{"meta":{"query_hash":"f042d3dd4442","filters":{"venue":"Applied Measurement in Education"},"cohort_total":12,"direct_labels_cover":0,"predictions_cover":12,"exported":12,"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/f042d3dd4442","api":"https://metacan.xera.ac/api/v1/cohort?venue=Applied+Measurement+in+Education"},"results":[{"id":"W1969608664","doi":"10.1207/s15324818ame1703_4","title":"Comparability of Bilingual Versions of Assessments: Sources of Incomparability of English and French Versions of Canada's National Achievement Tests","year":2004,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":62,"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 British Columbia","funders":"","keywords":"Comparability; Differential item functioning; Psychology; Reading (process); Item response theory; Psychometrics; Developmental psychology; Linguistics; Mathematics","score_opus":0.2715701847682983,"score_gpt":0.4269062826454618,"score_spread":0.15533609787716351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969608664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961377,0.00015054108,0.0004005036,0.000064529,0.00035070194,0.00036764017,0.000034059092,0.0000031863822,0.0024911787],"genre_scores_gemma":[0.98846006,0.0000063303464,0.011488439,0.000008167554,0.000016233575,0.000010606506,0.000005461011,0.0000028254053,0.0000018673434],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956943,0.00021849894,0.0013851082,0.00031440088,0.0022496227,0.00013809375],"domain_scores_gemma":[0.9913903,0.0038278557,0.0012467876,0.00041999336,0.0030480274,0.00006706948],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008387373,0.00010965969,0.00049297,0.0004315183,0.000044598753,0.0000046260175,0.00036633777,0.000052347437,0.000026572512],"category_scores_gemma":[0.026859224,0.00009530023,0.00005264134,0.0013880668,0.00023292401,0.00006646567,0.000092976705,0.00010005044,6.989185e-8],"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":[0.00006717769,0.0022823731,0.9710136,0.0001585683,0.000038080714,1.6668752e-8,0.0021943077,0.004583712,0.011880982,0.0023434716,0.00016269449,0.0052749985],"study_design_scores_gemma":[0.0007111569,0.00011608354,0.94602275,0.00010316538,0.000019438783,1.0147029e-7,0.009303373,0.000037042333,0.029265165,0.014269522,0.000078307836,0.00007388488],"about_ca_topic_score_codex":0.03255771,"about_ca_topic_score_gemma":0.015115227,"teacher_disagreement_score":0.02499086,"about_ca_system_score_codex":0.000342068,"about_ca_system_score_gemma":0.003462436,"threshold_uncertainty_score":0.98133796},"labels":[],"label_agreement":null},{"id":"W2011276392","doi":"10.1080/08957347.2011.607061","title":"An Experimental Test of Student Verbal Reports and Teacher Evaluations as a Source of Validity Evidence for Test Development","year":2011,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Science Education and Pedagogy","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Psychology; CLARITY; Test validity; Set (abstract data type); Association (psychology); Standards for Educational and Psychological Testing; Mathematics education; Content validity; Applied psychology; Social psychology; Psychometrics; Computer science; Higher education; Clinical psychology; Education theory","score_opus":0.4437717804134738,"score_gpt":0.4947924416640539,"score_spread":0.05102066125058008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011276392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936035,0.00016790899,0.0001996531,0.00011202764,0.00032841382,0.0009284915,2.9692998e-7,0.0000115048315,0.004648169],"genre_scores_gemma":[0.9968539,0.00001215565,0.0024618537,0.000042540414,0.00007325351,0.00047546029,0.0000033695628,0.0000053684626,0.00007210209],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983953,0.00009194715,0.0003899654,0.00025250966,0.0007218582,0.00014839167],"domain_scores_gemma":[0.9989337,0.00018228797,0.0002681196,0.00018711867,0.00033331648,0.00009548009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004424853,0.000078283054,0.000113715294,0.00010156126,0.00019455816,0.000019134823,0.00014888577,0.000046618574,0.00015395455],"category_scores_gemma":[0.0011756658,0.000082367216,0.000017522541,0.00020666,0.00014948999,0.00017192955,0.000014610437,0.000046136938,0.0000021215328],"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":[0.000022568775,0.0047556264,0.5436107,0.000024350727,0.000005885652,3.222234e-8,0.35461578,0.0000028710358,0.07450552,0.0016309188,0.00020330798,0.020622473],"study_design_scores_gemma":[0.00021929678,0.00019274947,0.6756202,0.00008735392,0.00002496963,7.9943635e-7,0.2036429,0.0000052754785,0.11761826,0.0008852561,0.0015448731,0.0001580306],"about_ca_topic_score_codex":0.0015255124,"about_ca_topic_score_gemma":0.0008193405,"teacher_disagreement_score":0.15097286,"about_ca_system_score_codex":0.0003331387,"about_ca_system_score_gemma":0.0026644177,"threshold_uncertainty_score":0.47265625},"labels":[],"label_agreement":null},{"id":"W2053906918","doi":"10.1207/s15324818ame1703_2","title":"Performance of SIBTEST When the Percentage of DIF Items is Large","year":2004,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":39,"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":"Differential item functioning; Statistics; Psychology; Item response theory; Test (biology); Mathematics; Psychometrics","score_opus":0.3321836598049474,"score_gpt":0.4109344435671419,"score_spread":0.07875078376219452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053906918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9838824,0.00031566058,0.0010914255,0.0005940866,0.00050738064,0.00033187887,0.0000026865694,0.000007670061,0.013266777],"genre_scores_gemma":[0.9955154,0.000053251944,0.0040766946,0.00020811245,0.0000530021,0.000035847253,0.000001453847,0.0000052928604,0.000050933304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99745446,0.00008611271,0.0006589605,0.00024643462,0.0013726667,0.000181364],"domain_scores_gemma":[0.99773616,0.0009921847,0.00042165033,0.00053376536,0.00028437053,0.000031898806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008470052,0.00009000178,0.00020229128,0.00027674926,0.000068805486,0.000023383098,0.000544811,0.000042627704,0.000113801136],"category_scores_gemma":[0.004016101,0.00005734235,0.000045559827,0.0009164349,0.000055821976,0.00008708298,0.000051597304,0.00010316695,0.000018113033],"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":[0.0000604955,0.0013008071,0.6753676,0.000067460314,0.000019093557,5.382973e-8,0.011701315,0.0003834654,0.04315415,0.0058060433,0.0029775042,0.25916204],"study_design_scores_gemma":[0.0006949356,0.00008189143,0.93697935,0.000099992016,0.000013562057,0.0000010680244,0.011240992,0.00010860805,0.021653365,0.02301773,0.0059746015,0.00013388664],"about_ca_topic_score_codex":0.00012259648,"about_ca_topic_score_gemma":0.000023959226,"teacher_disagreement_score":0.2616118,"about_ca_system_score_codex":0.00011351701,"about_ca_system_score_gemma":0.00022575862,"threshold_uncertainty_score":0.4807938},"labels":[],"label_agreement":null},{"id":"W2109920068","doi":"10.1080/08957347.2014.905787","title":"Testing Expert-Based Versus Student-Based Cognitive Models for a Grade 3 Diagnostic Mathematics Assessment","year":2014,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Educational and Psychological Assessments","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":"Medical Council of Canada; University of Alberta","funders":"","keywords":"Cognition; Psychology; Test (biology); Consistency (knowledge bases); Construct (python library); Cognitive test; Cognitive psychology; Statistics; Artificial intelligence; Computer science; Mathematics","score_opus":0.21851518099272743,"score_gpt":0.44217855728805466,"score_spread":0.22366337629532723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109920068","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5986949,0.00035349774,0.29074675,0.0027635233,0.0062848353,0.0065080305,0.00003065722,0.00022610245,0.09439171],"genre_scores_gemma":[0.95539427,0.0000013071045,0.033840645,0.001250344,0.0003034387,0.008989414,0.00015538023,0.000035650053,0.000029564837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9977715,0.0001417622,0.0005010576,0.00054706115,0.0006419721,0.00039662884],"domain_scores_gemma":[0.9957211,0.0032076053,0.00025876114,0.00031493953,0.00037492183,0.00012268062],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012950426,0.0002629938,0.0002587121,0.00016951152,0.00013151114,0.00005266006,0.00024118628,0.00011975934,0.00012352694],"category_scores_gemma":[0.00050933845,0.00025134743,0.00006603919,0.00031356668,0.000048418417,0.00005624059,0.000013050431,0.00018067277,0.000046847188],"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":[0.0014952343,0.1102479,0.07636062,0.0007610318,0.00063064613,0.0000017940932,0.014298263,0.0073917164,0.009007501,0.4007683,0.013648612,0.36538836],"study_design_scores_gemma":[0.033223502,0.002544886,0.7977805,0.0015132076,0.0005319374,0.0000021620356,0.03865654,0.014297825,0.0015685195,0.10318439,0.00432783,0.0023686637],"about_ca_topic_score_codex":0.00005562872,"about_ca_topic_score_gemma":0.00002090272,"teacher_disagreement_score":0.72141993,"about_ca_system_score_codex":0.0004200838,"about_ca_system_score_gemma":0.0004521378,"threshold_uncertainty_score":0.99999386},"labels":[],"label_agreement":null},{"id":"W2202994334","doi":"10.1080/08957347.2015.1102913","title":"Analyzing Fairness Among Linguistic Minority Populations Using a Latent Class Differential Item Functioning Approach","year":2015,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":8,"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":"Differential item functioning; Psychology; Item response theory; Race (biology); Latent class model; Ethnic group; Social psychology; Measurement invariance; Test (biology); Statistics; Developmental psychology; Psychometrics; Confirmatory factor analysis; Structural equation modeling; Mathematics; Sociology","score_opus":0.1834551797688675,"score_gpt":0.3591230444973037,"score_spread":0.1756678647284362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2202994334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9380074,0.00008841634,0.0115423985,0.00014955101,0.003559286,0.00048000424,5.555068e-7,0.000063581014,0.046108775],"genre_scores_gemma":[0.9977247,0.0000029506812,0.0008631087,0.000038928225,0.0011185455,0.000115404466,0.000025920426,0.000010554805,0.000099847515],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99838674,0.00017912358,0.0003174195,0.00030251767,0.0005159551,0.0002982145],"domain_scores_gemma":[0.99919105,0.00002027935,0.0001610097,0.00014295617,0.000342771,0.00014194647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010618364,0.00012328963,0.0001672743,0.0001818073,0.00035934517,0.00009027188,0.0001435226,0.00013510683,0.00002400477],"category_scores_gemma":[0.00037332348,0.00013600198,0.000048538186,0.0004946789,0.00010540888,0.00011653223,0.000021595575,0.00017681583,0.0000073019446],"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":[0.000058363756,0.0012974503,0.84990597,0.00003270233,0.000046942278,2.4565955e-7,0.03933227,0.0005436162,0.0019203747,0.0957669,0.0007328232,0.010362344],"study_design_scores_gemma":[0.0011179418,0.000039532537,0.9223461,0.00009014964,0.0001861201,8.99218e-7,0.048878625,0.0028146373,0.00008280448,0.020800492,0.0030060285,0.0006366808],"about_ca_topic_score_codex":0.008018148,"about_ca_topic_score_gemma":0.0035287607,"teacher_disagreement_score":0.07496641,"about_ca_system_score_codex":0.0012082177,"about_ca_system_score_gemma":0.00044312805,"threshold_uncertainty_score":0.99858755},"labels":[],"label_agreement":null},{"id":"W2320000683","doi":"10.1080/08957347.2016.1171768","title":"Evaluating the Psychometric Characteristics of Generated Multiple-Choice Test Items","year":2016,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","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":"Medical Council of Canada; University of Ottawa; University of Alberta","funders":"","keywords":"Item response theory; Item bank; Item analysis; Licensure; Psychology; Test (biology); Psychometrics; Cognition; Multiple choice; Differential item functioning; Applied psychology; Cognitive psychology; Computer science; Clinical psychology; Statistics; Medicine; Medical education","score_opus":0.1433803510187834,"score_gpt":0.4009891954820371,"score_spread":0.2576088444632537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320000683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957502,0.0002490041,0.00019366678,0.00143513,0.0005333007,0.00066714745,0.0000042735855,0.000020387199,0.0011468848],"genre_scores_gemma":[0.99823135,0.00011577234,0.0005720544,0.00038724253,0.00034598805,0.00019399846,0.000020027086,0.000014711791,0.000118851196],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99849504,0.00004498626,0.0005079143,0.00022255398,0.0005637342,0.00016579857],"domain_scores_gemma":[0.9879235,0.010806289,0.0002755947,0.00040492343,0.0004985972,0.00009109909],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001702891,0.00010678307,0.00021307752,0.00014680834,0.000036409976,0.000009104926,0.000089508314,0.0000664815,0.000051142266],"category_scores_gemma":[0.13965367,0.00006069112,0.000039180184,0.00057580497,0.000047642352,0.0000193779,0.000012353493,0.000104613486,0.00003333936],"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":[0.000056151508,0.0010163079,0.480281,0.000018424364,0.000013885147,4.7962367e-8,0.00008952293,0.0000014802366,0.15043533,0.00006678365,0.0005750424,0.36744604],"study_design_scores_gemma":[0.0016364981,0.00019185043,0.9893171,0.0009796123,0.00007346819,0.0000014695346,0.00007776323,0.000075811804,0.0069060638,0.00010181484,0.00055250636,0.00008602907],"about_ca_topic_score_codex":0.00007539517,"about_ca_topic_score_gemma":0.000013831017,"teacher_disagreement_score":0.5090361,"about_ca_system_score_codex":0.0001921021,"about_ca_system_score_gemma":0.0004330451,"threshold_uncertainty_score":0.8675934},"labels":[],"label_agreement":null},{"id":"W2607007324","doi":"10.1080/08957347.2017.1316276","title":"For Which Boys and Which Girls Are Reading Assessment Items Biased Against? Detection of Differential Item Functioning in Heterogeneous Gender Populations","year":2017,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"School Choice and Performance","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"Institute of Education Sciences","keywords":"Differential item functioning; Psychology; Disadvantage; Developmental psychology; Socioeconomic status; Gender bias; Item response theory; Demography; Psychometrics; Social psychology; Population","score_opus":0.11911824277966752,"score_gpt":0.36189019156186625,"score_spread":0.2427719487821987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607007324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932019,0.00006212814,0.0015103471,0.00025034766,0.00097228505,0.00076755334,0.0000023995278,0.000016317468,0.003216722],"genre_scores_gemma":[0.99876356,0.0000645998,0.00030629244,0.000030166842,0.00036405638,0.0004199852,0.00002083211,0.000010831978,0.000019676896],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987578,0.00006286146,0.00031405568,0.00024794435,0.00040265097,0.00021472476],"domain_scores_gemma":[0.9990309,0.000044997938,0.00034062995,0.00021713208,0.0003097595,0.00005660948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001154729,0.00010358469,0.00015306371,0.00018785999,0.00068144593,0.00014053716,0.000119943164,0.00010345297,0.0000064716996],"category_scores_gemma":[0.0003532072,0.000115785995,0.000023006187,0.00020339117,0.000026564318,0.00026527655,0.000015874195,0.00012110436,9.3798513e-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":[0.00007642937,0.00034259833,0.88730586,0.00014165563,0.000023622724,3.8949263e-8,0.0043900213,0.0009449901,0.07174831,0.0011416852,0.00008596254,0.03379886],"study_design_scores_gemma":[0.0006331923,0.000020422318,0.98953956,0.00011737942,0.000024867912,1.5715723e-7,0.003411435,0.0010655972,0.003839413,0.0006933319,0.0004971424,0.00015748586],"about_ca_topic_score_codex":0.0012121854,"about_ca_topic_score_gemma":0.044517662,"teacher_disagreement_score":0.10223375,"about_ca_system_score_codex":0.00044153997,"about_ca_system_score_gemma":0.00030300271,"threshold_uncertainty_score":0.9729174},"labels":[],"label_agreement":null},{"id":"W3126939008","doi":"10.1080/08957347.2020.1835911","title":"Rethinking Think-Alouds: The Often-Problematic Collection of Response Process Data","year":2021,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Think aloud protocol; Psychology; Unobservable; Process (computing); Test (biology); Cognitive psychology; Data collection; Applied psychology; Computer science; Epistemology; Social science; Sociology","score_opus":0.37739825751434847,"score_gpt":0.3923418996521501,"score_spread":0.014943642137801638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126939008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96485555,0.0024478675,0.00015867429,0.0067473566,0.001572462,0.0010780245,0.0000062786285,0.000049420712,0.023084372],"genre_scores_gemma":[0.99827594,0.00003687787,0.00039909303,0.00063985464,0.00006975587,0.00027608726,0.00003167002,0.0000102936365,0.0002604208],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9982158,0.00033970966,0.0004227982,0.0003947374,0.00044590083,0.0001810672],"domain_scores_gemma":[0.9986216,0.00013023436,0.00020136654,0.0007540135,0.00026642194,0.000026387317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029782718,0.000119823424,0.00018548072,0.00005499141,0.00014076989,0.000020340476,0.00038062915,0.00009705694,0.00023173944],"category_scores_gemma":[0.00025380086,0.0000846366,0.00002534584,0.0006832059,0.00006446467,0.000052080693,0.00006774547,0.00023060275,0.000033968146],"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":[0.005655857,0.017342532,0.039605726,0.0008273451,0.00055301865,0.0000074814566,0.339992,0.0000638454,0.13044958,0.03493101,0.17839104,0.25218058],"study_design_scores_gemma":[0.0017428818,0.00019734373,0.7917764,0.0004510158,0.00023508182,0.000024672443,0.057664376,0.000013033976,0.0048774197,0.13493668,0.0076007824,0.00048031728],"about_ca_topic_score_codex":0.00009469057,"about_ca_topic_score_gemma":0.00013759125,"teacher_disagreement_score":0.7521707,"about_ca_system_score_codex":0.00010929114,"about_ca_system_score_gemma":0.00024167736,"threshold_uncertainty_score":0.34513804},"labels":[],"label_agreement":null},{"id":"W4321452091","doi":"10.1080/08957347.2023.2172017","title":"Dissecting Knowledge, Guessing, and Blunder in Multiple Choice Assessments","year":2023,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Toronto","funders":"Division of Molecular and Cellular Biosciences; National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute","keywords":"Test (biology); Probabilistic logic; Mistake; Psychology; Proxy (statistics); Robustness (evolution); Bayesian probability; Social psychology; Computer science; Artificial intelligence; Machine learning; Political science","score_opus":0.8152165292421817,"score_gpt":0.575029629601757,"score_spread":0.24018689964042472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321452091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9586925,0.0006102983,0.00065720535,0.00024297592,0.0008178882,0.00097038504,5.8143326e-7,0.000011299635,0.03799687],"genre_scores_gemma":[0.9969668,0.000016289592,0.0007082941,0.00006144077,0.00009557604,0.000291867,0.000009463004,0.000010110416,0.0018401885],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9923301,0.0011001226,0.0030993875,0.0007346888,0.0024979373,0.00023780564],"domain_scores_gemma":[0.9957916,0.0015652888,0.0010192028,0.0009746587,0.00056986854,0.0000793539],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06437974,0.00017321053,0.0008654971,0.00071762677,0.000101536825,0.0003961639,0.00042158677,0.000058011527,0.00023956984],"category_scores_gemma":[0.015575084,0.0001123527,0.00011764216,0.0023304431,0.00001892641,0.0001648671,0.00006974534,0.00013036437,0.0006395519],"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":[0.0000035257956,0.00038051265,0.8331961,0.000094194555,0.000031884047,1.745126e-7,0.002389649,0.0001240489,0.0028125276,0.0012852203,0.0100146355,0.14966752],"study_design_scores_gemma":[0.00031062786,0.000006513758,0.9585586,0.00011206518,0.00003023288,3.8939615e-7,0.007457862,0.0038137804,0.00013646057,0.0058365553,0.023574725,0.00016215435],"about_ca_topic_score_codex":0.00007092561,"about_ca_topic_score_gemma":0.0016034276,"teacher_disagreement_score":0.14950536,"about_ca_system_score_codex":0.00020268018,"about_ca_system_score_gemma":0.00017542379,"threshold_uncertainty_score":0.99271715},"labels":[],"label_agreement":null},{"id":"W4365813887","doi":"10.1080/08957347.2023.2201703","title":"Multi-Group Generalizations of SIBTEST and Crossing-SIBTEST","year":2023,"lang":"en","type":"article","venue":"Applied Measurement in Education","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":"York University","funders":"","keywords":"Type I and type II errors; Differential item functioning; Statistics; Mathematics; Monte Carlo method; Logistic regression; Set (abstract data type); Population; Group (periodic table); Statistical power; Applied mathematics; Item response theory; Computer science; Psychometrics; Demography","score_opus":0.5905972101310687,"score_gpt":0.4788309874553456,"score_spread":0.11176622267572311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365813887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.975493,0.0005826306,0.017548906,0.0004522743,0.0010384307,0.00046510441,0.000004358495,0.000079835234,0.00433544],"genre_scores_gemma":[0.9632537,0.000049177106,0.03631192,0.00009164553,0.00006309922,0.000075605196,0.000009985295,0.000009390904,0.0001355049],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977792,0.00012856298,0.0006096356,0.00038144796,0.00090005825,0.00020107515],"domain_scores_gemma":[0.99705875,0.0018913733,0.00028256123,0.00037279635,0.0003295388,0.00006495764],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007057887,0.000102563485,0.00020191568,0.0007882515,0.00016049361,0.00015325543,0.00026667438,0.000057274287,0.00002914561],"category_scores_gemma":[0.01823118,0.00008741942,0.000027102933,0.003610788,0.000100470286,0.000098751494,0.000066862216,0.000076338605,0.000029260744],"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":[0.000011867692,0.00049654697,0.49147722,0.00003178439,0.000010117152,2.2788562e-7,0.0017933613,0.0007562803,0.11214468,0.0051278747,0.0049496475,0.3832004],"study_design_scores_gemma":[0.0003832292,0.000021048085,0.97671694,0.000034824625,0.0000071641257,9.450978e-7,0.0025246104,0.0014354517,0.0012168546,0.013031607,0.004500809,0.00012654284],"about_ca_topic_score_codex":0.00010914609,"about_ca_topic_score_gemma":0.00010171845,"teacher_disagreement_score":0.4852397,"about_ca_system_score_codex":0.000067469846,"about_ca_system_score_gemma":0.00019752115,"threshold_uncertainty_score":0.9900387},"labels":[],"label_agreement":null},{"id":"W4395110387","doi":"10.1080/08957347.2024.2345594","title":"A Critical Review of Fairness from Multiple Perspectives: Implications for Classroom Assessment Theory","year":2024,"lang":"en","type":"review","venue":"Applied Measurement in Education","topic":"Student Assessment and Feedback","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":"Queen's University","funders":"","keywords":"Psychology; Item response theory; Critical theory; Mathematics education; Political science; Developmental psychology; Psychometrics","score_opus":0.1496372500266458,"score_gpt":0.4788594395403927,"score_spread":0.3292221895137469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395110387","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":[6.3227037e-7,0.9658984,0.0010978892,0.0012189794,0.000915042,0.004639262,0.00009748145,0.000045147222,0.026087154],"genre_scores_gemma":[0.001294066,0.988445,0.0011836976,0.00015558393,0.0006002989,0.007940052,0.00023796843,0.000045020384,0.00009835713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708855,0.00038011407,0.00080409076,0.0006489864,0.00077201007,0.0003062323],"domain_scores_gemma":[0.9974158,0.0011943923,0.00031595712,0.00044801147,0.00053444365,0.00009142701],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003264273,0.00032420625,0.001007217,0.00024768634,0.00019044062,0.000080776554,0.0004897895,0.00021657131,0.00010557402],"category_scores_gemma":[0.0010151581,0.0002849067,0.0003772509,0.00062107376,0.00015281889,0.00007751377,0.000043816683,0.00032507733,0.000039072525],"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":[0.0000047105787,0.0008212969,0.000027299184,0.022496851,0.00012153052,2.710359e-8,0.0023660427,4.4347132e-8,0.0000014879687,0.51688343,0.006791314,0.45048597],"study_design_scores_gemma":[0.00013070884,0.000024822468,0.0001499932,0.06344053,0.001504282,6.400764e-8,0.013054452,3.4715956e-7,2.9992702e-7,0.030597333,0.89079094,0.00030624535],"about_ca_topic_score_codex":0.00010412796,"about_ca_topic_score_gemma":0.00012842758,"teacher_disagreement_score":0.8839996,"about_ca_system_score_codex":0.0023871684,"about_ca_system_score_gemma":0.00442754,"threshold_uncertainty_score":0.9999603},"labels":[],"label_agreement":null},{"id":"W4416211129","doi":"10.1080/08957347.2025.2563889","title":"Establishing Cognitive Item Models for Fair and Theory-Grounded Automatic Item Generation: A Large-Scale Assessment Study with Image-Based Math Items","year":2025,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"Fonds National de la Recherche Luxembourg","keywords":"Item response theory; Cognition; Item analysis; Differential item functioning; Test (biology); Equating; Item bank; Standardized test","score_opus":0.26271347576987486,"score_gpt":0.44115256739937964,"score_spread":0.17843909162950478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416211129","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":[0.39944476,0.00012693237,0.5934358,0.00024384023,0.0003385436,0.0021778515,0.0000053827507,0.00004937891,0.0041774907],"genre_scores_gemma":[0.9039317,0.0000027107935,0.093821004,0.00033482775,0.0000735252,0.0017247977,0.000019464018,0.000014462915,0.00007752952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963232,0.0005662334,0.0007674625,0.0007831723,0.0012417309,0.00031818077],"domain_scores_gemma":[0.9875879,0.010566975,0.0003995275,0.0004351857,0.0009371789,0.000073192474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018860351,0.00022766332,0.00039317846,0.0007776427,0.00033685638,0.000779983,0.00031584807,0.00006958295,0.000012970147],"category_scores_gemma":[0.009214113,0.00017206432,0.000040616585,0.0018736823,0.000046960435,0.00043635097,0.00005854543,0.00016333946,0.0000014031282],"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":[0.00054494495,0.0069910088,0.10529426,0.0002907903,0.000233188,0.000001314129,0.011323143,0.0024511875,0.003906493,0.06665377,0.0022662543,0.80004364],"study_design_scores_gemma":[0.0067346264,0.0005339031,0.18445231,0.00044553785,0.00024220167,0.0000019990716,0.17696886,0.48734587,0.00077583134,0.14160612,0.00027370956,0.00061902264],"about_ca_topic_score_codex":0.000038233193,"about_ca_topic_score_gemma":0.00018519266,"teacher_disagreement_score":0.79942465,"about_ca_system_score_codex":0.0003303513,"about_ca_system_score_gemma":0.0007973295,"threshold_uncertainty_score":0.9991317},"labels":[],"label_agreement":null}]}