441e-7,0.0008528112,0.0009483931,0.0004935671,0.00010987,0.00267784,0.9588231],"study_design_scores_gemma":[0.0007420568,0.0007018202,0.7268568,0.00004206871,0.0001018288,0.00002521892,0.009414387,0.1674901,0.0001289241,0.09252984,0.001857337,0.0001096267],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802135,0.0001993876,0.002174156,0.01175668,0.0002013404,0.0005508481,8.954883e-7,0.000004927162,0.004898242],"genre_scores_gemma":[0.9969881,0.00006887534,0.002331134,0.0001933768,0.0002484659,0.00002850989,0.000003385901,0.00000810423,0.0001300541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9587135,"threshold_uncertainty_score":0.9982628,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Program evaluation; Management science; Actuarial science; Applied psychology; Business; Political science; Economics; Public administration","authors":[{"name":"Katherine Ruff","is_ca":true},{"name":"Sara Olsen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3492754177554118,"gpt":0.5984297125613699,"spread":0.2491542948059581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04775453,0.00007351833,0.0002204141,0.0003000538,0.0002853643,0.0001512382,0.0002929288,0.00001620194,0.0002514507],"category_scores_gemma":[0.004443418,0.00003869888,0.0001715722,0.0009753183,0.000172395,0.0002877351,0.00001441349,0.00008366511,0.00002319799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004200279,"about_ca_system_score_gemma":0.0009987229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002001419,"about_ca_topic_score_gemma":0.0002343681,"domain_scores_codex":[0.9942046,0.0007885481,0.0008783338,0.0001121057,0.003849337,0.0001670799],"domain_scores_gemma":[0.9922832,0.0006376207,0.001266314,0.0001572156,0.00560306,0.00005255495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004314544,0.00004743732,0.02031304,4.281271e-7,0.00005942113,1.761869e-7,0.001836607,0.001042419,0.0009110133,0.0001711993,0.009870947,0.9653159],"study_design_scores_gemma":[0.002156125,0.002726547,0.8254433,0.00002024736,0.0001015038,0.00000992085,0.007832703,0.130376,0.0003627531,0.02266207,0.00817663,0.0001321743],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825596,0.0000785483,0.009103552,0.006392791,0.0004240537,0.0003005359,0.000001580692,0.000002129564,0.00113718],"genre_scores_gemma":[0.9987721,0.000008117022,0.0004664342,0.0001909904,0.0005188208,0.00001161951,6.258254e-7,0.000004204453,0.0000271215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9651837,"threshold_uncertainty_score":0.9805371,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Chi Yan Lam","is_ca":true},{"name":"Lyn M. Shulha","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3573519414879998,"gpt":0.5543062644225002,"spread":0.1969543229345004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02948773,0.0001271248,0.0003108129,0.0006763423,0.0002237846,0.000139524,0.0002498607,0.00003009329,0.0003482328],"category_scores_gemma":[0.0106585,0.00009235309,0.0001019309,0.001081292,0.00007460052,0.000587508,0.00002170007,0.0001243008,0.00003358059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005510459,"about_ca_system_score_gemma":0.001353875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005514293,"about_ca_topic_score_gemma":0.000009420181,"domain_scores_codex":[0.9924273,0.001099447,0.001266767,0.0002274849,0.004824639,0.0001543502],"domain_scores_gemma":[0.9901794,0.001384525,0.002165396,0.0001898382,0.006005756,0.00007515246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001011681,0.00004927513,0.002340295,0.000001382207,0.00002488618,8.615216e-8,0.000983902,0.03410359,0.003911706,0.0009134166,0.000354244,0.957216],"study_design_scores_gemma":[0.001746711,0.001271156,0.02380433,0.00005997321,0.00008945526,0.00001832487,0.00278479,0.9470034,0.00164949,0.01836389,0.003052178,0.0001562494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9296078,0.0000188831,0.06633253,0.0005001735,0.0005733205,0.0004174916,9.793494e-7,0.000004641747,0.002544188],"genre_scores_gemma":[0.9637597,0.000001576526,0.03519446,0.0006737629,0.000315431,0.00001922778,0.000006679888,0.00001052165,0.00001860453],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9570598,"threshold_uncertainty_score":0.9993466,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"James C. McDavid","is_ca":true},{"name":"Irene Huse","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2353065547670905,"gpt":0.4390290283376902,"spread":0.2037224735705997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007472538,0.00004047832,0.0001306701,0.0001813705,0.0001181285,0.0000281847,0.0001303719,0.00001982857,0.0006501031],"category_scores_gemma":[0.002281778,0.00003490921,0.0000541476,0.0004537871,0.0004890444,0.0006615245,0.000010154,0.00008984668,0.000003095719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006747455,"about_ca_system_score_gemma":0.002133624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004839952,"about_ca_topic_score_gemma":0.00009276404,"domain_scores_codex":[0.9977908,0.0005307609,0.0004094205,0.00006208854,0.001045431,0.0001615197],"domain_scores_gemma":[0.9976074,0.00008352325,0.0009230523,0.0001025064,0.001144142,0.0001393888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00009301938,0.0004234661,0.2680101,0.00001292562,0.0001344299,0.0000203406,0.03655045,0.00001899789,0.001004379,0.01942324,0.001863101,0.6724455],"study_design_scores_gemma":[0.000758535,0.003274263,0.8912675,0.0001015625,0.0001182901,0.0001920319,0.0283821,0.0006285807,0.005271524,0.00788349,0.06179137,0.0003307034],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9582841,0.00003806822,0.0001540441,0.001134929,0.0001382673,0.00007830625,6.514276e-7,0.000004294037,0.04016737],"genre_scores_gemma":[0.998984,0.00007331964,0.0005878127,0.00005715041,0.0001557658,0.000002651349,5.769373e-7,0.000003032125,0.0001356454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6721148,"threshold_uncertainty_score":0.7118174,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jenna van Draanen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2742311431016408,"gpt":0.5920985262212245,"spread":0.3178673831195837,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09055249,0.0001257669,0.0003259061,0.0006271381,0.0001223249,0.0001476205,0.0003868745,0.00002727156,0.00290052],"category_scores_gemma":[0.06624832,0.00007161531,0.0001135546,0.001342331,0.00009278153,0.001878579,0.0000547221,0.0001244341,0.0005750011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006600155,"about_ca_system_score_gemma":0.001374447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001592721,"about_ca_topic_score_gemma":0.00002255696,"domain_scores_codex":[0.9863702,0.003356433,0.001315626,0.0003397844,0.008401768,0.0002161953],"domain_scores_gemma":[0.9823862,0.002962429,0.002234655,0.0005467267,0.01166898,0.0002009665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002250011,0.00005731218,0.001591134,3.925302e-7,0.0000264272,7.10386e-7,0.0009156074,0.004240171,0.007446389,0.0002206645,0.004216145,0.98106],"study_design_scores_gemma":[0.01141051,0.01407316,0.4623476,0.0005768739,0.001693052,0.0006814192,0.02728199,0.1015814,0.01488805,0.07719248,0.28682,0.001453446],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.854856,0.00007019765,0.07263486,0.06347413,0.0012168,0.0005208367,0.000002706035,0.00001044464,0.007214026],"genre_scores_gemma":[0.9784046,0.00002437414,0.01923585,0.001618274,0.0005298529,0.00001915708,9.498153e-7,0.000009457117,0.0001575186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9796066,"threshold_uncertainty_score":0.998011,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Sherri Bisset","is_ca":true},{"name":"Mark Daniel","is_ca":true},{"name":"Louise Potvin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8024925403175549,"gpt":0.7139293653214512,"spread":0.08856317499610367,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01063568,0.00006901781,0.0001794797,0.0001484336,0.0003621348,0.00001400243,0.0002108499,0.00001068414,0.0004735535],"category_scores_gemma":[0.003088569,0.00004521157,0.0000695921,0.0004552,0.00009509247,0.0005470156,0.00002041493,0.0003760495,0.0001148455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003273035,"about_ca_system_score_gemma":0.000466223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000100398,"about_ca_topic_score_gemma":0.00005084522,"domain_scores_codex":[0.9954991,0.002405629,0.001023287,0.00008710184,0.0007262776,0.0002585693],"domain_scores_gemma":[0.9961103,0.001139697,0.001467573,0.0001649342,0.001004325,0.000113224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006350529,0.00001990695,0.00152907,0.000005497428,0.00001238593,5.344424e-7,0.02701365,0.00009309717,0.0004070413,0.0003994392,0.004646824,0.965809],"study_design_scores_gemma":[0.003786505,0.003852329,0.6826535,0.0007306382,0.0001363461,0.00005436165,0.2142536,0.002114371,0.0006359386,0.003600823,0.08792953,0.000252009],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9495773,0.00004164516,0.008279584,0.04007573,0.0007812098,0.0003730703,0.000001592563,0.000009338962,0.0008605498],"genre_scores_gemma":[0.9889599,0.00003163684,0.0004452308,0.01014105,0.0003191893,0.00002857655,4.247173e-7,0.000004924675,0.00006903907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.965557,"threshold_uncertainty_score":0.5185078,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Colleen Duggan","is_ca":true},{"name":"Kenneth Bush","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1709391473582322,"gpt":0.5305063413621447,"spread":0.3595671940039125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06623144,0.00009237957,0.0003533835,0.0003560708,0.000107383,0.0000810874,0.0004307726,0.00004890933,0.0003315472],"category_scores_gemma":[0.02091448,0.00005319772,0.0001225884,0.000918387,0.0003102502,0.0002444209,0.00003661621,0.000372753,0.00003740172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009960783,"about_ca_system_score_gemma":0.0005958839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002308513,"about_ca_topic_score_gemma":0.00006439133,"domain_scores_codex":[0.9902571,0.003298657,0.001551049,0.0001542243,0.004569861,0.0001690545],"domain_scores_gemma":[0.9897972,0.004575419,0.002650918,0.0003268758,0.002571414,0.00007811784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001645737,0.00005105074,0.04854803,0.000002090342,0.00002796799,3.938782e-7,0.002245365,0.007588828,0.0006303901,0.003010751,0.0009338136,0.9367967],"study_design_scores_gemma":[0.001973331,0.00166022,0.6225384,0.0001215376,0.00007932783,0.00003361523,0.007795542,0.3185892,0.0006269467,0.03457974,0.01182913,0.0001728862],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9824148,0.0001150778,0.005631241,0.00953013,0.0004374113,0.0001641932,5.41453e-7,0.000002406751,0.001704238],"genre_scores_gemma":[0.997949,0.00006562105,0.001223085,0.0006066838,0.0001099364,0.000004964359,5.781604e-7,0.000005451012,0.00003465832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9366239,"threshold_uncertainty_score":0.9873328,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Steve Jacob","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2784832306773482,"gpt":0.5746443419319662,"spread":0.296161111254618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0233068,0.0001539974,0.0003979249,0.0005201458,0.0004021183,0.0001923397,0.0004576409,0.0000430967,0.003820667],"category_scores_gemma":[0.006783783,0.0001159314,0.0002466225,0.001263135,0.0002324815,0.001187666,0.0000388299,0.0001299725,0.00009066455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002781866,"about_ca_system_score_gemma":0.003654215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001476363,"about_ca_topic_score_gemma":0.00001845535,"domain_scores_codex":[0.9909388,0.0007187479,0.00154122,0.0002994675,0.006284186,0.0002175095],"domain_scores_gemma":[0.9870718,0.0009452715,0.002296606,0.0004118052,0.009064811,0.0002096677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004446738,0.000177891,0.06797379,0.000003169107,0.00009690419,0.000002322555,0.006549357,0.1139909,0.0004107434,0.0008017536,0.02399519,0.7855533],"study_design_scores_gemma":[0.007515629,0.002455994,0.4717497,0.00003966225,0.0003004572,0.0003063045,0.002725441,0.4497278,0.000543059,0.04557355,0.01869688,0.0003654683],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9142166,0.0001860889,0.07712578,0.004286835,0.001019204,0.000773086,0.000006413502,0.00001080858,0.002375198],"genre_scores_gemma":[0.9880214,0.00002724109,0.009464083,0.0004095201,0.0007562141,0.00003797961,0.00002224966,0.00001457347,0.001246709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7851878,"threshold_uncertainty_score":0.99709,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Management science; Computer science; Sociology; Economics","authors":[{"name":"J. Bradley Cousins","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.191202468548675,"gpt":0.5583508310794473,"spread":0.3671483625307723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05146149,0.0001728499,0.0003958164,0.0005592022,0.0002179653,0.0002551442,0.0004548453,0.00003921416,0.001891687],"category_scores_gemma":[0.01885372,0.0001326994,0.0001753346,0.00123552,0.0001532537,0.001982066,0.0000547012,0.0002721194,0.0002943819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009412289,"about_ca_system_score_gemma":0.002242262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001062587,"about_ca_topic_score_gemma":0.00004021624,"domain_scores_codex":[0.9862009,0.002469627,0.001613611,0.0003046525,0.009169579,0.0002416108],"domain_scores_gemma":[0.9867216,0.001619279,0.003348606,0.0004720627,0.007644819,0.0001936408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007735094,0.0005899616,0.00337492,0.000003237973,0.0002019044,0.00001263415,0.008346802,0.1044093,0.002159581,0.0009107261,0.005471374,0.873746],"study_design_scores_gemma":[0.04039069,0.01687083,0.1536892,0.0006496352,0.004328044,0.00223607,0.1554815,0.2436929,0.01018826,0.1389873,0.2315634,0.001922228],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9330601,0.0002038145,0.004345444,0.05492942,0.000812595,0.0006016433,0.000001913846,0.00001102522,0.006034017],"genre_scores_gemma":[0.9737535,0.00007298121,0.01839489,0.007387835,0.0003086499,0.00002256019,0.00001118549,0.00001376172,0.0000346817],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8718238,"threshold_uncertainty_score":0.9990207,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Colombe Lemire","is_ca":true},{"name":"Michel Rousseau","is_ca":true},{"name":"Carmen Dionne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1101399459900095,"gpt":0.5610765366306308,"spread":0.4509365906406213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006381253,0.00004516518,0.0002101671,0.0001638902,0.00003521499,0.000006357345,0.0001835352,0.00002531905,0.003056438],"category_scores_gemma":[0.0003578172,0.00003708737,0.0001183518,0.0004443649,0.00008398093,0.0000789288,0.00002859606,0.0004632808,0.000001149575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007140228,"about_ca_system_score_gemma":0.00007454569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002274933,"about_ca_topic_score_gemma":0.0001913151,"domain_scores_codex":[0.9961308,0.002073589,0.0007975657,0.0000798006,0.0008203958,0.00009781494],"domain_scores_gemma":[0.9978563,0.0008122801,0.0008958104,0.0001719391,0.0002455565,0.00001812282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005312542,0.0006061941,0.7480851,0.000007817671,0.00003956688,9.242504e-7,0.02013385,0.00039044,0.0005737824,0.000209187,0.000895183,0.2285266],"study_design_scores_gemma":[0.0007616846,0.004294024,0.8259926,0.0000126766,0.00004011428,0.00000447481,0.1666809,0.0004248156,0.0002437519,0.001472952,0.00004039301,0.00003151946],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967793,0.00008981136,0.001610024,0.0009255951,0.0001480865,0.0002487543,0.000009177549,0.000001021755,0.0001882054],"genre_scores_gemma":[0.999674,9.116326e-7,0.0001246411,0.0001340454,0.00002054053,0.00002710252,0.00001337545,0.000002965088,0.000002480454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2284951,"threshold_uncertainty_score":0.9978549,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Raglan Maddox","is_ca":true},{"name":"Genevieve Blais","is_ca":true},{"name":"Angela Mashford‐Pringle","is_ca":false},{"name":"Renée Monchalin","is_ca":true},{"name":"Michelle Firestone","is_ca":true},{"name":"Carolyn Ziegler","is_ca":true},{"name":"Melody E. Morton Ninomiya","is_ca":true},{"name":"Janet Smylie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07921618690179015,"gpt":0.4988806023287977,"spread":0.4196644154270076,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.03291468,0.0002957818,0.003861679,0.0004660833,0.001478812,0.000109697,0.0003049832,0.0001129682,0.00005230489],"category_scores_gemma":[0.0006448454,0.0002200894,0.0003246612,0.002356924,0.000157641,0.0002900007,0.000003197978,0.0005219508,0.00001311766],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002051141,"about_ca_system_score_gemma":0.09866263,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01080064,"about_ca_topic_score_gemma":0.1005949,"domain_scores_codex":[0.9797377,0.01501022,0.002952988,0.0003035789,0.001519495,0.0004759986],"domain_scores_gemma":[0.9899327,0.0007829016,0.006186835,0.0003265427,0.002483926,0.0002871058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[5.55895e-7,0.0001071492,0.000001292576,0.3336823,0.00008165288,0.000002300135,0.06747729,3.578861e-7,4.946468e-10,0.0002352251,0.00002213109,0.5983897],"study_design_scores_gemma":[0.00008984207,0.0002048805,0.000004169867,0.5798957,0.001886076,0.0001025022,0.002296819,0.000001925107,2.041534e-9,0.00003397666,0.4153309,0.000153169],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003926699,0.9875264,0.00001344879,0.0007268729,0.0003521251,0.01092538,0.000005466955,0.00001289168,0.000398171],"genre_scores_gemma":[0.00001206036,0.9982873,0.0006495008,0.0004341012,0.000291697,0.0001735762,0.0000582966,0.00002930479,0.00006420879],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5982366,"threshold_uncertainty_score":0.9998211,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Hind Al Hudib","is_ca":true},{"name":"J. Bradley Cousins","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6422351798637937,"gpt":0.5788854004605903,"spread":0.06334977940320341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07109134,0.0001749869,0.000444308,0.0006292838,0.0003255839,0.0004068244,0.0002623756,0.00004136195,0.002225097],"category_scores_gemma":[0.01900109,0.000144034,0.0001078762,0.00189557,0.0001383128,0.001288021,0.00005584027,0.000150083,0.00001008632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269403,"about_ca_system_score_gemma":0.004764233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001622955,"about_ca_topic_score_gemma":0.0002211908,"domain_scores_codex":[0.9855019,0.005340896,0.001399178,0.0004268483,0.00713083,0.0002003479],"domain_scores_gemma":[0.9802753,0.001270871,0.001666459,0.0004059212,0.01619892,0.0001824943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000138703,0.0007506969,0.03016198,0.00001013013,0.0002319331,0.000001417982,0.009007017,0.01840287,0.0008209313,0.005143231,0.0005524355,0.9347786],"study_design_scores_gemma":[0.007601839,0.003343962,0.1499069,0.00007633449,0.001101125,0.0001704189,0.05635031,0.6142021,0.0002460723,0.1656319,0.001014087,0.0003550002],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9289254,0.0002187918,0.06434616,0.003787547,0.0005458596,0.001278346,0.00001220698,0.000008135012,0.0008775378],"genre_scores_gemma":[0.9942707,0.00003019857,0.00459513,0.0004867862,0.0004617034,0.00005993485,0.00004673362,0.00001631745,0.00003251616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9344236,"threshold_uncertainty_score":0.998687,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Naomi C. Z. Andrews","is_ca":true},{"name":"Debra Pepler","is_ca":true},{"name":"Mary Motz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8556213530259436,"gpt":0.7057655941049885,"spread":0.149855758920955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04314834,0.00009298832,0.0002417993,0.0004457354,0.0009168671,0.0000672196,0.00007754718,0.00003943509,0.0001820404],"category_scores_gemma":[0.001396216,0.00007115433,0.00001098593,0.00057957,0.0004764583,0.0005963637,0.00003331755,0.0008745446,0.00001241418],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000321081,"about_ca_system_score_gemma":0.006495786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004811898,"about_ca_topic_score_gemma":0.0003926021,"domain_scores_codex":[0.9846673,0.01254099,0.0006768224,0.0001490168,0.001658284,0.0003075862],"domain_scores_gemma":[0.9905158,0.005089563,0.000873381,0.0002313476,0.003142004,0.000147919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0017859,0.000519597,0.5181473,0.001788557,0.0002386322,0.000005347042,0.295388,0.008283526,0.003805611,0.02054154,0.006999356,0.1424966],"study_design_scores_gemma":[0.008760233,0.008783492,0.3045672,0.0007919206,0.0001565746,0.00008101807,0.6168603,0.04474342,0.0001128073,0.0129322,0.001902816,0.0003079853],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894729,0.00005981845,0.0005152438,0.006036582,0.00006340104,0.001816781,0.000005466168,0.00000736429,0.002022439],"genre_scores_gemma":[0.9931628,0.00001275029,0.004963431,0.001638851,0.00006224233,0.0001216303,0.000009685858,0.00001072658,0.00001786808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3214723,"threshold_uncertainty_score":0.9991364,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Sanjeev Sridharan","is_ca":false},{"name":"Bernadette Campbell","is_ca":true},{"name":"Heidi M. Zinzow","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4786542061575202,"gpt":0.5785712379293496,"spread":0.09991703177182937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02800635,0.0001317296,0.0005466081,0.0005213225,0.0001283543,0.00004278498,0.0002558331,0.00004165398,0.0003828456],"category_scores_gemma":[0.002031491,0.00009502313,0.0002545939,0.001227078,0.0001685483,0.0004252667,0.00002649883,0.00008671324,0.000003450863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003218639,"about_ca_system_score_gemma":0.002178472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005968901,"about_ca_topic_score_gemma":0.00003896652,"domain_scores_codex":[0.9915067,0.00104521,0.001920679,0.0001767951,0.005160028,0.0001905785],"domain_scores_gemma":[0.9814537,0.0004779235,0.004222254,0.0001765832,0.01362538,0.00004421773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004521639,0.0003610906,0.04731387,0.00001532271,0.0001648793,2.359438e-7,0.00254547,0.07432165,0.007035482,0.0005936426,0.0005710389,0.8666251],"study_design_scores_gemma":[0.00429584,0.002216439,0.4510524,0.00009302406,0.000552861,0.00001003428,0.002428895,0.5255904,0.003433482,0.009895286,0.0002570865,0.0001742606],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9750329,0.00006220213,0.02328197,0.0005429164,0.0001508307,0.0007138599,0.00001230298,0.000004129228,0.0001988698],"genre_scores_gemma":[0.9909809,0.000004071643,0.008737455,0.0000245882,0.000163252,0.00002402475,0.0000392403,0.00001051615,0.00001597562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8664509,"threshold_uncertainty_score":0.9706498,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"John A. Ross","is_ca":true},{"name":"Khaled Barkaoui","is_ca":true},{"name":"Garth Scott","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.103493342416852,"gpt":0.4664295884873363,"spread":0.3629362460704843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009862582,0.00005105742,0.0001151192,0.00009527585,0.0003807295,0.00002578492,0.0001558457,0.00002090853,0.000588064],"category_scores_gemma":[0.001369476,0.00003581063,0.00007181631,0.0004836786,0.0005402757,0.0002877363,0.000009886938,0.0001269436,0.00001143918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329404,"about_ca_system_score_gemma":0.00116315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003918705,"about_ca_topic_score_gemma":0.001198748,"domain_scores_codex":[0.9977714,0.0003896553,0.0003402059,0.00005934168,0.001291132,0.0001482653],"domain_scores_gemma":[0.9967366,0.0008817049,0.0007971375,0.000103807,0.001406423,0.00007429507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006858729,0.0001381684,0.3226682,0.000002801557,0.00006664988,2.819947e-7,0.02228625,0.0003610983,0.000132534,0.003280296,0.002099918,0.6488951],"study_design_scores_gemma":[0.0006068033,0.0003806707,0.9327306,0.00007622007,0.0002331062,0.00002229065,0.03947637,0.000360124,0.000352046,0.006327555,0.0193092,0.0001249748],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9795229,0.0002958992,0.0006346142,0.01101041,0.0004281566,0.0003410946,8.46777e-7,0.000002734772,0.007763337],"genre_scores_gemma":[0.9982579,0.00007113709,0.0006680286,0.0002614153,0.0006212679,0.000008474603,0.000002734953,0.000003892304,0.0001051547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6487702,"threshold_uncertainty_score":0.6438888,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Intuition; Psychology; Epistemology; Social psychology; Management science; Cognitive science","authors":[{"name":"Marthe Hurteau","is_ca":true},{"name":"Jeiran Rahmanian","is_ca":true},{"name":"Sylvain Houle","is_ca":true},{"name":"Marie-Pier Marchand","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.117224265564639,"gpt":0.4903323073651327,"spread":0.3731080418004937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01718286,0.00007543248,0.000255177,0.0001901508,0.00007531082,0.00006790161,0.0002247182,0.00001736097,0.000218326],"category_scores_gemma":[0.004969893,0.00004411964,0.00006238672,0.0008267024,0.000165686,0.0003705403,0.0000460855,0.0001373526,0.000012834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009049195,"about_ca_system_score_gemma":0.0003882512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001076768,"about_ca_topic_score_gemma":0.00002768371,"domain_scores_codex":[0.9946591,0.0008213959,0.001103019,0.0001468227,0.003168671,0.0001010189],"domain_scores_gemma":[0.9948945,0.001840134,0.001413921,0.0001452646,0.001621644,0.00008451859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000248491,0.00002317164,0.01335202,5.566451e-7,0.00001074844,2.458963e-7,0.002881943,0.004180878,0.001211066,0.0004358496,0.0001169416,0.9775381],"study_design_scores_gemma":[0.001935175,0.002967627,0.2862721,0.00007812794,0.00007302203,0.0000139456,0.03204533,0.5063393,0.002143866,0.1652449,0.002760598,0.0001260445],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895865,0.0006045569,0.005347468,0.003406425,0.0001090588,0.0002252218,0.00000137203,0.000001440824,0.0007179636],"genre_scores_gemma":[0.9975567,0.0002202764,0.001905019,0.0002487733,0.00005662919,0.00000615874,7.153767e-7,0.000003658807,0.000002072357],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.977412,"threshold_uncertainty_score":0.5955272,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Kate Svensson","is_ca":true},{"name":"Barbara Szijarto","is_ca":true},{"name":"Peter Milley","is_ca":true},{"name":"J. Bradley Cousins","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4567176324915049,"gpt":0.6367359267377268,"spread":0.180018294246222,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03242493,0.00009744492,0.0002772156,0.0005883753,0.0003478636,0.0001617544,0.0003506595,0.00002642556,0.003952151],"category_scores_gemma":[0.006609104,0.00007178003,0.000111762,0.00229221,0.0003309103,0.0006909236,0.00003920698,0.0001589559,0.0003063791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001653074,"about_ca_system_score_gemma":0.00112026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007162983,"about_ca_topic_score_gemma":0.00001396408,"domain_scores_codex":[0.992362,0.00103432,0.001291858,0.0001798744,0.004962357,0.0001695766],"domain_scores_gemma":[0.9859452,0.0005964832,0.00221532,0.0002272656,0.01095013,0.00006558836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006317173,0.00004459918,0.004868916,4.280241e-7,0.00002693595,3.216153e-7,0.002506852,0.0004301437,0.002399535,0.001169689,0.00447415,0.9840153],"study_design_scores_gemma":[0.003316854,0.007265324,0.5896171,0.00005132813,0.0002882856,0.0001256379,0.01670001,0.2807485,0.00214496,0.07520051,0.02406925,0.0004722529],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9731865,0.00001838984,0.01290626,0.004857179,0.0007245293,0.0001432968,0.000001799586,0.00000757816,0.008154453],"genre_scores_gemma":[0.9889687,0.000002435818,0.008880067,0.0008206981,0.00115058,0.000005978549,0.00000260326,0.000007642472,0.0001613165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.983543,"threshold_uncertainty_score":0.9969584,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Cameron D. Norman","is_ca":true},{"name":"Allan Best","is_ca":true},{"name":"Sharon T. Mortimer","is_ca":true},{"name":"Timothy R. Huerta","is_ca":false},{"name":"A.M.J. Buchan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2891501171514995,"gpt":0.5838757997116935,"spread":0.2947256825601939,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06435224,0.00006191109,0.0002726377,0.00056643,0.0002147265,0.0002989538,0.0006991006,0.00001095012,0.00005496132],"category_scores_gemma":[0.008036617,0.00003411005,0.00005625509,0.002883241,0.0007915532,0.0009887591,0.00008535916,0.0002643187,0.000005990748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001506756,"about_ca_system_score_gemma":0.002953773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001052869,"about_ca_topic_score_gemma":0.0002326872,"domain_scores_codex":[0.9919734,0.001360197,0.00112824,0.0001674273,0.005164202,0.0002065181],"domain_scores_gemma":[0.9929796,0.0009800481,0.001875296,0.0003475477,0.003735019,0.00008243678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006934531,0.0002174668,0.01163964,0.000009503089,0.00002110461,0.000002668488,0.009029349,0.06623778,0.3277297,0.005509307,0.001718684,0.5771913],"study_design_scores_gemma":[0.0008620449,0.005399738,0.2858467,0.00008056198,0.00001350435,0.000090441,0.03704444,0.6593426,0.00100633,0.01010614,0.00009830137,0.0001091367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931541,0.00006698093,0.001400879,0.004161816,0.0004761521,0.0002820952,0.000003318349,0.000001088553,0.0004535561],"genre_scores_gemma":[0.9989868,0.000002883738,0.0007855728,0.00003961925,0.0001379861,0.000005630632,7.989378e-7,0.000003110657,0.00003762724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5931048,"threshold_uncertainty_score":0.9634463,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Steven Lâm","is_ca":true},{"name":"Kelly Skinner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3614297121157451,"gpt":0.6078438813411042,"spread":0.2464141692253591,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06344813,0.0003283481,0.003111648,0.0008705746,0.00007778259,0.0001451385,0.0008925869,0.000150824,0.000862468],"category_scores_gemma":[0.02940827,0.000210491,0.0009969742,0.004559773,0.0003184494,0.0008796083,0.0001514113,0.000626304,0.000005179373],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004433475,"about_ca_system_score_gemma":0.01066186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001759566,"about_ca_topic_score_gemma":0.00003016786,"domain_scores_codex":[0.9744276,0.01011017,0.006840216,0.000479472,0.007875055,0.000267486],"domain_scores_gemma":[0.9659846,0.006484188,0.0153905,0.001249932,0.01079496,0.00009581108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00002495414,0.0001067715,0.00009509738,0.008238254,0.0001095714,0.000001106611,0.0002323378,0.0002331895,0.000004452129,0.00001877128,0.0003988632,0.9905366],"study_design_scores_gemma":[0.00121767,0.001650457,0.002898832,0.8531283,0.003162652,0.00008665565,0.001316484,0.004767446,0.00001077354,0.0004746058,0.1307919,0.0004943014],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009881364,0.99584,0.0002422294,0.0001898818,0.0006852604,0.00195228,0.00004335276,0.000001978404,0.00005688611],"genre_scores_gemma":[0.0003083153,0.9953063,0.003974634,0.00006226773,0.0001516031,0.00006913425,0.00005179028,0.00002152715,0.00005439825],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9900423,"threshold_uncertainty_score":0.9949468,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Richard J. Kitto","is_ca":true},{"name":"John Barnett","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3466871645174802,"gpt":0.5830954045773991,"spread":0.2364082400599189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04729543,0.0000471855,0.0003216623,0.0003513708,0.00005708563,0.00001151893,0.0003158368,0.00001627168,0.000297144],"category_scores_gemma":[0.003113667,0.00003768329,0.0001173206,0.001725284,0.0003267912,0.0002386745,0.00003201472,0.00009599188,9.402407e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008049388,"about_ca_system_score_gemma":0.0001971631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009528692,"about_ca_topic_score_gemma":0.002349253,"domain_scores_codex":[0.995819,0.002512141,0.000583844,0.00009028961,0.0008851765,0.0001094931],"domain_scores_gemma":[0.9968578,0.000854468,0.001145726,0.0001989441,0.0008732802,0.00006975556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002920472,0.00008836927,0.00443787,0.000002315031,0.0004575696,9.978604e-7,0.01716785,0.0001785483,0.000143193,0.0009697193,0.0001088323,0.9764155],"study_design_scores_gemma":[0.0009615064,0.001807382,0.6480573,0.0001807564,0.00835973,0.000004370476,0.274673,0.03169628,0.0001824466,0.005374548,0.02835092,0.0003517581],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8404301,0.0008390259,0.1549185,0.001666102,0.0002041586,0.00008444699,0.00002256175,0.000003534438,0.001831553],"genre_scores_gemma":[0.9619763,0.0001388582,0.03754467,0.0001462932,0.0001444278,1.604512e-7,0.00001947229,0.00000319298,0.00002660366],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9760638,"threshold_uncertainty_score":0.9810098,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Kim Hunt","is_ca":false},{"name":"Sanjeev Sridharan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08324908097625391,"gpt":0.4245087693437239,"spread":0.34125968836747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01208945,0.00006300175,0.0001492387,0.0001307145,0.0004180949,0.00005863825,0.0002614864,0.00002132441,0.00004810809],"category_scores_gemma":[0.007399987,0.00003561044,0.0001527117,0.001169311,0.0002217576,0.0001564243,0.0000230033,0.000183176,0.000001401843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001420252,"about_ca_system_score_gemma":0.0008221652,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01627661,"about_ca_topic_score_gemma":0.01627459,"domain_scores_codex":[0.9969135,0.0008024083,0.0004519253,0.00008779858,0.001616646,0.0001277286],"domain_scores_gemma":[0.9949748,0.0002052119,0.0008975163,0.000206988,0.003648915,0.00006655276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00004225816,0.00007683133,0.004779831,0.000004639558,0.0000891664,1.524457e-7,0.0571483,0.01688192,0.01067068,0.0005185712,0.001219571,0.9085681],"study_design_scores_gemma":[0.000277478,0.0001745989,0.02731835,0.00009325664,0.002302676,0.00003313402,0.9167891,0.05024474,0.0005406819,0.0007928755,0.001304097,0.0001290349],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895496,0.00005163949,0.002959836,0.00471064,0.0005060761,0.0002426756,8.667907e-7,0.000003022035,0.001975665],"genre_scores_gemma":[0.9975426,0.00002725721,0.001554258,0.0003216581,0.0005284036,0.000007264075,8.137254e-7,0.000004714115,0.00001307853],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.908439,"threshold_uncertainty_score":0.9902741,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Nadini Persaud","is_ca":false},{"name":"Ruby Dagher","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2049595892506882,"gpt":0.5292134531119421,"spread":0.3242538638612539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02939576,0.0001181352,0.0003020225,0.0002112065,0.0002047771,0.0002603254,0.0009626947,0.00003379702,0.001120021],"category_scores_gemma":[0.007438891,0.00005926482,0.00014723,0.001277025,0.0001005575,0.000573332,0.00004824345,0.0004652278,0.00008212418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001541922,"about_ca_system_score_gemma":0.0008171258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003836093,"about_ca_topic_score_gemma":0.0009055299,"domain_scores_codex":[0.9907645,0.003613057,0.001074686,0.0002155834,0.00414227,0.0001899104],"domain_scores_gemma":[0.9852945,0.01037187,0.001550384,0.0007366632,0.001993438,0.0000531269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001102214,0.0001013154,0.2132199,0.00000107535,0.00004317016,0.00000269485,0.04831369,0.01409465,0.00004423306,0.001799048,0.01459488,0.7076751],"study_design_scores_gemma":[0.001431923,0.0009020899,0.8187229,0.00009469385,0.0001272922,0.00002597402,0.08027123,0.05187843,0.00003738908,0.01155749,0.0347821,0.0001684932],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.912735,0.0002097115,0.002096794,0.07606922,0.0008425427,0.0005031081,0.000003683607,0.000004821316,0.00753509],"genre_scores_gemma":[0.9932316,0.00005019708,0.0003137209,0.005934393,0.0004095969,0.00001465553,0.000006444624,0.000006504833,0.00003286759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7075067,"threshold_uncertainty_score":0.9997931,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Barbara Szijarto","is_ca":true},{"name":"J. Bradley Cousins","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3892532860461554,"gpt":0.5842406175819069,"spread":0.1949873315357515,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01797598,0.00007641927,0.0002248543,0.0003075267,0.000190626,0.0001057005,0.0002151333,0.00001770097,0.000992467],"category_scores_gemma":[0.005158906,0.00005486158,0.000111979,0.0006110971,0.0001654277,0.0004649557,0.00002159349,0.000118678,0.00009168536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001222234,"about_ca_system_score_gemma":0.0004932402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003195221,"about_ca_topic_score_gemma":0.00001221011,"domain_scores_codex":[0.9962205,0.0006004805,0.0006375875,0.0001494743,0.00224833,0.0001436421],"domain_scores_gemma":[0.9922931,0.00102154,0.001631698,0.0001463815,0.00485026,0.00005701714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002987474,0.00002598946,0.00678361,6.557418e-7,0.00003326428,3.559015e-7,0.002659165,0.006485262,0.0006516275,0.001097936,0.002466325,0.9794971],"study_design_scores_gemma":[0.001953756,0.01036178,0.07185193,0.00009561897,0.0001734788,0.00006289627,0.02559674,0.7988341,0.001300418,0.02890033,0.06060287,0.0002660374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6728446,0.00006098587,0.3155853,0.002783869,0.0007353945,0.0002740647,0.00000121623,0.000007709418,0.007706829],"genre_scores_gemma":[0.9772994,0.000005415716,0.02156897,0.00028941,0.0005669217,0.000006874215,7.289678e-7,0.000006974675,0.0002553026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.979231,"threshold_uncertainty_score":0.9999208,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Laura Haylock","is_ca":false},{"name":"Carol Miller","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3677671345545405,"gpt":0.5374349974415299,"spread":0.1696678628869894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0361091,0.0001581637,0.000366566,0.0005196322,0.0002525092,0.0002157307,0.0001689649,0.0000336934,0.0001909915],"category_scores_gemma":[0.002028212,0.0001214128,0.00005309286,0.0007771955,0.0001595601,0.001257684,0.00005322139,0.000139413,0.00003631078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004071357,"about_ca_system_score_gemma":0.0007350713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002910627,"about_ca_topic_score_gemma":0.00002587938,"domain_scores_codex":[0.992205,0.001255735,0.0009446979,0.0002393816,0.005139417,0.0002157785],"domain_scores_gemma":[0.995243,0.0003213944,0.0008891976,0.0000955103,0.003165124,0.0002857854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001647859,0.00002686885,0.004789352,0.000001775511,0.00003203472,5.922293e-7,0.05449653,0.0002151856,0.0002567,0.00007500024,0.0004852441,0.9394559],"study_design_scores_gemma":[0.007333697,0.003508987,0.5746704,0.000129846,0.0005970101,0.0002911826,0.1838822,0.210718,0.0009277072,0.01000065,0.007269978,0.0006703087],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906209,0.0001968032,0.001713498,0.004661172,0.0003572711,0.0006253083,0.00000561995,0.000005908513,0.001813479],"genre_scores_gemma":[0.9946082,0.00002460847,0.004373093,0.0006233861,0.0002803467,0.00005741185,0.000004205081,0.000009586924,0.00001916834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9387856,"threshold_uncertainty_score":0.9925285,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Raymond J. Struyk","is_ca":false},{"name":"Mawadda Damon","is_ca":false},{"name":"Samuel R. Haddaway","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1885404601512432,"gpt":0.5539368367300723,"spread":0.3653963765788291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01534924,0.00004809388,0.000103133,0.000393363,0.0006467111,0.00009033969,0.0002015366,0.00002962435,0.000194303],"category_scores_gemma":[0.0224777,0.00004563512,0.00004331314,0.001083757,0.0003441089,0.0002991884,0.00001676745,0.0002472044,0.000007865389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003162195,"about_ca_system_score_gemma":0.002635417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005829831,"about_ca_topic_score_gemma":0.0003389099,"domain_scores_codex":[0.9974042,0.0004935923,0.0002949164,0.00008898314,0.001509971,0.0002083924],"domain_scores_gemma":[0.9914264,0.0006819863,0.000363452,0.00006311892,0.007379686,0.00008534674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005991491,0.0001027692,0.005415597,0.000004985573,0.00007596561,5.79263e-7,0.0232877,0.0005769378,0.1046983,0.6042749,0.001862111,0.2596403],"study_design_scores_gemma":[0.003593855,0.002338751,0.07458399,0.000235831,0.0002422493,0.00005730241,0.0244647,0.02602488,0.01732479,0.7783831,0.07193263,0.0008179234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784132,0.000006151732,0.003279021,0.01341732,0.0005706163,0.0002652994,0.000002076422,0.00000756233,0.004038746],"genre_scores_gemma":[0.9574761,0.000007701443,0.04051429,0.00009537303,0.00173477,0.000010349,0.000002601209,0.000008272698,0.0001505717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2588224,"threshold_uncertainty_score":0.9857564,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jill Anne Chouinard","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1817166479435985,"gpt":0.51942008015783,"spread":0.3377034322142315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06268525,0.00009861006,0.0002914318,0.0004393014,0.0001142715,0.0002504708,0.0003711442,0.00002844849,0.002327336],"category_scores_gemma":[0.03287345,0.00005761548,0.0001020102,0.001353803,0.0002034815,0.001969533,0.00003322879,0.0002041087,0.000118345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000271745,"about_ca_system_score_gemma":0.001478455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009459017,"about_ca_topic_score_gemma":0.0001065366,"domain_scores_codex":[0.987496,0.003961464,0.001668443,0.0001698034,0.006512096,0.0001922569],"domain_scores_gemma":[0.9793283,0.004750343,0.003336522,0.0003734613,0.01212216,0.00008915857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006828456,0.00009669466,0.01100698,8.342536e-7,0.00003247356,3.18182e-7,0.001292311,0.002552748,0.0006450415,0.0005639796,0.002063098,0.9816772],"study_design_scores_gemma":[0.002801644,0.001632238,0.632232,0.00005724032,0.0001499873,0.00007358374,0.02625064,0.2905151,0.0003866102,0.02760956,0.01809752,0.000193901],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97212,0.0004359832,0.001140545,0.01748668,0.0005504793,0.0006908134,9.514484e-7,0.000002723555,0.007571862],"genre_scores_gemma":[0.9983479,0.00008907158,0.0009407014,0.0004127844,0.00009871848,0.00004284217,0.000001748497,0.000006128696,0.00006013187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9814833,"threshold_uncertainty_score":0.9985847,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Tony C. M. Lam","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04228701723909126,"gpt":0.418141853921784,"spread":0.3758548366826928,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003664411,0.0001559284,0.0002804245,0.0004410008,0.0001046441,0.00007990584,0.000231025,0.00004819937,0.001890404],"category_scores_gemma":[0.0001235932,0.0001385335,0.0000911048,0.0009472864,0.00002691745,0.0002202855,0.00001323566,0.0002336129,0.0003034644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002583266,"about_ca_system_score_gemma":0.0001770417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002780913,"about_ca_topic_score_gemma":0.000002110707,"domain_scores_codex":[0.9973574,0.0004807336,0.0006121545,0.0001974223,0.001071031,0.0002813087],"domain_scores_gemma":[0.9981852,0.0001280603,0.0007170695,0.0002315806,0.0005798217,0.0001582749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004027112,0.00008794501,0.01794258,0.000001115338,0.00009869032,0.000006083123,0.006167089,0.0009088446,0.0001124136,0.00003234247,0.004705535,0.9695346],"study_design_scores_gemma":[0.001278901,0.001911025,0.9890778,0.0001007337,0.0001789889,0.00003951945,0.001594375,0.0002845741,0.00007587009,0.0005906018,0.004612552,0.0002550499],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900874,0.0001599507,0.002795889,0.0009434809,0.0005975954,0.0003137962,3.842397e-7,0.00002442658,0.00507709],"genre_scores_gemma":[0.9915255,0.00001577766,0.007065607,0.0007594628,0.0004132163,0.00001533213,0.000004903749,0.00001375615,0.0001864354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9711352,"threshold_uncertainty_score":0.999022,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Rhonda Cockerill","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.355370496696108,"gpt":0.5926022913441982,"spread":0.2372317946480902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06237026,0.0001156855,0.0003148406,0.0004145918,0.0003348171,0.0001538117,0.000404113,0.00003089105,0.004724113],"category_scores_gemma":[0.003291319,0.00008755118,0.0001753835,0.000762441,0.0001168033,0.000566063,0.000009255357,0.0002414249,0.0000750351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002274203,"about_ca_system_score_gemma":0.001180201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000148749,"about_ca_topic_score_gemma":0.000009231274,"domain_scores_codex":[0.9909324,0.003138678,0.001111716,0.0001442373,0.004499125,0.0001738352],"domain_scores_gemma":[0.9913967,0.002398506,0.001293387,0.0003836383,0.004428474,0.00009931434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000218975,0.00007571337,0.002677432,0.000001663419,0.00001858504,1.617544e-7,0.001187037,0.1951955,0.0001625109,0.00002498113,0.001848153,0.7985893],"study_design_scores_gemma":[0.003456121,0.002461023,0.05898298,0.0000729696,0.0002517479,0.00001941933,0.004721344,0.8889052,0.0004275333,0.01508133,0.02542954,0.0001907646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.971195,0.0000836268,0.02122697,0.002004132,0.0002990387,0.0005212631,0.000005445922,0.000007950127,0.004656533],"genre_scores_gemma":[0.9918718,0.000004860321,0.006567748,0.001197864,0.0001764294,0.00004239155,0.00002692832,0.000009950096,0.0001020307],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7983985,"threshold_uncertainty_score":0.9961857,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Rhonda Cockerill","is_ca":true},{"name":"Ted Myers","is_ca":false},{"name":"Dan Allman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.355370496696108,"gpt":0.5926022913441982,"spread":0.2372317946480902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06237026,0.0001156855,0.0003148406,0.0004145918,0.0003348171,0.0001538117,0.000404113,0.00003089105,0.004724113],"category_scores_gemma":[0.003291319,0.00008755118,0.0001753835,0.000762441,0.0001168033,0.000566063,0.000009255357,0.0002414249,0.0000750351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002274203,"about_ca_system_score_gemma":0.001180201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000148749,"about_ca_topic_score_gemma":0.000009231274,"domain_scores_codex":[0.9909324,0.003138678,0.001111716,0.0001442373,0.004499125,0.0001738352],"domain_scores_gemma":[0.9913967,0.002398506,0.001293387,0.0003836383,0.004428474,0.00009931434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000218975,0.00007571337,0.002677432,0.000001663419,0.00001858504,1.617544e-7,0.001187037,0.1951955,0.0001625109,0.00002498113,0.001848153,0.7985893],"study_design_scores_gemma":[0.003456121,0.002461023,0.05898298,0.0000729696,0.0002517479,0.00001941933,0.004721344,0.8889052,0.0004275333,0.01508133,0.02542954,0.0001907646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.971195,0.0000836268,0.02122697,0.002004132,0.0002990387,0.0005212631,0.000005445922,0.000007950127,0.004656533],"genre_scores_gemma":[0.9918718,0.000004860321,0.006567748,0.001197864,0.0001764294,0.00004239155,0.00002692832,0.000009950096,0.0001020307],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7983985,"threshold_uncertainty_score":0.9961857,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Rebecca J. Macy","is_ca":false},{"name":"Amanda Eckhardt","is_ca":false},{"name":"Christopher J. Wretman","is_ca":false},{"name":"Ran Hu","is_ca":true},{"name":"Jeong-Suk Kim","is_ca":false},{"name":"Xinyi Wang","is_ca":false},{"name":"Cindy Bombeeck","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2469876266596626,"gpt":0.4708132701818361,"spread":0.2238256435221735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009145265,0.00012625,0.0002702837,0.0003253245,0.0006186764,0.00004892617,0.0001535022,0.00002804422,0.0002899189],"category_scores_gemma":[0.0001400425,0.0001294887,0.0000989467,0.0004689929,0.00006212645,0.0002483322,0.00001274356,0.0002176558,0.000001652178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004671635,"about_ca_system_score_gemma":0.0006837659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006414676,"about_ca_topic_score_gemma":0.00008216727,"domain_scores_codex":[0.9963183,0.001458118,0.0007075237,0.000240307,0.0009937383,0.0002820482],"domain_scores_gemma":[0.9976869,0.00011293,0.001233874,0.000176599,0.0006912638,0.00009848588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001380601,0.0003244902,0.002270516,0.00001204967,0.00007395555,8.123018e-7,0.01536015,0.01375645,0.0001087051,0.001269035,0.0002575169,0.9664283],"study_design_scores_gemma":[0.01096042,0.0209194,0.4563456,0.0001109118,0.001496619,0.0005351222,0.1519966,0.3402092,0.0001723888,0.008686041,0.00754875,0.001018915],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9838761,0.0002645905,0.01294465,0.0004796814,0.0005585575,0.001503674,0.000004034421,0.00003126005,0.0003374399],"genre_scores_gemma":[0.9874447,0.000002457937,0.01138323,0.0001828813,0.0003797742,0.0004636763,0.0001075736,0.00002834615,0.000007345629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9654093,"threshold_uncertainty_score":0.5280398,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Maria Barrados","is_ca":true},{"name":"Julie Blain","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1859485882753664,"gpt":0.471487866355326,"spread":0.2855392780799596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007876904,0.0001079376,0.0002530985,0.0002658463,0.000174957,0.0002305051,0.0003901989,0.00002812559,0.0004698732],"category_scores_gemma":[0.004184056,0.00005809321,0.0001039655,0.001164414,0.0003520456,0.00246344,0.00004899225,0.0002085144,0.00004903307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047802,"about_ca_system_score_gemma":0.0008794796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001048687,"about_ca_topic_score_gemma":0.000006596494,"domain_scores_codex":[0.9937508,0.0007834167,0.001392076,0.0001783376,0.003743235,0.0001521583],"domain_scores_gemma":[0.9920714,0.001154982,0.002717976,0.0003344838,0.003656103,0.00006507713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000139515,0.000105534,0.01956916,0.000001701454,0.00004186733,1.323805e-7,0.002950251,0.0361484,0.0002198267,0.00006828856,0.003005744,0.9377496],"study_design_scores_gemma":[0.0008916254,0.002573115,0.4857509,0.00003683663,0.00007080796,0.00001953702,0.003552267,0.4999062,0.0006189755,0.0004521826,0.006026628,0.0001009325],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917656,0.00003234569,0.003750489,0.002639652,0.0002678761,0.0006962406,0.000007497932,0.000006514174,0.0008337753],"genre_scores_gemma":[0.9884297,0.00003514143,0.01090145,0.0003518318,0.0001339702,0.00005322903,0.000006847192,0.000006287286,0.00008151281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9376487,"threshold_uncertainty_score":0.5144783,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Michelle Searle","is_ca":true},{"name":"Amanda Cooper","is_ca":true},{"name":"Paisley Worthington","is_ca":true},{"name":"Jennifer Hughes","is_ca":true},{"name":"Rebecca Gokiert","is_ca":true},{"name":"Cheryl Poth","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3963496705860396,"gpt":0.6096230452322937,"spread":0.2132733746462541,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08210161,0.0004954277,0.003228513,0.00223475,0.0000997984,0.0004734593,0.0007927963,0.000151141,0.003571033],"category_scores_gemma":[0.01385763,0.0003117169,0.001280477,0.005360445,0.0001573339,0.001246108,0.000125568,0.0008452235,0.0001614961],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007985375,"about_ca_system_score_gemma":0.009483951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003811492,"about_ca_topic_score_gemma":0.000007560161,"domain_scores_codex":[0.9761772,0.005817201,0.005761955,0.0006198691,0.01129239,0.00033142],"domain_scores_gemma":[0.9775426,0.002087946,0.01042543,0.0008989124,0.008858827,0.0001863375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00000690153,0.00003255912,0.000004615372,0.02486003,0.000170816,0.00000466711,0.0003594472,0.00005311384,0.000001747064,0.00002172998,0.004030986,0.9704534],"study_design_scores_gemma":[0.0002287242,0.0002862889,0.00002289194,0.7237769,0.003256736,0.0002522659,0.0002333116,0.003133127,8.039011e-7,0.0004263143,0.2681032,0.0002794889],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00004722523,0.994104,0.0007665065,0.0005753961,0.001592816,0.00248639,0.00003457269,0.00000987375,0.0003832301],"genre_scores_gemma":[0.00007774415,0.9972134,0.001438352,0.0003372779,0.0004686073,0.0001236094,0.0001041802,0.00004231192,0.0001944651],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9701739,"threshold_uncertainty_score":0.9999335,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Bernadette Campbell","is_ca":true},{"name":"Melvin M. Mark","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3507628690464508,"gpt":0.5660418537784816,"spread":0.2152789847320308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1630506,0.0001559835,0.0004168125,0.001070075,0.0003130811,0.0004216423,0.0006180592,0.00004487909,0.0008065109],"category_scores_gemma":[0.03493905,0.0001113944,0.0001516456,0.002130639,0.000456819,0.001146569,0.00005744426,0.0004431675,0.00007110489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006674662,"about_ca_system_score_gemma":0.001609149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002409852,"about_ca_topic_score_gemma":0.0001430389,"domain_scores_codex":[0.9736034,0.01285644,0.001002929,0.0003755904,0.01181072,0.0003508941],"domain_scores_gemma":[0.9778165,0.003449526,0.001751166,0.0005884119,0.0161928,0.0002015955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001422308,0.00005843239,0.003521509,0.000001276627,0.00003330616,6.286903e-7,0.002602225,0.006487806,0.0009581125,0.004125887,0.001550273,0.9805183],"study_design_scores_gemma":[0.002832068,0.004219403,0.1480535,0.0001135586,0.0002653636,0.00007255682,0.05233879,0.3488426,0.001824856,0.419526,0.02151506,0.0003962717],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9120359,0.0003260424,0.06723417,0.01154733,0.0009122904,0.0006408161,0.00000521318,0.00001027508,0.007288008],"genre_scores_gemma":[0.9956565,0.0000432569,0.003111081,0.0003469563,0.0004194455,0.00003445047,0.000009024697,0.00001354998,0.0003657308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.980122,"threshold_uncertainty_score":0.9731901,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Emma Richardson","is_ca":true},{"name":"Mary Phillips","is_ca":false},{"name":"Alejandra Colom","is_ca":false},{"name":"Jennica Nichols","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.365242125327843,"gpt":0.5972764607902662,"spread":0.2320343354624232,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04510768,0.0001825128,0.0004701016,0.0006165534,0.0003340753,0.0002657525,0.0005279736,0.00004815541,0.00640595],"category_scores_gemma":[0.02022677,0.0001385053,0.0001714869,0.001459548,0.0003943392,0.001216178,0.0000583794,0.0001982049,0.0002221552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006580432,"about_ca_system_score_gemma":0.002684269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001561682,"about_ca_topic_score_gemma":0.00005856277,"domain_scores_codex":[0.9871544,0.002785433,0.001600402,0.0003810636,0.007823776,0.0002549208],"domain_scores_gemma":[0.9846693,0.001060557,0.002850818,0.000556968,0.01059896,0.0002633484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003641899,0.00009501248,0.009795102,0.000001919874,0.00006848305,0.000001607077,0.03944372,0.002929155,0.002742385,0.0005268288,0.00399789,0.9400337],"study_design_scores_gemma":[0.00500857,0.008353051,0.2218361,0.0001547844,0.0008224171,0.0002856332,0.1414216,0.5060673,0.006270869,0.04660919,0.06222608,0.0009444193],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9412824,0.0002206365,0.04130579,0.00261212,0.002041383,0.0004106675,0.000001706436,0.0000159826,0.01210933],"genre_scores_gemma":[0.9787729,0.0000292103,0.01907745,0.0008598754,0.0009621045,0.0000396885,0.000004570396,0.00001361022,0.0002405465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9390893,"threshold_uncertainty_score":0.9945023,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}