{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":38,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":38,"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"},"query_hash":"eaebb99799eb","filters":{"venue":"Educational Measurement Issues and Practice"}},"results":[{"id":"W2170853093","doi":"10.1111/j.1745-3992.2003.tb00136.x","title":"Using Multidimensional Item Response Theory to Evaluate Educational and Psychological Tests","year":2003,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Item response theory; Test (biology); Measure (data warehouse); Ninth; Computer science; Process (computing); Meaning (existential); Multidimensional analysis; Psychology; Mathematics education; Psychometrics; Management science; Econometrics; Mathematics; Data mining; Developmental psychology; Psychotherapist","retraction":null,"screen_n_in":null,"score":{"opus":0.8128600435609681,"gpt":0.6116511900217015,"spread":0.2012088535392665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05058032,0.0001947472,0.0002388297,0.0003752727,0.0004601169,0.0002583107,0.000209834,0.0000757461,0.001204988],"category_scores_gemma":[0.6463413,0.0001460503,0.0000420616,0.0009438032,0.0001126364,0.0004408504,0.00007613112,0.000183248,0.00009124365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009356135,"about_ca_system_score_gemma":0.0003446095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002454763,"about_ca_topic_score_gemma":0.000001745588,"domain_scores_codex":[0.9904012,0.00588029,0.0005715716,0.0007551193,0.002108174,0.000283652],"domain_scores_gemma":[0.8754453,0.1217538,0.0003417781,0.0004156052,0.00171895,0.0003245768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0105423,0.005656771,0.2253975,0.00004733429,0.0003970318,0.00001585365,0.008179787,0.0007752535,0.07944028,0.4385619,0.08696332,0.1440227],"study_design_scores_gemma":[0.0005090386,0.0002813728,0.6620944,0.00005153928,0.00005219252,0.0004490313,0.002137011,0.00009915711,0.0001408088,0.1328589,0.2010121,0.0003144805],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.913103,0.007822783,0.003829669,0.06630247,0.001771152,0.0004524864,0.000007636509,0.00002046664,0.006690371],"genre_scores_gemma":[0.6327977,0.00006669179,0.3634975,0.002033121,0.000256745,0.00003090728,0.000001416599,0.00001156304,0.001304368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.595761,"threshold_uncertainty_score":0.9997081,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139397945","doi":"10.1111/j.1745-3992.2007.00090.x","title":"Defining and Evaluating Models of Cognition Used in Educational Measurement to Make Inferences About Examinees' Thinking Processes","year":2007,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":166,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cognition; Identification (biology); Psychology; Cognitive psychology; Computer science; Management science","retraction":null,"screen_n_in":null,"score":{"opus":0.2732332005606202,"gpt":0.4452723569892246,"spread":0.1720391564286045,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008417928,0.0001711788,0.0001968663,0.0002165649,0.000181962,0.00008648606,0.00008599655,0.00005773254,0.0002431956],"category_scores_gemma":[0.01608524,0.0001759387,0.00001784228,0.0003305279,0.0000618197,0.0003835731,0.00004264727,0.0001597846,0.000007765088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001107899,"about_ca_system_score_gemma":0.0005294985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001140399,"about_ca_topic_score_gemma":0.0009434323,"domain_scores_codex":[0.9973978,0.000285515,0.0005391173,0.0003930338,0.001116627,0.0002679361],"domain_scores_gemma":[0.9929942,0.004125259,0.0003084998,0.0001166544,0.002353761,0.000101554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001501431,0.004118659,0.344027,0.001589671,0.0005811568,0.000004665968,0.2071286,0.0003532573,0.005634312,0.224201,0.0006518011,0.2102084],"study_design_scores_gemma":[0.00121861,0.0005338464,0.8854444,0.001852085,0.0002173331,0.00005943449,0.05349979,0.00008513312,0.0004813083,0.05435985,0.001744185,0.000504002],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.920895,0.02116424,0.001697123,0.01245273,0.0005849478,0.0009382836,0.00001468927,0.00002388924,0.04222906],"genre_scores_gemma":[0.988376,0.00006913002,0.01067155,0.0004137131,0.000226499,0.0001315132,0.00001806014,0.00001444622,0.00007908809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5414174,"threshold_uncertainty_score":0.9922027,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1985695119","doi":"10.1111/j.1745-3992.2004.tb00164.x","title":"Avoiding Misconception, Misuse, and Missed Opportunities: The Collection of Verbal Reports in Educational Achievement Testing","year":2004,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":121,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Cognition; Data collection; Trustworthiness; Nonverbal communication; Test (biology); Cognitive psychology; Developmental psychology; Applied psychology; Social psychology; Social science","retraction":null,"screen_n_in":null,"score":{"opus":0.3226938867206189,"gpt":0.4332718452277097,"spread":0.1105779585070908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002881187,0.0001452996,0.0001413371,0.00009237876,0.0003507852,0.00005215577,0.00008336962,0.00006185799,0.0004940513],"category_scores_gemma":[0.002406023,0.0001177465,0.00002324468,0.0002704854,0.0001256771,0.0002425804,0.00002125987,0.0002474659,0.000007319416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001528515,"about_ca_system_score_gemma":0.0004970864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00137099,"about_ca_topic_score_gemma":0.00003599371,"domain_scores_codex":[0.9980255,0.000480106,0.0004930365,0.0003373594,0.0004869931,0.0001770115],"domain_scores_gemma":[0.9971278,0.001735792,0.000377553,0.0001662615,0.0005046473,0.00008794272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001458339,0.01896385,0.3461807,0.0004362468,0.001044052,0.00004257488,0.115755,0.0003530055,0.01322296,0.4223003,0.06033102,0.01991205],"study_design_scores_gemma":[0.0008339116,0.0002539548,0.8604285,0.0002606077,0.00007931481,0.0005232756,0.03174417,0.000002479247,0.00009101814,0.03584974,0.06967563,0.000257403],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6960731,0.007544415,0.00006702762,0.2653149,0.001567773,0.0006018981,0.000006402762,0.00001320501,0.02881126],"genre_scores_gemma":[0.9931052,0.0002607673,0.002965138,0.001404986,0.0003784376,0.0001843082,0.0000260082,0.0000100404,0.001665136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5142478,"threshold_uncertainty_score":0.5409516,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018691396","doi":"10.1111/j.1745-3992.2010.00173.x","title":"Application of Think Aloud Protocols for Examining and Confirming Sources of Differential Item Functioning Identified by Expert Reviews","year":2010,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of New Brunswick; University of British Columbia","funders":"","keywords":"Differential item functioning; Think aloud protocol; Psychology; Empirical evidence; Cognitive psychology; Expert opinion; Applied psychology; Social psychology; Item response theory; Computer science; Developmental psychology; Psychometrics; Epistemology; Medicine; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.2023495907107836,"gpt":0.4728441178860088,"spread":0.2704945271752253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001662908,0.0001296774,0.000225644,0.0000473525,0.0001419244,0.0000447028,0.0001051568,0.00008419656,0.0004987039],"category_scores_gemma":[0.001203508,0.0001102558,0.00003315174,0.00007763204,0.00008802914,0.0001894848,0.00001800479,0.0001392137,0.000004853775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001067432,"about_ca_system_score_gemma":0.00004097329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002082165,"about_ca_topic_score_gemma":0.000007002213,"domain_scores_codex":[0.9985638,0.0002063796,0.0004727711,0.0003194734,0.0003128155,0.0001247164],"domain_scores_gemma":[0.9974834,0.001228006,0.0005938286,0.0001884958,0.0004393053,0.00006692913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001599898,0.005595442,0.07213385,0.0009407509,0.0006466612,2.078119e-7,0.04051256,7.962824e-7,0.5735736,0.07974873,0.09145597,0.1337915],"study_design_scores_gemma":[0.001170967,0.0004183462,0.186633,0.0002131624,0.0001400613,0.00002887531,0.008288768,0.00001953057,0.002813801,0.003099626,0.7968639,0.0003100168],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9197653,0.01361539,0.0109119,0.02742371,0.003381612,0.01717111,0.00006342203,0.00003902283,0.00762851],"genre_scores_gemma":[0.9848647,0.00009815132,0.007568381,0.0003537376,0.0006468606,0.004862154,0.0000699054,0.0000144948,0.001521672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7054079,"threshold_uncertainty_score":0.5460458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061554266","doi":"10.1111/j.1745-3992.2004.tb00165.x","title":"Assessing School Readiness: Validity and Bias in Preschool and Kindergarten Teachers' Ratings","year":2004,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Early Childhood Education and Development","field":"Social Sciences","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Psychology; Head start; Vocabulary; Developmental psychology; Association (psychology); Early childhood education; Early childhood; Preschool education; Academic skills; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.1814566607573539,"gpt":0.4182170293389201,"spread":0.2367603685815662,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004092366,0.0001129765,0.0001167713,0.00008955173,0.0004975424,0.0006677088,0.00006487397,0.00006652955,0.0001125412],"category_scores_gemma":[0.01066654,0.0001131232,0.00001071154,0.0001778712,0.0001021525,0.001661181,0.00002622972,0.0001951738,0.00001234369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002257519,"about_ca_system_score_gemma":0.001631191,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00737318,"about_ca_topic_score_gemma":0.0009926421,"domain_scores_codex":[0.998268,0.0004487006,0.0002237991,0.000284858,0.000584505,0.0001901409],"domain_scores_gemma":[0.9987459,0.0005152487,0.0001392602,0.00008620002,0.0002880709,0.0002253301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008698631,0.001184905,0.5862174,0.0000968946,0.0001007734,0.000004129397,0.3456522,0.00002005446,0.0007849698,0.03780454,0.00982657,0.01822054],"study_design_scores_gemma":[0.0004727261,0.00003206031,0.8309138,0.0001499048,0.00002758708,0.00001057854,0.05338886,7.508151e-7,0.00003583835,0.008744118,0.1060217,0.0002020426],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7813438,0.003738693,0.00003107045,0.1976583,0.000387945,0.0003950908,7.135899e-7,0.00002713993,0.01641718],"genre_scores_gemma":[0.9873822,0.001012714,0.009482057,0.001092402,0.0004479932,0.00003205696,0.000004218029,0.000008005143,0.0005383061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2922634,"threshold_uncertainty_score":0.9992368,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2172179933","doi":"10.1111/emip.12018","title":"Instructional Topics in Educational Measurement (ITEMS) Module: Using Automated Processes to Generate Test Items","year":2013,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Rendering (computer graphics); Test (biology); Item bank; Process (computing); Item response theory; Task (project management); Item analysis; Artificial intelligence; Machine learning; Information retrieval; Psychometrics; Programming language; Psychology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09722074847346185,"gpt":0.3606391693617605,"spread":0.2634184208882987,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001455702,0.0002425037,0.0001866668,0.0003161802,0.0003179031,0.0003812745,0.000464349,0.00009852262,0.0001703531],"category_scores_gemma":[0.004121631,0.0002444782,0.00002519468,0.0008894023,0.00005681445,0.001701275,0.0001206347,0.0002243657,0.0001013479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005964222,"about_ca_system_score_gemma":0.002337386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006193183,"about_ca_topic_score_gemma":0.00007027721,"domain_scores_codex":[0.997122,0.0001753803,0.000489036,0.0005947059,0.00128764,0.0003311685],"domain_scores_gemma":[0.9961851,0.0004681657,0.0002313594,0.0003440555,0.002588964,0.0001823385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00009925635,0.01479127,0.1709418,0.0009387482,0.0006787927,0.000007734254,0.007997799,0.007727795,0.05192865,0.5267627,0.1755575,0.04256794],"study_design_scores_gemma":[0.001059022,0.0003262331,0.6858827,0.0006362207,0.00007846624,0.0004206425,0.001321236,0.0189504,0.004005948,0.05083995,0.2349783,0.001500852],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2060344,0.006340825,0.009182005,0.7691264,0.003721789,0.001906059,0.00001380151,0.000329894,0.003344827],"genre_scores_gemma":[0.7649267,0.0001408142,0.2308248,0.001919076,0.0009850654,0.000575269,0.0000200151,0.00001839259,0.0005898114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7672073,"threshold_uncertainty_score":0.9969531,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119322254","doi":"10.1111/j.1745-3992.2001.tb00060.x","title":"Illustrating the Utility of Differential Bundle Functioning Analyses to Identify and Interpret Group Differences on Achievement Tests","year":2001,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Bundle; Differential (mechanical device); Interpretation (philosophy); Psychology; Computer science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.304702775564566,"gpt":0.5091262291350933,"spread":0.2044234535705273,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001084223,0.0001565848,0.000161527,0.00006586821,0.0002767229,0.000110659,0.0001417072,0.00004718059,0.002335743],"category_scores_gemma":[0.0008270727,0.0001041334,0.0000363318,0.0001794321,0.00009088263,0.0001589922,0.00004429753,0.0001783472,0.00002620332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002623998,"about_ca_system_score_gemma":0.00003152646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005663462,"about_ca_topic_score_gemma":0.00006131073,"domain_scores_codex":[0.9980773,0.0004971349,0.0003325175,0.0003681558,0.0005506889,0.0001741875],"domain_scores_gemma":[0.9980038,0.001273674,0.0001645896,0.0002087765,0.0002470429,0.0001021044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001667909,0.008280548,0.8904446,0.00006522143,0.0009249071,0.000001800236,0.01197411,0.000004210834,0.006944783,0.0384666,0.01640476,0.02482049],"study_design_scores_gemma":[0.0001867834,0.0004613846,0.9829115,0.00006595674,0.00008574572,0.0000145695,0.005912103,0.00001047827,0.00001934885,0.002051987,0.008165428,0.0001147452],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9462587,0.001043181,0.0005161614,0.03715726,0.001125985,0.000296884,0.00000747782,0.00001112309,0.01358321],"genre_scores_gemma":[0.9974282,0.00006296118,0.000455914,0.0009561619,0.0003842609,0.00009890863,0.00001330258,0.000006383333,0.0005938854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09246681,"threshold_uncertainty_score":0.9985763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111648217","doi":"10.1111/j.1745-3992.2010.00181.x","title":"Developing Score Reports for Cognitive Diagnostic Assessments","year":2010,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Context (archaeology); Test (biology); Cognition; Diagnostic test; Hierarchy; Sample (material); Knowledge management; Data science; Psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.165780093144807,"gpt":0.4552123800807414,"spread":0.2894322869359344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001502616,0.00009186042,0.00008233803,0.000053845,0.0002089524,0.0003417542,0.0001405197,0.00003120907,0.00003432103],"category_scores_gemma":[0.01656031,0.00008870458,0.00001818056,0.0001446674,0.00002473697,0.001010508,0.00005850535,0.00008721004,0.0000113225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003265068,"about_ca_system_score_gemma":0.0005229164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000304628,"about_ca_topic_score_gemma":0.00002100082,"domain_scores_codex":[0.9988559,0.00006240166,0.0002096835,0.0002877398,0.0004547391,0.0001294728],"domain_scores_gemma":[0.9966125,0.001709468,0.0001961055,0.0001772344,0.00122394,0.00008072382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002093245,0.0005529723,0.006985798,0.00009661648,0.0001417021,0.000008806072,0.0008880873,0.000002938094,0.0006654864,0.93872,0.02511074,0.02680593],"study_design_scores_gemma":[0.000409533,0.0001098099,0.02471811,0.0001847337,0.0001083729,0.0002051385,0.0004468932,0.001091455,0.001070919,0.03520958,0.9360324,0.0004130511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002726362,0.0007574659,0.9029152,0.08679445,0.00275249,0.0006183059,0.00001181337,0.00005981429,0.00336412],"genre_scores_gemma":[0.6360547,0.0002561946,0.3560744,0.005791929,0.0007179109,0.0001686242,0.0001381618,0.00001663455,0.0007814888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9109216,"threshold_uncertainty_score":0.9917236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109560181","doi":"10.1111/j.1745-3992.2005.00002.x","title":"Using Dimensionality‐Based DIF Analyses to Identify and Interpret Constructs That Elicit Group Differences","year":2005,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Matching (statistics); Psychology; Selection (genetic algorithm); Curse of dimensionality; Contrast (vision); Cognitive psychology; Test (biology); Social psychology; Computer science; Statistics; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8614623269368624,"gpt":0.6322567921565106,"spread":0.2292055347803518,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008691677,0.0001818178,0.0002999942,0.0003893523,0.0003293598,0.0006283202,0.0002763558,0.00005206035,0.0004214508],"category_scores_gemma":[0.1030996,0.0001331808,0.00004545771,0.0007507514,0.0001130304,0.0007332371,0.0001281688,0.0001317977,0.00002119806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006594827,"about_ca_system_score_gemma":0.0001142723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003800329,"about_ca_topic_score_gemma":0.0000348302,"domain_scores_codex":[0.9956569,0.00108809,0.0005017433,0.0005793473,0.001947805,0.0002261296],"domain_scores_gemma":[0.9723477,0.02605094,0.0003006471,0.0003084338,0.0007749212,0.0002173003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000685163,0.0009832658,0.7105658,0.00007674759,0.0003353155,0.000005889706,0.003744719,0.0003570731,0.05656612,0.0129467,0.01625961,0.1974736],"study_design_scores_gemma":[0.0004166067,0.0001355295,0.9290572,0.0001740343,0.0001478111,0.00008626118,0.004557073,0.001411287,0.0009648817,0.01517604,0.0474659,0.0004073187],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9271033,0.007943781,0.01477479,0.0469338,0.0009059166,0.0002678038,0.00001203261,0.00002451395,0.002034018],"genre_scores_gemma":[0.8506394,0.00007271052,0.147112,0.00182623,0.0002556107,0.00000926067,0.000001958205,0.000006194981,0.00007663307],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2184914,"threshold_uncertainty_score":0.9044554,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2006618588","doi":"10.1111/j.1745-3992.2000.tb00036.x","title":"An NCME Instructional Module on Exploring the Logic of Tatsuoka's Rule‐Space Model for Test Development and Analysis","year":2000,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Social Sciences and Humanities Research Council; Alberta Advanced Education; University of Alberta","funders":"","keywords":"Test (biology); Set (abstract data type); Space (punctuation); Blueprint; Computer science; Cognition; Artificial intelligence; Rule-based system; Machine learning; Psychology; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1492879822400197,"gpt":0.3656347844741414,"spread":0.2163468022341217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001090509,0.0001113784,0.0001162878,0.0001129744,0.00034723,0.00007882206,0.0002475746,0.00003137862,0.00002965507],"category_scores_gemma":[0.000330308,0.00008746333,0.00002667344,0.0002782818,0.00006448316,0.0006504263,0.00002395989,0.00009430978,0.000003222555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005869552,"about_ca_system_score_gemma":0.000279863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001964678,"about_ca_topic_score_gemma":0.000008357982,"domain_scores_codex":[0.9988487,0.00007211651,0.0002048228,0.0003087095,0.0004396865,0.0001259634],"domain_scores_gemma":[0.998576,0.0006643852,0.0001196756,0.0002518686,0.00033088,0.00005711896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00008383154,0.001961672,0.003888498,0.00003973617,0.000498269,2.710507e-7,0.004743099,0.01274711,0.000544825,0.8575131,0.000684545,0.117295],"study_design_scores_gemma":[0.001074306,0.0007390098,0.4916705,0.0001266096,0.0006747203,0.00007084537,0.002955934,0.1894535,0.005760927,0.1833819,0.1230859,0.001005825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6354553,0.002303079,0.1227581,0.2357238,0.000477788,0.0007581887,0.00002321319,0.00008317462,0.002417352],"genre_scores_gemma":[0.716076,0.0001547576,0.2828101,0.000341376,0.00007250908,0.0001921249,0.00001133601,0.000003974881,0.0003377865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6741312,"threshold_uncertainty_score":0.3566651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057691077","doi":"10.1111/j.1745-3992.2009.01133.x","title":"Inclusive Achievement Testing for Linguistically and Culturally Diverse Test Takers: Essential Considerations for Test Developers and Decision Makers","year":2009,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Disability Education and Employment","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Carleton University","funders":"","keywords":"Ell; Accountability; Test (biology); Government (linguistics); Standardized test; No child left behind; Equity (law); Achievement test; Political science; Language assessment; Psychology; English language; Public relations; Pedagogy; Mathematics education; Teaching method","retraction":null,"screen_n_in":null,"score":{"opus":0.125304747687676,"gpt":0.4253981248863941,"spread":0.3000933771987181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.002114357,0.000129116,0.0001208173,0.00004141072,0.001499152,0.0004066132,0.00005684313,0.00004543771,0.00005129894],"category_scores_gemma":[0.103024,0.0001228859,0.00002182739,0.00009097559,0.0001833442,0.0003464656,0.00002605473,0.00005986066,0.000002428243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001714648,"about_ca_system_score_gemma":0.0007077053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004258592,"about_ca_topic_score_gemma":0.000589828,"domain_scores_codex":[0.9986703,0.00007951049,0.0002651174,0.0003264361,0.0004478232,0.0002108492],"domain_scores_gemma":[0.9886548,0.009237464,0.0001369688,0.00008244598,0.001687278,0.0002010607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008286298,0.006998331,0.06646917,0.0002632328,0.0002640693,0.00000252921,0.15944,0.00003699815,0.00520507,0.4014929,0.1363333,0.2226659],"study_design_scores_gemma":[0.001988371,0.0007965352,0.1046026,0.0002362543,0.0003950092,0.00002026527,0.09344415,0.0001292247,0.00008943016,0.1183324,0.6793038,0.000662024],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.05241347,0.002157657,0.002050287,0.928278,0.001316055,0.003906266,0.000103572,0.00007582469,0.009698877],"genre_scores_gemma":[0.8214747,0.0002172198,0.1734451,0.003603147,0.0007861763,0.0001361445,0.00002366472,0.000008531233,0.0003053184],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9246749,"threshold_uncertainty_score":0.9998007,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2064530600","doi":"10.1111/j.1745-3992.2009.01135.x","title":"An NCME Instructional Module on Using Differential Step Functioning to Refine the Analysis of DIF in Polytomous Items","year":2009,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":33,"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":"Polytomous Rasch model; Differential item functioning; Item response theory; Psychology; Rasch model; Task (project management); Test (biology); Statistics; Differential (mechanical device); Psychometrics; Mathematics; Clinical psychology; Developmental psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.5327361304287398,"gpt":0.5248611500943309,"spread":0.007874980334408921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007238746,0.0001168661,0.0002609933,0.0008978979,0.0002285094,0.0002007398,0.0002730471,0.00004051357,0.0002488868],"category_scores_gemma":[0.04353613,0.00007806699,0.00006009658,0.003031455,0.00003424635,0.0003797659,0.0000255921,0.0001465813,0.000003774149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000854115,"about_ca_system_score_gemma":0.00008565572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006463495,"about_ca_topic_score_gemma":0.00006197618,"domain_scores_codex":[0.9962616,0.0008634061,0.0005535306,0.0003932663,0.00176574,0.0001624877],"domain_scores_gemma":[0.9909241,0.007550091,0.0003879569,0.0003739862,0.0006759188,0.00008795558],"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":[0.001951756,0.002885353,0.1895699,0.00001088488,0.000793245,0.000002534487,0.003854938,0.07914255,0.02704292,0.02859668,0.002302604,0.6638466],"study_design_scores_gemma":[0.0001786068,0.0002179768,0.9834813,0.00001942131,0.000141899,0.000009569892,0.001428231,0.006084207,0.00009572852,0.0027129,0.005520713,0.0001094544],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9744468,0.0005978637,0.006566284,0.01610884,0.0007601034,0.0001508183,0.00000705802,0.000008392677,0.001353865],"genre_scores_gemma":[0.97606,0.00001874602,0.02301306,0.000478551,0.0003175205,0.00000544481,0.00000476732,0.000003796375,0.00009817346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7939114,"threshold_uncertainty_score":0.9645206,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391227797","doi":"10.1111/emip.12590","title":"Using OpenAI GPT to Generate Reading Comprehension Items","year":2024,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Reading comprehension; Comprehension; Reading (process); Sentence; Computer science; Cognition; Natural language processing; Artificial intelligence; Sample (material); Psychology; Cognitive psychology; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2292006550062576,"gpt":0.4155313631435855,"spread":0.1863307081373279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001704657,0.0001047963,0.00009004534,0.00009532482,0.0002226522,0.000774877,0.0002056665,0.000032653,0.00002960349],"category_scores_gemma":[0.0006401949,0.00009690991,0.00002161835,0.0003286944,0.00001569259,0.001271681,0.00008151884,0.00009931235,0.0001067519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001414958,"about_ca_system_score_gemma":0.0002199734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003025889,"about_ca_topic_score_gemma":0.000005727326,"domain_scores_codex":[0.9985257,0.0002062378,0.0001985759,0.0004062213,0.0005169924,0.0001462632],"domain_scores_gemma":[0.9987654,0.0004283536,0.00004776786,0.0002811834,0.0003633639,0.0001139023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007012863,0.0004982131,0.0003934867,0.0002686988,0.0001461469,0.000009297942,0.01374296,0.001700214,0.1939696,0.6359912,0.03557215,0.1176379],"study_design_scores_gemma":[0.00007562586,0.00006630782,0.003512979,0.0002037378,0.00003635377,0.0001331102,0.0002806189,0.02679518,0.00274914,0.005684999,0.9601875,0.0002744761],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04994125,0.02207053,0.5330088,0.3808956,0.005057779,0.001035916,0.000006668714,0.0002831639,0.007700377],"genre_scores_gemma":[0.8433148,0.0001380662,0.154156,0.001317128,0.000539774,0.00002584427,0.000006179279,0.00001019621,0.0004920173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9246153,"threshold_uncertainty_score":0.7472157,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2885169382","doi":"10.1111/emip.12211","title":"How Robust Are Cross‐Country Comparisons of PISA Scores to the Scaling Model Used?","year":2018,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":25,"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":"Criticism; Robustness (evolution); Underpinning; Item response theory; Psychology; Test (biology); Cross country; Psychometrics; Political science; Developmental psychology; Economics; Demographic economics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1301498662001438,"gpt":0.3787550552457036,"spread":0.2486051890455598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001391535,0.0001000907,0.0001168024,0.00005065544,0.0003299742,0.0005123011,0.0003984438,0.00002893876,0.000007386586],"category_scores_gemma":[0.002075884,0.00007472435,0.00002486233,0.0002445434,0.00008539332,0.0005280875,0.00009570461,0.0001333374,0.00001503834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003151627,"about_ca_system_score_gemma":0.0002116854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001239838,"about_ca_topic_score_gemma":0.00007187411,"domain_scores_codex":[0.9986129,0.0001263701,0.0001627559,0.000243162,0.000700334,0.0001544801],"domain_scores_gemma":[0.9980717,0.0003478651,0.0002080062,0.0003328501,0.0009592777,0.00008035629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000248513,0.002645121,0.1090599,0.0003144594,0.0005599114,0.000002831286,0.029784,0.2281277,0.002448642,0.3478672,0.2693268,0.00961485],"study_design_scores_gemma":[0.0004008404,0.000234534,0.0497829,0.0003613918,0.0001257088,0.00003367427,0.003131678,0.4887249,0.0008174491,0.003682131,0.4522132,0.0004915953],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.02731458,0.002817017,0.2651742,0.7021272,0.0008571699,0.0002327467,0.00001135517,0.00004648148,0.001419336],"genre_scores_gemma":[0.8978047,0.00003590594,0.09946898,0.001008572,0.0006902865,0.000006493733,0.000002126218,0.000006492901,0.0009763939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8704902,"threshold_uncertainty_score":0.4940132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3046538170","doi":"10.1111/emip.12382","title":"Synergy and Tension between Large‐Scale and Classroom Assessment: International Trends","year":2020,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Queen's University; Brock University","funders":"","keywords":"Scale (ratio); Test (biology); Political science; Mathematics education; Pedagogy; Sociology; Psychology; Geography; Geology; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.09632131387335943,"gpt":0.4206769110651631,"spread":0.3243555971918037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001338029,0.0001105199,0.0001332382,0.00005548412,0.0004620808,0.0002840409,0.0001031014,0.00005820222,0.0003935548],"category_scores_gemma":[0.0007046846,0.0001074821,0.00001981759,0.000144964,0.0000912692,0.000678461,0.00007887384,0.0001339768,0.000008068414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006137519,"about_ca_system_score_gemma":0.0001281849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003634855,"about_ca_topic_score_gemma":0.0001217818,"domain_scores_codex":[0.9982424,0.0002485282,0.0001736722,0.0002905626,0.0008713591,0.0001735126],"domain_scores_gemma":[0.9988795,0.0004481317,0.0001217065,0.00005784315,0.0002909317,0.0002019014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001222111,0.0004374725,0.8149075,0.00003774134,0.0003562179,0.000002594953,0.05000371,9.079566e-7,0.0006667293,0.06397557,0.03959125,0.02989812],"study_design_scores_gemma":[0.0003244299,0.00005331112,0.3227398,0.00001653907,0.00007424561,0.000001483268,0.01613181,0.00004029073,0.000003847855,0.0004635765,0.6600313,0.0001193701],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06594703,0.003649217,0.000281559,0.8006032,0.0008205088,0.0002368584,0.00002517447,0.00005304952,0.1283834],"genre_scores_gemma":[0.989265,0.001826033,0.004208669,0.001433643,0.001640826,0.00001379258,0.00004049318,0.000009167736,0.001562389],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.923318,"threshold_uncertainty_score":0.4382993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2562551526","doi":"10.1111/emip.12129","title":"A Process for Reviewing and Evaluating Generated Test Items","year":2016,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Test (biology); Process (computing); Subject-matter expert; Quality (philosophy); Domain (mathematical analysis); Computerized adaptive testing; Item bank; Item response theory; Data science; Artificial intelligence; Psychometrics; Expert system; Mathematics; Statistics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.2464384762232207,"gpt":0.4293302723194807,"spread":0.18289179609626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003246549,0.00009676581,0.0001053364,0.00003632392,0.0002495731,0.0001710147,0.0001140323,0.00002275727,0.000009624368],"category_scores_gemma":[0.009328654,0.00006709971,0.00001601981,0.00008805052,0.00001386406,0.0007657589,0.00002769258,0.00004599572,0.000008729598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004630772,"about_ca_system_score_gemma":0.0001366717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002792605,"about_ca_topic_score_gemma":0.000001093036,"domain_scores_codex":[0.9988226,0.0001487449,0.0002040837,0.000292691,0.0003856871,0.0001461568],"domain_scores_gemma":[0.9972374,0.001422132,0.0001765302,0.0001206002,0.0009836692,0.00005967383],"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":[0.00009147698,0.0005360389,0.01147234,0.001007356,0.0002389004,0.000002162071,0.01161925,0.00007867711,0.1559656,0.4058563,0.004294302,0.4088376],"study_design_scores_gemma":[0.0005587229,0.0004486511,0.00405378,0.00157576,0.00006164302,0.0000992026,0.0006378458,0.002302137,0.004046478,0.003634486,0.9821467,0.0004346101],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03711686,0.08924071,0.5798398,0.2832959,0.003176091,0.002820685,0.000009729967,0.000214437,0.004285828],"genre_scores_gemma":[0.9344079,0.0007348306,0.05617469,0.0006895736,0.001398982,0.0002653913,0.000001931473,0.00001875436,0.006307872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9778524,"threshold_uncertainty_score":0.9990162,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313410276","doi":"10.1111/emip.12537","title":"Using Active Learning Methods to Strategically Select Essays for Automated Scoring","year":2022,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for Advancing Health Outcomes; University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Scalability; Active learning (machine learning); Encoder; Transformer; Database; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.3365902019122547,"gpt":0.5652165547572977,"spread":0.228626352845043,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01562862,0.0001633782,0.0001947711,0.0001715124,0.001185579,0.00008752313,0.0001350655,0.00004298462,0.0008784932],"category_scores_gemma":[0.007200068,0.0001748068,0.00003965682,0.0003704728,0.00002393888,0.0001820065,0.00006125948,0.0006333948,0.000008827799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002882008,"about_ca_system_score_gemma":0.0002601426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004462705,"about_ca_topic_score_gemma":0.000001725886,"domain_scores_codex":[0.9921517,0.006381372,0.0002697522,0.0004365322,0.0004546564,0.0003059548],"domain_scores_gemma":[0.9961637,0.002719143,0.0002639127,0.0001428696,0.0006252194,0.0000851161],"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":[0.006707138,0.003153496,0.005395372,0.0001911587,0.002414115,0.00001157611,0.1569949,0.04890833,0.2272839,0.2500341,0.01912157,0.2797843],"study_design_scores_gemma":[0.0009108151,0.0011308,0.01750909,0.0000509554,0.000220843,0.000176937,0.0367869,0.003835209,0.0006428717,0.002928182,0.9352193,0.0005880861],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1618159,0.00530098,0.612847,0.05863455,0.007582868,0.003125969,0.00003469316,0.0009440279,0.149714],"genre_scores_gemma":[0.3901102,0.000003001759,0.6057253,0.000819337,0.0005210682,0.0003524213,0.00002104359,0.00004000297,0.002407686],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9160978,"threshold_uncertainty_score":0.9618885,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034257998","doi":"10.1111/emip.12052","title":"What Role Does, and Should, the Test <i>Standards</i> Play Outside of the United States of America?","year":2014,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Citation; Library science; Test (biology); Sociology; Political science; History; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.3389256374159915,"gpt":0.4786025746879919,"spread":0.1396769372720004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01617788,0.0001007864,0.0001970461,0.0001100849,0.0002138964,0.0002259591,0.0003730406,0.00002971321,0.0001006452],"category_scores_gemma":[0.2861833,0.00004396259,0.00003583603,0.0008843489,0.0002594176,0.0003892498,0.0001058782,0.0001332872,0.000001357805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001993323,"about_ca_system_score_gemma":0.0001163488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007685683,"about_ca_topic_score_gemma":0.00002208641,"domain_scores_codex":[0.9960136,0.001193407,0.0004500376,0.0002351371,0.001984146,0.0001236305],"domain_scores_gemma":[0.8983328,0.09821402,0.0008656449,0.0005233313,0.00199701,0.00006715506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005335416,0.001274077,0.4425583,0.0001290866,0.0003596289,4.391799e-7,0.03222039,0.001027322,0.009417335,0.0113025,0.1390386,0.3621388],"study_design_scores_gemma":[0.0001797678,0.0001092169,0.08928046,0.00007528387,0.00005429429,0.000008853614,0.02627731,0.0002275823,0.00146944,0.03257034,0.849658,0.00008940934],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3747042,0.0322652,0.003314059,0.5672406,0.004421299,0.000997756,0.0001221057,0.00002939659,0.01690535],"genre_scores_gemma":[0.9872172,0.002594127,0.007262933,0.002270564,0.0001784478,0.00001133185,0.000002689145,0.000007372052,0.0004553016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7106194,"threshold_uncertainty_score":0.7198294,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052069113","doi":"10.1111/emip.12003","title":"Validating Student Score Inferences With Person‐Fit Statistic and Verbal Reports: A Person‐Fit Study for Cognitive Diagnostic Assessment","year":2013,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Science Education and Pedagogy","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Statistic; Test (biology); Cognition; Consistency (knowledge bases); Psychology; Test statistic; Cognitive psychology; Artificial intelligence; Statistical hypothesis testing; Computer science; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3346735437565425,"gpt":0.504415793140177,"spread":0.1697422493836346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.004090074,0.0001697079,0.0001825724,0.00007908034,0.001315883,0.0008519161,0.0001140039,0.00003805379,0.0008568967],"category_scores_gemma":[0.01376665,0.0001435059,0.00001983706,0.0002046201,0.0002500664,0.001051542,0.00001994622,0.0001522427,0.00001128581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001817657,"about_ca_system_score_gemma":0.001495688,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008992793,"about_ca_topic_score_gemma":0.001966834,"domain_scores_codex":[0.9969896,0.0006644831,0.0002455241,0.0004827941,0.001320379,0.000297184],"domain_scores_gemma":[0.9918097,0.005891545,0.000350554,0.0001181215,0.001588743,0.0002413401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005651791,0.002100943,0.5686002,0.00005854704,0.0002447054,0.00000582631,0.4070252,0.000005210776,0.00002379614,0.006200463,0.00570953,0.009969058],"study_design_scores_gemma":[0.000293582,0.0004870402,0.3976256,0.00008424925,0.0001579607,0.00001548395,0.5949493,0.00001173883,0.000001571473,0.0003633191,0.00583843,0.000171739],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9348512,0.001481954,0.0004617436,0.0509715,0.001065921,0.003128484,0.00001433289,0.00003088097,0.007993989],"genre_scores_gemma":[0.9937828,0.0001406654,0.003191191,0.0004607043,0.0004871206,0.0009474742,0.00001246418,0.00001028355,0.0009672504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1879241,"threshold_uncertainty_score":0.9999843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2279705546","doi":"10.1111/emip.12103","title":"The Role of Socioeconomic Status in SAT–Freshman Grade Relationships Across Gender and Racial Subgroups","year":2016,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"School Choice and Performance","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Socioeconomic status; Ethnic group; Race (biology); Demography; Psychology; Test (biology); Predictive power; Academic achievement; Developmental psychology; Sociology; Gender studies; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.1052190430503295,"gpt":0.3906782734469965,"spread":0.285459230396667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003922009,0.00006170332,0.0000702923,0.00002373202,0.0007234277,0.00008695839,0.00008197485,0.00004833342,0.00007756356],"category_scores_gemma":[0.002336605,0.00004302952,0.00001462867,0.00006058585,0.0002037971,0.000717357,0.00001834142,0.0001083218,0.00002339695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000113645,"about_ca_system_score_gemma":0.0002782556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001946492,"about_ca_topic_score_gemma":0.008090938,"domain_scores_codex":[0.9987236,0.0004140832,0.0001857945,0.0001354929,0.0003331008,0.0002078978],"domain_scores_gemma":[0.9977562,0.001776153,0.0001410441,0.00008829879,0.0001642809,0.0000739984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001208719,0.0001246438,0.8583173,0.000009515046,0.00003410868,9.642505e-8,0.06392982,0.00000106757,0.0004748248,0.06092535,0.001379425,0.01468295],"study_design_scores_gemma":[0.0001621768,0.00001257092,0.5692189,0.00001120035,0.000008107664,6.547954e-7,0.02394616,9.496181e-7,0.00004278172,0.01236081,0.3941802,0.00005547136],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9201291,0.01754199,0.0000035343,0.0528601,0.0003082647,0.0001902812,0.000009834769,0.000006853446,0.008949986],"genre_scores_gemma":[0.9938078,0.005074644,0.0001703032,0.0000976067,0.0004978814,0.00002204917,0.000001810725,0.000004307902,0.0003236008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3928007,"threshold_uncertainty_score":0.5564094,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061917416","doi":"10.1111/emip.12015","title":"The Multiple‐Use of Accountability Assessments: Implications for the Process of Validation","year":2013,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Manitoba","funders":"","keywords":"Accountability; Process (computing); Argument (complex analysis); Quality (philosophy); Management science; Process management; Computer science; Best practice; Psychology; Political science; Medicine; Business; Engineering; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.4021609414534796,"gpt":0.5386433098125486,"spread":0.136482368359069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006528222,0.000101448,0.0001302985,0.00004948464,0.0004697872,0.0003932938,0.0004193373,0.00002820337,0.0001416399],"category_scores_gemma":[0.02662457,0.00005389663,0.00005711911,0.0002953236,0.0001497011,0.001507936,0.0000434385,0.0000692178,0.000007785246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006021834,"about_ca_system_score_gemma":0.0004898212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005208202,"about_ca_topic_score_gemma":0.00004187745,"domain_scores_codex":[0.9973544,0.000268045,0.000701758,0.0002549735,0.001289191,0.0001316325],"domain_scores_gemma":[0.9655555,0.02612468,0.0008263744,0.0004936074,0.006952137,0.00004769082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004818703,0.004102544,0.4740013,0.0001705762,0.0006918529,6.038855e-9,0.005663354,0.0004428162,0.02140578,0.1593301,0.1320303,0.2016796],"study_design_scores_gemma":[0.0002377618,0.0001197779,0.7525235,0.00001906846,0.00009019927,0.000001291946,0.01085174,0.0003184871,0.001659494,0.07418159,0.1598928,0.0001042372],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3007029,0.00339294,0.01117155,0.6761726,0.001645659,0.005296246,0.000104053,0.00001434808,0.001499663],"genre_scores_gemma":[0.9930841,0.0001567515,0.00481854,0.0002970136,0.000154882,0.0009025418,0.00001480098,0.000006116953,0.0005651976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6923812,"threshold_uncertainty_score":0.9815746,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2055319746","doi":"10.1111/j.1745-3992.2004.tb00161.x","title":"Modeling Passing Rates on a Computer‐Based Medical Licensing Examination: An Application of Survival Data Analysis","year":2004,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Medical Education and Admissions","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Covariate; United States Medical Licensing Examination; Proportional hazards model; Survival analysis; Medical school; Variable (mathematics); Medicine; Medical education; Computer science; Psychology; Statistics; Surgery; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2274161709273148,"gpt":0.4633927414507003,"spread":0.2359765705233855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003244457,0.0001213929,0.0002490772,0.0001941063,0.0001615242,0.00004469776,0.00014269,0.00007588392,0.0003721322],"category_scores_gemma":[0.009451598,0.0001053533,0.00003575464,0.000464286,0.00005962834,0.0002918797,0.00002988847,0.0001872713,0.000006606178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009349953,"about_ca_system_score_gemma":0.002187687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004258551,"about_ca_topic_score_gemma":0.00005322517,"domain_scores_codex":[0.9973338,0.000274691,0.000383285,0.0003952713,0.001488188,0.0001247223],"domain_scores_gemma":[0.9974387,0.0005305152,0.0001673352,0.0005050888,0.0007661154,0.0005921884],"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":[0.002833464,0.05426504,0.01568476,0.001927754,0.00554358,0.00003443482,0.01837749,0.1012452,0.0102259,0.1304764,0.003852318,0.6555337],"study_design_scores_gemma":[0.002214906,0.0004602897,0.04099958,0.0007698305,0.001955397,0.00004486825,0.002710075,0.9315375,0.0004056052,0.0005916689,0.01795547,0.0003547937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08146984,0.001517301,0.4710386,0.4424405,0.0007089739,0.0006750302,0.0000171279,0.00006672582,0.002065815],"genre_scores_gemma":[0.942075,0.00007748626,0.05372532,0.002862748,0.0006900364,0.0000113749,0.0005214916,0.00001053819,0.00002601193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8606051,"threshold_uncertainty_score":0.9988922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2795852592","doi":"10.1111/emip.12198","title":"A Review of Recent Research on Individual‐Level Score Reports","year":2018,"lang":"en","type":"review","venue":"Educational Measurement Issues and Practice","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Test (biology); Computer science; Focus (optics); Knowledge management; Psychology; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.8619976910036018,"gpt":0.6550214592649924,"spread":0.2069762317386094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01566091,0.0003925577,0.0009974786,0.0003027703,0.000211398,0.00006467659,0.0004097661,0.0002763655,0.01204313],"category_scores_gemma":[0.007893226,0.0002938593,0.0001852352,0.0008379045,0.0002189225,0.0001383613,0.00009846828,0.0008362135,0.0007113995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002051836,"about_ca_system_score_gemma":0.0013002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001067442,"about_ca_topic_score_gemma":0.000002543984,"domain_scores_codex":[0.9918364,0.003377513,0.001277481,0.0009589893,0.002159024,0.0003906247],"domain_scores_gemma":[0.9909995,0.003730173,0.001322876,0.0008715204,0.002866091,0.0002098265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000367291,0.002057377,0.00001568505,0.02171743,0.0005696143,0.000006475711,0.0002928548,3.620432e-9,7.690469e-8,0.006812384,0.6030199,0.3654715],"study_design_scores_gemma":[0.00006889992,0.0003483306,0.0005875271,0.07285575,0.0005657261,0.0002989682,0.0001964128,1.27923e-9,1.716711e-7,0.001785569,0.9230408,0.0002518554],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001544391,0.8878733,9.895169e-7,0.01559044,0.002726556,0.001321125,0.00007251647,0.0000104841,0.09240305],"genre_scores_gemma":[0.000004775834,0.9897828,0.0009371408,0.002479854,0.001724006,0.0008626519,0.0004010241,0.00003893572,0.003768816],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3652196,"threshold_uncertainty_score":0.9999514,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035205464","doi":"10.1111/emip.12353","title":"Exploring the Structure of Teachers’ Emotional Labor in the Classroom: A Multitrait–Multimethod Analysis","year":2020,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Emotional Labor in Professions","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada; Education University of Hong Kong","keywords":"Psychology; Emotional labor; Pride; Valence (chemistry); Social psychology; Anxiety; Negative emotion; School teachers; Emotional expression; Developmental psychology; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.2881136308792331,"gpt":0.4361760759650995,"spread":0.1480624450858664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003512266,0.00009240398,0.0001303301,0.0000665612,0.0004822843,0.0000673356,0.0003005461,0.00004031389,0.0003578129],"category_scores_gemma":[0.01202227,0.00005954973,0.00005538562,0.00112196,0.0001505781,0.0005408271,0.00002820565,0.0003090779,0.000005277909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006829801,"about_ca_system_score_gemma":0.0003804627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001954621,"about_ca_topic_score_gemma":0.001087491,"domain_scores_codex":[0.9959121,0.002259297,0.0002512661,0.0002012792,0.001225207,0.0001507961],"domain_scores_gemma":[0.9959139,0.003154669,0.0001795187,0.0001344404,0.0005483909,0.00006914499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0001250439,0.0006082558,0.07602108,0.00004069878,0.0007695211,0.000001290932,0.5966793,0.0007378435,0.00294171,0.3115954,0.004099728,0.006380171],"study_design_scores_gemma":[0.0002174357,0.00002943286,0.7044086,0.00003602165,0.00037526,0.000001317255,0.1242537,0.00006681509,0.00007439599,0.004025107,0.1663764,0.0001355981],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3450758,0.001620956,0.0001607378,0.6485308,0.0003484052,0.0004422058,0.00004607999,0.00001302937,0.003762009],"genre_scores_gemma":[0.9862344,0.0002626587,0.01059477,0.002182842,0.0005674023,0.00002244495,0.00001283082,0.000005288721,0.000117347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6463479,"threshold_uncertainty_score":0.9962999,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2804917593","doi":"10.1111/emip.12201","title":"Methodologies for Investigating and Interpreting Student–Teacher Rating Incongruence in Noncognitive Assessment","year":2018,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Education, Achievement, and Giftedness","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"American Psychological Association; American Educational Research Association","keywords":"Psychology; Construct (python library); Variety (cybernetics); Congruence (geometry); Predictive validity; Interpretation (philosophy); Divergence (linguistics); Construct validity; Descriptive statistics; Mathematics education; Social psychology; Psychometrics; Developmental psychology; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2581577380829526,"gpt":0.5537707121933004,"spread":0.2956129741103478,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007374536,0.0001667263,0.0001824999,0.0001072429,0.0002954731,0.0001430535,0.0001174868,0.00006626463,0.0001960817],"category_scores_gemma":[0.0093787,0.0001637703,0.00001937431,0.0001501405,0.0002059686,0.0004627889,0.00005894245,0.0001980329,0.000005266024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001180374,"about_ca_system_score_gemma":0.0002212604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001012596,"about_ca_topic_score_gemma":0.000344201,"domain_scores_codex":[0.9975345,0.00110893,0.0003840627,0.0004443146,0.0002812851,0.0002469729],"domain_scores_gemma":[0.9948756,0.003849062,0.0003224825,0.0001475114,0.0007255664,0.0000797432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001708966,0.0008017028,0.8063116,0.0001051029,0.0002867258,6.634256e-7,0.1377367,0.000001370091,0.00298296,0.02595911,0.002705243,0.02293794],"study_design_scores_gemma":[0.0009069818,0.0004410142,0.7945104,0.0003315842,0.0001217125,0.00001676177,0.1825566,0.00006784064,0.000254247,0.008598365,0.01184341,0.0003510791],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.907374,0.004166922,0.005021853,0.04782296,0.002670334,0.001411702,0.000009611162,0.0000436294,0.03147903],"genre_scores_gemma":[0.8900746,0.00005784324,0.1067968,0.001353623,0.0007967387,0.0004189632,0.00001397529,0.00001671799,0.0004707178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.101775,"threshold_uncertainty_score":0.9989657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002384848","doi":"10.1111/j.1745-3992.2002.tb00103.x","title":"What Do School‐Level Scores From Large‐Scale Assessments Really Measure?","year":2002,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Public Health","funders":"","keywords":"Reading (process); Scale (ratio); Variance (accounting); Psychology; Cognition; Measure (data warehouse); Subject (documents); Illusion; Mathematics education; Cognitive psychology; Computer science; Linguistics; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2066488833662569,"gpt":0.420967314211943,"spread":0.2143184308456861,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001877834,0.000220596,0.0002008242,0.00007329907,0.0003204797,0.0004953707,0.0001628792,0.00008800816,0.01894274],"category_scores_gemma":[0.003928123,0.0002174774,0.00005441325,0.0001521079,0.00005930189,0.001283786,0.00005854323,0.0002858386,0.0007662129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001246504,"about_ca_system_score_gemma":0.0001007373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001231755,"about_ca_topic_score_gemma":0.0001656324,"domain_scores_codex":[0.9972222,0.0005882959,0.0003513517,0.0005590451,0.0009232163,0.0003558886],"domain_scores_gemma":[0.9964151,0.001779913,0.0002287165,0.0003565527,0.001006664,0.0002130283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009737561,0.009947849,0.2923798,0.0001307143,0.00208951,0.0000371961,0.05270398,0.000004340163,0.001516728,0.0250965,0.3709186,0.244201],"study_design_scores_gemma":[0.00144311,0.0002332184,0.4472019,0.0005086889,0.0002868849,0.00006039243,0.05200572,0.00002712387,0.00004230738,0.007411547,0.4902259,0.000553186],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2435073,0.2163925,0.0009069377,0.1508336,0.01259159,0.001651161,0.0002695092,0.0002038083,0.3736435],"genre_scores_gemma":[0.9768193,0.002192085,0.007094012,0.002845784,0.001894177,0.0001691541,0.0000607303,0.00004162074,0.008883161],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.733312,"threshold_uncertainty_score":0.9848372,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2615786270","doi":"10.1111/emip.12150","title":"Differential Prediction in the Use of the SAT and High School Grades in Predicting College Performance: Joint Effects of Race and Language","year":2017,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Higher Education Research Studies","field":"Social 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 Waterloo","funders":"University of Minnesota","keywords":"Ethnic group; Language proficiency; Psychology; Race (biology); Standardized test; Affect (linguistics); First language; Language assessment; Mathematics education; Linguistics; Sociology; Gender studies","retraction":null,"screen_n_in":null,"score":{"opus":0.09120021442940497,"gpt":0.3903774829567992,"spread":0.2991772685273942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001732661,0.00005769072,0.0001001832,0.00004858049,0.0005477876,0.0001051322,0.000109996,0.00002867397,0.00001939791],"category_scores_gemma":[0.01159187,0.00003759945,0.00000991489,0.00008684689,0.0002930481,0.0005419176,0.00005452463,0.0001333976,3.290609e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005188028,"about_ca_system_score_gemma":0.0001874392,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006841575,"about_ca_topic_score_gemma":0.001206144,"domain_scores_codex":[0.9984018,0.0006141022,0.0001574836,0.0001139233,0.0006080354,0.000104607],"domain_scores_gemma":[0.9982737,0.001180961,0.0001925606,0.0001399997,0.0001783952,0.00003433969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004952714,0.0002309061,0.9349256,0.0001835274,0.00003049143,2.474927e-7,0.05949792,0.000002321024,0.001029665,0.002001568,0.001305416,0.0007427701],"study_design_scores_gemma":[0.0002457474,0.00003654478,0.9827394,0.0001881091,0.0000233804,9.999862e-7,0.01331704,0.00001409611,0.0002520366,0.0001035282,0.003045983,0.00003315122],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.962194,0.001464271,7.431825e-7,0.03533066,0.0002540761,0.0004677338,0.000006215022,0.000001929109,0.0002804285],"genre_scores_gemma":[0.9977342,0.001562098,0.0001379339,0.00004044169,0.0001644929,0.00005099775,9.667619e-7,0.000002535037,0.0003062877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04781374,"threshold_uncertainty_score":0.999772,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1876976565","doi":"10.1111/j.1745-3992.2010.00198.x","title":"Reporting the Percentage of Students above a Cut Score: The Effect of Group Size","year":2011,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","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":"University of Toronto","funders":"","keywords":"Mathematics education; Scale (ratio); Statistics; Psychology; Reading (process); Mathematics; Geography; Cartography; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.3899556216284745,"gpt":0.5438855402313928,"spread":0.1539299186029183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03953705,0.00009783889,0.0001913273,0.00003967813,0.0002130492,0.00009444424,0.0004550954,0.00002394023,0.001373268],"category_scores_gemma":[0.03317422,0.00004538244,0.00006488707,0.0002139869,0.0001179918,0.0004297386,0.00008153635,0.0001182061,0.00002473365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003048049,"about_ca_system_score_gemma":0.0001512515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003700551,"about_ca_topic_score_gemma":0.00005052711,"domain_scores_codex":[0.9940634,0.001141178,0.00106062,0.0002124548,0.003411679,0.0001106974],"domain_scores_gemma":[0.9905308,0.006110097,0.00207376,0.0004303168,0.0008130316,0.00004193594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005202565,0.0005024013,0.9531571,0.00004684442,0.0001836036,6.400788e-7,0.02030051,0.00001099256,0.00193411,0.004738849,0.006600878,0.01200386],"study_design_scores_gemma":[0.0003138801,0.0003783671,0.9580823,0.00005625459,0.0001182407,0.0000177112,0.00786855,0.00002860305,0.001874361,0.001465321,0.02972298,0.00007349921],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9649192,0.001573741,0.00005889601,0.01449225,0.0007190075,0.0006166679,0.000002823798,0.000004426049,0.01761299],"genre_scores_gemma":[0.9981534,0.0001425018,0.0005780228,0.0003428422,0.0001201214,0.00004017439,0.000001079458,0.000004540211,0.000617358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03323416,"threshold_uncertainty_score":0.9995396,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405618562","doi":"10.1111/emip.12663","title":"Instruction‐Tuned Large‐Language Models for Quality Control in Automatic Item Generation: A Feasibility Study","year":2024,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Quality (philosophy); Computer science; Control (management); Item response theory; Language proficiency; Mathematics education; Natural language processing; Psychology; Artificial intelligence; Psychometrics; Developmental psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1967005621322491,"gpt":0.4278503410420334,"spread":0.2311497789097843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005749509,0.000120679,0.0001613308,0.00009274339,0.0001460665,0.0003856867,0.0001815943,0.00003596849,0.00002230146],"category_scores_gemma":[0.001928048,0.0001137154,0.00003452355,0.000202767,0.000009175192,0.00147966,0.00003713127,0.0001145597,0.000004883827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002008802,"about_ca_system_score_gemma":0.0003292847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00028818,"about_ca_topic_score_gemma":0.0001914033,"domain_scores_codex":[0.9978186,0.0005365051,0.0004124921,0.0004844852,0.0005806974,0.0001671958],"domain_scores_gemma":[0.9982303,0.0009441695,0.00009201572,0.0003467821,0.0003262642,0.00006044625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002264336,0.005907715,0.00945171,0.0009870771,0.0005332706,0.00001373641,0.1164344,0.004923196,0.003104149,0.7764305,0.003272068,0.0787157],"study_design_scores_gemma":[0.00132691,0.000116066,0.008536451,0.00006225905,0.00004774348,0.00001959335,0.003598936,0.969852,0.00003303837,0.0134019,0.002790081,0.0002149741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1889016,0.0071505,0.7537353,0.04604129,0.001803602,0.001851264,0.00001110202,0.000123558,0.0003818061],"genre_scores_gemma":[0.9584287,0.00001324042,0.04036526,0.0004096206,0.0004125712,0.0002524418,0.00000526028,0.000006703417,0.0001061687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9649289,"threshold_uncertainty_score":0.4637178,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319790235","doi":"10.1111/emip.12539","title":"Machine Learning Literacy for Measurement Professionals: A Practical Tutorial","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Toolbox; Computer science; Python (programming language); Data science; Context (archaeology); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1935689270038954,"gpt":0.4464950114435416,"spread":0.2529260844396461,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008937494,0.0002009159,0.0001840253,0.0001633759,0.0006569765,0.0005912802,0.0003241475,0.00007163228,0.00006990657],"category_scores_gemma":[0.02769241,0.000185878,0.00006183858,0.0005415924,0.00003771522,0.002499542,0.000160272,0.0002816986,0.0002548616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002127617,"about_ca_system_score_gemma":0.000774089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001512388,"about_ca_topic_score_gemma":0.00001429768,"domain_scores_codex":[0.9961962,0.0006087186,0.0004197842,0.000564319,0.001790801,0.0004202135],"domain_scores_gemma":[0.9940224,0.002528862,0.0002588505,0.0003177389,0.002692967,0.0001792292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006714257,0.002015183,0.0005219921,0.0002912403,0.0003083005,0.00002023077,0.01615319,0.0002782043,0.006922656,0.8153793,0.1067606,0.05067773],"study_design_scores_gemma":[0.0002718051,0.0002422335,0.0004608881,0.0001163294,0.00004231407,0.00003760927,0.0009699821,0.01192593,0.001534666,0.02189523,0.9622102,0.0002928239],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.001262328,0.009274556,0.1718987,0.7974012,0.0100641,0.002651719,0.00001269722,0.000651554,0.006783124],"genre_scores_gemma":[0.6779231,0.001302929,0.3006404,0.004045403,0.006503541,0.001802153,0.00008787464,0.00009295139,0.007601681],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.8554496,"threshold_uncertainty_score":0.9804978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386482646","doi":"10.1111/emip.12572","title":"Digital Module 33: Fairness in Classroom Assessment: Dimensions and Tensions","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Legitimacy; Perception; Psychology; Disengagement theory; Critical reflection; Social psychology; Pedagogy; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.1105547684473078,"gpt":0.4277434972698937,"spread":0.3171887288225859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001956744,0.0001117897,0.0001300975,0.0001373155,0.0005760218,0.0003445279,0.00009734905,0.00005695872,0.0001102905],"category_scores_gemma":[0.001916277,0.0001090962,0.00002226493,0.0004800252,0.0001224274,0.001040561,0.00006147143,0.0001472335,0.00006538955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001135871,"about_ca_system_score_gemma":0.0003128315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008637399,"about_ca_topic_score_gemma":0.0005159203,"domain_scores_codex":[0.9981396,0.0002305761,0.0001928653,0.0002794463,0.0008939307,0.0002636171],"domain_scores_gemma":[0.9983431,0.00102623,0.00008493406,0.0001097991,0.000302262,0.0001337477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007850265,0.001197746,0.6932337,0.00004227895,0.0001554957,0.00001429496,0.02457322,0.00003580787,0.0006499944,0.2204437,0.04708235,0.012493],"study_design_scores_gemma":[0.0003149052,0.0000326041,0.5868399,0.00005128288,0.00003387219,0.000002894498,0.02771617,0.00007061109,0.000002120903,0.005760249,0.3789951,0.0001803277],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3753265,0.002834674,0.00007137426,0.3405716,0.001880621,0.001058806,0.00003050287,0.000169603,0.2780563],"genre_scores_gemma":[0.9923266,0.001745045,0.0007591359,0.0002500136,0.0003146202,0.00004968646,0.00002528848,0.00001021359,0.004519389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6170001,"threshold_uncertainty_score":0.4448814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389347402","doi":"10.1111/emip.12585","title":"Digital Module 34: Introduction to Multilevel Measurement Modeling","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Mental Health Research Topics","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Structural equation modeling; Multilevel model; Computer science; Code (set theory); Latent variable; Process (computing); Data mining; Software engineering; Programming language; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.3432883525820852,"gpt":0.4905485480493123,"spread":0.1472601954672271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004080219,0.0001580144,0.0001402292,0.0002052521,0.0002748343,0.0001582988,0.0001444175,0.00005913303,0.000753038],"category_scores_gemma":[0.004608686,0.0001599971,0.00002959989,0.0003266405,0.00002526532,0.0005118931,0.00007435048,0.0002151849,0.002228218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000471025,"about_ca_system_score_gemma":0.0002015437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004172751,"about_ca_topic_score_gemma":0.0000231326,"domain_scores_codex":[0.996765,0.0002728549,0.0003368159,0.0005123418,0.001683855,0.0004291064],"domain_scores_gemma":[0.9980372,0.0002173234,0.00008188723,0.0003369318,0.001024626,0.0003020985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001393629,0.002324721,0.001433248,0.0003295265,0.0004386689,0.00001160152,0.01145334,0.002024181,0.002520324,0.03520524,0.6256315,0.3172341],"study_design_scores_gemma":[0.0005544291,0.000262665,0.01102636,0.00007085458,0.00003386927,0.00003944804,0.00514918,0.002565835,0.0000972792,0.001930421,0.9779594,0.0003102718],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.05292246,0.005829594,0.006789848,0.8632123,0.009147673,0.002818066,0.00005982863,0.0003068279,0.0589134],"genre_scores_gemma":[0.9751769,0.0001869329,0.003521669,0.001268366,0.005053176,0.0005058621,0.00007054169,0.00004580778,0.01417075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9222544,"threshold_uncertainty_score":0.9985487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4233643233","doi":"10.1111/emip.12321","title":"Digital Module 12: Think‐aloud Interviews and Cognitive Labs https://ncme.elevate.commpartners.com","year":2020,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Credibility; Think aloud protocol; Cognitive interview; Glossary; Interview; Cognition; Data collection; Psychology; Computer science; Protocol analysis; Comprehension; Reliability (semiconductor); Test (biology); Multimedia; Human–computer interaction; Cognitive science; Usability; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1497824668143513,"gpt":0.3536044543898638,"spread":0.2038219875755124,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011437,0.0001790525,0.0001727878,0.00005594382,0.0002660307,0.0008215471,0.0002990907,0.00003623982,0.00006755101],"category_scores_gemma":[0.00314872,0.0001630932,0.00003636665,0.0002592599,0.0001051565,0.002851674,0.0002853794,0.0002015651,0.000130645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002963104,"about_ca_system_score_gemma":0.000171575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002871982,"about_ca_topic_score_gemma":0.000005756979,"domain_scores_codex":[0.9981343,0.0001965204,0.0002445855,0.0005295089,0.0006599417,0.0002351958],"domain_scores_gemma":[0.9981884,0.0006493343,0.0002030647,0.0001524748,0.0005586191,0.0002480563],"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":[0.0003546282,0.001369939,0.005171317,0.0003286227,0.0005349805,0.00003280023,0.1583865,0.000009771939,0.002957333,0.0853393,0.06536274,0.6801521],"study_design_scores_gemma":[0.001751043,0.000959058,0.02521732,0.0005791876,0.0002097642,0.0001708015,0.02912798,0.006652228,0.001538335,0.01731921,0.91514,0.001335089],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.02879693,0.01806952,0.09041177,0.7746806,0.001253945,0.001160619,0.00003131026,0.0002090572,0.08538628],"genre_scores_gemma":[0.9859746,0.0003382035,0.003800112,0.008676792,0.0003905892,0.00001771667,0.00001208913,0.000008602256,0.0007812661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9571777,"threshold_uncertainty_score":0.7922197,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034878828","doi":"10.1111/j.1745-3992.2002.tb00087.x","title":"Scoring Examinee Responses for Multiple Inferences: Multiple Scoring in Assessments","year":2002,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"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":"Scoring system; Inference; Scale (ratio); Computer science; Psychology; Artificial intelligence; Medicine; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.8659566286900213,"gpt":0.5782094015970195,"spread":0.2877472270930018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01608875,0.000165765,0.0002617254,0.0004906423,0.0002692019,0.0004104097,0.000357761,0.00005859238,0.0002495822],"category_scores_gemma":[0.585434,0.0001377767,0.00004555586,0.0009185281,0.00004507967,0.00101933,0.00008038079,0.0001639219,0.00002724147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047855,"about_ca_system_score_gemma":0.00009514834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003411385,"about_ca_topic_score_gemma":0.0000915038,"domain_scores_codex":[0.9960557,0.0009064197,0.0006670631,0.0005724049,0.001485432,0.0003130113],"domain_scores_gemma":[0.8640235,0.1342553,0.0004048414,0.0003451539,0.0008587765,0.0001124156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002076816,0.0004573162,0.8855349,0.00002856653,0.00003440274,0.000001689805,0.001180058,0.0001254706,0.001200998,0.0008014815,0.003512766,0.1069147],"study_design_scores_gemma":[0.001186625,0.0002325074,0.8225355,0.0001624404,0.00002507749,0.00002027394,0.005178811,0.005266111,0.0002820428,0.007421266,0.1573713,0.0003180987],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9215936,0.01570768,0.0165434,0.02553661,0.004173244,0.001457987,0.00002701806,0.00007369718,0.01488675],"genre_scores_gemma":[0.8953777,0.0003440425,0.1024071,0.0002137453,0.0003259873,0.0001225874,0.000002183409,0.00001020207,0.001196426],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5693452,"threshold_uncertainty_score":0.5618371,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4362673096","doi":"10.1111/emip.12553","title":"Validation as Evaluating Desired and Undesired Effects: Insights From Cross‐Classified Mixed Effects Model","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"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":"Reliability (semiconductor); Variance (accounting); Computer science; Reliability engineering; Variance components; Validity; External validity; Cross-validation; Random effects model; Statistics; Data mining; Econometrics; Psychology; Artificial intelligence; Psychometrics; Mathematics; Engineering; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.7119997234981603,"gpt":0.5622263498475483,"spread":0.1497733736506121,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01347975,0.000213868,0.0003144408,0.0003787768,0.0005754098,0.0008650662,0.0002775135,0.0001070101,0.00004028981],"category_scores_gemma":[0.4101432,0.0001707012,0.00004773663,0.001294741,0.00008779406,0.0009524752,0.0001273676,0.0001685876,0.0001028595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008545153,"about_ca_system_score_gemma":0.0002314982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002091887,"about_ca_topic_score_gemma":0.000003984146,"domain_scores_codex":[0.9933771,0.002520011,0.0005828443,0.0007529683,0.002508761,0.0002582866],"domain_scores_gemma":[0.890418,0.1072798,0.000547323,0.0004201914,0.001148305,0.0001863913],"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":[0.001921345,0.001128687,0.06301504,0.0004484719,0.0008575063,0.00003044801,0.01588792,0.006930881,0.2273681,0.04712259,0.02953679,0.6057522],"study_design_scores_gemma":[0.001290331,0.0002734272,0.5001058,0.0001758449,0.0001606178,0.00001408562,0.001669305,0.0356035,0.006539955,0.4502565,0.003512927,0.0003976749],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9763839,0.005302481,0.005637723,0.007132469,0.001612637,0.0005514916,0.000004216169,0.00009106506,0.003284041],"genre_scores_gemma":[0.9405107,0.0002501942,0.05758426,0.0003746934,0.0003159837,0.00008404921,0.00002143589,0.00001710798,0.0008415729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6053545,"threshold_uncertainty_score":0.8341854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4237928641","doi":"10.1111/emip.12098","title":"On This Issue's Cover","year":2015,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Education Practices and Evaluation","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Scrolling; Test (biology); Depiction; Set (abstract data type); Psychology; Session (web analytics); Think aloud protocol; Multiple choice; Computer science; Applied psychology; Human–computer interaction; World Wide Web; Artificial intelligence; Visual arts; Usability; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2812239541239853,"gpt":0.4813383893869291,"spread":0.2001144352629438,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007505347,0.0000897219,0.00008036222,0.00005890987,0.000429802,0.0002436116,0.0001032831,0.00005607778,0.006737548],"category_scores_gemma":[0.02475066,0.00008771056,0.00001922354,0.0001759364,0.000074303,0.001174304,0.00001291813,0.0001211579,0.003112706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002698963,"about_ca_system_score_gemma":0.001152523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002898125,"about_ca_topic_score_gemma":0.00007709861,"domain_scores_codex":[0.9971421,0.0008187766,0.0001657851,0.0002111292,0.001494773,0.0001673804],"domain_scores_gemma":[0.9968337,0.00132062,0.0001817773,0.0001441638,0.001288514,0.0002311892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001349811,0.0004497606,0.0004375916,0.000006540838,0.00003546983,3.04186e-7,0.033798,0.00002383458,0.00001732291,0.1849292,0.775543,0.004623962],"study_design_scores_gemma":[0.0001853984,0.00007930988,0.0008609031,0.00001812499,0.00004451872,0.000002724056,0.01465487,0.000008852934,0.00001167867,0.01026002,0.9737614,0.0001121544],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.002382948,0.002312138,0.00002820787,0.4315665,0.001816851,0.0002150332,0.000001264522,0.00002331337,0.5616537],"genre_scores_gemma":[0.8489295,0.00197287,0.005810003,0.01404293,0.004987917,0.0001076276,0.00002651576,0.00002471777,0.1240979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8465466,"threshold_uncertainty_score":0.9976635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4246593371","doi":"10.1111/emip.12090","title":"Issue Information ‐ TOC &amp; Editorial board","year":2016,"lang":"en","type":"paratext","venue":"Educational Measurement Issues and Practice","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":0,"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":"Editorial board; Computer science; Business; Environmental science; Library science","retraction":null,"screen_n_in":null,"score":{"opus":0.1602917520950539,"gpt":0.4656371866650795,"spread":0.3053454345700256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008893053,0.0004531054,0.0004792442,0.0004482617,0.0004435481,0.001650241,0.0007588356,0.0003310454,0.03395348],"category_scores_gemma":[0.0220886,0.0003249165,0.0001319366,0.0003772921,0.0001088871,0.004090543,0.0001820963,0.0004285724,0.08371153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000472598,"about_ca_system_score_gemma":0.002283642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004070014,"about_ca_topic_score_gemma":0.00003071548,"domain_scores_codex":[0.9896669,0.0007011881,0.001340136,0.0006838873,0.007206767,0.0004010612],"domain_scores_gemma":[0.9866531,0.00441414,0.001481456,0.0007446764,0.006415636,0.0002909351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001429134,0.0002129531,0.0000416687,0.0000403199,0.0001073908,4.196752e-8,0.0007798625,0.000002430023,0.00009342958,0.001772748,0.9852611,0.01154509],"study_design_scores_gemma":[0.0003908048,0.0001111219,0.0005643442,0.0001302868,0.00008118197,0.00000487677,0.001012222,7.492849e-7,0.00002893178,0.005670287,0.9915726,0.0004325573],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00005130797,0.005890021,0.0008083585,0.3131757,0.3214286,0.001004832,0.0002406387,0.00002157788,0.3573789],"genre_scores_gemma":[0.0008409128,0.002908908,0.006055466,0.004654479,0.2241094,0.000461695,0.0007554438,0.00004279583,0.7601709],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.402792,"threshold_uncertainty_score":0.9999203,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388223267","doi":"10.1111/emip.12582","title":"Comparing Large‐Scale Assessments in Two Proctoring Modalities with Interactive Log Data Analysis","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Modalities; Comparability; Modality (human–computer interaction); Test (biology); Scale (ratio); Medicine; Computer science; Human–computer interaction; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5444063599822654,"gpt":0.5751607052320205,"spread":0.03075434524975507,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002164447,0.0001080422,0.0002141866,0.0002895569,0.0001352275,0.00007875306,0.00009814365,0.00002445611,0.00009303857],"category_scores_gemma":[0.001169057,0.00009533534,0.00001790496,0.0008304546,0.00002784771,0.0007596993,0.0000596219,0.0001983901,0.00003520074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002056722,"about_ca_system_score_gemma":0.0004120805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004610889,"about_ca_topic_score_gemma":0.003140795,"domain_scores_codex":[0.9983882,0.0001600628,0.0002957809,0.0003620409,0.000571355,0.0002225542],"domain_scores_gemma":[0.9983239,0.0006007801,0.0001343032,0.0003297607,0.0005141077,0.00009711559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005639302,0.0007361787,0.9779504,0.0001460324,0.0005277825,0.000005141645,0.01497887,0.0003468847,0.0001177934,0.000718736,0.001168079,0.002740156],"study_design_scores_gemma":[0.0003635056,0.0002487792,0.8119233,0.0005604404,0.00123737,0.00003960701,0.1338442,0.01807157,0.0005523928,0.001390188,0.03142526,0.0003434051],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9452178,0.001071018,0.0009661897,0.04610939,0.0005437516,0.0006083435,0.00001393392,0.00005278895,0.005416753],"genre_scores_gemma":[0.9947213,0.0002365149,0.003443235,0.0002737172,0.0003816273,0.00006959916,0.0003108289,0.00001045418,0.0005527437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1660272,"threshold_uncertainty_score":0.6970315,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}