{"meta":{"query_hash":"eaebb99799eb","filters":{"venue":"Educational Measurement Issues and Practice"},"cohort_total":38,"direct_labels_cover":0,"predictions_cover":38,"exported":38,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/eaebb99799eb","api":"https://metacan.xera.ac/api/v1/cohort?venue=Educational+Measurement+Issues+and+Practice"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics education; Scale (ratio); Statistics; Psychology; Reading (process); Mathematics; Geography; Cartography; Political science","score_opus":0.3899556216284745,"score_gpt":0.5438855402313928,"score_spread":0.15392991860291827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1876976565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9649192,0.0015737412,0.000058896014,0.014492251,0.0007190075,0.00061666785,0.0000028237985,0.0000044260487,0.01761299],"genre_scores_gemma":[0.9981534,0.0001425018,0.0005780228,0.00034284216,0.00012012136,0.000040174393,0.0000010794581,0.000004540211,0.00061735796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940634,0.0011411776,0.0010606196,0.00021245483,0.0034116793,0.00011069735],"domain_scores_gemma":[0.99053085,0.0061100973,0.00207376,0.00043031684,0.0008130316,0.00004193594],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039537046,0.00009783889,0.0001913273,0.000039678132,0.00021304924,0.000094444236,0.00045509537,0.000023940232,0.0013732683],"category_scores_gemma":[0.033174224,0.000045382443,0.00006488707,0.00021398686,0.00011799181,0.0004297386,0.00008153635,0.00011820608,0.000024733654],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052025646,0.0005024013,0.95315707,0.000046844423,0.00018360355,6.400788e-7,0.020300506,0.000010992564,0.0019341097,0.004738849,0.006600878,0.0120038595],"study_design_scores_gemma":[0.00031388013,0.00037836705,0.95808226,0.000056254587,0.000118240656,0.0000177112,0.00786855,0.000028603052,0.0018743606,0.0014653207,0.029722976,0.000073499206],"about_ca_topic_score_codex":0.00037005506,"about_ca_topic_score_gemma":0.00005052711,"teacher_disagreement_score":0.033234164,"about_ca_system_score_codex":0.000030480485,"about_ca_system_score_gemma":0.0001512515,"threshold_uncertainty_score":0.9995396},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.32269388672061894,"score_gpt":0.43327184522770973,"score_spread":0.11057795850709079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985695119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6960731,0.0075444146,0.00006702762,0.26531494,0.0015677728,0.00060189806,0.000006402762,0.000013205009,0.028811265],"genre_scores_gemma":[0.9931052,0.00026076726,0.002965138,0.0014049861,0.00037843763,0.00018430821,0.000026008198,0.0000100403995,0.0016651361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9980255,0.00048010598,0.00049303647,0.00033735938,0.00048699309,0.00017701155],"domain_scores_gemma":[0.99712783,0.001735792,0.00037755302,0.00016626145,0.00050464727,0.00008794272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028811875,0.00014529958,0.00014133712,0.00009237876,0.00035078518,0.000052155774,0.000083369625,0.00006185799,0.0004940513],"category_scores_gemma":[0.0024060227,0.00011774651,0.00002324468,0.00027048544,0.00012567712,0.00024258038,0.00002125987,0.00024746585,0.000007319416],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014583388,0.018963845,0.34618068,0.00043624683,0.0010440516,0.000042574884,0.11575496,0.00035300545,0.013222955,0.42230028,0.060331017,0.01991205],"study_design_scores_gemma":[0.00083391165,0.00025395484,0.8604285,0.00026060775,0.00007931481,0.0005232756,0.031744175,0.0000024792473,0.00009101814,0.035849743,0.06967563,0.00025740304],"about_ca_topic_score_codex":0.0013709904,"about_ca_topic_score_gemma":0.000035993708,"teacher_disagreement_score":0.51424783,"about_ca_system_score_codex":0.00015285151,"about_ca_system_score_gemma":0.0004970864,"threshold_uncertainty_score":0.54095155},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.20664888336625692,"score_gpt":0.420967314211943,"score_spread":0.21431843084568608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002384848","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24350734,0.21639247,0.0009069377,0.15083364,0.01259159,0.0016511615,0.00026950915,0.00020380835,0.37364355],"genre_scores_gemma":[0.9768193,0.0021920854,0.0070940116,0.0028457837,0.0018941766,0.00016915411,0.0000607303,0.00004162074,0.0088831615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972222,0.0005882959,0.00035135171,0.0005590451,0.0009232163,0.00035588862],"domain_scores_gemma":[0.99641514,0.001779913,0.00022871654,0.0003565527,0.0010066641,0.00021302834],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018778344,0.00022059603,0.00020082424,0.00007329907,0.00032047968,0.0004953707,0.00016287915,0.00008800816,0.018942736],"category_scores_gemma":[0.003928123,0.00021747735,0.000054413253,0.00015210788,0.00005930189,0.0012837859,0.00005854323,0.00028583856,0.0007662129],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097375613,0.0099478485,0.29237983,0.0001307143,0.0020895102,0.000037196096,0.05270398,0.000004340163,0.0015167284,0.025096502,0.37091857,0.24420102],"study_design_scores_gemma":[0.0014431102,0.00023321835,0.44720188,0.00050868886,0.0002868849,0.000060392427,0.052005723,0.000027123868,0.000042307376,0.007411547,0.49022594,0.000553186],"about_ca_topic_score_codex":0.0012317547,"about_ca_topic_score_gemma":0.00016563242,"teacher_disagreement_score":0.73331195,"about_ca_system_score_codex":0.00012465038,"about_ca_system_score_gemma":0.000100737314,"threshold_uncertainty_score":0.9848372},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1492879822400197,"score_gpt":0.36563478447414144,"score_spread":0.21634680223412173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006618588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6354553,0.0023030788,0.12275811,0.23572378,0.00047778798,0.0007581887,0.000023213186,0.00008317462,0.0024173516],"genre_scores_gemma":[0.716076,0.0001547576,0.28281012,0.000341376,0.00007250908,0.00019212488,0.00001133601,0.0000039748807,0.00033778654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9988487,0.00007211651,0.00020482282,0.00030870945,0.0004396865,0.00012596343],"domain_scores_gemma":[0.99857605,0.00066438515,0.000119675606,0.0002518686,0.00033088,0.000057118956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010905091,0.00011137839,0.00011628775,0.000112974405,0.00034722997,0.000078822064,0.00024757462,0.000031378622,0.000029655072],"category_scores_gemma":[0.00033030796,0.000087463326,0.00002667344,0.00027828178,0.00006448316,0.0006504263,0.000023959887,0.00009430978,0.0000032225546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008383154,0.001961672,0.0038884983,0.000039736165,0.00049826904,2.7105068e-7,0.0047430987,0.012747106,0.00054482504,0.8575131,0.000684545,0.11729503],"study_design_scores_gemma":[0.0010743061,0.0007390098,0.4916705,0.00012660964,0.0006747203,0.000070845366,0.0029559345,0.18945353,0.005760927,0.18338192,0.12308588,0.0010058245],"about_ca_topic_score_codex":0.000019646777,"about_ca_topic_score_gemma":0.000008357982,"teacher_disagreement_score":0.6741312,"about_ca_system_score_codex":0.000058695518,"about_ca_system_score_gemma":0.00027986304,"threshold_uncertainty_score":0.35666507},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.20234959071078357,"score_gpt":0.47284411788600883,"score_spread":0.27049452717522526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018691396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9197653,0.013615391,0.0109119015,0.027423711,0.0033816118,0.017171111,0.000063422034,0.000039022834,0.00762851],"genre_scores_gemma":[0.98486465,0.00009815132,0.0075683813,0.00035373762,0.0006468606,0.0048621544,0.0000699054,0.0000144948,0.0015216719],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985638,0.00020637955,0.00047277106,0.0003194734,0.0003128155,0.00012471642],"domain_scores_gemma":[0.99748343,0.0012280062,0.00059382856,0.00018849579,0.0004393053,0.00006692913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016629079,0.00012967737,0.00022564405,0.000047352503,0.00014192442,0.000044702803,0.00010515679,0.00008419656,0.0004987039],"category_scores_gemma":[0.0012035077,0.00011025575,0.000033151744,0.000077632045,0.00008802914,0.00018948477,0.000018004792,0.00013921366,0.0000048537754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015998981,0.005595442,0.072133854,0.0009407509,0.0006466612,2.0781194e-7,0.04051256,7.9628245e-7,0.5735736,0.079748735,0.091455966,0.13379152],"study_design_scores_gemma":[0.0011709674,0.0004183462,0.18663299,0.00021316242,0.0001400613,0.00002887531,0.008288768,0.000019530575,0.0028138014,0.0030996262,0.79686385,0.00031001677],"about_ca_topic_score_codex":0.00020821654,"about_ca_topic_score_gemma":0.000007002213,"teacher_disagreement_score":0.70540786,"about_ca_system_score_codex":0.000010674317,"about_ca_system_score_gemma":0.000040973293,"threshold_uncertainty_score":0.54604584},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Citation; Library science; Test (biology); Sociology; Political science; History; Computer science","score_opus":0.33892563741599147,"score_gpt":0.4786025746879919,"score_spread":0.13967693727200042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034257998","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37470424,0.032265205,0.0033140585,0.5672406,0.004421299,0.000997756,0.00012210575,0.000029396588,0.016905345],"genre_scores_gemma":[0.98721725,0.0025941266,0.0072629326,0.0022705644,0.00017844782,0.000011331847,0.000002689145,0.000007372052,0.0004553016],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99601364,0.0011934075,0.00045003762,0.00023513711,0.001984146,0.0001236305],"domain_scores_gemma":[0.89833283,0.09821402,0.0008656449,0.0005233313,0.0019970099,0.00006715506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016177876,0.000100786354,0.00019704615,0.000110084904,0.00021389639,0.00022595905,0.00037304062,0.00002971321,0.000100645215],"category_scores_gemma":[0.28618333,0.00004396259,0.000035836027,0.0008843489,0.00025941757,0.0003892498,0.00010587816,0.00013328719,0.0000013578052],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005335416,0.0012740765,0.4425583,0.00012908662,0.0003596289,4.3917987e-7,0.032220393,0.0010273219,0.009417335,0.011302497,0.13903862,0.36213878],"study_design_scores_gemma":[0.00017976777,0.00010921686,0.08928046,0.00007528387,0.000054294294,0.000008853614,0.026277313,0.0002275823,0.0014694398,0.03257034,0.849658,0.00008940934],"about_ca_topic_score_codex":0.0007685683,"about_ca_topic_score_gemma":0.00002208641,"teacher_disagreement_score":0.71061945,"about_ca_system_score_codex":0.000019933232,"about_ca_system_score_gemma":0.00011634884,"threshold_uncertainty_score":0.71982944},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scoring system; Inference; Scale (ratio); Computer science; Psychology; Artificial intelligence; Medicine; Geography","score_opus":0.8659566286900213,"score_gpt":0.5782094015970195,"score_spread":0.2877472270930018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034878828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9215936,0.015707685,0.016543403,0.025536606,0.004173244,0.001457987,0.000027018057,0.00007369718,0.014886753],"genre_scores_gemma":[0.8953777,0.0003440425,0.10240713,0.00021374527,0.00032598726,0.00012258737,0.0000021834092,0.000010202069,0.0011964265],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99605566,0.0009064197,0.00066706305,0.0005724049,0.0014854324,0.00031301135],"domain_scores_gemma":[0.8640235,0.13425532,0.0004048414,0.00034515385,0.0008587765,0.00011241561],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016088754,0.00016576496,0.00026172536,0.0004906423,0.0002692019,0.00041040967,0.00035776105,0.00005859238,0.00024958223],"category_scores_gemma":[0.585434,0.00013777669,0.00004555586,0.0009185281,0.00004507967,0.0010193295,0.00008038079,0.00016392185,0.00002724147],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020768156,0.0004573162,0.8855349,0.000028566534,0.00003440274,0.0000016898053,0.0011800578,0.00012547059,0.0012009979,0.00080148154,0.0035127657,0.106914684],"study_design_scores_gemma":[0.0011866252,0.00023250737,0.82253546,0.00016244037,0.00002507749,0.000020273936,0.0051788106,0.005266111,0.00028204283,0.0074212663,0.1573713,0.0003180987],"about_ca_topic_score_codex":0.0003411385,"about_ca_topic_score_gemma":0.0000915038,"teacher_disagreement_score":0.56934524,"about_ca_system_score_codex":0.00010478553,"about_ca_system_score_gemma":0.00009514834,"threshold_uncertainty_score":0.5618371},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.33467354375654246,"score_gpt":0.504415793140177,"score_spread":0.16974224938363458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052069113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93485117,0.0014819542,0.0004617436,0.050971504,0.0010659213,0.0031284837,0.000014332885,0.00003088097,0.007993989],"genre_scores_gemma":[0.9937828,0.00014066536,0.003191191,0.00046070426,0.00048712065,0.00094747415,0.000012464185,0.00001028355,0.0009672504],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9969896,0.0006644831,0.00024552413,0.00048279407,0.0013203785,0.00029718396],"domain_scores_gemma":[0.9918097,0.0058915447,0.00035055404,0.000118121505,0.0015887432,0.0002413401],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0040900735,0.00016970793,0.00018257236,0.00007908034,0.0013158834,0.0008519161,0.00011400388,0.000038053793,0.00085689675],"category_scores_gemma":[0.01376665,0.0001435059,0.000019837056,0.00020462013,0.00025006643,0.0010515421,0.000019946225,0.00015224269,0.000011285805],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056517907,0.0021009431,0.5686002,0.00005854704,0.00024470544,0.00000582631,0.40702525,0.000005210776,0.000023796145,0.006200463,0.0057095303,0.009969058],"study_design_scores_gemma":[0.00029358204,0.00048704023,0.39762557,0.00008424925,0.00015796075,0.00001548395,0.5949493,0.000011738829,0.0000015714731,0.00036331912,0.00583843,0.00017173898],"about_ca_topic_score_codex":0.008992793,"about_ca_topic_score_gemma":0.0019668336,"teacher_disagreement_score":0.18792409,"about_ca_system_score_codex":0.00018176572,"about_ca_system_score_gemma":0.0014956883,"threshold_uncertainty_score":0.99998426},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.22741617092731478,"score_gpt":0.4633927414507003,"score_spread":0.23597657052338553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055319746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08146984,0.0015173007,0.47103864,0.44244054,0.0007089739,0.0006750302,0.0000171279,0.00006672582,0.0020658146],"genre_scores_gemma":[0.942075,0.000077486264,0.053725325,0.0028627482,0.0006900364,0.000011374896,0.0005214916,0.00001053819,0.000026011927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973338,0.00027469103,0.00038328505,0.00039527126,0.0014881882,0.00012472234],"domain_scores_gemma":[0.9974387,0.0005305152,0.00016733524,0.0005050888,0.00076611544,0.0005921884],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032444573,0.000121392855,0.00024907725,0.00019410627,0.00016152416,0.00004469776,0.00014268995,0.000075883916,0.00037213223],"category_scores_gemma":[0.009451598,0.00010535328,0.000035754638,0.00046428601,0.00005962834,0.00029187973,0.000029888473,0.0001872713,0.000006606178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028334637,0.054265037,0.01568476,0.0019277538,0.0055435803,0.000034434815,0.018377487,0.101245195,0.010225904,0.13047636,0.003852318,0.65553373],"study_design_scores_gemma":[0.0022149056,0.0004602897,0.040999584,0.0007698305,0.001955397,0.000044868255,0.0027100747,0.9315375,0.00040560518,0.00059166894,0.017955473,0.00035479365],"about_ca_topic_score_codex":0.00042585508,"about_ca_topic_score_gemma":0.000053225165,"teacher_disagreement_score":0.8606051,"about_ca_system_score_codex":0.000093499526,"about_ca_system_score_gemma":0.0021876865,"threshold_uncertainty_score":0.9988922},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.125304747687676,"score_gpt":0.42539812488639406,"score_spread":0.3000933771987181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057691077","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05241347,0.002157657,0.0020502866,0.92827797,0.001316055,0.003906266,0.000103572005,0.00007582469,0.009698877],"genre_scores_gemma":[0.8214747,0.00021721976,0.17344514,0.003603147,0.0007861763,0.00013614455,0.000023664723,0.000008531233,0.00030531836],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986703,0.000079510486,0.00026511739,0.00032643607,0.00044782323,0.00021084919],"domain_scores_gemma":[0.9886548,0.009237464,0.00013696883,0.00008244598,0.0016872784,0.00020106068],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0021143574,0.00012911602,0.00012081735,0.000041410716,0.0014991523,0.00040661317,0.00005684313,0.00004543771,0.000051298935],"category_scores_gemma":[0.10302398,0.00012288586,0.000021827385,0.00009097559,0.00018334416,0.00034646565,0.000026054731,0.000059860664,0.0000024282429],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008286298,0.0069983313,0.06646917,0.00026323283,0.00026406927,0.00000252921,0.15944,0.000036998154,0.00520507,0.40149286,0.13633326,0.22266588],"study_design_scores_gemma":[0.0019883707,0.0007965352,0.10460256,0.00023625432,0.00039500924,0.00002026527,0.09344415,0.00012922475,0.000089430156,0.118332416,0.67930377,0.00066202396],"about_ca_topic_score_codex":0.00042585918,"about_ca_topic_score_gemma":0.000589828,"teacher_disagreement_score":0.92467487,"about_ca_system_score_codex":0.00017146478,"about_ca_system_score_gemma":0.00070770533,"threshold_uncertainty_score":0.99980074},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Psychology; Head start; Vocabulary; Developmental psychology; Association (psychology); Early childhood education; Early childhood; Preschool education; Academic skills; Mathematics education","score_opus":0.18145666075735387,"score_gpt":0.4182170293389201,"score_spread":0.2367603685815662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061554266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7813438,0.0037386927,0.000031070453,0.19765835,0.00038794504,0.0003950908,7.135899e-7,0.000027139928,0.016417176],"genre_scores_gemma":[0.98738223,0.0010127135,0.009482057,0.0010924019,0.00044799322,0.000032056956,0.0000042180286,0.000008005143,0.00053830614],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998268,0.0004487006,0.00022379914,0.00028485805,0.00058450503,0.00019014085],"domain_scores_gemma":[0.9987459,0.00051524874,0.00013926023,0.00008620002,0.00028807088,0.00022533014],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0040923664,0.00011297651,0.00011677128,0.00008955173,0.00049754244,0.0006677088,0.00006487397,0.00006652955,0.00011254122],"category_scores_gemma":[0.010666543,0.0001131232,0.000010711537,0.00017787116,0.00010215245,0.0016611806,0.000026229716,0.00019517376,0.000012343692],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008698631,0.0011849051,0.5862174,0.0000968946,0.000100773424,0.0000041293974,0.34565222,0.000020054458,0.00078496983,0.037804537,0.00982657,0.018220544],"study_design_scores_gemma":[0.00047272607,0.000032060314,0.83091384,0.00014990482,0.000027587079,0.000010578537,0.053388864,7.508151e-7,0.000035838348,0.008744118,0.10602167,0.00020204262],"about_ca_topic_score_codex":0.00737318,"about_ca_topic_score_gemma":0.0009926421,"teacher_disagreement_score":0.29226336,"about_ca_system_score_codex":0.00022575192,"about_ca_system_score_gemma":0.0016311909,"threshold_uncertainty_score":0.9992368},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4021609414534796,"score_gpt":0.5386433098125486,"score_spread":0.13648236835906902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061917416","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30070293,0.00339294,0.011171551,0.6761726,0.0016456585,0.005296246,0.00010405302,0.000014348079,0.0014996625],"genre_scores_gemma":[0.99308413,0.00015675153,0.0048185396,0.00029701358,0.000154882,0.0009025418,0.000014800984,0.0000061169526,0.00056519755],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973544,0.00026804497,0.00070175796,0.00025497348,0.0012891906,0.00013163252],"domain_scores_gemma":[0.9655555,0.026124684,0.0008263744,0.00049360737,0.006952137,0.000047690824],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006528222,0.000101448,0.00013029853,0.000049484643,0.00046978722,0.0003932938,0.00041933733,0.000028203367,0.00014163995],"category_scores_gemma":[0.026624568,0.000053896627,0.00005711911,0.00029532358,0.00014970111,0.0015079362,0.000043438497,0.0000692178,0.000007785246],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048187026,0.004102544,0.47400126,0.00017057621,0.0006918529,6.038855e-9,0.005663354,0.00044281618,0.021405783,0.15933011,0.13203026,0.20167957],"study_design_scores_gemma":[0.00023776176,0.00011977793,0.75252354,0.000019068462,0.00009019927,0.000001291946,0.01085174,0.00031848706,0.001659494,0.074181594,0.15989284,0.000104237195],"about_ca_topic_score_codex":0.0005208202,"about_ca_topic_score_gemma":0.00004187745,"teacher_disagreement_score":0.6923812,"about_ca_system_score_codex":0.000060218343,"about_ca_system_score_gemma":0.0004898212,"threshold_uncertainty_score":0.9815746},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5327361304287398,"score_gpt":0.5248611500943309,"score_spread":0.007874980334408921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064530600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9744468,0.00059786375,0.006566284,0.016108844,0.0007601034,0.00015081828,0.0000070580204,0.000008392677,0.0013538648],"genre_scores_gemma":[0.97606,0.000018746015,0.023013057,0.00047855097,0.0003175205,0.00000544481,0.00000476732,0.000003796375,0.000098173456],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962616,0.0008634061,0.0005535306,0.0003932663,0.0017657399,0.00016248772],"domain_scores_gemma":[0.9909241,0.0075500906,0.00038795685,0.00037398623,0.0006759188,0.00008795558],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0072387457,0.00011686607,0.00026099329,0.00089789793,0.00022850937,0.00020073976,0.00027304707,0.000040513565,0.00024888682],"category_scores_gemma":[0.043536127,0.00007806699,0.000060096576,0.0030314554,0.00003424635,0.00037976587,0.0000255921,0.00014658127,0.000003774149],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019517561,0.002885353,0.18956992,0.000010884884,0.000793245,0.0000025344868,0.0038549383,0.07914255,0.027042922,0.02859668,0.002302604,0.6638466],"study_design_scores_gemma":[0.00017860682,0.00021797678,0.9834813,0.00001942131,0.000141899,0.0000095698915,0.0014282307,0.006084207,0.00009572852,0.0027128996,0.0055207126,0.0001094544],"about_ca_topic_score_codex":0.0006463495,"about_ca_topic_score_gemma":0.00006197618,"teacher_disagreement_score":0.7939114,"about_ca_system_score_codex":0.0000854115,"about_ca_system_score_gemma":0.000085655716,"threshold_uncertainty_score":0.9645206},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8614623269368624,"score_gpt":0.6322567921565106,"score_spread":0.22920553478035177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109560181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92710334,0.007943781,0.014774793,0.0469338,0.0009059166,0.00026780384,0.000012032606,0.000024513947,0.0020340176],"genre_scores_gemma":[0.8506394,0.00007271052,0.14711201,0.0018262304,0.0002556107,0.00000926067,0.0000019582046,0.000006194981,0.00007663307],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956569,0.0010880899,0.00050174334,0.00057934725,0.001947805,0.00022612959],"domain_scores_gemma":[0.97234774,0.026050944,0.0003006471,0.00030843375,0.0007749212,0.00021730026],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008691677,0.00018181783,0.00029999416,0.0003893523,0.00032935978,0.00062832015,0.00027635577,0.000052060353,0.00042145076],"category_scores_gemma":[0.10309957,0.00013318083,0.00004545771,0.0007507514,0.00011303038,0.0007332371,0.00012816882,0.00013179766,0.000021198057],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000685163,0.0009832658,0.7105658,0.00007674759,0.0003353155,0.0000058897062,0.0037447189,0.00035707306,0.05656612,0.0129467035,0.016259607,0.19747359],"study_design_scores_gemma":[0.00041660672,0.00013552945,0.92905724,0.00017403427,0.00014781112,0.00008626118,0.0045570727,0.0014112875,0.0009648817,0.015176036,0.047465898,0.00040731873],"about_ca_topic_score_codex":0.0003800329,"about_ca_topic_score_gemma":0.0000348302,"teacher_disagreement_score":0.21849145,"about_ca_system_score_codex":0.00006594827,"about_ca_system_score_gemma":0.00011427232,"threshold_uncertainty_score":0.9044554},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16578009314480702,"score_gpt":0.4552123800807414,"score_spread":0.28943228693593437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111648217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027263619,0.0007574659,0.9029152,0.08679445,0.0027524899,0.0006183059,0.000011813368,0.000059814294,0.00336412],"genre_scores_gemma":[0.6360547,0.00025619456,0.35607436,0.0057919286,0.00071791094,0.00016862419,0.00013816176,0.000016634549,0.0007814888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885595,0.00006240166,0.00020968354,0.00028773982,0.00045473906,0.00012947276],"domain_scores_gemma":[0.99661255,0.0017094683,0.00019610551,0.00017723435,0.00122394,0.000080723825],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001502616,0.00009186042,0.000082338025,0.000053845004,0.00020895244,0.0003417542,0.00014051968,0.00003120907,0.000034321027],"category_scores_gemma":[0.016560314,0.000088704575,0.000018180559,0.00014466744,0.00002473697,0.0010105084,0.000058505346,0.00008721004,0.000011322497],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020932446,0.00055297225,0.0069857975,0.00009661648,0.00014170213,0.000008806072,0.0008880873,0.0000029380944,0.00066548644,0.93872,0.025110742,0.026805926],"study_design_scores_gemma":[0.00040953298,0.00010980988,0.02471811,0.00018473367,0.00010837289,0.00020513854,0.00044689325,0.0010914551,0.0010709191,0.035209585,0.9360324,0.00041305108],"about_ca_topic_score_codex":0.000030462796,"about_ca_topic_score_gemma":0.000021000818,"teacher_disagreement_score":0.91092163,"about_ca_system_score_codex":0.000032650678,"about_ca_system_score_gemma":0.0005229164,"threshold_uncertainty_score":0.9917236},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bundle; Differential (mechanical device); Interpretation (philosophy); Psychology; Computer science; Engineering","score_opus":0.30470277556456604,"score_gpt":0.5091262291350933,"score_spread":0.20442345357052727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119322254","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9462587,0.0010431809,0.0005161614,0.037157264,0.0011259852,0.00029688395,0.00000747782,0.000011123088,0.013583211],"genre_scores_gemma":[0.99742824,0.00006296118,0.000455914,0.00095616194,0.0003842609,0.00009890863,0.000013302578,0.000006383333,0.0005938854],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99807733,0.00049713487,0.00033251746,0.0003681558,0.00055068894,0.00017418755],"domain_scores_gemma":[0.99800384,0.0012736744,0.00016458958,0.00020877653,0.00024704295,0.00010210442],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010842227,0.00015658478,0.00016152699,0.00006586821,0.00027672295,0.000110659006,0.00014170719,0.00004718059,0.002335743],"category_scores_gemma":[0.00082707265,0.000104133425,0.000036331796,0.00017943214,0.000090882626,0.00015899222,0.000044297532,0.00017834718,0.000026203323],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016679092,0.008280548,0.89044464,0.00006522143,0.0009249071,0.0000018002362,0.011974109,0.0000042108336,0.0069447835,0.038466595,0.01640476,0.024820494],"study_design_scores_gemma":[0.00018678336,0.00046138462,0.98291147,0.000065956745,0.00008574572,0.0000145695,0.005912103,0.000010478269,0.000019348847,0.002051987,0.008165428,0.00011474518],"about_ca_topic_score_codex":0.0005663462,"about_ca_topic_score_gemma":0.000061310726,"teacher_disagreement_score":0.09246681,"about_ca_system_score_codex":0.00002623998,"about_ca_system_score_gemma":0.000031526455,"threshold_uncertainty_score":0.9985763},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cognition; Identification (biology); Psychology; Cognitive psychology; Computer science; Management science","score_opus":0.27323320056062017,"score_gpt":0.4452723569892246,"score_spread":0.17203915642860446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139397945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92089504,0.021164242,0.0016971234,0.012452733,0.00058494776,0.00093828357,0.000014689273,0.000023889244,0.04222906],"genre_scores_gemma":[0.988376,0.000069130016,0.010671548,0.00041371313,0.00022649903,0.00013151315,0.000018060144,0.000014446222,0.000079088095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973978,0.00028551498,0.0005391173,0.00039303384,0.0011166268,0.00026793615],"domain_scores_gemma":[0.99299425,0.0041252594,0.00030849976,0.00011665439,0.0023537609,0.000101553975],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008417928,0.0001711788,0.0001968663,0.0002165649,0.00018196196,0.000086486056,0.00008599655,0.000057732537,0.0002431956],"category_scores_gemma":[0.016085245,0.0001759387,0.000017842283,0.00033052792,0.0000618197,0.00038357306,0.000042647265,0.00015978463,0.0000077650875],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015014312,0.0041186586,0.34402704,0.001589671,0.00058115675,0.0000046659684,0.20712857,0.00035325732,0.0056343116,0.22420102,0.00065180106,0.21020842],"study_design_scores_gemma":[0.0012186099,0.00053384644,0.8854444,0.0018520848,0.00021733313,0.00005943449,0.053499788,0.00008513312,0.00048130832,0.054359853,0.001744185,0.00050400203],"about_ca_topic_score_codex":0.0011403995,"about_ca_topic_score_gemma":0.00094343233,"teacher_disagreement_score":0.54141736,"about_ca_system_score_codex":0.00011078988,"about_ca_system_score_gemma":0.0005294985,"threshold_uncertainty_score":0.9922027},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8128600435609681,"score_gpt":0.6116511900217015,"score_spread":0.20120885353926654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170853093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.913103,0.007822783,0.003829669,0.06630247,0.0017711519,0.00045248642,0.000007636509,0.000020466636,0.0066903713],"genre_scores_gemma":[0.63279766,0.00006669179,0.36349753,0.0020331214,0.000256745,0.00003090728,0.0000014165988,0.000011563038,0.0013043681],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9904012,0.0058802897,0.0005715716,0.0007551193,0.0021081744,0.00028365204],"domain_scores_gemma":[0.8754453,0.121753804,0.00034177813,0.00041560523,0.0017189502,0.00032457677],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05058032,0.0001947472,0.00023882971,0.00037527274,0.00046011695,0.0002583107,0.00020983403,0.0000757461,0.0012049885],"category_scores_gemma":[0.6463413,0.00014605027,0.000042061598,0.0009438032,0.0001126364,0.0004408504,0.000076131124,0.00018324803,0.00009124365],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010542296,0.005656771,0.22539754,0.00004733429,0.00039703184,0.000015853648,0.008179787,0.0007752535,0.07944028,0.43856186,0.08696332,0.14402269],"study_design_scores_gemma":[0.00050903857,0.00028137284,0.66209435,0.00005153928,0.000052192518,0.00044903133,0.0021370107,0.00009915711,0.00014080881,0.13285889,0.20101209,0.00031448054],"about_ca_topic_score_codex":0.000024547635,"about_ca_topic_score_gemma":0.0000017455881,"teacher_disagreement_score":0.595761,"about_ca_system_score_codex":0.00009356135,"about_ca_system_score_gemma":0.00034460946,"threshold_uncertainty_score":0.99970806},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09722074847346185,"score_gpt":0.36063916936176055,"score_spread":0.2634184208882987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172179933","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20603442,0.006340825,0.009182005,0.76912636,0.0037217895,0.001906059,0.000013801515,0.00032989404,0.0033448269],"genre_scores_gemma":[0.76492673,0.00014081418,0.23082483,0.0019190763,0.0009850654,0.000575269,0.000020015099,0.000018392593,0.00058981136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99712205,0.00017538032,0.00048903597,0.0005947059,0.0012876398,0.00033116847],"domain_scores_gemma":[0.9961851,0.0004681657,0.00023135939,0.00034405547,0.0025889638,0.00018233847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014557017,0.00024250368,0.00018666676,0.0003161802,0.00031790312,0.00038127447,0.000464349,0.00009852262,0.00017035307],"category_scores_gemma":[0.004121631,0.00024447817,0.000025194684,0.0008894023,0.000056814453,0.0017012751,0.000120634664,0.00022436568,0.000101347934],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009925635,0.014791272,0.17094181,0.00093874824,0.0006787927,0.000007734254,0.007997799,0.0077277953,0.05192865,0.52676266,0.17555752,0.042567942],"study_design_scores_gemma":[0.0010590225,0.00032623307,0.68588275,0.00063622074,0.00007846624,0.00042064252,0.0013212361,0.018950395,0.004005948,0.050839953,0.2349783,0.0015008523],"about_ca_topic_score_codex":0.0006193183,"about_ca_topic_score_gemma":0.00007027721,"teacher_disagreement_score":0.7672073,"about_ca_system_score_codex":0.00059642224,"about_ca_system_score_gemma":0.0023373861,"threshold_uncertainty_score":0.99695307},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1052190430503295,"score_gpt":0.3906782734469965,"score_spread":0.285459230396667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2279705546","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9201291,0.017541992,0.0000035343003,0.052860104,0.00030826466,0.00019028124,0.000009834769,0.0000068534464,0.008949986],"genre_scores_gemma":[0.9938078,0.005074644,0.00017030319,0.0000976067,0.00049788144,0.000022049171,0.0000018107253,0.0000043079017,0.00032360083],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987236,0.0004140832,0.00018579447,0.00013549288,0.00033310076,0.00020789779],"domain_scores_gemma":[0.99775624,0.0017761532,0.00014104406,0.00008829879,0.00016428092,0.000073998395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039220094,0.00006170332,0.0000702923,0.00002373202,0.0007234277,0.00008695839,0.000081974846,0.000048333422,0.000077563556],"category_scores_gemma":[0.0023366055,0.00004302952,0.000014628671,0.000060585848,0.0002037971,0.00071735703,0.000018341425,0.00010832178,0.00002339695],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012087192,0.0001246438,0.8583173,0.000009515046,0.00003410868,9.642505e-8,0.06392982,0.0000010675702,0.00047482483,0.060925353,0.0013794249,0.014682953],"study_design_scores_gemma":[0.00016217679,0.000012570919,0.56921893,0.00001120035,0.000008107664,6.5479543e-7,0.023946157,9.496181e-7,0.000042781718,0.01236081,0.39418018,0.000055471362],"about_ca_topic_score_codex":0.0019464915,"about_ca_topic_score_gemma":0.0080909375,"teacher_disagreement_score":0.39280075,"about_ca_system_score_codex":0.000113644965,"about_ca_system_score_gemma":0.00027825564,"threshold_uncertainty_score":0.5564094},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2464384762232207,"score_gpt":0.4293302723194807,"score_spread":0.18289179609625997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562551526","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03711686,0.08924071,0.5798398,0.28329587,0.0031760905,0.0028206853,0.000009729967,0.00021443701,0.0042858277],"genre_scores_gemma":[0.93440795,0.00073483057,0.05617469,0.0006895736,0.0013989822,0.00026539134,0.0000019314734,0.000018754356,0.006307872],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988226,0.00014874493,0.00020408366,0.000292691,0.00038568708,0.00014615682],"domain_scores_gemma":[0.9972374,0.0014221322,0.00017653019,0.000120600234,0.0009836692,0.000059673832],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032465486,0.00009676581,0.00010533635,0.000036323923,0.0002495731,0.00017101468,0.000114032264,0.000022757275,0.0000096243675],"category_scores_gemma":[0.009328654,0.00006709971,0.000016019805,0.00008805052,0.000013864061,0.00076575886,0.000027692577,0.00004599572,0.000008729598],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091476984,0.00053603895,0.0114723435,0.0010073557,0.00023890038,0.0000021620708,0.011619252,0.000078677105,0.15596563,0.40585625,0.004294302,0.40883762],"study_design_scores_gemma":[0.00055872294,0.00044865112,0.00405378,0.00157576,0.00006164302,0.0000992026,0.00063784583,0.0023021372,0.0040464783,0.0036344856,0.9821467,0.00043461015],"about_ca_topic_score_codex":0.000027926046,"about_ca_topic_score_gemma":0.0000010930361,"teacher_disagreement_score":0.9778524,"about_ca_system_score_codex":0.00004630772,"about_ca_system_score_gemma":0.00013667168,"threshold_uncertainty_score":0.99901617},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09120021442940497,"score_gpt":0.3903774829567992,"score_spread":0.29917726852739424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615786270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96219397,0.0014642711,7.4318245e-7,0.035330657,0.0002540761,0.00046773377,0.000006215022,0.000001929109,0.00028042847],"genre_scores_gemma":[0.99773425,0.0015620976,0.00013793385,0.000040441686,0.00016449293,0.000050997747,9.66762e-7,0.0000025350369,0.00030628766],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984018,0.00061410223,0.00015748362,0.000113923255,0.0006080354,0.000104606974],"domain_scores_gemma":[0.99827373,0.0011809615,0.00019256056,0.00013999971,0.00017839517,0.000034339686],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017326612,0.000057690715,0.00010018319,0.00004858049,0.0005477876,0.00010513218,0.00010999597,0.000028673967,0.000019397912],"category_scores_gemma":[0.011591868,0.000037599453,0.00000991489,0.000086846885,0.00029304813,0.0005419176,0.00005452463,0.00013339757,3.2906092e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004952714,0.00023090611,0.9349256,0.00018352742,0.000030491427,2.474927e-7,0.059497923,0.000002321024,0.0010296649,0.0020015677,0.0013054161,0.00074277015],"study_design_scores_gemma":[0.00024574742,0.00003654478,0.9827394,0.00018810906,0.000023380402,9.999862e-7,0.013317045,0.000014096108,0.00025203664,0.00010352822,0.0030459827,0.000033151224],"about_ca_topic_score_codex":0.0068415753,"about_ca_topic_score_gemma":0.0012061441,"teacher_disagreement_score":0.04781374,"about_ca_system_score_codex":0.000051880277,"about_ca_system_score_gemma":0.00018743923,"threshold_uncertainty_score":0.99977195},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Test (biology); Computer science; Focus (optics); Knowledge management; Psychology; Data science","score_opus":0.8619976910036018,"score_gpt":0.6550214592649924,"score_spread":0.20697623173860935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795852592","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015443914,0.8878733,9.895169e-7,0.015590441,0.0027265556,0.0013211251,0.00007251647,0.000010484101,0.09240305],"genre_scores_gemma":[0.000004775834,0.9897828,0.00093714084,0.002479854,0.0017240065,0.00086265185,0.00040102407,0.000038935716,0.0037688161],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99183637,0.003377513,0.001277481,0.00095898926,0.0021590241,0.00039062471],"domain_scores_gemma":[0.9909995,0.003730173,0.0013228758,0.0008715204,0.0028660905,0.00020982654],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015660912,0.00039255773,0.0009974786,0.00030277035,0.00021139802,0.00006467659,0.00040976613,0.0002763655,0.012043133],"category_scores_gemma":[0.007893226,0.00029385928,0.00018523521,0.0008379045,0.0002189225,0.00013836131,0.000098468285,0.00083621347,0.0007113995],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036729096,0.002057377,0.00001568505,0.021717425,0.0005696143,0.000006475711,0.00029285482,3.620432e-9,7.690469e-8,0.006812384,0.6030199,0.36547145],"study_design_scores_gemma":[0.00006889992,0.00034833056,0.0005875271,0.07285575,0.00056572614,0.00029896823,0.00019641282,1.2792304e-9,1.7167109e-7,0.0017855688,0.9230408,0.00025185544],"about_ca_topic_score_codex":0.00010674425,"about_ca_topic_score_gemma":0.000002543984,"teacher_disagreement_score":0.3652196,"about_ca_system_score_codex":0.00020518363,"about_ca_system_score_gemma":0.0013001999,"threshold_uncertainty_score":0.99995136},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2581577380829526,"score_gpt":0.5537707121933004,"score_spread":0.2956129741103478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804917593","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90737396,0.004166922,0.005021853,0.047822956,0.0026703337,0.0014117025,0.000009611162,0.0000436294,0.031479027],"genre_scores_gemma":[0.8900746,0.00005784324,0.10679682,0.0013536226,0.00079673866,0.0004189632,0.00001397529,0.000016717988,0.00047071776],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99753445,0.0011089304,0.00038406273,0.00044431456,0.00028128506,0.00024697292],"domain_scores_gemma":[0.9948756,0.0038490624,0.00032248252,0.00014751137,0.00072556635,0.0000797432],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0073745362,0.00016672628,0.00018249988,0.00010724286,0.00029547315,0.0001430535,0.000117486794,0.000066264634,0.00019608167],"category_scores_gemma":[0.0093787,0.00016377025,0.000019374314,0.00015014052,0.00020596864,0.0004627889,0.000058942453,0.00019803291,0.0000052660243],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017089664,0.00080170284,0.8063116,0.00010510293,0.00028672576,6.634256e-7,0.1377367,0.0000013700907,0.00298296,0.025959106,0.0027052427,0.02293794],"study_design_scores_gemma":[0.0009069818,0.00044101424,0.7945104,0.00033158425,0.00012171252,0.000016761765,0.18255657,0.000067840636,0.000254247,0.008598365,0.01184341,0.0003510791],"about_ca_topic_score_codex":0.0010125958,"about_ca_topic_score_gemma":0.00034420102,"teacher_disagreement_score":0.101774976,"about_ca_system_score_codex":0.00011803737,"about_ca_system_score_gemma":0.00022126036,"threshold_uncertainty_score":0.99896574},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.13014986620014385,"score_gpt":0.37875505524570363,"score_spread":0.24860518904555978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885169382","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027314585,0.002817017,0.26517418,0.70212716,0.0008571699,0.0002327467,0.000011355174,0.00004648148,0.0014193364],"genre_scores_gemma":[0.89780474,0.000035905938,0.099468976,0.0010085722,0.0006902865,0.0000064937326,0.0000021262179,0.0000064929013,0.0009763939],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986129,0.00012637007,0.00016275591,0.00024316197,0.000700334,0.00015448006],"domain_scores_gemma":[0.9980717,0.00034786513,0.00020800623,0.00033285006,0.0009592777,0.00008035629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013915348,0.00010009074,0.000116802425,0.00005065544,0.00032997417,0.0005123011,0.0003984438,0.000028938759,0.0000073865863],"category_scores_gemma":[0.0020758838,0.00007472435,0.000024862333,0.0002445434,0.000085393316,0.0005280875,0.000095704614,0.00013333741,0.000015038342],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024851304,0.0026451212,0.109059855,0.00031445938,0.0005599114,0.0000028312859,0.029784001,0.22812775,0.0024486417,0.34786722,0.26932684,0.00961485],"study_design_scores_gemma":[0.00040084042,0.00023453396,0.049782902,0.00036139184,0.00012570876,0.000033674267,0.0031316783,0.48872492,0.0008174491,0.003682131,0.45221317,0.0004915953],"about_ca_topic_score_codex":0.00012398383,"about_ca_topic_score_gemma":0.000071874114,"teacher_disagreement_score":0.8704902,"about_ca_system_score_codex":0.00003151627,"about_ca_system_score_gemma":0.00021168536,"threshold_uncertainty_score":0.49401316},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.28811363087923314,"score_gpt":0.4361760759650995,"score_spread":0.14806244508586636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035205464","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34507576,0.0016209556,0.00016073778,0.6485308,0.00034840524,0.00044220575,0.000046079986,0.000013029367,0.0037620093],"genre_scores_gemma":[0.9862344,0.00026265866,0.010594771,0.0021828418,0.00056740234,0.000022444952,0.000012830819,0.0000052887212,0.00011734703],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99591213,0.002259297,0.00025126612,0.00020127921,0.001225207,0.00015079611],"domain_scores_gemma":[0.99591386,0.003154669,0.00017951871,0.00013444039,0.0005483909,0.00006914499],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035122656,0.00009240398,0.00013033005,0.000066561195,0.00048228432,0.0000673356,0.00030054612,0.000040313895,0.0003578129],"category_scores_gemma":[0.012022267,0.000059549726,0.00005538562,0.0011219596,0.00015057805,0.00054082705,0.000028205652,0.00030907788,0.0000052779087],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012504392,0.0006082558,0.076021075,0.00004069878,0.00076952105,0.0000012909317,0.5966793,0.0007378435,0.0029417102,0.3115954,0.004099728,0.006380171],"study_design_scores_gemma":[0.00021743566,0.00002943286,0.7044086,0.000036021655,0.00037526005,0.0000013172548,0.12425367,0.00006681509,0.00007439599,0.004025107,0.16637637,0.00013559811],"about_ca_topic_score_codex":0.0019546212,"about_ca_topic_score_gemma":0.0010874912,"teacher_disagreement_score":0.64634794,"about_ca_system_score_codex":0.00006829801,"about_ca_system_score_gemma":0.00038046273,"threshold_uncertainty_score":0.99629986},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09632131387335943,"score_gpt":0.42067691106516314,"score_spread":0.32435559719180374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046538170","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06594703,0.003649217,0.000281559,0.80060315,0.00082050875,0.00023685837,0.000025174471,0.00005304952,0.12838344],"genre_scores_gemma":[0.98926497,0.001826033,0.0042086686,0.0014336434,0.0016408261,0.000013792584,0.00004049318,0.000009167736,0.0015623894],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982424,0.00024852817,0.00017367216,0.00029056263,0.00087135914,0.00017351263],"domain_scores_gemma":[0.9988795,0.00044813173,0.00012170651,0.00005784315,0.00029093173,0.0002019014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013380293,0.000110519926,0.00013323821,0.000055484117,0.0004620808,0.00028404087,0.0001031014,0.00005820222,0.00039355477],"category_scores_gemma":[0.0007046846,0.000107482105,0.000019817593,0.00014496403,0.000091269205,0.000678461,0.00007887384,0.00013397678,0.000008068414],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012221112,0.00043747245,0.8149075,0.000037741338,0.0003562179,0.000002594953,0.050003715,9.0795663e-7,0.0006667293,0.063975565,0.039591245,0.029898124],"study_design_scores_gemma":[0.00032442992,0.000053311116,0.3227398,0.000016539068,0.00007424561,0.0000014832684,0.016131815,0.000040290728,0.0000038478547,0.00046357646,0.66003126,0.00011937006],"about_ca_topic_score_codex":0.00036348545,"about_ca_topic_score_gemma":0.000121781835,"teacher_disagreement_score":0.92331797,"about_ca_system_score_codex":0.00006137519,"about_ca_system_score_gemma":0.00012818491,"threshold_uncertainty_score":0.43829933},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.14978246681435134,"score_gpt":0.35360445438986376,"score_spread":0.20382198757551243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233643233","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028796926,0.018069522,0.090411775,0.77468055,0.0012539447,0.0011606193,0.00003131026,0.00020905721,0.08538628],"genre_scores_gemma":[0.9859746,0.0003382035,0.0038001116,0.0086767925,0.00039058924,0.000017716666,0.000012089129,0.000008602256,0.0007812661],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99813426,0.00019652041,0.0002445855,0.0005295089,0.0006599417,0.00023519575],"domain_scores_gemma":[0.99818844,0.00064933434,0.00020306469,0.00015247481,0.0005586191,0.00024805628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011437001,0.00017905248,0.00017278784,0.00005594382,0.0002660307,0.00082154706,0.00029909067,0.00003623982,0.00006755101],"category_scores_gemma":[0.0031487204,0.00016309315,0.00003636665,0.00025925995,0.00010515647,0.0028516743,0.00028537938,0.00020156511,0.00013064501],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035462817,0.0013699386,0.005171317,0.00032862267,0.0005349805,0.000032800228,0.15838645,0.000009771939,0.0029573326,0.0853393,0.065362744,0.6801521],"study_design_scores_gemma":[0.0017510431,0.000959058,0.02521732,0.00057918765,0.0002097642,0.00017080149,0.029127976,0.006652228,0.0015383348,0.017319212,0.91514,0.0013350885],"about_ca_topic_score_codex":0.000028719822,"about_ca_topic_score_gemma":0.0000057569787,"teacher_disagreement_score":0.9571777,"about_ca_system_score_codex":0.000029631045,"about_ca_system_score_gemma":0.00017157504,"threshold_uncertainty_score":0.7922197},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2812239541239853,"score_gpt":0.4813383893869291,"score_spread":0.20011443526294376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237928641","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023829478,0.0023121382,0.000028207867,0.43156654,0.001816851,0.00021503319,0.0000012645219,0.000023313369,0.56165373],"genre_scores_gemma":[0.8489295,0.0019728704,0.0058100033,0.014042926,0.0049879174,0.00010762764,0.000026515758,0.000024717772,0.12409789],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99714214,0.0008187766,0.00016578507,0.00021112921,0.001494773,0.00016738036],"domain_scores_gemma":[0.99683374,0.0013206201,0.00018177726,0.0001441638,0.001288514,0.0002311892],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0075053466,0.0000897219,0.00008036222,0.000058909874,0.00042980196,0.00024361163,0.000103283055,0.00005607778,0.006737548],"category_scores_gemma":[0.02475066,0.000087710556,0.000019223542,0.0001759364,0.000074303,0.0011743043,0.000012918133,0.00012115792,0.003112706],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013498106,0.0004497606,0.00043759157,0.0000065408376,0.000035469835,3.0418602e-7,0.033798,0.000023834576,0.000017322905,0.18492924,0.775543,0.004623962],"study_design_scores_gemma":[0.00018539843,0.00007930988,0.0008609031,0.000018124994,0.00004451872,0.0000027240565,0.014654871,0.000008852934,0.0000116786705,0.010260019,0.97376144,0.00011215439],"about_ca_topic_score_codex":0.0028981245,"about_ca_topic_score_gemma":0.00007709861,"teacher_disagreement_score":0.8465466,"about_ca_system_score_codex":0.0002698963,"about_ca_system_score_gemma":0.0011525226,"threshold_uncertainty_score":0.9976635},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Editorial board; Computer science; Business; Environmental science; Library science","score_opus":0.16029175209505392,"score_gpt":0.46563718666507947,"score_spread":0.30534543457002555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246593371","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051307972,0.0058900206,0.00080835854,0.3131757,0.32142863,0.001004832,0.00024063872,0.000021577884,0.3573789],"genre_scores_gemma":[0.0008409128,0.0029089076,0.006055466,0.0046544787,0.22410941,0.000461695,0.00075544376,0.00004279583,0.7601709],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98966694,0.00070118805,0.0013401362,0.0006838873,0.007206767,0.00040106123],"domain_scores_gemma":[0.98665315,0.0044141402,0.001481456,0.0007446764,0.006415636,0.0002909351],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008893053,0.00045310543,0.00047924425,0.0004482617,0.00044354805,0.0016502413,0.0007588356,0.00033104545,0.033953477],"category_scores_gemma":[0.022088602,0.00032491653,0.0001319366,0.00037729213,0.00010888713,0.004090543,0.00018209628,0.0004285724,0.08371153],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001429134,0.00021295309,0.0000416687,0.000040319897,0.00010739082,4.1967525e-8,0.00077986246,0.000002430023,0.00009342958,0.0017727476,0.98526114,0.01154509],"study_design_scores_gemma":[0.00039080478,0.00011112194,0.0005643442,0.00013028682,0.00008118197,0.00000487677,0.0010122219,7.492849e-7,0.000028931776,0.005670287,0.9915726,0.00043255728],"about_ca_topic_score_codex":0.0004070014,"about_ca_topic_score_gemma":0.000030715477,"teacher_disagreement_score":0.40279198,"about_ca_system_score_codex":0.00047259795,"about_ca_system_score_gemma":0.0022836423,"threshold_uncertainty_score":0.9999203},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.33659020191225475,"score_gpt":0.5652165547572977,"score_spread":0.22862635284504296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313410276","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16181593,0.00530098,0.612847,0.05863455,0.0075828675,0.0031259693,0.000034693163,0.00094402785,0.14971404],"genre_scores_gemma":[0.39011016,0.0000030017586,0.6057253,0.00081933703,0.00052106817,0.00035242134,0.00002104359,0.000040002975,0.0024076859],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99215174,0.0063813715,0.00026975223,0.0004365322,0.00045465643,0.0003059548],"domain_scores_gemma":[0.9961637,0.0027191427,0.00026391266,0.0001428696,0.0006252194,0.0000851161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015628623,0.00016337822,0.0001947711,0.00017151242,0.0011855788,0.000087523134,0.00013506551,0.00004298462,0.00087849324],"category_scores_gemma":[0.007200068,0.00017480677,0.00003965682,0.00037047276,0.000023938885,0.0001820065,0.00006125948,0.0006333948,0.000008827799],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067071384,0.0031534964,0.0053953724,0.00019115875,0.0024141148,0.0000115761095,0.15699494,0.048908334,0.22728392,0.25003406,0.019121574,0.2797843],"study_design_scores_gemma":[0.00091081514,0.0011307998,0.017509086,0.0000509554,0.000220843,0.00017693696,0.036786903,0.0038352092,0.0006428717,0.0029281822,0.9352193,0.0005880861],"about_ca_topic_score_codex":0.0004462705,"about_ca_topic_score_gemma":0.0000017258862,"teacher_disagreement_score":0.91609776,"about_ca_system_score_codex":0.00028820077,"about_ca_system_score_gemma":0.0002601426,"threshold_uncertainty_score":0.9618885},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Toolbox; Computer science; Python (programming language); Data science; Context (archaeology); Artificial intelligence","score_opus":0.19356892700389544,"score_gpt":0.4464950114435416,"score_spread":0.25292608443964615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319790235","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012623277,0.009274556,0.17189871,0.7974012,0.010064101,0.002651719,0.000012697221,0.00065155403,0.0067831236],"genre_scores_gemma":[0.6779231,0.0013029289,0.3006404,0.0040454026,0.006503541,0.001802153,0.000087874636,0.00009295139,0.0076016807],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99619615,0.0006087186,0.00041978425,0.00056431897,0.001790801,0.0004202135],"domain_scores_gemma":[0.99402237,0.0025288619,0.0002588505,0.00031773894,0.0026929672,0.00017922922],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008937494,0.00020091592,0.0001840253,0.00016337585,0.00065697654,0.00059128023,0.00032414746,0.00007163228,0.00006990657],"category_scores_gemma":[0.027692406,0.00018587803,0.00006183858,0.0005415924,0.00003771522,0.0024995415,0.00016027196,0.00028169857,0.00025486163],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006714257,0.002015183,0.0005219921,0.0002912403,0.00030830054,0.000020230775,0.016153187,0.0002782043,0.006922656,0.81537926,0.10676059,0.05067773],"study_design_scores_gemma":[0.0002718051,0.00024223347,0.00046088808,0.000116329444,0.00004231407,0.00003760927,0.0009699821,0.011925931,0.0015346659,0.021895234,0.9622102,0.00029282385],"about_ca_topic_score_codex":0.00015123878,"about_ca_topic_score_gemma":0.000014297683,"teacher_disagreement_score":0.8554496,"about_ca_system_score_codex":0.00021276169,"about_ca_system_score_gemma":0.000774089,"threshold_uncertainty_score":0.9804978},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.7119997234981603,"score_gpt":0.5622263498475483,"score_spread":0.14977337365061205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362673096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97638386,0.005302481,0.0056377235,0.007132469,0.0016126372,0.0005514916,0.000004216169,0.00009106506,0.0032840406],"genre_scores_gemma":[0.9405107,0.00025019422,0.057584263,0.0003746934,0.0003159837,0.000084049214,0.000021435892,0.000017107977,0.00084157294],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99337715,0.0025200113,0.00058284425,0.0007529683,0.0025087607,0.00025828657],"domain_scores_gemma":[0.890418,0.10727979,0.000547323,0.00042019144,0.0011483055,0.00018639129],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0134797525,0.00021386797,0.00031444078,0.00037877684,0.0005754098,0.00086506625,0.00027751352,0.00010701006,0.000040289808],"category_scores_gemma":[0.4101432,0.00017070115,0.000047736634,0.0012947412,0.00008779406,0.0009524752,0.00012736762,0.0001685876,0.0001028595],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019213455,0.0011286873,0.06301504,0.0004484719,0.0008575063,0.000030448007,0.015887924,0.006930881,0.22736813,0.04712259,0.029536793,0.60575217],"study_design_scores_gemma":[0.0012903309,0.00027342723,0.5001058,0.00017584494,0.00016061777,0.000014085617,0.0016693048,0.035603505,0.006539955,0.45025653,0.0035129269,0.00039767486],"about_ca_topic_score_codex":0.00020918867,"about_ca_topic_score_gemma":0.000003984146,"teacher_disagreement_score":0.60535455,"about_ca_system_score_codex":0.00008545153,"about_ca_system_score_gemma":0.00023149817,"threshold_uncertainty_score":0.83418536},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Legitimacy; Perception; Psychology; Disengagement theory; Critical reflection; Social psychology; Pedagogy; Political science","score_opus":0.11055476844730784,"score_gpt":0.42774349726989375,"score_spread":0.3171887288225859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386482646","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3753265,0.0028346744,0.000071374256,0.34057158,0.0018806208,0.0010588059,0.000030502868,0.000169603,0.27805632],"genre_scores_gemma":[0.9923266,0.0017450446,0.00075913593,0.00025001357,0.0003146202,0.00004968646,0.000025288478,0.000010213589,0.0045193895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99813956,0.00023057607,0.00019286534,0.0002794463,0.00089393073,0.00026361714],"domain_scores_gemma":[0.99834305,0.0010262298,0.00008493406,0.00010979914,0.000302262,0.00013374774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019567437,0.00011178975,0.00013009754,0.00013731551,0.0005760218,0.0003445279,0.000097349046,0.000056958725,0.000110290486],"category_scores_gemma":[0.0019162768,0.0001090962,0.000022264927,0.0004800252,0.00012242737,0.0010405605,0.00006147143,0.00014723347,0.000065389555],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007850265,0.0011977461,0.69323367,0.00004227895,0.00015549571,0.000014294961,0.02457322,0.00003580787,0.00064999436,0.22044367,0.04708235,0.012492997],"study_design_scores_gemma":[0.00031490525,0.0000326041,0.58683985,0.000051282885,0.000033872195,0.0000028944983,0.02771617,0.00007061109,0.0000021209025,0.005760249,0.3789951,0.00018032767],"about_ca_topic_score_codex":0.00086373993,"about_ca_topic_score_gemma":0.00051592034,"teacher_disagreement_score":0.6170001,"about_ca_system_score_codex":0.000113587055,"about_ca_system_score_gemma":0.00031283146,"threshold_uncertainty_score":0.4448814},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5444063599822654,"score_gpt":0.5751607052320205,"score_spread":0.030754345249755066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388223267","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94521785,0.0010710178,0.00096618966,0.046109393,0.00054375164,0.0006083435,0.000013933924,0.000052788953,0.0054167532],"genre_scores_gemma":[0.9947213,0.00023651494,0.0034432348,0.00027371716,0.0003816273,0.00006959916,0.00031082888,0.0000104541805,0.00055274373],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99838823,0.00016006283,0.00029578086,0.00036204088,0.000571355,0.00022255421],"domain_scores_gemma":[0.9983239,0.00060078007,0.00013430319,0.0003297607,0.0005141077,0.00009711559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002164447,0.00010804223,0.0002141866,0.00028955692,0.00013522748,0.00007875306,0.00009814365,0.000024456109,0.00009303857],"category_scores_gemma":[0.0011690565,0.00009533534,0.00001790496,0.0008304546,0.000027847711,0.00075969927,0.000059621903,0.00019839015,0.00003520074],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005639302,0.00073617866,0.9779504,0.00014603235,0.0005277825,0.0000051416455,0.014978872,0.00034688466,0.00011779339,0.00071873603,0.0011680791,0.0027401557],"study_design_scores_gemma":[0.00036350556,0.00024877922,0.81192327,0.0005604404,0.00123737,0.000039607006,0.13384423,0.018071571,0.0005523928,0.0013901882,0.031425264,0.00034340515],"about_ca_topic_score_codex":0.0046108887,"about_ca_topic_score_gemma":0.0031407946,"teacher_disagreement_score":0.16602716,"about_ca_system_score_codex":0.00020567223,"about_ca_system_score_gemma":0.00041208052,"threshold_uncertainty_score":0.6970315},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3432883525820852,"score_gpt":0.4905485480493123,"score_spread":0.14726019546722713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389347402","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052922465,0.005829594,0.006789848,0.8632123,0.009147673,0.0028180662,0.000059828628,0.00030682792,0.0589134],"genre_scores_gemma":[0.9751769,0.00018693291,0.003521669,0.0012683665,0.005053176,0.0005058621,0.00007054169,0.000045807785,0.014170748],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996765,0.00027285487,0.00033681587,0.0005123418,0.0016838552,0.0004291064],"domain_scores_gemma":[0.99803716,0.00021732341,0.00008188723,0.00033693181,0.0010246262,0.00030209852],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040802187,0.00015801445,0.0001402292,0.00020525213,0.00027483428,0.0001582988,0.00014441748,0.000059133028,0.000753038],"category_scores_gemma":[0.004608686,0.00015999706,0.000029599885,0.00032664053,0.000025265319,0.0005118931,0.00007435048,0.0002151849,0.0022282177],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013936289,0.0023247206,0.001433248,0.00032952652,0.00043866885,0.000011601515,0.011453337,0.0020241814,0.0025203242,0.03520524,0.62563145,0.31723407],"study_design_scores_gemma":[0.0005544291,0.00026266495,0.011026358,0.000070854585,0.000033869266,0.000039448045,0.0051491796,0.002565835,0.0000972792,0.0019304205,0.9779594,0.00031027177],"about_ca_topic_score_codex":0.00041727512,"about_ca_topic_score_gemma":0.0000231326,"teacher_disagreement_score":0.92225444,"about_ca_system_score_codex":0.000471025,"about_ca_system_score_gemma":0.00020154368,"threshold_uncertainty_score":0.9985487},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2292006550062576,"score_gpt":0.41553136314358546,"score_spread":0.18633070813732786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391227797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04994125,0.022070535,0.53300875,0.38089556,0.005057779,0.0010359164,0.000006668714,0.00028316394,0.0077003767],"genre_scores_gemma":[0.84331477,0.00013806619,0.15415604,0.0013171277,0.00053977396,0.000025844269,0.0000061792794,0.00001019621,0.00049201725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99852574,0.0002062378,0.00019857587,0.0004062213,0.0005169924,0.0001462632],"domain_scores_gemma":[0.9987654,0.00042835355,0.000047767862,0.00028118337,0.00036336394,0.000113902315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017046565,0.000104796316,0.00009004534,0.000095324816,0.00022265218,0.00077487703,0.00020566647,0.000032653,0.000029603489],"category_scores_gemma":[0.0006401949,0.00009690991,0.000021618347,0.00032869435,0.000015692593,0.0012716807,0.00008151884,0.00009931235,0.00010675185],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070128626,0.0004982131,0.00039348673,0.00026869884,0.00014614686,0.000009297942,0.013742962,0.0017002141,0.1939696,0.63599116,0.035572145,0.11763793],"study_design_scores_gemma":[0.00007562586,0.000066307824,0.003512979,0.00020373781,0.00003635377,0.00013311022,0.0002806189,0.026795179,0.0027491401,0.005684999,0.9601875,0.00027447607],"about_ca_topic_score_codex":0.0003025889,"about_ca_topic_score_gemma":0.0000057273255,"teacher_disagreement_score":0.9246153,"about_ca_system_score_codex":0.00014149577,"about_ca_system_score_gemma":0.0002199734,"threshold_uncertainty_score":0.7472157},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.19670056213224912,"score_gpt":0.4278503410420334,"score_spread":0.23114977890978428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405618562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18890157,0.0071504996,0.7537353,0.046041287,0.0018036021,0.0018512642,0.000011102016,0.000123558,0.0003818061],"genre_scores_gemma":[0.95842874,0.000013240424,0.040365264,0.00040962058,0.00041257116,0.00025244182,0.0000052602804,0.000006703417,0.000106168656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781865,0.0005365051,0.0004124921,0.00048448524,0.00058069744,0.0001671958],"domain_scores_gemma":[0.99823034,0.00094416953,0.00009201572,0.00034678206,0.00032626415,0.000060446255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057495087,0.00012067898,0.00016133075,0.000092743394,0.00014606652,0.00038568667,0.00018159428,0.00003596849,0.000022301465],"category_scores_gemma":[0.0019280479,0.00011371537,0.000034523546,0.00020276695,0.000009175192,0.00147966,0.000037131274,0.000114559676,0.0000048838274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022643364,0.0059077153,0.00945171,0.0009870771,0.00053327065,0.000013736412,0.116434395,0.0049231956,0.003104149,0.77643055,0.0032720685,0.0787157],"study_design_scores_gemma":[0.0013269099,0.000116065996,0.008536451,0.000062259045,0.00004774348,0.000019593348,0.0035989361,0.96985203,0.000033038366,0.013401899,0.002790081,0.00021497409],"about_ca_topic_score_codex":0.00028817996,"about_ca_topic_score_gemma":0.00019140335,"teacher_disagreement_score":0.96492887,"about_ca_system_score_codex":0.00020088023,"about_ca_system_score_gemma":0.0003292847,"threshold_uncertainty_score":0.46371782},"labels":[],"label_agreement":null}]}