{"meta":{"query_hash":"4cda1ec5ea24","filters":{"venue":"Educational and Psychological Measurement"},"cohort_total":101,"direct_labels_cover":1,"predictions_cover":101,"exported":101,"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/4cda1ec5ea24","api":"https://metacan.xera.ac/api/v1/cohort?venue=Educational+and+Psychological+Measurement"},"results":[{"id":"W1501970797","doi":"10.1177/0013164415593777","title":"Testing Mediation in Structural Equation Modeling","year":2015,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Attachment and Relationship Dynamics","field":"Psychology","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Bootstrapping (finance); Structural equation modeling; Monte Carlo method; Latent variable; Mediation; Econometrics; Contrast (vision); Statistical hypothesis testing; Statistics; Computer science; Latent variable model; Mathematics; Artificial intelligence","score_opus":0.43403025857533684,"score_gpt":0.4648977677929242,"score_spread":0.030867509217587352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501970797","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":[0.9720743,0.0006000636,0.0040811133,0.003000506,0.0013073805,0.00021597443,0.0000014797408,0.000026330423,0.018692868],"genre_scores_gemma":[0.9970842,0.0000017869386,0.0022416865,0.00015045787,0.00030123384,0.00005985066,0.000028351915,0.000005400768,0.00012703842],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988624,0.00011892374,0.00025965576,0.0002506426,0.00034846205,0.00015992235],"domain_scores_gemma":[0.9994659,0.00009408989,0.000063448315,0.00009361228,0.00017937101,0.000103607184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007914322,0.000095503725,0.00008710481,0.00008402816,0.00006727328,0.00002059227,0.000066084816,0.000096122814,0.00015207815],"category_scores_gemma":[0.00036000318,0.0000765965,0.000016102675,0.00019483644,0.000030019932,0.00007805286,0.000011732721,0.00015778601,0.00005765739],"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":[0.00008031313,0.0003679759,0.9222157,0.0000055420983,0.000018906832,0.0000012290664,0.0033659104,0.0045829774,0.000091389506,0.05688288,0.00044937019,0.011937804],"study_design_scores_gemma":[0.0007680241,0.00012287071,0.8682479,0.000015892108,0.000007687935,0.000010680148,0.0007219403,0.049439196,4.01628e-7,0.08046315,0.00005865296,0.00014358223],"about_ca_topic_score_codex":0.000046332105,"about_ca_topic_score_gemma":0.000013548578,"teacher_disagreement_score":0.053967774,"about_ca_system_score_codex":0.00012412388,"about_ca_system_score_gemma":0.000040411676,"threshold_uncertainty_score":0.31235147},"labels":[],"label_agreement":null},{"id":"W1763331641","doi":"10.1177/0013164415584576","title":"It Might Not Make a Big DIF","year":2015,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":130,"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":"Differential item functioning; Item response theory; Statistics; Polytomous Rasch model; Computer science; Monte Carlo method; Econometrics; Type I and type II errors; Statistical hypothesis testing; Machine learning; Data mining; Artificial intelligence; Psychometrics; Mathematics","score_opus":0.9118226372485674,"score_gpt":0.5444501445426981,"score_spread":0.36737249270586925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1763331641","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":[0.5929533,0.002606433,0.00848812,0.16969456,0.009603234,0.00044963733,0.000017086873,0.00008240417,0.21610522],"genre_scores_gemma":[0.9806212,0.00002262595,0.011479998,0.0047788606,0.0007407291,0.000041514893,0.0000019464915,0.000005069896,0.0023080264],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99589324,0.000466154,0.000541566,0.00062367745,0.0021950505,0.0002803024],"domain_scores_gemma":[0.99423337,0.0040869103,0.00017826223,0.000395327,0.00071644643,0.00038966478],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010138696,0.00014899787,0.00024056114,0.00020872647,0.00013978122,0.00016674433,0.00048087898,0.00008620465,0.0005668987],"category_scores_gemma":[0.05947007,0.00008797546,0.00007200234,0.0008806389,0.00012229441,0.000040405703,0.00007949272,0.00016401333,0.00025464472],"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":[0.00014594277,0.00089368504,0.06984503,0.0000036354772,0.00002580343,0.0000035264814,0.0005898251,0.000008374251,0.0004786453,0.006006123,0.19425382,0.7277456],"study_design_scores_gemma":[0.00044849116,0.00023733632,0.6071104,0.000011681144,0.000005832416,0.000032370684,0.00038340047,0.000015698592,0.0000282667,0.119155295,0.2724169,0.00015438048],"about_ca_topic_score_codex":0.000013465686,"about_ca_topic_score_gemma":0.000011422254,"teacher_disagreement_score":0.7275912,"about_ca_system_score_codex":0.000054206153,"about_ca_system_score_gemma":0.000084218365,"threshold_uncertainty_score":0.9484524},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W1966169084","doi":"10.1177/0013164410387382","title":"Invariance of the Measurement Model Underlying the Wechsler Adult Intelligence Scale-IV in the United States and Canada","year":2010,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":48,"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 Calgary; BC Mental Health & Substance Use Services; University of British Columbia","funders":"American Psychological Association; American Educational Research Association","keywords":"Psychology; Wechsler Adult Intelligence Scale; Measurement invariance; Normative; Generality; Construct validity; Intelligence quotient; Latent variable; Wechsler Preschool and Primary Scale of Intelligence; Psychometrics; Cognition; Developmental psychology; Construct (python library); Scale (ratio); Set (abstract data type); Latent variable model; Wechsler Intelligence Scale for Children; Sample (material); Statistics; Confirmatory factor analysis; Structural equation modeling; Mathematics","score_opus":0.23908308271066525,"score_gpt":0.35532753374293286,"score_spread":0.1162444510322676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966169084","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":[0.967531,0.00021753377,0.00022113665,0.026965566,0.00049270195,0.000394957,0.000011104863,0.000004278883,0.0041617155],"genre_scores_gemma":[0.99568844,0.000028999197,0.00012870812,0.003926845,0.000048405058,0.00012354249,0.0000026009996,0.000004815519,0.000047625035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99842376,0.0002274023,0.00028554793,0.0002724339,0.0005904518,0.00020038898],"domain_scores_gemma":[0.9986559,0.00049260457,0.00010160862,0.0002750482,0.0004278204,0.00004701815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015119044,0.00012278499,0.000103623985,0.000031677257,0.00024794758,0.000038918373,0.00029398347,0.000048506907,0.00017398901],"category_scores_gemma":[0.0005319834,0.00005951138,0.000026053383,0.00021855877,0.00032420937,0.000022842898,0.00003978294,0.00040142197,0.0000013113508],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006582119,0.005203539,0.3533269,0.00020744489,0.00034491724,0.0000049225864,0.06324825,0.0015660811,0.0058657406,0.41524538,0.026079608,0.12824902],"study_design_scores_gemma":[0.00025017984,0.00007134879,0.9264714,0.00007472785,0.000020601681,0.00001857093,0.0076529854,0.00077591126,0.00003005518,0.06307649,0.0014175626,0.00014017211],"about_ca_topic_score_codex":0.14644723,"about_ca_topic_score_gemma":0.40405753,"teacher_disagreement_score":0.5731445,"about_ca_system_score_codex":0.000056756187,"about_ca_system_score_gemma":0.00015665244,"threshold_uncertainty_score":0.85923666},"labels":[],"label_agreement":null},{"id":"W1973036726","doi":"10.1177/0013164410379335","title":"Confidence Intervals for Squared Semipartial Correlation Coefficients: The Effect of Nonnormality","year":2010,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Confidence interval; Mathematics; Percentile; Coverage probability; Robust confidence intervals; Sample size determination; CDF-based nonparametric confidence interval; Regression analysis; Correlation coefficient; Confidence distribution; Correlation; Linear regression; Regression","score_opus":0.23018771376746072,"score_gpt":0.4782251453698139,"score_spread":0.2480374316023532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973036726","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":[0.18067512,0.000037044527,0.816075,0.0012636442,0.0007571474,0.00060453516,0.000026148477,0.000009197913,0.0005521009],"genre_scores_gemma":[0.9601151,0.0000017047589,0.03942794,0.0000843984,0.00012922728,0.00018018346,0.0000045832267,0.000004359049,0.000052540618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989464,0.00017624753,0.000286039,0.00019196118,0.0002776372,0.00012168733],"domain_scores_gemma":[0.99689204,0.0025394917,0.00012531386,0.00015745484,0.00022596197,0.000059721548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021650132,0.00009428823,0.00016438283,0.000013650908,0.00010592164,0.00001233494,0.000102907514,0.00005826202,0.00013346269],"category_scores_gemma":[0.0044174856,0.00005176007,0.000052839758,0.000048255162,0.00015609487,0.00003069408,0.000014747378,0.0001426051,0.0000019184763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007238027,0.0006414066,0.0014710531,0.00015884926,0.000039634004,1.2149499e-7,0.0003715611,0.000028225964,0.0136941625,0.9469221,0.0026339372,0.033315115],"study_design_scores_gemma":[0.0008770822,0.0010135741,0.020507868,0.000054793316,0.00006278859,0.0000070886413,0.000028951952,0.00096594746,0.0028575326,0.9722439,0.0012468068,0.00013366646],"about_ca_topic_score_codex":0.0000027881379,"about_ca_topic_score_gemma":0.0000039460206,"teacher_disagreement_score":0.7794399,"about_ca_system_score_codex":0.000011854722,"about_ca_system_score_gemma":0.000014025149,"threshold_uncertainty_score":0.5288462},"labels":[],"label_agreement":null},{"id":"W1973081171","doi":"10.1177/0013164408322017","title":"A Cross-Cultural Examination of the Psychometric Properties of Responses to the Achievement Goal Questionnaire","year":2008,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Education, Achievement, and Giftedness","field":"Psychology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Psychology; Confirmatory factor analysis; Structural equation modeling; Measurement invariance; Metric (unit); Psychometrics; Test validity; Academic achievement; Developmental psychology; Social psychology; Statistics; Mathematics","score_opus":0.205160770575988,"score_gpt":0.388235285087074,"score_spread":0.183074514511086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973081171","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":[0.9816932,0.0018339227,0.000039906095,0.012250275,0.0018360942,0.00063468004,0.000012612694,0.000011523632,0.0016877601],"genre_scores_gemma":[0.9960143,0.000053542197,0.00009289777,0.0006220079,0.00028360158,0.00031848,0.0000041444832,0.000007609095,0.0026034187],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99764353,0.0005340815,0.00048697306,0.00034527693,0.0007895458,0.00020058683],"domain_scores_gemma":[0.9983391,0.00008795855,0.00023389672,0.00041264383,0.0008450917,0.00008130188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014634233,0.0001632694,0.00016952287,0.0001273477,0.00037042407,0.000022000753,0.0003790891,0.00008390309,0.00029413358],"category_scores_gemma":[0.00071095116,0.00008186716,0.00008516163,0.0006852693,0.00052043534,0.00007673888,0.000040689156,0.00015853165,0.000020744572],"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":[0.00039855938,0.0037358096,0.95354444,0.000047465193,0.00010200133,1.5513206e-7,0.01273877,0.000008192408,0.0048925714,0.010181323,0.0050443104,0.009306384],"study_design_scores_gemma":[0.0003942657,0.00033221373,0.99452865,0.00007726993,0.000018461424,0.000015305219,0.0008621926,4.372204e-7,0.0005495354,0.00029297773,0.0028177206,0.00011097046],"about_ca_topic_score_codex":0.00011481037,"about_ca_topic_score_gemma":0.000022404742,"teacher_disagreement_score":0.04098419,"about_ca_system_score_codex":0.00006853663,"about_ca_system_score_gemma":0.00008502373,"threshold_uncertainty_score":0.3338446},"labels":[],"label_agreement":null},{"id":"W1975494033","doi":"10.1177/0013164413487738","title":"False Positives in Multiple Regression","year":2013,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":42,"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":"Type I and type II errors; Statistics; Regression; False positive paradox; Regression analysis; Econometrics; Observational error; Regression diagnostic; Nominal level; Inflation (cosmology); Computer science; Linear regression; False positives and false negatives; Mathematics; Polynomial regression; Confidence interval","score_opus":0.450798048209222,"score_gpt":0.4850311437518074,"score_spread":0.03423309554258541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975494033","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":[0.86384237,0.00066138885,0.11639652,0.010769796,0.00037433143,0.00077749236,0.000008923082,0.00003505592,0.007134133],"genre_scores_gemma":[0.80890477,0.000019305282,0.19046277,0.00023701969,0.00005855909,0.00014030837,0.0000016739276,0.0000044509547,0.00017116498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999048,0.000122609,0.00020040432,0.00025181536,0.00022836875,0.00014882622],"domain_scores_gemma":[0.9990852,0.0005633185,0.00004286361,0.00010783715,0.00010353283,0.00009728966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003928839,0.00009539343,0.00013084798,0.00003182792,0.00005754854,0.000015946229,0.000055128105,0.000047800648,0.00041588768],"category_scores_gemma":[0.0013984566,0.00006095699,0.000021247479,0.000057256646,0.00005635683,0.00006018958,0.000016663174,0.00010718926,0.000024432586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011478265,0.0038683352,0.015131795,0.00007721171,0.000025125224,0.0000033410163,0.0007792232,0.0000045512043,0.020631092,0.71002835,0.011329269,0.23800692],"study_design_scores_gemma":[0.0002612132,0.000070474496,0.18811972,0.00005502917,0.0000024918643,0.0000032836015,0.00006265477,0.000051502382,0.0001012813,0.8109105,0.00027836303,0.00008343883],"about_ca_topic_score_codex":0.0000107870255,"about_ca_topic_score_gemma":0.0000048532324,"teacher_disagreement_score":0.23792349,"about_ca_system_score_codex":0.00003225187,"about_ca_system_score_gemma":0.000009238373,"threshold_uncertainty_score":0.45536786},"labels":[],"label_agreement":null},{"id":"W1976267793","doi":"10.1177/0013164403258444","title":"Gender and Language Differences on the Test of Workplace Essential Skills: Using Overall Mean Scores and Item-Level Differential Item Functioning Analyses","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Teacher Professional Development and Motivation","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 Calgary","funders":"","keywords":"Psychology; Differential item functioning; Numeracy; Test (biology); Reading (process); Developmental psychology; Item response theory; Psychometrics; Literacy; Pedagogy","score_opus":0.29669886693486586,"score_gpt":0.40945114458084786,"score_spread":0.112752277645982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976267793","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":[0.9955927,0.00036158456,0.0003098104,0.002415865,0.00029305214,0.00016736313,0.0000040929663,0.000010033965,0.00084548024],"genre_scores_gemma":[0.99875635,0.00007638597,0.0004936008,0.00018367326,0.0002469142,0.0000132538635,0.0000044311364,0.0000035557928,0.00022183917],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99877465,0.00015675607,0.00017643272,0.00023394801,0.0005190833,0.00013912123],"domain_scores_gemma":[0.9991607,0.0005110275,0.000101422695,0.00005840084,0.00009521063,0.00007325929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048383028,0.000108718756,0.00011575447,0.00005359647,0.00049155124,0.00006474565,0.000072028335,0.000064422464,0.00019939101],"category_scores_gemma":[0.00059605495,0.00006592368,0.000024983681,0.00010304292,0.00022441847,0.000075755976,0.000026553686,0.000116568575,9.3317703e-7],"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":[0.00015209771,0.0020755406,0.85338676,0.00005001372,0.00016973593,9.665102e-7,0.043695327,0.000014083163,0.03451672,0.057805933,0.0005275454,0.0076052817],"study_design_scores_gemma":[0.00028935864,0.000048121507,0.98903203,0.00010484175,0.000020836775,0.0000010491482,0.0026530395,0.00000409293,0.00021297601,0.007512802,0.000027359565,0.00009350229],"about_ca_topic_score_codex":0.00020533621,"about_ca_topic_score_gemma":0.00008583613,"teacher_disagreement_score":0.13564527,"about_ca_system_score_codex":0.000050449533,"about_ca_system_score_gemma":0.000079600795,"threshold_uncertainty_score":0.37806645},"labels":[],"label_agreement":null},{"id":"W1977230984","doi":"10.1177/00164402062003002","title":"Pairwise Multiple Comparison Tests when Data are Nonnormal","year":2002,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Type I and type II errors; Pairwise comparison; Heteroscedasticity; Statistic; Mathematics; Statistical hypothesis testing; Test statistic; Truncated mean; Econometrics; Multiple comparisons problem; Estimator","score_opus":0.9427542988485699,"score_gpt":0.6099393060666746,"score_spread":0.3328149927818953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977230984","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":[0.4886989,0.00905558,0.16847438,0.21684323,0.018908076,0.007561861,0.0021711634,0.0011175516,0.08716925],"genre_scores_gemma":[0.6155851,0.000028673248,0.38267317,0.0006819262,0.0006948615,0.000058251262,0.000008198453,0.00001201145,0.00025780362],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99707955,0.00053804,0.0007182057,0.00062391546,0.0007601539,0.00028013872],"domain_scores_gemma":[0.987797,0.010768701,0.00024363372,0.00073356985,0.00020513956,0.00025190655],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00277651,0.0001947814,0.00041113814,0.00003528383,0.00014252224,0.0000519021,0.00048432802,0.00013344667,0.0041569006],"category_scores_gemma":[0.046842396,0.00014271865,0.000051809515,0.000099593926,0.00017251984,0.00007501017,0.00014565281,0.00029708134,0.00018381598],"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":[0.0001552093,0.010730999,0.13797215,0.00013238165,0.0001379626,0.0000059097515,0.0003890147,0.0000011927353,0.00016853392,0.029201614,0.7394271,0.08167792],"study_design_scores_gemma":[0.0011734465,0.00028099545,0.28521508,0.000105966166,0.000067955654,0.000012370849,0.00007983447,0.00065382593,0.000018854065,0.6973832,0.014689974,0.0003184823],"about_ca_topic_score_codex":0.000005529919,"about_ca_topic_score_gemma":0.000011692529,"teacher_disagreement_score":0.72473717,"about_ca_system_score_codex":0.000043374937,"about_ca_system_score_gemma":0.0000126521445,"threshold_uncertainty_score":0.99675345},"labels":[],"label_agreement":null},{"id":"W1977836768","doi":"10.1177/0013164402239324","title":"Psychometric Properties Of The French Canadian Version Of The State-Trait Anxiety Inventory For Children","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut universitaire en santé mentale de Montréal","funders":"","keywords":"State-Trait Anxiety Inventory; Psychology; Anxiety; Psychometrics; Trait anxiety; Trait; Clinical psychology; Developmental psychology; Internal consistency; Psychiatry","score_opus":0.07757421657594854,"score_gpt":0.27656635187134304,"score_spread":0.1989921352953945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977836768","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":[0.98509943,0.001508673,0.0000084315325,0.0045559024,0.0024745776,0.00062980136,0.00006364176,0.0000037712985,0.0056557897],"genre_scores_gemma":[0.99800354,0.000037363745,0.000044390472,0.0007386136,0.00009501472,0.000044087905,0.0000054490497,0.0000054626717,0.0010260823],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99877375,0.00011824154,0.0002830225,0.00024647158,0.00037644064,0.00020207501],"domain_scores_gemma":[0.99937195,0.000016597594,0.00012642032,0.00018850088,0.00019311826,0.000103417566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047077372,0.00011920067,0.00012965639,0.000067485766,0.00022016872,0.000008372325,0.00023249819,0.00006992266,0.00041693368],"category_scores_gemma":[0.00011559073,0.00006266927,0.00013292443,0.00033942427,0.00016411449,0.00001980582,0.000013081537,0.00011835562,0.0000054611687],"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":[0.00009077661,0.0024111213,0.8671469,0.00008283286,0.00020500757,2.0433927e-8,0.0018252956,0.0000051855613,0.0016080976,0.016166551,0.10054554,0.009912643],"study_design_scores_gemma":[0.0005009168,0.000056250385,0.9774894,0.000094183226,0.000014242491,0.0000040175264,0.00007021254,1.2766048e-7,0.0002651149,0.005942801,0.015473898,0.000088808374],"about_ca_topic_score_codex":0.0016519729,"about_ca_topic_score_gemma":0.00082654407,"teacher_disagreement_score":0.1103425,"about_ca_system_score_codex":0.00006935687,"about_ca_system_score_gemma":0.00018641674,"threshold_uncertainty_score":0.45651314},"labels":[],"label_agreement":null},{"id":"W1977904348","doi":"10.1177/0013164404264840","title":"Testing the Structure of Psychological Empowerment: Does Gender Make a Difference?","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Community Health and Development","field":"Health Professions","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Université de Montréal","funders":"","keywords":"Psychology; Confirmatory factor analysis; Competence (human resources); Social psychology; Construct validity; Structural equation modeling; Developmental psychology; Group analysis; Empowerment; Psychometrics; Statistics; Mathematics","score_opus":0.39198687972440754,"score_gpt":0.47928748055148107,"score_spread":0.08730060082707353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977904348","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":[0.974505,0.00037992184,0.00007403993,0.017118046,0.0010577383,0.0007502025,0.000017567654,0.000026028649,0.006071475],"genre_scores_gemma":[0.9913296,0.000039890052,0.0025039276,0.0056897844,0.00026205025,0.00008457841,0.000010377699,0.0000062031904,0.00007357757],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978554,0.00039244368,0.00053755264,0.00029829296,0.0005429169,0.00037335575],"domain_scores_gemma":[0.9984539,0.0005176175,0.00019443846,0.00031525566,0.000328108,0.00019066957],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007906764,0.00016506904,0.00020494482,0.00004471909,0.0008341648,0.000009321045,0.00025697716,0.0001516428,0.00095672364],"category_scores_gemma":[0.00066901935,0.00007733965,0.00003783006,0.00020260479,0.0001622166,0.000017479142,0.00008459518,0.0006567539,0.00002286265],"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":[0.00059689034,0.0048826723,0.7922832,0.0006015426,0.000117076364,0.0000032169687,0.021644326,0.000013888554,0.024353106,0.09631622,0.0050986055,0.054089297],"study_design_scores_gemma":[0.0006449467,0.00014367915,0.8605259,0.00009731046,0.0000075861494,0.0000071813415,0.0008939397,3.4475917e-7,0.000017206436,0.13587244,0.0016929009,0.00009654409],"about_ca_topic_score_codex":0.00007052096,"about_ca_topic_score_gemma":0.00007389175,"teacher_disagreement_score":0.06824276,"about_ca_system_score_codex":0.00013135848,"about_ca_system_score_gemma":0.00022652063,"threshold_uncertainty_score":0.99995655},"labels":[],"label_agreement":null},{"id":"W1978985895","doi":"10.1177/0013164409344498","title":"Testing the Second-Order Factor Structure and Measurement Equivalence of the Wong and Law Emotional Intelligence Scale Across Gender and Ethnicity","year":2009,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Emotional Intelligence and Performance","field":"Psychology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Marriott International (Canada)","funders":"","keywords":"Equivalence (formal languages); Psychology; Ethnic group; Emotional intelligence; Scale (ratio); Social psychology; Context (archaeology); Mathematics; Law; Political science","score_opus":0.33375031387670345,"score_gpt":0.4099216136148018,"score_spread":0.07617129973809833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978985895","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":[0.98967034,0.0036370102,0.00024675624,0.00336461,0.00043119676,0.00030396273,0.000048984195,0.000009314278,0.0022878242],"genre_scores_gemma":[0.99711084,0.00006396321,0.00040238403,0.0021181866,0.00017803999,0.000015230487,0.0000017473839,0.000005049619,0.00010455774],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982008,0.0001606922,0.0003314035,0.00043731317,0.00060885644,0.0002609429],"domain_scores_gemma":[0.99891686,0.00019229298,0.00013686263,0.00021723642,0.000431179,0.000105574414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008299434,0.00019283425,0.00016083369,0.000019588635,0.00043506405,0.00005110424,0.00019169523,0.000114314214,0.00070990215],"category_scores_gemma":[0.00014997204,0.00010835095,0.00003149033,0.00017042588,0.00063406804,0.00009207976,0.000060470393,0.00033001404,0.0000033567735],"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":[0.00042141118,0.002678202,0.53137785,0.000347801,0.00032581756,0.0000020036919,0.02441176,0.00007246901,0.05627546,0.17432848,0.002041282,0.20771743],"study_design_scores_gemma":[0.00012595738,0.00019572441,0.9622928,0.000067068475,0.000011291787,0.00007413684,0.0004246533,0.000019656745,0.0005597667,0.035768896,0.00032473446,0.0001353052],"about_ca_topic_score_codex":0.00003554484,"about_ca_topic_score_gemma":0.000055129498,"teacher_disagreement_score":0.43091494,"about_ca_system_score_codex":0.00003095352,"about_ca_system_score_gemma":0.00003356196,"threshold_uncertainty_score":0.777293},"labels":[],"label_agreement":null},{"id":"W1981221874","doi":"10.1177/0013164403261051","title":"A Note on How to Quantify and Report Whether Irt Parameter Invariance Holds: When Pearson Correlations are Not Enough","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":37,"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":"Item response theory; Measurement invariance; Pearson product-moment correlation coefficient; Mathematics; Econometrics; Statistics; Scale (ratio); Measure (data warehouse); Correlation; Psychology; Psychometrics; Confirmatory factor analysis; Computer science; Structural equation modeling; Data mining","score_opus":0.7338274295775041,"score_gpt":0.4936132193884701,"score_spread":0.24021421018903405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981221874","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":[0.7591046,0.00044197743,0.031444624,0.20198305,0.0019136121,0.00051117403,0.000016010981,0.00004126283,0.0045436737],"genre_scores_gemma":[0.9336081,0.0000206525,0.061132196,0.00398329,0.00026995066,0.00007005443,0.000002542926,0.000007836528,0.0009053679],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99652,0.0003189657,0.0004921851,0.0009272744,0.0014653844,0.00027620333],"domain_scores_gemma":[0.9934185,0.0050737695,0.00031844046,0.00050536444,0.00042337843,0.00026055632],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005228688,0.00019556766,0.00029579885,0.00023655636,0.00027606203,0.00028835365,0.00029976087,0.00012482589,0.00020892575],"category_scores_gemma":[0.06219046,0.00012873429,0.00006779595,0.00063767814,0.00011268815,0.00012692263,0.00006224519,0.0002604339,0.0000945006],"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":[0.0010608267,0.0055579618,0.4999641,0.000040886654,0.00017028327,0.000121386955,0.0075427745,0.0009446129,0.0056813676,0.06386925,0.12836342,0.28668314],"study_design_scores_gemma":[0.00036207755,0.00032594893,0.87117624,0.00006578492,0.00000814466,0.00009021415,0.00022254052,0.000010193642,0.000033514687,0.10506256,0.022458859,0.00018391528],"about_ca_topic_score_codex":0.000029003048,"about_ca_topic_score_gemma":0.000012742422,"teacher_disagreement_score":0.37121215,"about_ca_system_score_codex":0.00007410339,"about_ca_system_score_gemma":0.000056322573,"threshold_uncertainty_score":0.9457091},"labels":[],"label_agreement":null},{"id":"W1981571713","doi":"10.1177/0013164403258407","title":"Balancing the Need for Reliability and Time Efficiency: Short Forms of the Wechsler Adult Intelligence Scale-III","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":72,"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 Windsor","funders":"","keywords":"Wechsler Adult Intelligence Scale; Wechsler Preschool and Primary Scale of Intelligence; Psychology; Reliability (semiconductor); Short Forms; Scale (ratio); Wechsler Intelligence Scale for Children; Intelligence quotient; Statistics; Psychometrics; Raw score; Developmental psychology; Clinical psychology; Mathematics; Cognition; Psychiatry; Cartography; Raw data","score_opus":0.08200673823526182,"score_gpt":0.3386034828471236,"score_spread":0.25659674461186177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981571713","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":[0.979445,0.00029895594,0.001657528,0.010371483,0.00042294172,0.0007152491,0.000011969614,0.00001163596,0.0070652566],"genre_scores_gemma":[0.99844325,0.0000061182805,0.00034121095,0.0007837841,0.00011498303,0.00016773654,0.0000021378846,0.0000049978735,0.00013581409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99886554,0.00007023907,0.0002890961,0.0003236742,0.0002556055,0.00019582953],"domain_scores_gemma":[0.9988277,0.0004678395,0.0000681529,0.00022753648,0.00035390427,0.00005489106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010668999,0.00011405336,0.00013088832,0.000016814076,0.0002319741,0.000016948896,0.0001602945,0.00005855015,0.00021356677],"category_scores_gemma":[0.0006421967,0.000056362125,0.00006780606,0.0001275707,0.000361743,0.000026768257,0.00004041258,0.00013408107,0.00000579807],"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":[0.0015123109,0.008830819,0.29237244,0.00028943142,0.00028472592,7.881883e-7,0.02808273,0.00023473898,0.008331126,0.37361374,0.004243255,0.2822039],"study_design_scores_gemma":[0.0005083358,0.00043868195,0.8235789,0.00010231062,0.000036272064,0.000023805807,0.0019814435,0.000038470775,0.000403493,0.17233343,0.00039702738,0.00015782997],"about_ca_topic_score_codex":0.0000511337,"about_ca_topic_score_gemma":0.000012110095,"teacher_disagreement_score":0.5312065,"about_ca_system_score_codex":0.000043056327,"about_ca_system_score_gemma":0.000038325477,"threshold_uncertainty_score":0.23384064},"labels":[],"label_agreement":null},{"id":"W1989677836","doi":"10.1177/0013164408322027","title":"Comparing Treatment and Control Groups on Multiple Outcomes","year":2008,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of British Columbia; Simon Fraser University; University of Saskatchewan","funders":"","keywords":"Statistics; Mathematics; Normality; Type I and type II errors; Covariance; Homogeneity (statistics); Population; Statistical hypothesis testing; Treatment and control groups; Multivariate normal distribution; Analysis of covariance; A priori and a posteriori; Multivariate statistics; Econometrics","score_opus":0.8792290284703227,"score_gpt":0.5762263579324098,"score_spread":0.30300267053791285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989677836","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":[0.9862859,0.00014398548,0.0041505913,0.0054850215,0.0006164746,0.0005346768,0.000018130086,0.000039957114,0.0027252154],"genre_scores_gemma":[0.9464415,0.000056158795,0.05234701,0.0006906539,0.00022262527,0.00012335641,8.96718e-7,0.000008032747,0.00010978689],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983712,0.00033270515,0.0004043646,0.0003659374,0.00034336216,0.00018245362],"domain_scores_gemma":[0.98403883,0.01543065,0.00009364703,0.00017714308,0.00007906234,0.00018066051],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00091272173,0.00017545398,0.00042807023,0.000031165542,0.00017124291,0.000016123,0.00006948542,0.00007556819,0.00018571135],"category_scores_gemma":[0.015951196,0.00010871928,0.000065305256,0.000043084136,0.00017660561,0.000018605953,0.000013590617,0.00011641469,0.000021588543],"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":[0.000577031,0.0063127703,0.81624925,0.000032789772,0.00025187474,0.00000665983,0.00033117135,0.0000018691303,0.00032897602,0.16112998,0.0032357317,0.011541915],"study_design_scores_gemma":[0.0020976348,0.0005521702,0.679509,0.000018794497,0.000028890265,0.000012516462,0.000014047653,0.000015739946,0.000025137226,0.3172587,0.00035504843,0.000112373964],"about_ca_topic_score_codex":0.0000066431576,"about_ca_topic_score_gemma":0.000003349827,"teacher_disagreement_score":0.1561287,"about_ca_system_score_codex":0.00006787324,"about_ca_system_score_gemma":0.000016467517,"threshold_uncertainty_score":0.9923379},"labels":[],"label_agreement":null},{"id":"W1995196170","doi":"10.1177/0013164403256358","title":"Approximate Confidence Intervals for Effect Sizes","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":70,"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 Manitoba","funders":"","keywords":"Statistics; Confidence interval; Interval (graph theory); Contrast (vision); Coverage probability; Mathematics; Population; Credible interval; Tolerance interval; Econometrics; Demography; Computer science; Combinatorics","score_opus":0.7704275307910567,"score_gpt":0.5976349069448019,"score_spread":0.17279262384625482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995196170","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":[0.12291843,0.0012594654,0.80909747,0.012569586,0.0068579395,0.0053440984,0.00010177023,0.00018878706,0.041662477],"genre_scores_gemma":[0.4791962,0.000017958506,0.51915437,0.0005466006,0.00024750756,0.0005943283,9.807452e-7,0.000012408213,0.00022964529],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99771386,0.00078017503,0.0004945093,0.00040311294,0.00038216473,0.00022620193],"domain_scores_gemma":[0.975208,0.024094788,0.00013133114,0.00020694615,0.0002114082,0.0001475343],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0065475334,0.0001611382,0.00036790414,0.000024657498,0.00009761367,0.000037746202,0.00012845562,0.000100205194,0.00082816504],"category_scores_gemma":[0.11214416,0.00010771896,0.00010259425,0.00007100306,0.0001431431,0.000025809179,0.000013890644,0.00012772714,0.00001926902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016053309,0.00068039406,0.00055802625,0.00014898999,0.000051555417,3.36728e-7,0.00004318759,1.2774271e-7,0.0009075246,0.9791241,0.009429845,0.0088953255],"study_design_scores_gemma":[0.00082508544,0.0006506283,0.0032077893,0.0000730859,0.000044167802,0.000007808377,0.000012102889,0.000004600516,0.0011853932,0.9916546,0.002190242,0.00014454602],"about_ca_topic_score_codex":6.3792885e-7,"about_ca_topic_score_gemma":3.831762e-7,"teacher_disagreement_score":0.35627776,"about_ca_system_score_codex":0.000034496643,"about_ca_system_score_gemma":0.000026619915,"threshold_uncertainty_score":0.9067826},"labels":[],"label_agreement":null},{"id":"W1996585332","doi":"10.1177/0013164413514053","title":"Examining Student Factors in Sources of Setting Accommodation DIF","year":2013,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Disability Education and Employment","field":"Social Sciences","cited_by":18,"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 Saskatchewan","funders":"University of Toronto","keywords":"Covariate; Psychology; Accommodation; Multilevel model; Differential item functioning; Item response theory; Latent class model; Odds; Scale (ratio); Logistic regression; Reading (process); Statistics; Developmental psychology; Psychometrics; Mathematics","score_opus":0.2872603315525131,"score_gpt":0.41974628872881425,"score_spread":0.13248595717630113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996585332","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":[0.97823864,0.00007804999,0.000007370435,0.01014129,0.00031710044,0.00027792205,7.16496e-7,0.000009585196,0.010929352],"genre_scores_gemma":[0.99924016,0.00001698236,0.00020490354,0.00018556834,0.00010103979,0.00008077698,0.000004024905,0.0000022577206,0.00016428359],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987731,0.0001873091,0.00024162362,0.0001805259,0.0004717764,0.00014564229],"domain_scores_gemma":[0.9994612,0.00016551584,0.000074502284,0.000079097794,0.0001293692,0.00009035058],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009565895,0.00006630199,0.0000926683,0.00005070269,0.00012681875,0.000046500507,0.00011398774,0.000042111275,0.001560318],"category_scores_gemma":[0.00036342395,0.000052572595,0.000019327133,0.00012734017,0.00012923939,0.00010889245,0.00001588538,0.00006531752,0.000016863276],"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":[0.0000021545586,0.0009031561,0.9689481,0.0000054687275,0.0000052492787,1.2568438e-8,0.01701425,0.0000037205127,0.00018561668,0.004745512,0.0006637134,0.0075230035],"study_design_scores_gemma":[0.00009913324,0.000040155475,0.96908414,0.000020523146,0.000002272209,8.6095405e-8,0.025161007,7.425042e-7,0.000023101706,0.0042394646,0.0012688199,0.000060560622],"about_ca_topic_score_codex":0.0009066672,"about_ca_topic_score_gemma":0.0002013485,"teacher_disagreement_score":0.02100155,"about_ca_system_score_codex":0.000105065476,"about_ca_system_score_gemma":0.000056202145,"threshold_uncertainty_score":0.9993524},"labels":[],"label_agreement":null},{"id":"W2001638213","doi":"10.1177/0013164406288162","title":"Automated Simultaneous Assembly of Multistage Testlets for a High-Stakes Licensing Examination","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Spreadsheets and End-User Computing","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computerized adaptive testing; Test (biology); Computer science; Certification; Constraint (computer-aided design); Integer programming; Test Management Approach; Extension (predicate logic); Algorithm; Operations research; Reliability engineering; Programming language; Mathematics; Psychometrics; Statistics; Engineering","score_opus":0.1158456593923128,"score_gpt":0.34457860127844137,"score_spread":0.22873294188612858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001638213","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":[0.7088875,0.000191085,0.28783187,0.0011744663,0.00070433185,0.00027927133,0.0000029713437,0.00013783672,0.00079064927],"genre_scores_gemma":[0.9157251,0.000002623412,0.08390379,0.00018784196,0.00013173441,0.000008715138,0.0000047465237,0.0000043932605,0.000031067324],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99878156,0.00004251807,0.00028774748,0.00032345764,0.00035415005,0.00021057457],"domain_scores_gemma":[0.9986047,0.0006473583,0.00012608562,0.000166775,0.00037241055,0.00008262964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011588419,0.00010879796,0.00012723767,0.00007430822,0.00012118224,0.000052157786,0.00019596462,0.000057711844,0.000008745345],"category_scores_gemma":[0.00047002936,0.000087914785,0.000030444564,0.00016719574,0.000035578254,0.00008587533,0.000029333902,0.000058412108,0.0000029200564],"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":[0.00011874618,0.004706159,0.0036020735,0.00016149641,0.00010343332,0.000014123558,0.0033791163,0.00092047075,0.10624261,0.11228435,0.0030430662,0.7654244],"study_design_scores_gemma":[0.0011004936,0.00087282003,0.93266565,0.00012794638,0.000016215903,0.000036975533,0.000115014875,0.05339807,0.0057965647,0.003865038,0.0016402429,0.0003649816],"about_ca_topic_score_codex":0.000019709245,"about_ca_topic_score_gemma":0.0000064410433,"teacher_disagreement_score":0.92906356,"about_ca_system_score_codex":0.000051505893,"about_ca_system_score_gemma":0.000026075175,"threshold_uncertainty_score":0.35850608},"labels":[],"label_agreement":null},{"id":"W2004501768","doi":"10.1177/0013164402239317","title":"Differential Item Functioning Results May Change Depending On How An Item Is Scored: An Illustration With The Center For Epidemiologic Studies Depression Scale","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":97,"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; Logistic regression; Statistics; Psychometrics; Ordered logit; Scale (ratio); Clinical psychology; Center for Epidemiologic Studies Depression Scale; Persistence (discontinuity); Depressive symptoms; Mathematics; Cognition; Psychiatry","score_opus":0.8833118557082188,"score_gpt":0.5341469955629262,"score_spread":0.3491648601452926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004501768","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":[0.9712744,0.0005340384,0.010117543,0.014736181,0.0016048128,0.00071739434,0.000030372828,0.000034291108,0.0009510112],"genre_scores_gemma":[0.9908785,0.00004851168,0.0067388867,0.0012223518,0.00060591876,0.00027339472,0.000020055275,0.000008017185,0.00020434379],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99585414,0.0013445725,0.00046125043,0.00095587136,0.0010516446,0.00033249814],"domain_scores_gemma":[0.98866665,0.009783723,0.0004050175,0.00043504944,0.00054798654,0.000161582],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008030978,0.00022880733,0.00030776407,0.00016296543,0.000825972,0.000238538,0.0003107138,0.00010763405,0.00010452232],"category_scores_gemma":[0.025498893,0.000103585604,0.00007400031,0.0004474425,0.00014703957,0.00027927742,0.000027666581,0.00019956735,0.0000043815144],"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":[0.002155089,0.0022043455,0.63454056,0.000027691714,0.00013191673,0.0000014564039,0.0031052174,0.000097193915,0.0012595322,0.005647318,0.02736664,0.32346302],"study_design_scores_gemma":[0.0010655873,0.0017170797,0.9748963,0.00008042205,0.000023736287,0.00002320208,0.0038548526,0.00022881872,0.00016390903,0.010978049,0.0067367572,0.00023127272],"about_ca_topic_score_codex":0.0000050451154,"about_ca_topic_score_gemma":0.000021116064,"teacher_disagreement_score":0.34035575,"about_ca_system_score_codex":0.000059998394,"about_ca_system_score_gemma":0.000018946977,"threshold_uncertainty_score":0.98270977},"labels":[],"label_agreement":null},{"id":"W2004549974","doi":"10.1177/0013164403258402","title":"The Effect of Multicollinearity on Multilevel Modeling Parameter Estimates and Standard Errors","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":127,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Multicollinearity; Statistics; Mathematics; Multilevel model; Standard error; Covariance; Variance inflation factor; Variance (accounting); Econometrics; Correlation; Standard deviation; Linear regression","score_opus":0.35109228647864826,"score_gpt":0.4841609772101677,"score_spread":0.13306869073151945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004549974","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":[0.5887622,0.0004608,0.4088562,0.00067202264,0.00020827107,0.0004461893,0.000018000183,0.0000119041,0.0005643793],"genre_scores_gemma":[0.7759584,0.000021163762,0.22389396,0.000037477865,0.000015416505,0.000052296265,4.9711355e-7,0.0000050052554,0.00001578531],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887824,0.00021900774,0.00023309427,0.00022044739,0.00030550238,0.00014368528],"domain_scores_gemma":[0.9951861,0.0044382345,0.000059685033,0.00012574822,0.00010679788,0.00008345979],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013512007,0.00012307349,0.0001911157,0.000015001545,0.00016565641,0.00001701284,0.000047739366,0.000047068555,0.000021173899],"category_scores_gemma":[0.009470133,0.00006421127,0.000031123338,0.000029699626,0.00011754864,0.000018483655,0.000009534802,0.00012283272,7.1515933e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013259894,0.0010405631,0.0037171887,0.00025905488,0.00013619727,0.0000012973932,0.00042936415,0.0009919452,0.0012914573,0.8400839,0.0004554935,0.15026759],"study_design_scores_gemma":[0.0008147741,0.0010214094,0.0031791432,0.000061233535,0.000044927645,0.000004790433,0.000030620165,0.013028418,0.0009046028,0.9805874,0.00018917462,0.00013345717],"about_ca_topic_score_codex":0.0000017522647,"about_ca_topic_score_gemma":0.000001032009,"teacher_disagreement_score":0.18719618,"about_ca_system_score_codex":0.000019153294,"about_ca_system_score_gemma":0.000011313874,"threshold_uncertainty_score":0.99887353},"labels":[],"label_agreement":null},{"id":"W2009687691","doi":"10.1177/0013164403251283","title":"The Effects of Nonnormality on Parametric, Nonparametric, and Model Comparison Approaches to Pairwise Comparisons","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"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 Manitoba; York University","funders":"","keywords":"Type I and type II errors; Statistics; Nonparametric statistics; Statistic; Pairwise comparison; Econometrics; Mathematics; Normality; F-test of equality of variances; Parametric statistics; Levene's test; Sample size determination; Statistical hypothesis testing; Test statistic; Nominal level; Homogeneity (statistics); Confidence interval","score_opus":0.8627862254850819,"score_gpt":0.551136597639037,"score_spread":0.3116496278460449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009687691","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":[0.7011124,0.0019223839,0.2688137,0.009639605,0.0018537765,0.0032744976,0.000038668077,0.00005986322,0.01328513],"genre_scores_gemma":[0.6973537,0.0000351157,0.30216214,0.00021783379,0.0000429869,0.00013764182,3.3754802e-7,0.0000067997566,0.000043439937],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99681467,0.0010445876,0.0007265607,0.00042946998,0.0007259256,0.00025881708],"domain_scores_gemma":[0.9568767,0.04215392,0.00021950497,0.00034645642,0.00014337857,0.00026005547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004981774,0.00019405365,0.0004954055,0.00007839879,0.00019554101,0.000041978456,0.00017499317,0.000113097274,0.000022280208],"category_scores_gemma":[0.09427074,0.00011648184,0.000072293034,0.00037189326,0.0002521715,0.00001821822,0.000036898626,0.00027391597,0.00000737185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037638954,0.0047213132,0.008995165,0.00018655171,0.00010302754,3.3005153e-7,0.0001704752,0.00006933026,0.00007669595,0.9510098,0.01366292,0.020627977],"study_design_scores_gemma":[0.00077781203,0.0010048767,0.08364867,0.00007466653,0.00007177801,0.0000022593774,0.0000684234,0.0007818618,0.00048039985,0.91211563,0.00076238223,0.00021122066],"about_ca_topic_score_codex":0.0000026583273,"about_ca_topic_score_gemma":0.0000016618833,"teacher_disagreement_score":0.08928897,"about_ca_system_score_codex":0.00004663492,"about_ca_system_score_gemma":0.000036539208,"threshold_uncertainty_score":0.91335857},"labels":[],"label_agreement":null},{"id":"W2012610170","doi":"10.1177/0013164403260196","title":"The Analysis of Repeated Measurements with Mixed-Model Adjusted F Tests","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":130,"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 Manitoba","funders":"","keywords":"Type I and type II errors; Statistics; Repeated measures design; Sample size determination; Mixed model; Mathematics; Covariance; Univariate; Statistic; Homogeneity (statistics); Normality; Analysis of covariance; Heteroscedasticity; Statistical hypothesis testing; Econometrics; Multivariate statistics","score_opus":0.7953401039095214,"score_gpt":0.5668979603801602,"score_spread":0.2284421435293612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012610170","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":[0.8722825,0.00059951196,0.102247775,0.014646209,0.0008878165,0.0014659069,0.000080411846,0.000096141404,0.007693723],"genre_scores_gemma":[0.78469133,0.000023356508,0.2149148,0.0001581434,0.000057763755,0.0000819658,0.0000025411682,0.000008914207,0.00006116806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99712276,0.0003703196,0.00073959486,0.00040242038,0.0011345453,0.00023033816],"domain_scores_gemma":[0.99373406,0.0046805665,0.00031290913,0.0004221959,0.00069747324,0.00015281801],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0040491903,0.00017497882,0.00044014197,0.00007998074,0.00017035959,0.00002774597,0.00023016983,0.00009344631,0.000093749266],"category_scores_gemma":[0.019971477,0.0000918418,0.0001195846,0.0006472842,0.00030284785,0.000025559946,0.000027833277,0.00017113479,0.000004125243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029213,0.014703297,0.048151195,0.00020887467,0.010538243,0.0000056107224,0.00083972455,0.0029397926,0.0074993656,0.84501535,0.0070757126,0.060101517],"study_design_scores_gemma":[0.0009784771,0.0002980796,0.28070447,0.00006532309,0.00087934587,0.0000026139899,0.00003933883,0.000061725674,0.00030049466,0.7164808,0.000041757095,0.0001475836],"about_ca_topic_score_codex":0.000009111795,"about_ca_topic_score_gemma":0.00005498344,"teacher_disagreement_score":0.23255327,"about_ca_system_score_codex":0.00008847867,"about_ca_system_score_gemma":0.00009708048,"threshold_uncertainty_score":0.9882837},"labels":[],"label_agreement":null},{"id":"W2014421030","doi":"10.1177/00131640021970970","title":"Structural Equation Models and the Regression Bias for Measuring Correlates of Change","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Manitoba","funders":"","keywords":"Structural equation modeling; Skewness; Analysis of covariance; Regression analysis; Regression; Statistics; Psychology; Linear regression; Econometrics; Regression toward the mean; Covariance; Mathematics","score_opus":0.9410559504515326,"score_gpt":0.523874003364629,"score_spread":0.4171819470869036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014421030","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":[0.98354477,0.004270598,0.0025757097,0.0064765387,0.0005218126,0.0004954164,0.0000060355433,0.000009898579,0.0020992432],"genre_scores_gemma":[0.99453866,0.00017989546,0.004705471,0.00020485745,0.00014405018,0.00008938443,0.0000017741518,0.0000030232209,0.000132882],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978947,0.00035241735,0.0004349313,0.00033000464,0.000851439,0.0001364877],"domain_scores_gemma":[0.99248993,0.0067143,0.00020931131,0.00018910815,0.0003355541,0.00006179332],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00713073,0.00010110487,0.00021226054,0.00008780471,0.00022180106,0.000061830804,0.00020892246,0.000056888573,0.00029386787],"category_scores_gemma":[0.012463895,0.000045707373,0.000059975566,0.0003169197,0.00018793205,0.00012290414,0.000023471232,0.00008117962,0.0000024588298],"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":[0.00058455416,0.00009645323,0.037963055,0.000011835276,0.000020806792,7.384963e-8,0.0012143386,0.00015450243,0.000085499574,0.025573691,0.0006474599,0.93364775],"study_design_scores_gemma":[0.0008185556,0.00011532497,0.4363746,0.00003717657,0.000010686476,0.000007799115,0.0001739329,0.0072649983,0.000015277416,0.55471563,0.0003920105,0.000073979376],"about_ca_topic_score_codex":0.00001904707,"about_ca_topic_score_gemma":0.0000012811456,"teacher_disagreement_score":0.9335737,"about_ca_system_score_codex":0.000013031611,"about_ca_system_score_gemma":0.000012357713,"threshold_uncertainty_score":0.99585456},"labels":[],"label_agreement":null},{"id":"W2016558976","doi":"10.1177/0013164402062004013","title":"Stability of the Reliability of LibQual+™ Scores a Reliability Generalization Meta-Analysis Study","year":2002,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":45,"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":"Generalization; Reliability (semiconductor); Meta-analysis; Psychology; Statistics; Scale (ratio); Mathematics; Medicine; Geography","score_opus":0.43370644915744266,"score_gpt":0.43993877657209346,"score_spread":0.006232327414650796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016558976","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":[0.9874513,0.0010104784,0.000094980416,0.0058845864,0.000587856,0.0010356694,0.000088238965,0.000013339108,0.0038335184],"genre_scores_gemma":[0.9989361,0.0000027450303,0.00020645758,0.00015026577,0.000029907154,0.00031515563,0.000005490655,0.00000558545,0.00034826406],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964108,0.001089398,0.0010197947,0.0005567564,0.0007422581,0.00018097761],"domain_scores_gemma":[0.99786866,0.0002509938,0.00039356048,0.00086923107,0.000516929,0.00010061545],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022017236,0.00016385203,0.00054005795,0.00007677715,0.00010218516,0.000012534382,0.00028149664,0.00007287463,0.008617758],"category_scores_gemma":[0.00058893673,0.000097063756,0.00063247926,0.0007456363,0.00032148912,0.000069208276,0.00006208979,0.00013662006,0.000015544083],"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":[0.00022984884,0.063314036,0.90271956,0.0001626098,0.012707943,2.5729213e-7,0.003478438,0.00008963816,0.000120315584,0.01198088,0.0034613954,0.0017350827],"study_design_scores_gemma":[0.00030021957,0.0007704425,0.983462,0.000005026858,0.0063721775,0.0000010223359,0.00024642312,0.000013085351,0.00012416142,0.008482116,0.00012580838,0.00009753046],"about_ca_topic_score_codex":0.00023600803,"about_ca_topic_score_gemma":0.00008507298,"teacher_disagreement_score":0.08074243,"about_ca_system_score_codex":0.00008059701,"about_ca_system_score_gemma":0.000017002589,"threshold_uncertainty_score":0.99228853},"labels":[],"label_agreement":null},{"id":"W2019602618","doi":"10.1177/0013164404267277","title":"Validity Studies Psychometric Properties of Scores on the French and Korean Versions of the Hexaco Personality Inventory","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Personality Traits and Psychology","field":"Psychology","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":"Université du Québec à Montréal; Brock University; University of Calgary; Concordia University","funders":"Agence Nationale de la Recherche","keywords":"Psychology; Personality; Internal consistency; Psychometrics; Personality Assessment Inventory; California Psychological Inventory; Personality test; Big Five personality traits; Scale (ratio); Test validity; Social psychology; Clinical psychology","score_opus":0.47261731157670445,"score_gpt":0.3908928201723001,"score_spread":0.08172449140440435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019602618","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":[0.9630446,0.0050782547,0.0000040529176,0.026104687,0.0010706881,0.0003262729,0.000027196777,0.0000077557615,0.0043365145],"genre_scores_gemma":[0.9977415,0.00015573938,0.0000405993,0.00166724,0.00013340282,0.000072075425,0.000001430744,0.0000059231775,0.00018206338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99808365,0.00043117264,0.00035065424,0.00039027657,0.0005417259,0.00020250688],"domain_scores_gemma":[0.9989244,0.00021769127,0.00019002213,0.00034775425,0.0002393871,0.000080762795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012630544,0.00017770064,0.0002582366,0.00008457927,0.00024080672,0.000009953235,0.00027578018,0.00009679774,0.00032454985],"category_scores_gemma":[0.00042351367,0.00008557979,0.0001122854,0.00034281504,0.0011402036,0.000027178208,0.000044018416,0.00025188344,0.000008426831],"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":[0.00073470967,0.010793617,0.6704273,0.00027454534,0.0010020207,0.0000011534102,0.026000906,0.000007040623,0.006559938,0.23857173,0.04073629,0.0048906924],"study_design_scores_gemma":[0.000626752,0.0004830228,0.9812106,0.00013329204,0.000040778792,0.0000133844505,0.0011619107,1.3461157e-7,0.00018470034,0.015147558,0.0008916423,0.00010625089],"about_ca_topic_score_codex":0.0002166226,"about_ca_topic_score_gemma":0.000043818538,"teacher_disagreement_score":0.31078324,"about_ca_system_score_codex":0.000051107574,"about_ca_system_score_gemma":0.000050201354,"threshold_uncertainty_score":0.42011273},"labels":[],"label_agreement":null},{"id":"W2019613650","doi":"10.1177/0013164411410878","title":"A Demonstration of the Impact of Outliers on the Decisions About the Number of Factors in Exploratory Factor Analysis","year":2011,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Outlier; Econometrics; Exploratory factor analysis; Statistics; Exploratory research; Exploratory analysis; Computer science; Psychology; Mathematics; Psychometrics; Data science","score_opus":0.599656771734609,"score_gpt":0.500432737447792,"score_spread":0.09922403428681692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019613650","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":[0.9694299,0.000029984818,0.02834614,0.0002317446,0.00006196437,0.00022554939,0.000044595436,0.0000016527514,0.0016284757],"genre_scores_gemma":[0.9936748,0.000012841904,0.0062371646,0.000025092577,0.000009052333,0.000026137554,7.543042e-7,0.0000030855838,0.000011069665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987496,0.00030705382,0.00036713004,0.00013014866,0.00035827272,0.000087771885],"domain_scores_gemma":[0.9977644,0.0015587145,0.0002211167,0.00025140395,0.00016831461,0.000036069763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070702983,0.00009188548,0.00019781505,0.000035142726,0.000046237394,0.000002991664,0.00016177908,0.000041697767,0.00032299847],"category_scores_gemma":[0.0015706412,0.00003348415,0.00015555268,0.00027726512,0.00019993856,0.00002219524,0.000015597105,0.0001165633,5.0374206e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024844604,0.0037177738,0.39695323,0.000019894058,0.0006306828,1.2873672e-7,0.010095717,0.0001135791,0.0025110235,0.57819664,0.0004335711,0.007079305],"study_design_scores_gemma":[0.00007649206,0.000062545114,0.7045191,0.000025140387,0.000046169418,1.9248318e-7,0.00043663062,0.000017069482,0.0003253007,0.294456,0.0000020667255,0.000033269942],"about_ca_topic_score_codex":0.00003139015,"about_ca_topic_score_gemma":0.000015726559,"teacher_disagreement_score":0.30756587,"about_ca_system_score_codex":0.000028313812,"about_ca_system_score_gemma":0.000042935917,"threshold_uncertainty_score":0.35366067},"labels":[],"label_agreement":null},{"id":"W2021178079","doi":"10.1177/0013164403261762","title":"The Nature and Measurement of Emotional Intelligence Abilities: Basic Dimensions and Their Relationships with Other Cognitive Ability and Personality Variables","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Emotional Intelligence and Performance","field":"Psychology","cited_by":106,"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":"Psychology; Personality; Alexithymia; Cognition; Emotional intelligence; Developmental psychology; Big Five personality traits; Construct (python library); Congruence (geometry); Social psychology; Cognitive psychology","score_opus":0.17145077923785593,"score_gpt":0.3521081209423749,"score_spread":0.180657341704519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021178079","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":[0.97834265,0.008677285,0.0022990028,0.007816241,0.0002067232,0.00043904452,0.000048200185,0.000012011035,0.0021588225],"genre_scores_gemma":[0.9985446,0.00028188157,0.00043150195,0.0004901984,0.00009457038,0.000090229245,0.000005876633,0.0000069065445,0.00005423296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99824333,0.0003360191,0.00031095068,0.00046862266,0.00044545662,0.0001956215],"domain_scores_gemma":[0.9979781,0.0010346306,0.00011187058,0.0001649116,0.00058304524,0.00012746565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002901918,0.00019283204,0.0001706207,0.000039364975,0.0005140873,0.00003562454,0.0000794648,0.00014361831,0.00021901126],"category_scores_gemma":[0.00056810287,0.0001091753,0.00002971789,0.00012766985,0.0009788392,0.00008266404,0.000025944388,0.00041066343,0.000003793261],"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":[0.0009796688,0.0024745765,0.40875298,0.0001752127,0.0004658292,6.830592e-7,0.0119417,0.000030438516,0.0005768703,0.5532584,0.00031587656,0.021027738],"study_design_scores_gemma":[0.00026736417,0.00040227233,0.8617002,0.00019813165,0.000023585057,0.000045188248,0.0042029815,0.000007736011,0.000068238114,0.13245092,0.000488391,0.00014504131],"about_ca_topic_score_codex":0.000074134776,"about_ca_topic_score_gemma":0.00012957552,"teacher_disagreement_score":0.45294717,"about_ca_system_score_codex":0.000056203495,"about_ca_system_score_gemma":0.000082761966,"threshold_uncertainty_score":0.44520396},"labels":[],"label_agreement":null},{"id":"W2021930444","doi":"10.1177/0013164409355698","title":"The Motivation at Work Scale: Validation Evidence in Two Languages","year":2010,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Motivation and Self-Concept in Sports","field":"Psychology","cited_by":749,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Université du Québec à Montréal; Université de Montréal; Concordia University","funders":"","keywords":"Conceptualization; Scale (ratio); Psychology; Work (physics); Intrinsic motivation; Social psychology; Work motivation; Cognitive psychology; Computer science; Artificial intelligence; Geography; Physics","score_opus":0.1709997786686356,"score_gpt":0.4045055228999631,"score_spread":0.2335057442313275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021930444","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":[0.96802557,0.00059315807,0.000032968852,0.014665859,0.001725342,0.0002884639,0.0000011753235,0.000024239536,0.0146432305],"genre_scores_gemma":[0.99561244,0.000046753863,0.00022493358,0.0006717569,0.0003799003,0.00018490638,0.000012608041,0.0000064587953,0.0028602628],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985622,0.0001779891,0.00030253915,0.00035198548,0.00040166592,0.00020359087],"domain_scores_gemma":[0.9988819,0.0005223242,0.00011069831,0.00026398385,0.0001373845,0.00008373949],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014217068,0.00011820869,0.000095246,0.000050323037,0.00018010844,0.000047002664,0.0001536707,0.000082027735,0.0033701267],"category_scores_gemma":[0.00057233055,0.00007785864,0.000031470638,0.00024069501,0.00013470795,0.00007232493,0.000022339747,0.00029255348,0.00015834448],"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":[0.00010147887,0.00037593103,0.9524471,0.000002957899,0.000009074799,8.2499463e-7,0.0013162023,0.000002617651,0.0010201491,0.009895257,0.013113309,0.021715103],"study_design_scores_gemma":[0.0002906848,0.000036119753,0.9847191,0.00003099235,0.0000040619375,0.000009517995,0.00033636327,4.0908836e-7,0.00004820761,0.0019665032,0.0124582285,0.000099804674],"about_ca_topic_score_codex":0.000038563787,"about_ca_topic_score_gemma":0.00017945349,"teacher_disagreement_score":0.03227201,"about_ca_system_score_codex":0.000059816288,"about_ca_system_score_gemma":0.000018671622,"threshold_uncertainty_score":0.99754095},"labels":[],"label_agreement":null},{"id":"W2026285281","doi":"10.1177/0013164412448652","title":"Linking Cut-Scores Given Changes in the Decision-Making Process, Administration Time, and Proportions of Item Types Between Successive Administrations of a Test for a Large-Scale Assessment Program","year":2012,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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 Alberta","funders":"","keywords":"Test (biology); Process (computing); Scale (ratio); Psychology; Equating; Test score; Psychometrics; Computer science; Applied psychology; Statistics; Standardized test; Clinical psychology; Mathematics education; Mathematics; Developmental psychology","score_opus":0.4302050027001809,"score_gpt":0.5329682362061104,"score_spread":0.10276323350592953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026285281","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":[0.984461,0.00065039936,0.006269514,0.0051394408,0.00019235836,0.0014929585,0.00028157467,0.000014849297,0.0014979095],"genre_scores_gemma":[0.95313853,0.000010028095,0.046211574,0.000049973714,0.00016910059,0.00037610673,0.00002869573,0.0000036096394,0.000012357426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977934,0.00020814849,0.0006247197,0.00030096262,0.00086473074,0.00020806515],"domain_scores_gemma":[0.9791998,0.019502727,0.00051422627,0.00017858563,0.00053938373,0.000065240114],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0056571667,0.00011338738,0.00025125785,0.00018348395,0.00017893134,0.00007223349,0.00025349433,0.00007389515,0.00013530662],"category_scores_gemma":[0.025155237,0.00006552611,0.000044551918,0.0007345604,0.000109016786,0.0001243206,0.000029570901,0.000113198155,7.821893e-7],"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":[0.000041008465,0.0018917772,0.834395,0.00004127644,0.000015713424,1.4484549e-7,0.0009566533,0.0000024100298,0.00012770412,0.0011289711,0.0004911184,0.16090822],"study_design_scores_gemma":[0.00019595106,0.0008120564,0.96247035,0.00015904554,0.000024632773,0.000006001675,0.0009741313,0.00012709905,0.000061043276,0.034384508,0.0007006237,0.00008458436],"about_ca_topic_score_codex":0.0000012132095,"about_ca_topic_score_gemma":0.00003806011,"teacher_disagreement_score":0.16082363,"about_ca_system_score_codex":0.00001673814,"about_ca_system_score_gemma":0.00012497063,"threshold_uncertainty_score":0.9830563},"labels":[],"label_agreement":null},{"id":"W2026405046","doi":"10.1177/0013164404268675","title":"Effect Sizes and their Intervals: The Two-Level Repeated Measures Case","year":2005,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":45,"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 Manitoba","funders":"","keywords":"Statistics; Mathematics; Confidence interval; Estimator; Sample size determination; Variance (accounting); Coverage probability; Population; Econometrics; Demography","score_opus":0.7635696793982186,"score_gpt":0.5823470726920558,"score_spread":0.18122260670616286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026405046","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":[0.9256414,0.0025128247,0.021136852,0.040997174,0.0014839127,0.0016638513,0.0000829389,0.00012341862,0.006357629],"genre_scores_gemma":[0.9143822,0.000047929825,0.08349995,0.0010084955,0.00075727026,0.00015587355,7.6556586e-7,0.000013065066,0.00013442128],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99650425,0.0018370539,0.0005730296,0.00044909134,0.00040603004,0.00023053485],"domain_scores_gemma":[0.97552556,0.023634866,0.00014428042,0.0003198123,0.00020458446,0.00017089813],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009215028,0.0002309397,0.00037529823,0.000030120258,0.0002311203,0.00007041399,0.00016591416,0.000098117736,0.00044519745],"category_scores_gemma":[0.042521466,0.00011111319,0.00008988933,0.00010307269,0.0003096977,0.000038384176,0.00006129594,0.00029826292,0.000019209192],"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":[0.0004990446,0.0014405194,0.0010901979,0.00009404421,0.00026442343,0.000018727886,0.00093001145,0.000001460859,0.0013680826,0.06585635,0.011805338,0.9166318],"study_design_scores_gemma":[0.0019002794,0.0009764268,0.014591875,0.00014486167,0.0001341725,0.0009421635,0.00018458204,0.000063118474,0.0011221208,0.97500366,0.0045872717,0.00034945933],"about_ca_topic_score_codex":0.000010618051,"about_ca_topic_score_gemma":0.000020457997,"teacher_disagreement_score":0.91628236,"about_ca_system_score_codex":0.000046801357,"about_ca_system_score_gemma":0.00002138285,"threshold_uncertainty_score":0.9655438},"labels":[],"label_agreement":null},{"id":"W2027051144","doi":"10.1177/00131640021970655","title":"Development and Validation of Scores on a Two-Dimensional Workplace Friendship Scale","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Job Satisfaction and Organizational Behavior","field":"Business, Management and Accounting","cited_by":343,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Friendship; Nomological network; Psychology; Scale (ratio); Discriminant validity; Construct validity; Sample (material); Convergent validity; Predictive validity; Construct (python library); Social psychology; Test validity; Likert scale; External validity; Internal consistency; Replicate; Applied psychology; Psychometrics; Developmental psychology; Statistics; Mathematics; Computer science","score_opus":0.07775349235747162,"score_gpt":0.2954924167858354,"score_spread":0.21773892442836376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027051144","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":[0.99043226,0.00009543337,0.0000072249745,0.00238137,0.00017415266,0.00013367952,0.0000011962712,0.000019005685,0.0067556924],"genre_scores_gemma":[0.9971359,0.0000035035637,0.001122502,0.0012335825,0.0002440958,0.000023228293,0.000027602418,0.000006565314,0.00020307141],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989784,0.000013246866,0.00021793619,0.0002437161,0.00043995745,0.00010674814],"domain_scores_gemma":[0.9996502,0.0000324154,0.0000653341,0.00007081317,0.00015596209,0.000025302461],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002914167,0.00011022573,0.00010117408,0.00008261441,0.00014920138,0.00005101334,0.000051174895,0.000037803362,0.0035811367],"category_scores_gemma":[0.000042312917,0.00008767795,0.000017736016,0.0001680071,0.000054919463,0.00014249404,0.000014891295,0.00006830239,0.00015849741],"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":[0.0004474447,0.0020443422,0.84625095,0.00006397888,0.000040857158,0.0000011181114,0.00028140025,0.0002337617,0.0032928407,0.0509956,0.0051272246,0.0912205],"study_design_scores_gemma":[0.00050429965,0.000021916296,0.9862564,0.000049975337,0.000013588499,0.0000036598924,0.000030954507,0.00000749371,0.00057966734,0.0029113798,0.009492592,0.0001280629],"about_ca_topic_score_codex":0.00001373416,"about_ca_topic_score_gemma":0.000008552095,"teacher_disagreement_score":0.14000547,"about_ca_system_score_codex":0.000024876561,"about_ca_system_score_gemma":0.00002157058,"threshold_uncertainty_score":0.9973297},"labels":[],"label_agreement":null},{"id":"W2033678552","doi":"10.1177/0013164409344548","title":"The Impact of Outliers on Cronbach’s Coefficient Alpha Estimate of Reliability: Ordinal/Rating Scale Item Responses","year":2009,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":96,"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":"Cronbach's alpha; Outlier; Categorical variable; Ordinal data; Statistics; Likert scale; Mathematics; Econometrics; Reliability (semiconductor); Sample (material); Rating scale; Psychology; Psychometrics","score_opus":0.28035999649463217,"score_gpt":0.5147372816258765,"score_spread":0.23437728513124434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033678552","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":[0.9291537,0.00024743975,0.06422069,0.0031097492,0.00015369552,0.00039854617,0.00003493697,0.000015539988,0.0026657353],"genre_scores_gemma":[0.92007154,0.000017943757,0.07970042,0.000057680158,0.000035685087,0.000018220308,0.0000012216975,0.0000049040987,0.00009240677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984006,0.0002535229,0.0004457395,0.00025178163,0.0004595848,0.00018872532],"domain_scores_gemma":[0.9967936,0.0023560224,0.0001993764,0.00024831895,0.0003024874,0.00010015321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018613843,0.00013564467,0.00023868917,0.00003129429,0.00015200088,0.000014189702,0.00011810762,0.000047663474,0.00004545667],"category_scores_gemma":[0.005239347,0.000072575094,0.00009197636,0.000103415136,0.00019319168,0.000022761751,0.000012906614,0.00012530842,0.0000012944066],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054108053,0.013602079,0.008583158,0.00021338376,0.00017434426,0.000002326962,0.0020581349,0.002530069,0.02141706,0.58646804,0.010357323,0.34918326],"study_design_scores_gemma":[0.00040552884,0.002408241,0.23463392,0.00012199879,0.000026808999,0.000005432453,0.0001252846,0.0006029804,0.00059686066,0.7608211,0.000113060625,0.0001388108],"about_ca_topic_score_codex":0.000005282257,"about_ca_topic_score_gemma":8.142163e-7,"teacher_disagreement_score":0.34904447,"about_ca_system_score_codex":0.00007259304,"about_ca_system_score_gemma":0.000055208468,"threshold_uncertainty_score":0.6272366},"labels":[],"label_agreement":null},{"id":"W2036299295","doi":"10.1177/0013164405275668","title":"A Comparison of Four Methods for Detecting Differential Item Functioning in Ordered Response Items","year":2005,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Ottawa","funders":"","keywords":"Differential item functioning; Statistics; Psychology; Logistic regression; Item response theory; Type I and type II errors; Linear discriminant analysis; Ordinal regression; Skewness; Ordered logit; Discriminant function analysis; Sample (material); Psychometrics; Mathematics","score_opus":0.8267139799800711,"score_gpt":0.6035828191741548,"score_spread":0.22313116080591633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036299295","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":[0.79982466,0.0007578594,0.19470464,0.003047766,0.00087551516,0.0002670674,0.0000022898992,0.000012888537,0.0005073022],"genre_scores_gemma":[0.8085319,0.0000038056967,0.19099265,0.00008508631,0.00020259163,0.00007145528,7.896008e-7,0.000004391317,0.00010732286],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961089,0.0014275819,0.0009758526,0.00051506417,0.00072661426,0.00024596782],"domain_scores_gemma":[0.9650272,0.033789244,0.00039460324,0.0002350469,0.00045923603,0.0000946554],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01660389,0.000134141,0.0003899913,0.00040209419,0.00016388817,0.00007330627,0.00027669274,0.00009501773,0.000329475],"category_scores_gemma":[0.12302102,0.00009296528,0.00009579861,0.0008843424,0.000066718625,0.000078088735,0.000044280816,0.00017240389,0.0000041914495],"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":[0.0010676607,0.0006333358,0.16812888,0.000008109153,0.000017177272,7.877512e-8,0.0005126914,0.00013147808,0.022228692,0.0003845797,0.0007858325,0.8061015],"study_design_scores_gemma":[0.0008067818,0.00043401364,0.9704582,0.00003370296,0.0000084496005,0.000006885484,0.0007167471,0.002786707,0.00076298544,0.017140092,0.0067100893,0.00013536148],"about_ca_topic_score_codex":0.000008133952,"about_ca_topic_score_gemma":0.000010284618,"teacher_disagreement_score":0.80596614,"about_ca_system_score_codex":0.000066179186,"about_ca_system_score_gemma":0.000042885666,"threshold_uncertainty_score":0.88436615},"labels":[],"label_agreement":null},{"id":"W2036831393","doi":"10.1177/0013164411409929","title":"Difference Scores From the Point of View of Reliability and Repeated-Measures ANOVA","year":2011,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":167,"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; Carleton University","funders":"","keywords":"Reliability (semiconductor); Repeated measures design; Significant difference; Statistics; Psychology; Analysis of variance; Point (geometry); Mean difference; Mathematics; Econometrics; Confidence interval","score_opus":0.7554307011056853,"score_gpt":0.4653795213841227,"score_spread":0.29005117972156264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036831393","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":[0.98860765,0.0039974255,0.0012197683,0.0020714342,0.00040152454,0.000173817,0.000015468398,0.0000072714724,0.0035056574],"genre_scores_gemma":[0.99063116,0.00020932732,0.008859892,0.0002046245,0.000051857536,0.000013131721,8.0293455e-7,0.0000022499346,0.000026950762],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99710447,0.0006320529,0.00067854876,0.00045584215,0.0010029314,0.00012615735],"domain_scores_gemma":[0.99117297,0.0072896974,0.00034830376,0.00049262715,0.0006169453,0.00007945801],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070734816,0.00011133879,0.00028862836,0.000064427,0.00008802751,0.000022873754,0.00042112538,0.000057226753,0.000528036],"category_scores_gemma":[0.038842898,0.000052500855,0.00005942115,0.0004552616,0.0004226591,0.00004238106,0.00008314939,0.00011773344,0.0000028071436],"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":[0.000113094444,0.00047318308,0.8170224,0.000008307061,0.000021197777,1.8183279e-7,0.00078176934,5.0417697e-7,0.0019455802,0.0028460885,0.001250037,0.17553766],"study_design_scores_gemma":[0.00012203341,0.00015764173,0.7876037,0.000037415575,0.000008047821,0.0000026728283,0.00021966433,0.0000029281157,0.00027450657,0.21125218,0.0002680671,0.000051180283],"about_ca_topic_score_codex":0.00025032106,"about_ca_topic_score_gemma":0.00001019118,"teacher_disagreement_score":0.2084061,"about_ca_system_score_codex":0.000009741277,"about_ca_system_score_gemma":0.000032058808,"threshold_uncertainty_score":0.96925336},"labels":[],"label_agreement":null},{"id":"W2037678252","doi":"10.1177/00131640021970998","title":"Testing Repeated Measures Hypotheses When Covariance Matrices are Heterogeneous: Revisiting the Robustness of the Welch-James Test Again","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":42,"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 Manitoba","funders":"","keywords":"Statistics; Bootstrapping (finance); Estimator; Mathematics; Covariance; Robustness (evolution); Type I and type II errors; Sample size determination; Repeated measures design; Covariance matrix; Statistical hypothesis testing; Analysis of covariance; Econometrics","score_opus":0.350129595397415,"score_gpt":0.40376489889502787,"score_spread":0.05363530349761286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037678252","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":[0.76861435,0.01114655,0.15420875,0.048556123,0.0010519677,0.0028524264,0.00021037606,0.00020804406,0.013151424],"genre_scores_gemma":[0.8393068,0.000082646664,0.15934406,0.00044491328,0.000429121,0.000091912465,0.0000010033656,0.000016351138,0.0002832187],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980108,0.0003966494,0.0004580317,0.0003430554,0.00057172606,0.00021971036],"domain_scores_gemma":[0.9957351,0.0032366312,0.00028153593,0.00033711462,0.00034086138,0.000068764646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014312649,0.00017823058,0.00025016555,0.00001762849,0.00033423872,0.00004224678,0.00028661624,0.00006098898,0.00028576195],"category_scores_gemma":[0.0082318615,0.00008961707,0.0000682247,0.00018179523,0.00020239591,0.000042970976,0.00003142161,0.0001848818,0.0000027480314],"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":[0.00028686813,0.0024007333,0.016892381,0.0006359305,0.00026380055,0.000006850803,0.0014412105,0.006287569,0.0072754147,0.035167366,0.0059290957,0.9234128],"study_design_scores_gemma":[0.0006527101,0.00023504207,0.13479243,0.0014855014,0.00017245104,0.00012641473,0.0004099645,0.0013266227,0.0006565979,0.8536454,0.005946451,0.0005504214],"about_ca_topic_score_codex":0.0000093355675,"about_ca_topic_score_gemma":0.0000027985911,"teacher_disagreement_score":0.92286235,"about_ca_system_score_codex":0.000035520883,"about_ca_system_score_gemma":0.00003292793,"threshold_uncertainty_score":0.9854902},"labels":[],"label_agreement":null},{"id":"W2042963988","doi":"10.1177/0013164406292038","title":"The Telephone Interview Probe","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Attention Deficit Hyperactivity Disorder","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Toronto; Dalhousie University","funders":"","keywords":"Generalizability theory; Psychology; Impulsivity; Evening; Outcome (game theory); Clinical psychology; Reliability (semiconductor); Attention deficit hyperactivity disorder; Rating scale; Psychometrics; Item response theory; Test validity; Test (biology); Developmental psychology","score_opus":0.2604149209764455,"score_gpt":0.41315371948435314,"score_spread":0.15273879850790767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042963988","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":[0.87186265,0.0052247234,0.002957494,0.09586702,0.0006936666,0.00054106186,8.6751413e-7,0.00003291546,0.022819627],"genre_scores_gemma":[0.99570364,0.00012954978,0.00057589466,0.0016819013,0.00021014857,0.000035366567,0.0000032570877,0.000004791671,0.001655447],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999068,0.000042752345,0.0001812674,0.00017790303,0.00037564538,0.00015441609],"domain_scores_gemma":[0.99942935,0.00010772209,0.000043041047,0.00013594194,0.00018317715,0.000100763864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001276769,0.00007690447,0.000089627676,0.000022813809,0.00015159958,0.000019052353,0.000048561928,0.00003966113,0.00039492254],"category_scores_gemma":[0.00025920337,0.00004235196,0.00003734332,0.000100778394,0.0000851609,0.000023776598,0.000013698422,0.00014415442,0.00010607719],"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":[0.00073327025,0.010107383,0.1293041,0.00012409607,0.00026296495,0.000010914211,0.000527827,3.8010705e-7,0.021570113,0.031207202,0.034710012,0.77144176],"study_design_scores_gemma":[0.0004691982,0.00020471372,0.8900976,0.000037600967,0.000018051265,0.000089139125,0.00028113616,7.3590235e-7,0.000035754216,0.0021187211,0.10658418,0.00006318517],"about_ca_topic_score_codex":0.0000022461259,"about_ca_topic_score_gemma":0.000007904315,"teacher_disagreement_score":0.7713786,"about_ca_system_score_codex":0.000043888518,"about_ca_system_score_gemma":0.000026651016,"threshold_uncertainty_score":0.43241248},"labels":[],"label_agreement":null},{"id":"W2045458669","doi":"10.1177/0013164409355689","title":"Construct Commensurability and the Analysis of Change","year":2009,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"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 British Columbia","funders":"University of British Columbia","keywords":"Commensurability (mathematics); Construct (python library); Construct validity; Perspective (graphical); Psychology; Epistemology; Computer science; Psychometrics; Developmental psychology; Mathematics; Artificial intelligence","score_opus":0.8713064096796247,"score_gpt":0.5426906703775654,"score_spread":0.32861573930205934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045458669","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":[0.9444911,0.002050738,0.0004554794,0.046292927,0.00028041343,0.00021557197,0.000008392341,0.0000070067117,0.006198356],"genre_scores_gemma":[0.9960361,0.00006204933,0.0023317155,0.0014802987,0.00005910245,0.000012683387,9.596286e-7,6.881467e-7,0.00001641447],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976861,0.00063541986,0.00044362634,0.00031935918,0.0008038876,0.00011159025],"domain_scores_gemma":[0.9897334,0.009370411,0.00020761971,0.00028827737,0.00032918263,0.00007112291],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010055331,0.00007949014,0.00032305773,0.00019401281,0.00012208338,0.00004805479,0.00022817051,0.000033267,0.00026048467],"category_scores_gemma":[0.022415357,0.000036683512,0.00008918479,0.0014297498,0.00040027243,0.00004091449,0.000026868125,0.00009553167,0.0000015524076],"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":[0.00011335349,0.00023816127,0.28718925,0.0000014724195,0.000095942014,1.05867706e-7,0.00036340358,0.0000017304383,0.00004686611,0.027822027,0.0010321692,0.6830955],"study_design_scores_gemma":[0.00027342016,0.00006506579,0.8152519,0.0000026881091,0.000052127634,0.0000024827202,0.000103798775,0.000053899294,0.0000020953644,0.18353467,0.00061896443,0.000038885122],"about_ca_topic_score_codex":0.000017281247,"about_ca_topic_score_gemma":0.0000031745776,"teacher_disagreement_score":0.68305665,"about_ca_system_score_codex":0.00001031129,"about_ca_system_score_gemma":0.000010005382,"threshold_uncertainty_score":0.9858193},"labels":[],"label_agreement":null},{"id":"W2046847367","doi":"10.1177/0013164414523618","title":"Binary Logistic Regression Analysis for Detecting Differential Item Functioning","year":2014,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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":"Statistics; Differential item functioning; Sample size determination; Type I and type II errors; Logistic regression; Mathematics; Statistical power; Statistical hypothesis testing; Regression analysis; Psychology; Econometrics; Item response theory; Psychometrics","score_opus":0.7639754128351917,"score_gpt":0.5122407613224709,"score_spread":0.2517346515127208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046847367","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":[0.6241598,0.00029125196,0.3697023,0.0021410126,0.0016554483,0.00017413041,0.0000036163033,0.00003370863,0.0018386743],"genre_scores_gemma":[0.9831123,0.000006904824,0.01571086,0.00022689908,0.00055914884,0.000068984795,0.0000066363295,0.00000504428,0.00030322725],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968578,0.0005254154,0.00057160394,0.0007165021,0.0010654276,0.00026323614],"domain_scores_gemma":[0.9817921,0.016881417,0.00032244824,0.00034041647,0.0005095615,0.00015403917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006831338,0.00015848206,0.0003356064,0.00046037737,0.0004966154,0.00017856807,0.000298738,0.000093054536,0.0006398659],"category_scores_gemma":[0.08741688,0.000093967996,0.00018749737,0.0013966622,0.00008093782,0.00006725208,0.000056481786,0.00014129092,0.000015442529],"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":[0.00025873067,0.0006081151,0.53628665,0.000016851023,0.00021519283,3.6550307e-7,0.00014163075,0.00043744076,0.0037880188,0.0050985976,0.0051787165,0.4479697],"study_design_scores_gemma":[0.00031645037,0.00031645776,0.9364413,0.00001710218,0.00008326254,0.000003941901,0.00013140254,0.0033820306,0.00002667797,0.05620732,0.002932264,0.0001417942],"about_ca_topic_score_codex":0.0000073226997,"about_ca_topic_score_gemma":0.0000032726625,"teacher_disagreement_score":0.4478279,"about_ca_system_score_codex":0.00004066225,"about_ca_system_score_gemma":0.000016466529,"threshold_uncertainty_score":0.9202702},"labels":[],"label_agreement":null},{"id":"W2054014836","doi":"10.1177/00131640021970411","title":"Psychometric Properties of the Nonverbal Personality Questionnaire in Korea","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Psychology; Personality; Big Five personality traits; Nonverbal communication; Reliability (semiconductor); Internal consistency; Sample (material); Psychometrics; Consistency (knowledge bases); Clinical psychology; Developmental psychology; Social psychology; Computer science; Artificial intelligence","score_opus":0.17720356351181837,"score_gpt":0.3474471441320922,"score_spread":0.17024358062027384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054014836","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":[0.9521851,0.004236278,0.0000052500163,0.015059513,0.00093489466,0.00028764323,0.000010544967,0.000013774211,0.027267026],"genre_scores_gemma":[0.996563,0.0000576415,0.00003822728,0.0018018249,0.0002138305,0.000114604314,0.0000018102616,0.000007770873,0.0012012897],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99799615,0.00034181227,0.00041424704,0.00047574186,0.00048482046,0.00028722282],"domain_scores_gemma":[0.99935335,0.000027707982,0.00008800993,0.00032236593,0.000110579305,0.00009796687],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008914013,0.0001777273,0.00022414788,0.00009575202,0.000107011074,0.000014820803,0.00029180828,0.00015010567,0.0063518467],"category_scores_gemma":[0.00008571191,0.00010904756,0.000103303435,0.00057215465,0.00039030457,0.000046106652,0.000013694913,0.00028050478,0.00008964849],"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":[0.0010101817,0.0090168,0.8070205,0.00009667768,0.00014421296,0.0000016681555,0.008512563,0.0000053505873,0.0018580119,0.02433281,0.010761898,0.13723932],"study_design_scores_gemma":[0.0007234566,0.00015017841,0.98752123,0.000108275766,0.000011383135,0.00004340273,0.00012522543,0.0000013306275,0.000013924112,0.0034319172,0.0077283685,0.00014131969],"about_ca_topic_score_codex":0.0003048015,"about_ca_topic_score_gemma":0.000073582894,"teacher_disagreement_score":0.1805007,"about_ca_system_score_codex":0.000059721533,"about_ca_system_score_gemma":0.00004381042,"threshold_uncertainty_score":0.9945565},"labels":[],"label_agreement":null},{"id":"W2054970172","doi":"10.1177/0013164407305589","title":"Population Validity and Cross-Validity","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Confidence interval; Correlation coefficient; Sample size determination; Cross-validation; Mathematics; Population; Econometrics; Demography","score_opus":0.5024942114162912,"score_gpt":0.5054909374568204,"score_spread":0.0029967260405291407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054970172","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":[0.77626336,0.000066145985,0.21782905,0.0010735462,0.00044181297,0.0001718838,0.000009867149,0.000026552285,0.0041177967],"genre_scores_gemma":[0.85047793,0.000010856717,0.14903341,0.0001799946,0.0002301787,0.000010820714,0.0000037848117,0.0000042354973,0.00004880958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987812,0.000120195415,0.0002717088,0.0002784014,0.00037008728,0.00017838654],"domain_scores_gemma":[0.9986484,0.0008616018,0.000072464565,0.00011635971,0.00014656945,0.00015462645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024041287,0.00011038141,0.00014592652,0.000030247016,0.000151841,0.00005074964,0.000056365072,0.00007941664,0.0004083675],"category_scores_gemma":[0.0021075066,0.00008118749,0.00002492988,0.00007031209,0.00010331205,0.000046361507,0.00001984708,0.00012055643,0.000007266242],"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":[0.00006837136,0.000586432,0.2610955,0.000050421946,0.000008734784,0.000001368292,0.00008738536,2.3976115e-8,0.00028890406,0.686338,0.0012610138,0.050213866],"study_design_scores_gemma":[0.00009754609,0.00007087358,0.51712096,0.000010159447,0.0000061550827,0.00000800364,0.0000064818937,0.0000027491078,0.000024587947,0.4823628,0.00022815922,0.00006153887],"about_ca_topic_score_codex":0.000015126803,"about_ca_topic_score_gemma":0.00000805636,"teacher_disagreement_score":0.25602546,"about_ca_system_score_codex":0.000039061513,"about_ca_system_score_gemma":0.000010270017,"threshold_uncertainty_score":0.44713378},"labels":[],"label_agreement":null},{"id":"W2062055237","doi":"10.1177/00131640021970871","title":"Type I Error Rate Comparisons of Post Hoc Procedures for I j Chi-Square Tables","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":444,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Post hoc; Post-hoc analysis; Statistics; Pairwise comparison; Contingency table; Type I and type II errors; Homogeneity (statistics); Mathematics; Chi-square test; Null hypothesis; Monte Carlo method; Econometrics; Medicine; Dentistry","score_opus":0.40958901005991827,"score_gpt":0.48838846708274464,"score_spread":0.07879945702282637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062055237","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":[0.7345521,0.0028141087,0.23544721,0.013017201,0.00082856265,0.0023992108,0.00051830057,0.000080812555,0.010342489],"genre_scores_gemma":[0.61939555,0.000058886988,0.3792747,0.0003376747,0.00012312783,0.000120016586,0.000021520247,0.000010235356,0.00065830856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990493,0.000074805444,0.0002718248,0.00024000838,0.00020120639,0.00016286474],"domain_scores_gemma":[0.99895245,0.00042822488,0.0000736897,0.000117498894,0.00033617418,0.00009194329],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045583857,0.00011681456,0.00021305199,0.000021786442,0.00009643747,0.000010447119,0.00008074098,0.000051838197,0.0010987595],"category_scores_gemma":[0.0010686682,0.00008209762,0.000042135583,0.00007171183,0.00008219629,0.00003058109,0.000006840056,0.000068261084,0.0000061338174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020241672,0.0050334856,0.0007187171,0.00069129904,0.00013260491,5.621497e-7,0.00069619913,0.00006690654,0.0052328175,0.8630502,0.055438846,0.06691419],"study_design_scores_gemma":[0.0007871408,0.0012326919,0.032056153,0.00013546915,0.000054617398,0.0000069084153,0.00015556566,0.000118972406,0.00021315763,0.94807935,0.016922409,0.00023756902],"about_ca_topic_score_codex":0.0000025779134,"about_ca_topic_score_gemma":0.000008488671,"teacher_disagreement_score":0.14382747,"about_ca_system_score_codex":0.000016786289,"about_ca_system_score_gemma":0.00005164885,"threshold_uncertainty_score":0.9998144},"labels":[],"label_agreement":null},{"id":"W2064379877","doi":"10.1177/0013164402238082","title":"A Monte Carlo Comparison of Item and Person Statistics Based on Item Response Theory versus Classical Test Theory","year":2002,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Western University","funders":"","keywords":"Item response theory; Classical test theory; Monte Carlo method; Statistics; Psychology; Econometrics; Psychometrics; Test theory; Item analysis; Computerized adaptive testing; Test (biology); Differential item functioning; Statistical hypothesis testing; Mathematics","score_opus":0.7790233134897627,"score_gpt":0.505780321916664,"score_spread":0.2732429915730987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064379877","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":[0.97472155,0.0023402777,0.00535482,0.007777893,0.0012348074,0.00031165083,0.00009027667,0.000029971714,0.008138726],"genre_scores_gemma":[0.9894863,0.00001688989,0.009530709,0.0003684703,0.00010583567,0.000022705572,0.0000010193328,0.000006495478,0.0004615909],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951723,0.002010999,0.00054317253,0.0005771259,0.0014644585,0.00023189303],"domain_scores_gemma":[0.88360554,0.11528914,0.00026233093,0.00032079138,0.00034243037,0.00017976965],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010272065,0.00018193231,0.00035307993,0.00025248947,0.00019138474,0.000082195045,0.0002878135,0.00010497924,0.001011047],"category_scores_gemma":[0.17204197,0.000116132425,0.000063057065,0.000536033,0.00032833585,0.000044021486,0.000029994748,0.00024532824,0.00002152588],"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":[0.011648106,0.0060344893,0.27678025,0.00003284093,0.00008277433,0.0000072319654,0.0028754384,0.00015399372,0.0011073834,0.029802186,0.06665417,0.60482115],"study_design_scores_gemma":[0.001347528,0.002614317,0.9663729,0.000048269863,0.000025793242,0.000005199957,0.002115086,0.0057995,0.00002630321,0.018397728,0.003043179,0.00020421586],"about_ca_topic_score_codex":0.0000022476133,"about_ca_topic_score_gemma":0.0000013708054,"teacher_disagreement_score":0.68959266,"about_ca_system_score_codex":0.000054217824,"about_ca_system_score_gemma":0.000031082152,"threshold_uncertainty_score":0.9999022},"labels":[],"label_agreement":null},{"id":"W2065030780","doi":"10.1177/0013164404273942","title":"Understanding Parameter Invariance in Unidimensional IRT Models","year":2006,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":108,"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; University of Ottawa","funders":"","keywords":"Item response theory; Measurement invariance; Set (abstract data type); Differential item functioning; Psychology; Feature (linguistics); Property (philosophy); Econometrics; Variable (mathematics); Psychometrics; Cognitive psychology; Mathematics; Statistics; Applied mathematics; Computer science; Structural equation modeling; Confirmatory factor analysis; Mathematical analysis; Epistemology","score_opus":0.9212118758900417,"score_gpt":0.4959208972683364,"score_spread":0.42529097862170534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065030780","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":[0.79976904,0.0016931632,0.098765925,0.019852705,0.0018748252,0.00038201854,0.000007678052,0.000040567975,0.07761406],"genre_scores_gemma":[0.9801323,0.000015525844,0.018761618,0.0006260694,0.00015933353,0.00002558546,0.0000023115597,0.0000041157737,0.00027314102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99681085,0.00039214033,0.0005797533,0.0005941061,0.0013560219,0.00026713396],"domain_scores_gemma":[0.9924677,0.006867148,0.00014866501,0.00024663727,0.00017908985,0.000090780566],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0059311786,0.00013447698,0.00021876882,0.00029262583,0.00013800473,0.000114055314,0.00027748512,0.00008454702,0.00045133737],"category_scores_gemma":[0.008997417,0.00008952127,0.00005106472,0.0009926866,0.000111996465,0.00015182824,0.00005021436,0.00017735286,0.000027085815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014719395,0.0014844704,0.25258204,0.000006598603,0.000016629438,0.000007730636,0.00014933867,0.0030568475,0.0009778753,0.6835403,0.04488128,0.013149689],"study_design_scores_gemma":[0.00021426698,0.000044350185,0.38161772,0.000013222142,0.0000014204558,0.000009310204,0.00007674439,0.00054899475,0.0000049172827,0.6166646,0.000720934,0.000083554914],"about_ca_topic_score_codex":0.00004808021,"about_ca_topic_score_gemma":0.000021318705,"teacher_disagreement_score":0.18036324,"about_ca_system_score_codex":0.0001409192,"about_ca_system_score_gemma":0.000044242188,"threshold_uncertainty_score":0.9993502},"labels":[],"label_agreement":null},{"id":"W2066219327","doi":"10.1177/0013164403063003007","title":"Is the Test Attitude Survey Psychometrically Sound?","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Employer Branding and e-HRM","field":"Business, Management and Accounting","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Toronto","funders":"","keywords":"Psychology; Test (biology); Test validity; Psychometrics; Personality; Convergent validity; Criterion validity; Personality test; Measure (data warehouse); Applied psychology; Realm; Psychological testing; Social psychology; Clinical psychology; Construct validity; Internal consistency; Computer science; Data mining","score_opus":0.2665399833300074,"score_gpt":0.3411793357157336,"score_spread":0.07463935238572622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066219327","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":[0.82103103,0.0015762512,0.0003880267,0.04155241,0.002708038,0.0005200812,0.0000105098925,0.00009940945,0.13211425],"genre_scores_gemma":[0.98758084,0.000030861647,0.0001633122,0.010923017,0.0006899091,0.000047511054,0.00000785097,0.000010551546,0.00054616545],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985226,0.00004816181,0.00024170773,0.00037142207,0.00055895007,0.0002571632],"domain_scores_gemma":[0.9989481,0.00040131147,0.00009519196,0.00023394541,0.00028941364,0.000032051026],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019290227,0.00016449217,0.00013606348,0.000106767926,0.00039006988,0.00027381635,0.00021973437,0.000063592015,0.0013732589],"category_scores_gemma":[0.002209605,0.00009900795,0.00006257262,0.00063235254,0.000100318466,0.00013834822,0.000025092602,0.00016952856,0.0005478603],"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":[0.000022309576,0.0009337277,0.84728456,0.000016763046,0.000028553137,3.081539e-7,0.000034098193,0.0000011204462,0.000043415,0.018161926,0.13223568,0.0012375348],"study_design_scores_gemma":[0.00031039212,0.000028075663,0.8860273,0.0000126349,0.00001526282,0.0000039758575,0.000026042188,0.0000024926399,0.0000024561616,0.0428229,0.070598416,0.0001500943],"about_ca_topic_score_codex":0.000080796366,"about_ca_topic_score_gemma":0.000049162052,"teacher_disagreement_score":0.16654979,"about_ca_system_score_codex":0.000029172674,"about_ca_system_score_gemma":0.000017847198,"threshold_uncertainty_score":0.9995396},"labels":[],"label_agreement":null},{"id":"W2066906964","doi":"10.1177/0013164409344520","title":"Athletes’ Perceptions of Coaching Competency Scale II-High School Teams","year":2009,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Sport Psychology and Performance","field":"Psychology","cited_by":40,"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":"Psychology; Coaching; Athletes; Confirmatory factor analysis; Applied psychology; Construct validity; Scale (ratio); Construct (python library); Exploratory factor analysis; Structural equation modeling; Clinical psychology; Psychometrics; Statistics; Physical therapy; Mathematics; Medicine","score_opus":0.060808801704178836,"score_gpt":0.3496966861001845,"score_spread":0.28888788439600566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066906964","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":[0.9297983,0.0010333306,0.0002256909,0.007180746,0.001347832,0.0002465655,0.000013796009,0.000039674356,0.060114074],"genre_scores_gemma":[0.99403155,0.000072510615,0.0017291631,0.002238658,0.00047477812,0.000057740042,0.000028143611,0.000007316208,0.0013601559],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982503,0.00014533398,0.00044226836,0.0004919781,0.0003628676,0.00030724207],"domain_scores_gemma":[0.99907005,0.000053467076,0.0001453105,0.0003592109,0.00016989232,0.00020205666],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008450949,0.0001954031,0.00025667288,0.00010541947,0.00032904738,0.000012124431,0.00023007214,0.00017962194,0.012398161],"category_scores_gemma":[0.00005278204,0.00015848625,0.000087503766,0.00019740057,0.00019775199,0.00007780943,0.000018377594,0.00035626724,0.00029594754],"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":[0.0006337305,0.012875654,0.68389994,0.0000274972,0.00017775767,0.000004491978,0.0041311225,0.000014449342,0.0114683835,0.116939545,0.05882403,0.11100342],"study_design_scores_gemma":[0.0006598158,0.0009014199,0.9803407,0.000046297446,0.000022638906,0.00004805349,0.00034123374,0.0000012169681,0.000020114607,0.014630569,0.0028023059,0.00018559725],"about_ca_topic_score_codex":0.000028774915,"about_ca_topic_score_gemma":0.000005915041,"teacher_disagreement_score":0.2964408,"about_ca_system_score_codex":0.00004256546,"about_ca_system_score_gemma":0.000046088142,"threshold_uncertainty_score":0.98850465},"labels":[],"label_agreement":null},{"id":"W2070370199","doi":"10.1177/0013164407301530","title":"Concurrent Validity of Wechsler Adult Intelligence Scales–Third Edition Index Score Short Forms in the Canadian Standardization Sample","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BC Mental Health & Substance Use Services; University of British Columbia","funders":"","keywords":"Wechsler Adult Intelligence Scale; Psychology; Short Forms; Concurrent validity; Index (typography); Wechsler Preschool and Primary Scale of Intelligence; Sample (material); Intelligence quotient; Test validity; Psychometrics; Developmental psychology; Statistics; Clinical psychology; Wechsler Intelligence Scale for Children; Cognition; Mathematics; Psychiatry; Computer science","score_opus":0.19603925661791266,"score_gpt":0.41298764835950535,"score_spread":0.2169483917415927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070370199","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":[0.95876855,0.00012349185,0.02578944,0.0058603035,0.00032966668,0.00086200045,0.0000342352,0.0000064575133,0.008225835],"genre_scores_gemma":[0.99869025,0.000057694113,0.00011983017,0.0007941437,0.00017131702,0.00005683643,0.00009291156,0.0000032444796,0.000013759714],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99820566,0.00007763372,0.0002974522,0.00021247333,0.0009662673,0.00024049515],"domain_scores_gemma":[0.9988833,0.00012920919,0.000040369785,0.000106296575,0.00066821155,0.00017263502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022579427,0.00009405636,0.0001219471,0.00013914284,0.0001112408,0.000022205568,0.000084100575,0.000070073314,0.0002602754],"category_scores_gemma":[0.0004936301,0.000058485675,0.0000409846,0.00025858052,0.00014734863,0.000050618284,0.000010116878,0.00020585801,0.000004841257],"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":[0.00010368906,0.000923188,0.9370194,0.000041221927,0.00001744323,0.0000025645184,0.00023392297,0.0000011059476,0.00019278277,0.005700029,0.0012309477,0.054533694],"study_design_scores_gemma":[0.00028276735,0.000482108,0.99134284,0.000090238806,0.000013697721,0.000012035322,0.0003253065,0.000011297277,0.00040431233,0.0056484244,0.0013196309,0.00006732072],"about_ca_topic_score_codex":0.0015968636,"about_ca_topic_score_gemma":0.022571508,"teacher_disagreement_score":0.05446637,"about_ca_system_score_codex":0.00021199704,"about_ca_system_score_gemma":0.00018778125,"threshold_uncertainty_score":0.995264},"labels":[],"label_agreement":null},{"id":"W2081705014","doi":"10.1177/0013164414527449","title":"Seeing Perfectly Fitting Factor Models That Are Causally Misspecified","year":2014,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":53,"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":"Factor (programming language); Factor analysis; Causal model; Econometrics; Causal structure; Psychology; Statistics; Mathematics; Computer science","score_opus":0.8554756584236994,"score_gpt":0.49012879108660357,"score_spread":0.36534686733709587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081705014","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":[0.8962564,0.001363949,0.042248756,0.010497603,0.0021069697,0.000258757,0.000007877064,0.00007308759,0.04718663],"genre_scores_gemma":[0.9855183,0.000029300512,0.012296997,0.0010836825,0.00050583173,0.000024852434,0.0000015030267,0.000008488586,0.00053104083],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9957297,0.00069687323,0.0005377262,0.00080988574,0.001836822,0.0003889878],"domain_scores_gemma":[0.9899974,0.008510029,0.0003494757,0.0004280913,0.00047254088,0.00024249937],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007614276,0.0002047761,0.00033174944,0.00020885545,0.00037557803,0.00025802193,0.000505332,0.00010924459,0.0009531891],"category_scores_gemma":[0.031874646,0.00013083685,0.00010117404,0.0005551794,0.0000892616,0.00016152422,0.000087054825,0.0002429453,0.000074227886],"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":[0.00011076456,0.0008389912,0.42631793,0.000022808137,0.00005716894,0.0000027771043,0.00097331,0.00032780756,0.0026146327,0.016781181,0.021206805,0.5307458],"study_design_scores_gemma":[0.0002805086,0.0001288329,0.842547,0.000036790705,0.000005389289,0.000015271451,0.00037349842,0.00057172787,0.00005039683,0.145068,0.010722123,0.00020047797],"about_ca_topic_score_codex":0.000009931778,"about_ca_topic_score_gemma":0.0000035838611,"teacher_disagreement_score":0.53054535,"about_ca_system_score_codex":0.000051734765,"about_ca_system_score_gemma":0.000029047502,"threshold_uncertainty_score":0.99996006},"labels":[],"label_agreement":null},{"id":"W2083403230","doi":"10.1177/0013164406292030","title":"Confidence Intervals for an Effect Size Measure in Multiple Linear Regression","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Confidence interval; Coverage probability; Mathematics; CDF-based nonparametric confidence interval; Percentile; Linear regression; Robust confidence intervals; Sample size determination; Regression analysis; Tolerance interval; Measure (data warehouse); Confidence distribution; Regression; Computer science","score_opus":0.4771766274732445,"score_gpt":0.5316271763859817,"score_spread":0.05445054891273715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083403230","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":[0.18122141,0.0002502282,0.81544316,0.00090549584,0.00041366342,0.0008528099,0.000013214506,0.000026624431,0.00087338686],"genre_scores_gemma":[0.72661895,0.0000062132444,0.27284327,0.00019940111,0.00015656563,0.000106630476,0.0000028918164,0.000008266777,0.00005783197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984366,0.00020802606,0.00035805177,0.00039872574,0.0003520951,0.00024644416],"domain_scores_gemma":[0.9952188,0.004145924,0.00008744358,0.0001786764,0.00020371565,0.00016543396],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043651047,0.00015306022,0.00024433745,0.000035835197,0.0000876762,0.000012997887,0.00010548008,0.000097765485,0.00006317302],"category_scores_gemma":[0.0107034445,0.000100812984,0.000047553975,0.00007321099,0.00007033067,0.00006328088,0.000014689803,0.00015425144,0.0000025134402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042916327,0.0057804883,0.0100316275,0.0005049775,0.00006687089,0.000008018605,0.0014870939,0.000015825457,0.055390503,0.57047796,0.0035160584,0.34842893],"study_design_scores_gemma":[0.0013529458,0.0011686644,0.04502387,0.0002512332,0.000016497881,0.000008614476,0.00006742975,0.00019289443,0.0015312118,0.9495791,0.00059541606,0.00021211062],"about_ca_topic_score_codex":0.000005759754,"about_ca_topic_score_gemma":0.000036662925,"teacher_disagreement_score":0.5453975,"about_ca_system_score_codex":0.000057708297,"about_ca_system_score_gemma":0.000018021155,"threshold_uncertainty_score":0.9976298},"labels":[],"label_agreement":null},{"id":"W2084244869","doi":"10.1177/0013164403258450","title":"Measurement and Validity Characteristics of the Short Version of the Social and Emotional Loneliness Scale for Adults","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":373,"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 New Brunswick","funders":"","keywords":"Loneliness; Psychology; Discriminant validity; Convergent validity; UCLA Loneliness Scale; Construct validity; Concurrent validity; Scale (ratio); Clinical psychology; Test validity; Developmental psychology; Psychometrics; Social psychology; Internal consistency","score_opus":0.22830131559293207,"score_gpt":0.40131588898674714,"score_spread":0.17301457339381507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084244869","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":[0.9597067,0.0001560806,0.000053727155,0.038862027,0.00063630356,0.00034297572,0.000035285142,0.000002303697,0.00020458255],"genre_scores_gemma":[0.998975,0.000080874,0.00009993433,0.0005410676,0.00026380934,0.000020141502,0.0000015432545,0.0000018862494,0.000015754136],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988384,0.00010139227,0.00019891848,0.0001334105,0.00060800515,0.00011985337],"domain_scores_gemma":[0.9993839,0.000054626358,0.00007979103,0.000057045258,0.000365195,0.00005938808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011272156,0.000060063754,0.000112113245,0.000009689825,0.000536169,0.000011751696,0.00009130171,0.000057562796,0.000020844294],"category_scores_gemma":[0.00034799342,0.00003454684,0.00004513334,0.000060201397,0.00032023148,0.000026712689,0.000025900894,0.000058874204,1.5734803e-7],"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":[0.00027533682,0.0013329022,0.93659866,0.0005047819,0.00003272385,4.00057e-8,0.008601808,0.0000015252468,0.00034534914,0.038309902,0.0023657118,0.011631257],"study_design_scores_gemma":[0.0003073627,0.000038175247,0.9929418,0.00013173619,0.00001282419,4.766742e-7,0.00071996904,6.01243e-7,0.000042112235,0.0043372265,0.0014247844,0.000042910353],"about_ca_topic_score_codex":0.00020257784,"about_ca_topic_score_gemma":0.00025311907,"teacher_disagreement_score":0.05634316,"about_ca_system_score_codex":0.000071842136,"about_ca_system_score_gemma":0.00016308231,"threshold_uncertainty_score":0.41238323},"labels":[],"label_agreement":null},{"id":"W2090570025","doi":"10.1177/00131640021970330","title":"Number-Right, Item-Response, and Finite-State Scoring: Robustness with Respect to Lack of Equally Classifiable Options and Item Option Independence","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Robustness (evolution); Independence (probability theory); Mathematics; Statistics; Econometrics","score_opus":0.6325820280120732,"score_gpt":0.4842413224829055,"score_spread":0.14834070552916767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090570025","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":[0.9847274,0.0005532065,0.0063936724,0.0044867187,0.0001895282,0.00028278006,0.000013042014,0.000018923656,0.0033347209],"genre_scores_gemma":[0.9721106,0.00013805936,0.02553747,0.00020092982,0.00006862933,0.000046562403,0.0000012302969,0.000006612858,0.0018899018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964627,0.000629362,0.0005743394,0.0007245091,0.0013487367,0.00026035393],"domain_scores_gemma":[0.9884093,0.010352986,0.00018846324,0.0003094519,0.00047999484,0.000259814],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007185233,0.00018052741,0.00031206346,0.00024283194,0.0002357434,0.00017941606,0.00026639123,0.0000845103,0.001051625],"category_scores_gemma":[0.013257826,0.00011451685,0.000030871284,0.0011033203,0.0002067146,0.00017434516,0.000053398766,0.00018755277,0.000022476252],"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":[0.0065801586,0.00206298,0.5271822,0.000062456915,0.00012470601,0.000029838404,0.0021470475,0.0071184924,0.0042764824,0.011827021,0.003908586,0.43467999],"study_design_scores_gemma":[0.0005246933,0.00064471684,0.9721419,0.00009819966,0.000010781832,0.00009627269,0.00027261852,0.00031362302,0.00006662245,0.02092715,0.0046982737,0.00020512838],"about_ca_topic_score_codex":0.000022000564,"about_ca_topic_score_gemma":0.000014088469,"teacher_disagreement_score":0.4449597,"about_ca_system_score_codex":0.00004086659,"about_ca_system_score_gemma":0.000086369604,"threshold_uncertainty_score":0.99986154},"labels":[],"label_agreement":null},{"id":"W2093980226","doi":"10.1177/00131640021971005","title":"Implications of Test Dimensionality for Unidimensional Irt Scoring: An Investigation of a High-Stakes Testing Program","year":2000,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Item response theory; Psychology; Curse of dimensionality; Test (biology); Statistics; Psychometrics; Item analysis; Equating; Test validity; Homogeneous; Social psychology; Econometrics; Mathematics; Clinical psychology; Developmental psychology; Rasch model","score_opus":0.7984940592344482,"score_gpt":0.517856493671935,"score_spread":0.2806375655625132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093980226","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":[0.9937441,0.0002021197,0.00059670804,0.0034860328,0.00020922782,0.00056511845,0.000054933622,0.000028731916,0.0011130525],"genre_scores_gemma":[0.8504468,0.0000061183628,0.14903587,0.0001679182,0.00011136513,0.00014116334,0.000018587098,0.000005223329,0.00006696021],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969567,0.00028684756,0.0009214913,0.0005919157,0.0010356135,0.00020740481],"domain_scores_gemma":[0.984076,0.013222607,0.00043643024,0.00042343297,0.0016547948,0.000186716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005544698,0.0001461046,0.00031477143,0.00017397407,0.00020171859,0.000038594742,0.00033678842,0.00008099141,0.00041491725],"category_scores_gemma":[0.025710337,0.000101210746,0.000071658375,0.0010182635,0.00028820962,0.00013236383,0.000027044774,0.00009658598,0.0000038219464],"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":[0.000120659926,0.0023374727,0.48206806,0.000029770748,0.000026435002,1.04050436e-7,0.00018627054,0.00017779302,0.01624948,0.01931993,0.0018472747,0.47763675],"study_design_scores_gemma":[0.00025091766,0.0007390978,0.7217013,0.00003186986,0.000010780818,0.00000645732,0.00005236245,0.00009603452,0.000321545,0.27637053,0.00033319302,0.0000859018],"about_ca_topic_score_codex":0.00004625928,"about_ca_topic_score_gemma":0.0000036125402,"teacher_disagreement_score":0.47755083,"about_ca_system_score_codex":0.000029858955,"about_ca_system_score_gemma":0.00012236451,"threshold_uncertainty_score":0.9824965},"labels":[],"label_agreement":null},{"id":"W2116643860","doi":"10.1177/0013164410366683","title":"Using Cochran’s Z Statistic to Test the Kernel-Smoothed Item Response Function Differences Between Focal and Reference Groups","year":2010,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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 Alberta","funders":"","keywords":"Type I and type II errors; Mathematics; Statistics; Kernel smoother; Kernel (algebra); Statistic; Smoothing; Nonparametric statistics; Test statistic; Differential item functioning; Kernel method; Statistical hypothesis testing; Item response theory; Computer science; Radial basis function kernel; Artificial intelligence; Psychometrics; Support vector machine","score_opus":0.7546464432633119,"score_gpt":0.5131096502165755,"score_spread":0.24153679304673636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116643860","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":[0.97388226,0.00019796133,0.016381906,0.0076525896,0.0009526667,0.00025925427,0.000024567822,0.000019808576,0.00062896305],"genre_scores_gemma":[0.9889438,0.000008548801,0.010009923,0.00054481876,0.000336088,0.00003620147,0.00000163886,0.000005355997,0.000113582806],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965477,0.00076220644,0.0005129216,0.00064973714,0.0012643371,0.00026308038],"domain_scores_gemma":[0.9611433,0.037626605,0.0001991402,0.00037121453,0.0004102784,0.0002494255],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009894867,0.00017463563,0.00025736034,0.00017966423,0.00046467292,0.00027992454,0.0004132916,0.00010071898,0.00046757504],"category_scores_gemma":[0.087902226,0.00009121013,0.000033901564,0.0006948858,0.0002113241,0.00007913038,0.00008927649,0.00034849186,0.000029866358],"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":[0.00045897783,0.00035649101,0.85932845,0.000005839088,0.000022967435,8.722597e-7,0.0003994482,0.000002887369,0.012052662,0.0054362733,0.0021523172,0.11978284],"study_design_scores_gemma":[0.00019462257,0.000496687,0.9158918,0.000016451535,0.000015125699,0.000015026511,0.00027731434,0.000060094357,0.0000107090955,0.08085998,0.0020343869,0.00012778662],"about_ca_topic_score_codex":0.00003325279,"about_ca_topic_score_gemma":0.000026196001,"teacher_disagreement_score":0.11965506,"about_ca_system_score_codex":0.000027862472,"about_ca_system_score_gemma":0.00005713376,"threshold_uncertainty_score":0.91978073},"labels":[],"label_agreement":null},{"id":"W2122573908","doi":"10.1177/0013164415574086","title":"A Ratio Test of Interrater Agreement With High Specificity","year":2015,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; University of Ottawa","funders":"","keywords":"Inter-rater reliability; Agreement; Psychology; Validation test; Test validity; Test (biology); Psychometrics; Statistics; Clinical psychology; Developmental psychology; Rating scale; Mathematics; Geology","score_opus":0.4746679401283067,"score_gpt":0.40888115156470517,"score_spread":0.06578678856360154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122573908","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":[0.9590281,0.00026492556,0.0029383341,0.020894632,0.0007964507,0.0004871495,0.000013889053,0.0000118836,0.015564583],"genre_scores_gemma":[0.996219,0.00000853102,0.0022677628,0.00049437454,0.00019155044,0.000052131207,0.000004024907,0.0000037447808,0.00075892784],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9951897,0.00023349216,0.0006947219,0.0005495645,0.003134748,0.00019773492],"domain_scores_gemma":[0.9972599,0.00034613925,0.00024184467,0.0004372252,0.0014736382,0.00024122339],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052833296,0.00017015386,0.00026969425,0.00009512017,0.000083143656,0.00009737622,0.00038083596,0.00005455595,0.0017031877],"category_scores_gemma":[0.0019463446,0.000092129885,0.000052544536,0.00031576006,0.00023127042,0.0001226023,0.000055589688,0.00012587327,0.00015645582],"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":[0.0013313801,0.01477403,0.6793236,0.000044786415,0.0001753233,0.0000056489034,0.003288074,0.00034459258,0.017989663,0.03277455,0.21578151,0.03416684],"study_design_scores_gemma":[0.0012008036,0.0020276483,0.8835647,0.00006686495,0.000021134061,0.000011518307,0.0011293471,0.000023446295,0.0017933976,0.09393515,0.015975077,0.00025091038],"about_ca_topic_score_codex":0.000028590961,"about_ca_topic_score_gemma":0.000033550918,"teacher_disagreement_score":0.2042411,"about_ca_system_score_codex":0.00010234507,"about_ca_system_score_gemma":0.000108766566,"threshold_uncertainty_score":0.9992094},"labels":[],"label_agreement":null},{"id":"W2123520859","doi":"10.1177/0013164407313371","title":"Note on a Confidence Interval for the Squared Semipartial Correlation Coefficient","year":2008,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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 Manitoba","funders":"","keywords":"Statistics; Confidence interval; Percentile; Mathematics; Coverage probability; Correlation coefficient; Sample size determination; Correlation; Mean squared error; Regression analysis; Linear regression; Interval (graph theory); Combinatorics","score_opus":0.7435488238248646,"score_gpt":0.511461499220875,"score_spread":0.23208732460398962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123520859","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":[0.34348157,0.001336987,0.60196227,0.03777026,0.0070470553,0.0011464411,0.000021286964,0.000050058326,0.0071840845],"genre_scores_gemma":[0.99441576,0.000027171249,0.00330133,0.0013141003,0.00038243472,0.00011784686,0.0000021643161,0.000003689284,0.00043550011],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99728316,0.00028019006,0.00046055453,0.00047831633,0.001293839,0.00020396675],"domain_scores_gemma":[0.9799644,0.018928284,0.0001980473,0.0003023308,0.00050862564,0.000098309145],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0053136954,0.00011969467,0.00016948198,0.000101130645,0.00052168156,0.0000744916,0.00037589882,0.000062901956,0.0003545678],"category_scores_gemma":[0.042883024,0.00006127334,0.00009273494,0.00046223108,0.0001942408,0.00004630456,0.00003217218,0.0001491296,0.00006251136],"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":[0.0019657041,0.00312241,0.06542368,0.000014144909,0.00008606559,0.0000042075667,0.0038759834,0.004963069,0.001535176,0.068518974,0.28997084,0.56051975],"study_design_scores_gemma":[0.0006899783,0.00085133174,0.9083482,0.000027788272,0.0000124586495,0.000050448012,0.00027367787,0.004612749,0.000067575595,0.044340298,0.040555235,0.00017023041],"about_ca_topic_score_codex":0.000007214739,"about_ca_topic_score_gemma":0.0000020337461,"teacher_disagreement_score":0.84292454,"about_ca_system_score_codex":0.000045257744,"about_ca_system_score_gemma":0.000051079856,"threshold_uncertainty_score":0.9651792},"labels":[],"label_agreement":null},{"id":"W2124517593","doi":"10.1177/0013164414536184","title":"Application of the Overclaiming Technique to Scholastic Assessment","year":2014,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Robustness (evolution); Statistics; Reliability (semiconductor); Index (typography); Measure (data warehouse); Social psychology; Computer science; Mathematics; Data mining","score_opus":0.11770683296098142,"score_gpt":0.40411838869564654,"score_spread":0.28641155573466515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124517593","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":[0.6043282,0.00030261744,0.19939189,0.060089264,0.003198661,0.0020064036,0.0000280153,0.00006349396,0.13059145],"genre_scores_gemma":[0.9924343,0.0000017081634,0.0032201263,0.0033674224,0.0002507776,0.0005166837,0.0000030782755,0.000007902975,0.0001979908],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99839073,0.00029150298,0.00030519965,0.00041799757,0.0003922318,0.00020234557],"domain_scores_gemma":[0.9990776,0.00014683956,0.000115491064,0.00038906423,0.00015139653,0.00011958326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012962258,0.0001313804,0.00015943946,0.000056533587,0.00013601623,0.000014477585,0.00027165926,0.00010546568,0.00069202436],"category_scores_gemma":[0.0001464093,0.00008664767,0.00006305041,0.00021869848,0.00011789358,0.000029852838,0.000035652625,0.00021602576,0.000050682007],"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":[0.00015189705,0.0031679627,0.11067564,0.000045340195,0.0001021982,2.1357641e-7,0.0010603424,0.000015070585,0.05272832,0.7181166,0.014753775,0.09918264],"study_design_scores_gemma":[0.00024837663,0.00023810148,0.94159555,0.00002591697,0.0000141772825,0.000016950498,0.000046470428,0.000004882802,0.00006428453,0.01792926,0.039705638,0.00011040906],"about_ca_topic_score_codex":0.00003242096,"about_ca_topic_score_gemma":0.0000070959386,"teacher_disagreement_score":0.8309199,"about_ca_system_score_codex":0.000049513386,"about_ca_system_score_gemma":0.000025505171,"threshold_uncertainty_score":0.75771815},"labels":[],"label_agreement":null},{"id":"W2130969147","doi":"10.1177/0013164412452564","title":"The Relationship Between Root Mean Square Error of Approximation and Model Misspecification in Confirmatory Factor Analysis Models","year":2012,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":123,"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":"Structural equation modeling; Confirmatory factor analysis; Statistics; Mathematics; Population; Cutoff; Factor analysis; Econometrics; Physics","score_opus":0.8678825713483123,"score_gpt":0.5198963884873063,"score_spread":0.3479861828610059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130969147","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":[0.9509001,0.0017421886,0.042977232,0.002387522,0.00014046534,0.00021925179,0.000012858667,0.000008379014,0.0016120244],"genre_scores_gemma":[0.99444175,0.000017142685,0.005340768,0.000030677445,0.00007110826,0.000035202218,0.000006359273,0.0000031077593,0.00005390581],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99722916,0.0005539751,0.0007073024,0.00031441118,0.0010033204,0.00019181555],"domain_scores_gemma":[0.988543,0.01038811,0.00034521802,0.00029735605,0.00030187788,0.00012445229],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075779576,0.00010864872,0.00023779267,0.00034485338,0.00019952397,0.00006301185,0.00022926531,0.000083916304,0.00004083526],"category_scores_gemma":[0.012377111,0.00006407404,0.000063589076,0.001205762,0.0001245797,0.00021060395,0.000029994348,0.00014426814,0.0000033080094],"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":[0.000017031365,0.00013033047,0.964588,0.000004486167,0.000022145665,9.8313775e-9,0.00084108283,0.00037946057,0.000040608127,0.024627909,0.00014803218,0.009200902],"study_design_scores_gemma":[0.00012459508,0.000020854544,0.8544398,0.000006883301,0.000022625769,5.772437e-7,0.00045310773,0.0031969687,0.000006812667,0.14159171,0.00006805847,0.0000679831],"about_ca_topic_score_codex":0.000009985933,"about_ca_topic_score_gemma":0.000011623998,"teacher_disagreement_score":0.116963804,"about_ca_system_score_codex":0.000043961223,"about_ca_system_score_gemma":0.00002529704,"threshold_uncertainty_score":0.99594206},"labels":[],"label_agreement":null},{"id":"W2138135002","doi":"10.1177/0013164406299101","title":"An Item Response Theory Examination of Two Popular Goal Orientation Measures","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Motivation and Self-Concept in Sports","field":"Psychology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Marriott International (Canada)","funders":"","keywords":"Goal orientation; Construct (python library); Orientation (vector space); Item response theory; Psychology; Scale (ratio); Psychometrics; Construct validity; Cognitive psychology; Social psychology; Computer science; Developmental psychology; Mathematics","score_opus":0.11772278215911086,"score_gpt":0.3977912221514822,"score_spread":0.28006843999237135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138135002","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":[0.98234755,0.00034242394,0.005985164,0.0005073783,0.0012160204,0.00031389383,0.0000062078293,0.000036651865,0.009244725],"genre_scores_gemma":[0.9974292,0.000005417797,0.0010144993,0.00054675026,0.00028948652,0.00004753883,0.000042761345,0.000011035413,0.00061329745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9973369,0.0007998924,0.00050803146,0.00043817054,0.00069008424,0.00022689212],"domain_scores_gemma":[0.9985892,0.00031827675,0.00021337037,0.00028825444,0.00042332363,0.00016758603],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0073487405,0.00015646587,0.00016623914,0.0001670526,0.00011967527,0.000019016854,0.0001393231,0.00011762106,0.0025414657],"category_scores_gemma":[0.00043514182,0.00013035817,0.000050724,0.00023328586,0.00014591542,0.00010666261,0.000008309173,0.00014168734,0.00003256058],"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":[0.00440315,0.005928226,0.24021177,0.000019400522,0.00011705598,0.0000089704845,0.018564738,0.000009728089,0.021684533,0.4547356,0.0020051172,0.25231168],"study_design_scores_gemma":[0.00083627796,0.0005072782,0.9832468,0.000015824762,0.0000179339,0.000018614093,0.002505043,7.5771646e-7,0.0002558386,0.009691725,0.0027533588,0.00015053917],"about_ca_topic_score_codex":0.000014213292,"about_ca_topic_score_gemma":0.000008122862,"teacher_disagreement_score":0.743035,"about_ca_system_score_codex":0.000079012934,"about_ca_system_score_gemma":0.000031113366,"threshold_uncertainty_score":0.99837035},"labels":[],"label_agreement":null},{"id":"W2139940744","doi":"10.1177/0013164404268668","title":"Reliability Generalization of Responses by Care Providers to the Center for Epidemiologic Studies-Depression Scale","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Mental Health Treatment and Access","field":"Psychology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Center for Epidemiologic Studies Depression Scale; Reliability (semiconductor); Scale (ratio); Generalization; Psychology; Clinical psychology; Depression (economics); Psychometrics; Item response theory; Gerontology; Psychiatry; Depressive symptoms; Medicine; Cognition; Mathematics","score_opus":0.24454511919170627,"score_gpt":0.4761799233039707,"score_spread":0.23163480411226442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139940744","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":[0.96171296,0.0076486473,0.0005497359,0.026532765,0.0010927598,0.0017995917,0.00010057935,0.000015804222,0.0005471782],"genre_scores_gemma":[0.9948219,0.00008373947,0.0011753421,0.0023796523,0.00015276956,0.0011000342,0.00006612928,0.0000059660456,0.00021447848],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985415,0.000270477,0.0003515256,0.00040921074,0.00022316235,0.00020412832],"domain_scores_gemma":[0.9990596,0.00024564972,0.00011917107,0.00022070241,0.0002627935,0.00009207868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008813435,0.00012884648,0.00018462942,0.000030103727,0.00025191504,0.000008746177,0.00013256114,0.00006985499,0.00010004206],"category_scores_gemma":[0.00034565546,0.00006964962,0.000055630448,0.00009853625,0.00009609323,0.000036050842,0.00002415344,0.00006259627,0.000013042118],"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":[0.0076685622,0.011337281,0.41351977,0.0006840693,0.00032466068,9.911049e-7,0.023877809,0.00029648637,0.0056350227,0.009240372,0.3674271,0.15998787],"study_design_scores_gemma":[0.0024256534,0.0016204858,0.9526126,0.0001519735,0.00004336711,0.000005594438,0.003172787,9.0768674e-7,0.0009034702,0.012941783,0.025904238,0.00021716896],"about_ca_topic_score_codex":0.00006352242,"about_ca_topic_score_gemma":0.000022433916,"teacher_disagreement_score":0.5390928,"about_ca_system_score_codex":0.00014779391,"about_ca_system_score_gemma":0.000019641499,"threshold_uncertainty_score":0.2840229},"labels":[],"label_agreement":null},{"id":"W2140588557","doi":"10.1177/0013164414548894","title":"A Cautionary Note on the Use of the Vale and Maurelli Method to Generate Multivariate, Nonnormal Data for Simulation Purposes","year":2014,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":37,"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":"Kurtosis; Skewness; Statistics; Univariate; Mathematics; Monte Carlo method; Population; Variable (mathematics); Multivariate statistics; Sample (material); Econometrics; Algorithm","score_opus":0.6134090036945616,"score_gpt":0.49396079300045054,"score_spread":0.1194482106941111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140588557","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":[0.012264572,0.00001625825,0.9757903,0.010873096,0.0002045924,0.0005862925,0.00013735905,0.0000056635163,0.00012182086],"genre_scores_gemma":[0.34029892,0.0000021897208,0.6583948,0.0010501913,0.00012972261,0.00006700528,0.0000066569537,0.00000471309,0.000045751756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987095,0.00042235001,0.00022016992,0.0002695693,0.00027014085,0.000108297034],"domain_scores_gemma":[0.99422765,0.005105071,0.00008770207,0.00034390422,0.00017770895,0.000057937126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015508406,0.000098203884,0.00012547345,0.000018069917,0.0001708144,0.0000327052,0.00017260505,0.00004599249,0.00005013205],"category_scores_gemma":[0.0051674843,0.000047787627,0.000023695524,0.00007563266,0.000064552856,0.000038618124,0.00006599741,0.00008105265,0.0000015259207],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015609959,0.0005353406,0.00038590812,0.000045476543,0.000031586882,4.4692477e-8,0.00017927955,0.00028630858,0.0020470072,0.92474717,0.0055656806,0.066020116],"study_design_scores_gemma":[0.00032795587,0.00034914352,0.11743164,0.00007564614,0.000061602776,0.0000031636089,0.000013406207,0.03590698,0.0002853294,0.8327518,0.012643755,0.00014954338],"about_ca_topic_score_codex":0.000012548456,"about_ca_topic_score_gemma":0.0000032851833,"teacher_disagreement_score":0.32803437,"about_ca_system_score_codex":0.000013137179,"about_ca_system_score_gemma":0.000021689699,"threshold_uncertainty_score":0.6186335},"labels":[],"label_agreement":null},{"id":"W2143769021","doi":"10.1177/0013164406296976","title":"The Impact of Outliers on Cronbach's Coefficient Alpha Estimate of Reliability: Visual Analogue Scales","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cronbach's alpha; Outlier; Statistics; Sample (material); Population; Reliability (semiconductor); Statistic; Context (archaeology); Mathematics; Econometrics; Psychometrics; Demography; Geography; Chemistry","score_opus":0.24588333650656144,"score_gpt":0.5254813432007601,"score_spread":0.27959800669419865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143769021","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":[0.7237012,0.00019623023,0.27284172,0.00071073056,0.00021061863,0.00032004947,0.000031007316,0.000010433393,0.0019780502],"genre_scores_gemma":[0.9517711,0.00001595622,0.048086792,0.000031952088,0.000045664772,0.000013069131,0.0000027308847,0.000006157929,0.000026611191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984846,0.00012553929,0.00045872285,0.00023546665,0.00048191732,0.00021375949],"domain_scores_gemma":[0.9971873,0.0020230114,0.00017803605,0.00019230884,0.0002961921,0.00012315754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025814169,0.00012988561,0.00022433273,0.00003638637,0.00011430676,0.000008474264,0.000107595755,0.000055221488,0.000043185395],"category_scores_gemma":[0.002524885,0.0000683578,0.00009598085,0.00010597535,0.0003381782,0.000016641672,0.000018542612,0.00011993999,0.0000017474089],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019769054,0.011014064,0.009969966,0.00015580504,0.0002244305,0.0000020608695,0.0006473643,0.0012341902,0.005878607,0.7504942,0.004144181,0.21425822],"study_design_scores_gemma":[0.0004030046,0.001523878,0.34334388,0.00006309153,0.000023723649,0.0000038608296,0.00011276033,0.000344616,0.00053797226,0.6533895,0.00012261089,0.00013107203],"about_ca_topic_score_codex":0.0000105561085,"about_ca_topic_score_gemma":0.0000050297826,"teacher_disagreement_score":0.33337393,"about_ca_system_score_codex":0.00007629671,"about_ca_system_score_gemma":0.00003547875,"threshold_uncertainty_score":0.30227056},"labels":[],"label_agreement":null},{"id":"W2145368831","doi":"10.1177/0013164404267286","title":"Items in Context: Assessing the Dimensionality of Raven’s Advanced Progressive Matrices","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto; Université de Moncton","funders":"","keywords":"Rasch model; Principal component analysis; Raven's Progressive Matrices; Curse of dimensionality; Context (archaeology); Set (abstract data type); Psychology; Test (biology); Artificial intelligence; Cognitive psychology; Mathematics; Statistics; Computer science; Cognition","score_opus":0.15614162299139392,"score_gpt":0.4156424825958814,"score_spread":0.25950085960448743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145368831","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":[0.98047,0.0050342083,0.000054933334,0.0066245445,0.00045751364,0.00034089273,0.0000053793906,0.000009303809,0.00700324],"genre_scores_gemma":[0.99878025,0.000009525215,0.00037771714,0.0005282108,0.00010797101,0.00015427412,0.0000041091334,0.0000044924777,0.00003345513],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99876046,0.00016342521,0.00031314,0.00028537336,0.00030220996,0.00017539984],"domain_scores_gemma":[0.9989917,0.0004428336,0.0001497432,0.00013628943,0.0002311293,0.000048256166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080833683,0.00010519988,0.00014679311,0.00003780119,0.00009882768,0.00002008117,0.00009764782,0.00004839933,0.0005394932],"category_scores_gemma":[0.00039169044,0.00006524858,0.000042022144,0.00015408751,0.00020267766,0.000052527404,0.000023295035,0.00015487321,0.000010203442],"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":[0.00042692755,0.009358573,0.396346,0.000114017086,0.00017377074,0.000019968014,0.012611234,0.00008651622,0.0029217368,0.26294577,0.0006141606,0.3143813],"study_design_scores_gemma":[0.0006634378,0.00016028134,0.9432523,0.00013907497,0.000008628377,0.000021090917,0.0032670319,9.02941e-7,0.0000533068,0.051830593,0.0005132155,0.00009011187],"about_ca_topic_score_codex":0.00011269041,"about_ca_topic_score_gemma":0.000022787393,"teacher_disagreement_score":0.5469063,"about_ca_system_score_codex":0.00006160495,"about_ca_system_score_gemma":0.000051100265,"threshold_uncertainty_score":0.59070724},"labels":[],"label_agreement":null},{"id":"W2147389406","doi":"10.1177/0013164404267293","title":"Employment-Related Motivational Distortion: Its Nature, Measurement, and Reduction","year":2005,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Personality Traits and Psychology","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":"University of British Columbia","funders":"","keywords":"Psychology; Scale (ratio); Statistics; Reliability (semiconductor); Facet (psychology); Econometrics; California Psychological Inventory; Personality; Minnesota Multiphasic Personality Inventory; Social psychology; Mathematics; Big Five personality traits","score_opus":0.16023899951099507,"score_gpt":0.3733470839528351,"score_spread":0.21310808444184004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147389406","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":[0.85745144,0.014791319,0.00016619555,0.0709594,0.003938473,0.0006223688,0.0000359565,0.00011326663,0.05192158],"genre_scores_gemma":[0.9937595,0.00010080119,0.00035520503,0.0022564512,0.0010985221,0.00017268627,0.00003968588,0.000017425213,0.0021997092],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9972335,0.00024045329,0.00049872,0.00081266573,0.00084223377,0.00037243866],"domain_scores_gemma":[0.99889284,0.000052819014,0.0001625947,0.00023457587,0.0003959366,0.00026120682],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012403587,0.00027598007,0.00023122942,0.00012613494,0.00029060067,0.000047982878,0.00014973925,0.00035079502,0.006053178],"category_scores_gemma":[0.00013029693,0.00023412949,0.000075150485,0.00021022059,0.00021003469,0.00014988704,0.000023735563,0.00051103585,0.00022977615],"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":[0.0010186859,0.010947433,0.034307603,0.000063615174,0.0010459104,0.000007023797,0.004756105,0.000009003744,0.012381936,0.45567706,0.2521273,0.22765835],"study_design_scores_gemma":[0.0012715688,0.00027867002,0.8882977,0.000033265853,0.000040608764,0.00024075211,0.00013197602,0.0000028754748,0.000046084115,0.00793307,0.10141847,0.00030495107],"about_ca_topic_score_codex":0.000011483341,"about_ca_topic_score_gemma":0.000010008815,"teacher_disagreement_score":0.8539901,"about_ca_system_score_codex":0.00017920157,"about_ca_system_score_gemma":0.000044458815,"threshold_uncertainty_score":0.9948554},"labels":[],"label_agreement":null},{"id":"W2151034533","doi":"10.1177/0013164411429821","title":"Impact of Outliers Arising From Unintended and Unknowingly Included Subpopulations on the Decisions About the Number of Factors in Exploratory Factor Analysis","year":2012,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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 British Columbia","funders":"","keywords":"Outlier; Principal component analysis; Exploratory factor analysis; Affect (linguistics); Sample (material); Statistics; Econometrics; Psychology; Mathematics; Psychometrics; Chemistry","score_opus":0.5576272671228929,"score_gpt":0.5227089697684599,"score_spread":0.03491829735443297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151034533","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":[0.96078485,0.0001116214,0.038091756,0.00046205075,0.00008430408,0.000162078,0.00007913831,0.0000035600008,0.00022062483],"genre_scores_gemma":[0.98722196,0.000019270892,0.0126511725,0.00004043181,0.000029929102,0.000019215327,0.0000068734394,0.0000051629163,0.0000060036245],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986959,0.00030205143,0.00035993222,0.00016045636,0.0003374482,0.00014420267],"domain_scores_gemma":[0.9962113,0.0032055778,0.00015560114,0.00020409717,0.00013221311,0.00009124667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007053037,0.00012036168,0.0002528224,0.000061019924,0.00010353765,0.000009963991,0.00009377193,0.00005204878,0.00023658894],"category_scores_gemma":[0.0027004522,0.00005559439,0.00009804904,0.00025526743,0.00017309793,0.00005242875,0.00002584057,0.00015111055,7.1724367e-7],"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":[0.00009136096,0.0015076812,0.8141432,0.0000057673237,0.00044514335,9.2964505e-8,0.0058282376,0.000059457463,0.000952205,0.17280938,0.00013022328,0.004027261],"study_design_scores_gemma":[0.00011061823,0.000031176194,0.74328285,0.000023870529,0.00007005862,1.7918208e-7,0.0005384351,0.000029368386,0.000031632255,0.25582105,0.000008584537,0.00005216772],"about_ca_topic_score_codex":0.00006407488,"about_ca_topic_score_gemma":0.000021057718,"teacher_disagreement_score":0.08301167,"about_ca_system_score_codex":0.000055121152,"about_ca_system_score_gemma":0.000023269184,"threshold_uncertainty_score":0.32328886},"labels":[],"label_agreement":null},{"id":"W2154413108","doi":"10.1177/0013164406299132","title":"Correction for Attenuation With Biased Reliability Estimates and Correlated Errors in Populations and Samples","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Statistics; Reliability (semiconductor); Monte Carlo method; Correction for attenuation; Attenuation; Sample size determination; Observational error; Mathematics; Population; Sampling error; Sample (material); Sampling (signal processing); Random variable; Econometrics; Computer science; Physics; Demography; Optics","score_opus":0.34262566925646354,"score_gpt":0.449982568421525,"score_spread":0.10735689916506147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154413108","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":[0.5564217,0.00006575381,0.44134447,0.001347724,0.00022860072,0.0003803177,0.000008810413,0.000013931338,0.000188695],"genre_scores_gemma":[0.6704177,0.0000048515803,0.32943785,0.000049499264,0.000025143008,0.000042409058,0.000008864227,0.0000033524427,0.000010265079],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99919134,0.000052254443,0.00023326893,0.00024640068,0.00015485554,0.00012187245],"domain_scores_gemma":[0.99808234,0.0015620237,0.000067913636,0.000066667824,0.00014755034,0.00007351834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011533252,0.00009227342,0.000128526,0.00005103781,0.00010477513,0.000021116313,0.000021431179,0.00005986179,0.00003251789],"category_scores_gemma":[0.0030725102,0.00006474728,0.000009619359,0.00010216007,0.00010041592,0.00003934249,0.0000058625433,0.000083911065,3.442668e-7],"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":[0.0005829203,0.0011175208,0.6447486,0.00011919245,0.000019853887,6.825098e-7,0.0006150044,0.000005742834,0.00063408935,0.24653736,0.0013210863,0.10429792],"study_design_scores_gemma":[0.00027209896,0.00015948854,0.6173151,0.000050165556,0.000013725611,0.000007054945,0.00006510629,0.0003568377,0.000017932662,0.3816535,0.000027130744,0.00006189423],"about_ca_topic_score_codex":0.000037294205,"about_ca_topic_score_gemma":0.00011258374,"teacher_disagreement_score":0.13511613,"about_ca_system_score_codex":0.000037409154,"about_ca_system_score_gemma":0.000015937021,"threshold_uncertainty_score":0.36783037},"labels":[],"label_agreement":null},{"id":"W2154633345","doi":"10.1177/0013164403258393","title":"Impact of Test Design, Item Quality, and Item Bank Size on the Psychometric Properties of Computer-Based Credentialing Examinations","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Education and Child Care","funders":"","keywords":"Credentialing; Computerized adaptive testing; Item bank; Test (biology); Quality (philosophy); Computer science; Consistency (knowledge bases); Test design; Item response theory; Psychology; Psychometrics; Applied psychology; Statistics; Reliability engineering; Artificial intelligence; Medical education; Test method; Medicine; Mathematics; Clinical psychology","score_opus":0.8330425941791564,"score_gpt":0.5172334143779688,"score_spread":0.3158091798011876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154633345","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":[0.97582203,0.00080441724,0.018032275,0.004136453,0.0003508073,0.000358375,0.00001169164,0.000012015777,0.00047191017],"genre_scores_gemma":[0.98531806,0.000027048129,0.014260613,0.0002388922,0.00010062269,0.000030235631,7.1142745e-7,0.000004948118,0.00001884103],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996316,0.0007359767,0.0008326067,0.0004527099,0.0014749139,0.0001877484],"domain_scores_gemma":[0.9602904,0.037679374,0.00053639023,0.0003807231,0.0010008994,0.00011224202],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008970078,0.0001673623,0.00033434803,0.00040080203,0.00019844565,0.00010376129,0.0004178979,0.00007152487,0.00018736791],"category_scores_gemma":[0.10974809,0.00008266083,0.000111165,0.0021079066,0.00027755013,0.00006438365,0.000044198685,0.00014264033,0.000003959107],"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":[0.0004194061,0.008656241,0.7963242,0.000084072606,0.00018950677,7.959198e-7,0.0009826015,0.0023584673,0.04658718,0.008919579,0.003256941,0.132221],"study_design_scores_gemma":[0.00052108965,0.0011105608,0.97960484,0.000098217344,0.0000100467905,0.0000048982997,0.00011081848,0.00010333683,0.0007538317,0.017553251,0.000022589373,0.00010649413],"about_ca_topic_score_codex":0.000050902756,"about_ca_topic_score_gemma":0.0000014217205,"teacher_disagreement_score":0.18328066,"about_ca_system_score_codex":0.000059529455,"about_ca_system_score_gemma":0.000118530654,"threshold_uncertainty_score":0.89775085},"labels":[],"label_agreement":null},{"id":"W2158599033","doi":"10.1177/0013164407313368","title":"Factorial Invariance of the Academic Amotivation Inventory (AAI) Across Gender and Grade in a Sample of Canadian High School Students","year":2008,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Motivation and Self-Concept in Sports","field":"Psychology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Université du Québec en Outaouais","funders":"","keywords":"Amotivation; Psychology; Measurement invariance; Metric (unit); Sample (material); Internal consistency; Factorial; Construct validity; Confirmatory factor analysis; Developmental psychology; Test validity; Psychometrics; Social psychology; Structural equation modeling; Statistics; Mathematics; Intrinsic motivation","score_opus":0.25205896513744275,"score_gpt":0.3812125439226223,"score_spread":0.12915357878517958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158599033","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":[0.99626106,0.00026888106,0.000020855903,0.00094144925,0.001335537,0.00033483145,0.00003398113,0.000003981811,0.00079943467],"genre_scores_gemma":[0.9988304,0.00006747055,0.00009768832,0.0006165267,0.00019078972,0.000052515705,0.00001323582,0.0000052477153,0.00012611832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984673,0.00016789061,0.0004065469,0.0002777365,0.00048524022,0.00019525358],"domain_scores_gemma":[0.9992865,0.00008904954,0.00017734745,0.00017312345,0.00012405019,0.00014994414],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005904109,0.0001107056,0.00016554884,0.0001178865,0.000103565144,0.0000058462197,0.00019196949,0.00015125106,0.0010334727],"category_scores_gemma":[0.0003390339,0.000081457634,0.000030541196,0.0003332029,0.00021097198,0.000052556894,0.000025574427,0.00025758042,0.000003947376],"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":[0.000039133767,0.00042991573,0.98312026,0.000007981651,0.000021296339,3.9832835e-7,0.0050492072,0.0000024158678,0.00021305418,0.007949858,0.0029788425,0.00018761506],"study_design_scores_gemma":[0.0007625921,0.000059102455,0.991302,0.000024852005,0.000004153621,0.000005234649,0.00046759477,1.5983785e-7,0.00002838193,0.005045071,0.0022214802,0.000079388694],"about_ca_topic_score_codex":0.01233363,"about_ca_topic_score_gemma":0.0017278952,"teacher_disagreement_score":0.010605735,"about_ca_system_score_codex":0.00008985195,"about_ca_system_score_gemma":0.000115102855,"threshold_uncertainty_score":0.9998797},"labels":[],"label_agreement":null},{"id":"W2160937459","doi":"10.1177/0013164406288161","title":"Confidence Interval Coverage for Cohen's Effect Size Statistic","year":2006,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":62,"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 Manitoba","funders":"","keywords":"Statistics; Confidence interval; Percentile; Statistic; Mathematics; Sample size determination; Coverage probability; Population; Robust confidence intervals; Truncated mean; Econometrics; Medicine","score_opus":0.24095559011322293,"score_gpt":0.46794666524031703,"score_spread":0.2269910751270941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160937459","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":[0.025072908,0.00017753446,0.969767,0.0013362796,0.00041963573,0.00059865875,0.00008356532,0.000027245393,0.0025172075],"genre_scores_gemma":[0.75415164,0.0000063641905,0.24457732,0.00026798062,0.00022103275,0.0002706592,0.000008859582,0.000009474693,0.00048663685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99870735,0.0001460001,0.00028811107,0.0003304374,0.00031711435,0.00021100396],"domain_scores_gemma":[0.99501705,0.004502312,0.00008584469,0.00012617542,0.00017675667,0.000091865484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086944253,0.00015247372,0.00023398057,0.000016446946,0.0001128298,0.00003122111,0.00008309371,0.000054015058,0.00028354328],"category_scores_gemma":[0.0033215536,0.00010939759,0.00005282411,0.0000415813,0.00009378977,0.000036963844,0.00001392421,0.00009579843,0.000007064588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016776133,0.000484753,0.00019750107,0.00010271059,0.000017945793,0.0000011088074,0.000029676836,0.0000045131364,0.0012667971,0.9768467,0.010862784,0.010017772],"study_design_scores_gemma":[0.00065628544,0.0005407867,0.016361713,0.000045899254,0.000030182013,0.0000082586275,0.000006584885,0.0000516735,0.0000991089,0.9799551,0.0020973338,0.0001471147],"about_ca_topic_score_codex":0.000008709344,"about_ca_topic_score_gemma":0.000004415031,"teacher_disagreement_score":0.72907877,"about_ca_system_score_codex":0.00005319736,"about_ca_system_score_gemma":0.000021020656,"threshold_uncertainty_score":0.44611043},"labels":[],"label_agreement":null},{"id":"W2161220067","doi":"10.1177/0013164404272499","title":"Can Percentiles Replace Raw Scores in the Statistical Analysis of Test Data?","year":2005,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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 British Columbia; Carleton University","funders":"","keywords":"Percentile; Raw score; Statistics; Nonparametric statistics; Percentile rank; Statistical power; Raw data; Mathematics; Statistical hypothesis testing; Test (biology); Statistical analysis; Econometrics","score_opus":0.4758787201349256,"score_gpt":0.5112399896517614,"score_spread":0.035361269516835825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161220067","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":[0.39437512,0.0010786492,0.553256,0.042661708,0.00027466594,0.0010443047,0.0012394283,0.00003248477,0.006037647],"genre_scores_gemma":[0.82881385,0.000033877215,0.17062682,0.00034586468,0.00006971044,0.000026086622,0.0000441534,0.000003393402,0.000036264777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99848586,0.0002157754,0.0003550275,0.00032917364,0.00046322355,0.0001509233],"domain_scores_gemma":[0.9967351,0.0026315197,0.000080075704,0.00039443033,0.0000947977,0.00006410906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015669713,0.00010003988,0.00023127947,0.00006734143,0.00005675368,0.000016520862,0.00024408351,0.000037217113,0.0003733293],"category_scores_gemma":[0.0036299003,0.00005904876,0.000029702867,0.00024045518,0.00013825788,0.000036676814,0.000034580164,0.00012611094,0.0000017382038],"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":[0.000116003524,0.0054579866,0.033016477,0.00006903438,0.0002482361,0.0000028793788,0.001612336,0.0001374205,0.0004350853,0.89126706,0.013933948,0.05370356],"study_design_scores_gemma":[0.0002758304,0.0001252069,0.5989844,0.000026778229,0.0002709099,0.000004813936,0.00024773134,0.0014557474,0.000008755646,0.39701208,0.0014595039,0.00012823354],"about_ca_topic_score_codex":0.000024434168,"about_ca_topic_score_gemma":0.0002600079,"teacher_disagreement_score":0.5659679,"about_ca_system_score_codex":0.00002985641,"about_ca_system_score_gemma":0.000027407876,"threshold_uncertainty_score":0.43455917},"labels":[],"label_agreement":null},{"id":"W2166456938","doi":"10.1177/0013164406292089","title":"A Test of the Age-Based Measurement Invariance and Temporal Stability of Antonovsky's Sense of Coherence Scale","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Health, psychology, and well-being","field":"Health Professions","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Measurement invariance; Structural equation modeling; Psychology; Scale (ratio); Stability (learning theory); Population; Test (biology); Statistics; Developmental psychology; Mathematics; Demography; Confirmatory factor analysis; Geography; Computer science","score_opus":0.26464359229387174,"score_gpt":0.4371949212201265,"score_spread":0.17255132892625474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166456938","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":[0.9869743,0.00047788897,0.00038530552,0.005089591,0.00057671167,0.0008859834,0.000022489547,0.000008186495,0.005579518],"genre_scores_gemma":[0.99741536,0.000028811004,0.0013000823,0.0010862696,0.000100448546,0.00004035313,0.000002428306,0.000006068803,0.000020180894],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99710137,0.00062120263,0.00091315666,0.0003464271,0.0007194176,0.00029840684],"domain_scores_gemma":[0.9974397,0.00081370363,0.00046048776,0.0003568181,0.0007875617,0.00014173277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007325362,0.00014164415,0.0003219963,0.00005077264,0.00022945537,0.0000024859678,0.00013876778,0.00017471958,0.00020255249],"category_scores_gemma":[0.0011935163,0.000092789305,0.000054259264,0.00023050123,0.0005190454,0.000029179366,0.00003414217,0.00036409302,0.0000023163414],"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":[0.00025513343,0.0016928677,0.9577019,0.00048883655,0.000016691361,4.42172e-7,0.0016056529,4.7953466e-7,0.032839652,0.00085839984,0.0006665252,0.003873423],"study_design_scores_gemma":[0.0008469713,0.00033362213,0.9913112,0.00037095326,0.000016081907,0.000001873393,0.00046481207,0.0000022595705,0.0023324045,0.0034425883,0.0007895829,0.00008768457],"about_ca_topic_score_codex":0.0003208688,"about_ca_topic_score_gemma":0.00039747765,"teacher_disagreement_score":0.03360927,"about_ca_system_score_codex":0.00009786906,"about_ca_system_score_gemma":0.00038818968,"threshold_uncertainty_score":0.37838382},"labels":[],"label_agreement":null},{"id":"W2168109053","doi":"10.1177/0013164413492419","title":"Effectiveness of Combining Statistical Tests and Effect Sizes When Using Logistic Discriminant Function Regression to Detect Differential Item Functioning for Polytomous Items","year":2013,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":43,"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":"Statistics; Differential item functioning; Polytomous Rasch model; Discriminant function analysis; Sample size determination; Mathematics; Logistic regression; Linear discriminant analysis; Psychology; Statistical hypothesis testing; Econometrics; Psychometrics; Item response theory","score_opus":0.5320350509278347,"score_gpt":0.4801596014508845,"score_spread":0.051875449476950164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168109053","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":[0.7450351,0.00034898665,0.25248644,0.00017984022,0.0011492791,0.0006821795,0.000009389906,0.000014879931,0.00009390678],"genre_scores_gemma":[0.97647905,0.0000045876955,0.02311096,0.00004264078,0.00013863112,0.00018877257,0.0000056611943,0.000009192694,0.000020528118],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965783,0.000995175,0.00057625014,0.0006816829,0.00088083587,0.00028775865],"domain_scores_gemma":[0.96487254,0.033960678,0.00025463512,0.0002200931,0.0004835558,0.00020850831],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004952921,0.00021501699,0.00045910996,0.00025510843,0.0003139445,0.0001738374,0.00017225055,0.00009801979,0.00018420485],"category_scores_gemma":[0.051269073,0.0001256745,0.00006770079,0.000361326,0.00014456484,0.0001099424,0.00008164125,0.00013277646,0.0000059327913],"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":[0.0021564967,0.000564463,0.3081382,0.00033645576,0.00009710169,9.382959e-7,0.0002681679,0.00010837487,0.18882313,0.002678513,0.0016174507,0.4952107],"study_design_scores_gemma":[0.0007151644,0.002334883,0.9229598,0.0002352608,0.000046708614,0.000015587893,0.00010788087,0.00070518366,0.0003875064,0.07228404,0.000046731224,0.00016121854],"about_ca_topic_score_codex":0.00007661951,"about_ca_topic_score_gemma":0.0000020679827,"teacher_disagreement_score":0.6148217,"about_ca_system_score_codex":0.000057897752,"about_ca_system_score_gemma":0.000027442196,"threshold_uncertainty_score":0.9567225},"labels":[],"label_agreement":null},{"id":"W2309234137","doi":"10.1177/0013164415596421","title":"Improving the Factor Structure of Psychological Scales","year":2015,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":58,"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":"Likert scale; Psychology; Scale (ratio); Confirmatory factor analysis; Exploratory factor analysis; Acquiescence; Guttman scale; Psychometrics; Social psychology; Statistics; Clinical psychology; Structural equation modeling; Developmental psychology; Mathematics","score_opus":0.17015467455922587,"score_gpt":0.3575145933061743,"score_spread":0.18735991874694843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2309234137","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":[0.9787708,0.0017581407,0.00012578009,0.009052657,0.0030384474,0.0002936782,0.00003848308,0.000024973093,0.0068970323],"genre_scores_gemma":[0.99726164,0.000020403277,0.00030506524,0.0012913393,0.00069224235,0.000017181186,0.000013449411,0.000007246496,0.00039143447],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99823916,0.0001542081,0.00035219573,0.00041091637,0.0005958862,0.00024760718],"domain_scores_gemma":[0.99913603,0.00007285228,0.00013629548,0.00021317851,0.00023792172,0.0002037009],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035076388,0.0001812745,0.00018799742,0.000041924162,0.00013976125,0.000027424227,0.00024183225,0.00012512598,0.0012608477],"category_scores_gemma":[0.00013130289,0.00010069045,0.000078617304,0.00016189745,0.00023588247,0.00003809835,0.0000369101,0.00023177735,0.000056662426],"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":[0.0014953939,0.011458821,0.26764184,0.00012083056,0.0004132916,0.0000071684112,0.007830977,0.000009526429,0.02467436,0.25988352,0.19447374,0.2319905],"study_design_scores_gemma":[0.00066708156,0.0002517314,0.97367954,0.000029050016,0.000010405898,0.000033137007,0.00034067305,8.976442e-7,0.000047463625,0.019147567,0.0056300615,0.00016238925],"about_ca_topic_score_codex":0.000021500442,"about_ca_topic_score_gemma":0.0000075958424,"teacher_disagreement_score":0.7060377,"about_ca_system_score_codex":0.000042791835,"about_ca_system_score_gemma":0.000034172226,"threshold_uncertainty_score":0.99965215},"labels":[],"label_agreement":null},{"id":"W2329897787","doi":"10.1177/0013164415618240","title":"The Impact of Ignoring the Level of Nesting Structure in Nonparametric Multilevel Latent Class Models","year":2015,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nesting (process); Nonparametric statistics; Latent class model; Class (philosophy); Econometrics; Multilevel model; Statistics; Structural equation modeling; Mathematics; Psychology; Computer science; Artificial intelligence; Engineering","score_opus":0.6967470229892968,"score_gpt":0.4920068167406266,"score_spread":0.20474020624867023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2329897787","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":[0.87138057,0.00053007295,0.124647066,0.0013214885,0.00028853788,0.00042230744,0.000057416142,0.000005955923,0.0013465765],"genre_scores_gemma":[0.9266747,0.000010338185,0.07322375,0.00001548453,0.000044575983,0.000016638165,6.418963e-7,0.0000036839624,0.000010146408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987261,0.00019649699,0.00036558896,0.00014724467,0.00041645442,0.00014809208],"domain_scores_gemma":[0.99753773,0.0017437552,0.0001622875,0.00016407158,0.00032141697,0.00007071382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014116177,0.00010058639,0.0001748773,0.000039657876,0.000057211004,0.000016000198,0.00016931107,0.000049674734,0.00002381458],"category_scores_gemma":[0.0035523768,0.000044136734,0.00004531997,0.00020593118,0.0001265406,0.000027851613,0.000027780328,0.00015963255,4.1049574e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021068793,0.0012540201,0.05123694,0.00007329946,0.0000945276,7.9382187e-7,0.0017953247,0.0007550431,0.0016599689,0.79279286,0.001613484,0.14851306],"study_design_scores_gemma":[0.00019173652,0.00010393159,0.33603066,0.00003590965,0.00000659733,0.0000037086584,0.00007914141,0.001989823,0.00004075438,0.66146994,0.0000035139701,0.000044288612],"about_ca_topic_score_codex":0.00011553794,"about_ca_topic_score_gemma":0.000012397722,"teacher_disagreement_score":0.28479373,"about_ca_system_score_codex":0.00006268565,"about_ca_system_score_gemma":0.000087567394,"threshold_uncertainty_score":0.42527834},"labels":[],"label_agreement":null},{"id":"W2406198090","doi":"10.1177/0013164416651116","title":"Multidimensional Extension of Multiple Indicators Multiple Causes Models to Detect DIF","year":2016,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","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 Alberta","funders":"","keywords":"Differential item functioning; Item response theory; Type I and type II errors; Statistics; Statistical power; Sample size determination; Context (archaeology); Correlation; Mathematics; Econometrics; Psychometrics","score_opus":0.16975496614616864,"score_gpt":0.3494013428645477,"score_spread":0.17964637671837907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406198090","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":[0.13320446,0.00012733681,0.8630716,0.0029849205,0.00019738686,0.00025577834,0.000013855086,0.000075822594,0.00006878404],"genre_scores_gemma":[0.6457766,0.00001885306,0.35379976,0.00029458728,0.00002857285,0.00006215786,7.977504e-7,0.0000046297314,0.000013992328],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99816996,0.000083759136,0.00033039667,0.000568315,0.0006170517,0.00023049096],"domain_scores_gemma":[0.998426,0.0005811085,0.00009263586,0.00036811002,0.00030030104,0.00023182036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042039817,0.00015622149,0.0001826585,0.00013230076,0.00008321844,0.000010855181,0.00030391966,0.00006772664,0.000026684205],"category_scores_gemma":[0.0009513221,0.000095136355,0.000042931606,0.00019807092,0.00009752422,0.00015347383,0.00014538903,0.00007656603,0.000015980866],"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":[0.0002899514,0.0018849637,0.0072001023,0.000031422776,0.000053084925,0.000004887745,0.0004981621,0.0005207825,0.35894284,0.21035226,0.0037159214,0.4165056],"study_design_scores_gemma":[0.0015124499,0.0011732136,0.29659298,0.00037165743,0.000014202424,0.000022996479,0.000016749062,0.0066794516,0.035428517,0.655746,0.0017283086,0.0007135021],"about_ca_topic_score_codex":0.000013646632,"about_ca_topic_score_gemma":0.0000059613567,"teacher_disagreement_score":0.51257217,"about_ca_system_score_codex":0.00006688434,"about_ca_system_score_gemma":0.00004463078,"threshold_uncertainty_score":0.3879548},"labels":[],"label_agreement":null},{"id":"W2467932880","doi":"10.1177/0013164416654740","title":"An Unbiased Estimate of Global Interrater Agreement","year":2016,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; University of Ottawa","funders":"","keywords":"Inter-rater reliability; Statistics; Agreement; Econometrics; Psychology; Mathematics; Rating scale; Linguistics","score_opus":0.40228873007278076,"score_gpt":0.47602807594491,"score_spread":0.07373934587212921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467932880","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":[0.9668057,0.00016877758,0.0062217433,0.02041754,0.0008634564,0.0002825336,0.000031291645,0.000014046925,0.005194914],"genre_scores_gemma":[0.9975572,0.000011789124,0.0016178658,0.00047623247,0.00012474941,0.000040532104,0.0000017642567,0.00000279572,0.00016704097],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99566996,0.00036404424,0.00076895545,0.00063515257,0.0023242258,0.00023767653],"domain_scores_gemma":[0.99799365,0.00023398563,0.00022089656,0.0005532801,0.00077174685,0.00022644755],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00468477,0.00016850828,0.00024208507,0.000048808477,0.000097328986,0.0000705069,0.00053024787,0.00006647132,0.0040821107],"category_scores_gemma":[0.0012375994,0.0000809371,0.00008718234,0.00023945885,0.00024096154,0.0001792417,0.000049381568,0.000053947435,0.00022056495],"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":[0.0004415165,0.0051180273,0.60805285,0.000017311946,0.0000770604,0.0000015019536,0.00024916933,0.000024598812,0.060346335,0.030824706,0.026554117,0.26829278],"study_design_scores_gemma":[0.00054767285,0.0005817458,0.8357299,0.00006297764,0.000010246678,0.0000039890397,0.000090140544,0.000010932419,0.00066665065,0.15925543,0.0029006568,0.00013966886],"about_ca_topic_score_codex":0.000012254346,"about_ca_topic_score_gemma":0.000025491332,"teacher_disagreement_score":0.2681531,"about_ca_system_score_codex":0.00013589315,"about_ca_system_score_gemma":0.000059725386,"threshold_uncertainty_score":0.9968283},"labels":[],"label_agreement":null},{"id":"W2529050713","doi":"10.1177/0013164416667987","title":"Perspectives on the Use of Null Hypothesis Statistical Testing. Part II: Is Null Hypothesis Statistical Testing an Irregular Bulk of Masonry?","year":2016,"lang":"en","type":"editorial","venue":"Educational and Psychological Measurement","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Null hypothesis; Statistical hypothesis testing; Null (SQL); Alternative hypothesis; Statistical analysis; Statistics; Null distribution; Mathematics; Econometrics; Test statistic; Computer science; Data mining","score_opus":0.2622178999809283,"score_gpt":0.3365527785065162,"score_spread":0.0743348785255879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529050713","genre_codex":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3195367,0.004762767,0.05179797,0.033234704,0.5096802,0.010965406,0.051029928,0.0012506316,0.017741714],"genre_scores_gemma":[0.1993807,0.00037208412,0.5447418,0.00035476172,0.2527202,0.001377837,0.0001533905,0.0002505508,0.0006486906],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674183,0.00030505276,0.00067387917,0.0007044799,0.0012043582,0.00037038134],"domain_scores_gemma":[0.9819037,0.016231606,0.00023664365,0.00057113316,0.00082562264,0.0002312968],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007904292,0.00043454728,0.0005807303,0.00007500121,0.00020410265,0.00005419316,0.00035456472,0.00031905554,0.00070882123],"category_scores_gemma":[0.01321015,0.00027341853,0.00009478856,0.00023821485,0.00047046898,0.000056692268,0.000046426918,0.0005006337,0.000028752162],"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":[0.00011946701,0.0030006338,0.00013073556,0.00021799111,0.0002697921,0.0000013354396,0.0004258205,0.000054315537,0.0046556816,0.02460037,0.89861363,0.067910224],"study_design_scores_gemma":[0.0013664453,0.0044196835,0.14437212,0.0018771233,0.00076355645,0.00001085341,0.00040169628,0.00059672404,0.00084644585,0.2107119,0.63233715,0.0022962983],"about_ca_topic_score_codex":0.000031371255,"about_ca_topic_score_gemma":0.0000012822135,"teacher_disagreement_score":0.49294382,"about_ca_system_score_codex":0.000106049716,"about_ca_system_score_gemma":0.00011458263,"threshold_uncertainty_score":0.9999718},"labels":[],"label_agreement":null},{"id":"W2529333171","doi":"10.1177/0013164416667986","title":"Perspectives on the Use of Null Hypothesis Statistical Testing. Part I: The Mighty Frames of Scientific and Statistical Inference","year":2016,"lang":"en","type":"editorial","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Statistical hypothesis testing; Statistical inference; Null hypothesis; Inference; Statistical analysis; Null (SQL); Alternative hypothesis; Fiducial inference; Econometrics; Psychology; Statistics; Frequentist inference; Mathematics; Computer science; Artificial intelligence; Bayesian inference; Data mining; Bayesian probability","score_opus":0.544732837323388,"score_gpt":0.4694654802050009,"score_spread":0.07526735711838706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529333171","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":[0.014146925,0.0021570548,0.665699,0.014923956,0.28083616,0.0035287843,0.01621111,0.00007504428,0.002421942],"genre_scores_gemma":[0.091276795,0.0005414139,0.828192,0.00019430283,0.07831951,0.00045686698,0.000053112508,0.00007225807,0.0008937201],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965229,0.0006666275,0.00058201724,0.00062737375,0.0013469649,0.00025412708],"domain_scores_gemma":[0.9198746,0.07822229,0.0003459986,0.00042242877,0.0010093724,0.00012527232],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018324038,0.00028372745,0.00046979293,0.000049689585,0.00025128023,0.00008256268,0.00024640997,0.00021499734,0.00037844386],"category_scores_gemma":[0.09830331,0.00012445646,0.00004866549,0.000110938076,0.00199185,0.000039826315,0.00006775415,0.0004743858,0.000003838309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013239634,0.0007774366,0.000046811256,0.00011231118,0.00006749789,5.8914867e-7,0.00030968428,4.825467e-7,0.000081339,0.5349152,0.44997436,0.013581898],"study_design_scores_gemma":[0.00021985055,0.0005311177,0.004028664,0.0004454435,0.00011257502,0.0000014760873,0.000112401074,0.000017089254,0.000017471439,0.91639954,0.0778984,0.00021597267],"about_ca_topic_score_codex":0.000009667599,"about_ca_topic_score_gemma":0.000003567729,"teacher_disagreement_score":0.38148436,"about_ca_system_score_codex":0.000049303722,"about_ca_system_score_gemma":0.00019228391,"threshold_uncertainty_score":0.90929204},"labels":[],"label_agreement":null},{"id":"W2529752630","doi":"10.1177/0013164416667988","title":"Perspectives on the Use of Null Hypothesis Statistical Testing. Part III: The Various Nuts and Bolts of Statistical and Hypothesis Testing","year":2016,"lang":"en","type":"editorial","venue":"Educational and Psychological Measurement","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Statistical hypothesis testing; Nuts and bolts; Null hypothesis; Statistical analysis; Alternative hypothesis; Null (SQL); Statistics; One- and two-tailed tests; Econometrics; Statistical power; Mathematics; Null distribution; Computer science; Test statistic; Data mining; Geometry","score_opus":0.14158344641718815,"score_gpt":0.28863508568802093,"score_spread":0.14705163927083278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529752630","genre_codex":"editorial","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":[0.26141995,0.019153707,0.010219361,0.017195376,0.6569485,0.008862891,0.009553107,0.0006447204,0.016002377],"genre_scores_gemma":[0.93396634,0.00036063927,0.0032751227,0.00008561886,0.061845448,0.00026263803,0.0000059361428,0.000046159566,0.00015209499],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979875,0.000256682,0.0004595028,0.00038313132,0.0007046755,0.00020852679],"domain_scores_gemma":[0.9790804,0.020084023,0.00015535302,0.00022441523,0.0003481071,0.00010769593],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007436612,0.00026969876,0.00038646554,0.000052339572,0.00014601229,0.00006641727,0.00012687,0.00020653846,0.00008313418],"category_scores_gemma":[0.013028647,0.00013765687,0.00003414462,0.00009844651,0.00040258575,0.00002912369,0.000022053211,0.000340742,0.0000040108894],"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":[0.00037744248,0.0006630391,0.00059332506,0.00030890637,0.00048004306,0.0000029810003,0.00091010396,0.000039775303,0.0013099969,0.005806394,0.9030238,0.086484216],"study_design_scores_gemma":[0.0049135643,0.004657561,0.37538305,0.0033880977,0.0009730124,0.00011866832,0.0017964336,0.0024054127,0.00013713849,0.03579057,0.5680765,0.0023599965],"about_ca_topic_score_codex":0.00006768348,"about_ca_topic_score_gemma":0.000007910281,"teacher_disagreement_score":0.6725464,"about_ca_system_score_codex":0.000061632294,"about_ca_system_score_gemma":0.000060560982,"threshold_uncertainty_score":0.99528503},"labels":[],"label_agreement":null},{"id":"W2568498297","doi":"10.1177/0013164416685599","title":"Retrofitting Diagnostic Classification Models to Responses From IRT-Based Assessment Forms","year":2017,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":55,"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":"Retrofitting; Item response theory; Computer science; Process (computing); Test (biology); Data mining; Engineering; Psychometrics; Mathematics; Statistics","score_opus":0.8783454710157835,"score_gpt":0.5694813197426731,"score_spread":0.3088641512731104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568498297","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":[0.86764574,0.00025236793,0.07320807,0.039226193,0.0014848049,0.00039822143,0.000031739626,0.00003583509,0.017717028],"genre_scores_gemma":[0.9380841,0.000015451546,0.060038634,0.0012141044,0.00030008695,0.00013956142,0.000006445977,0.0000069805533,0.00019460451],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957938,0.00049650716,0.0006600329,0.0008731709,0.0018827635,0.00029368428],"domain_scores_gemma":[0.97738063,0.020171879,0.0004968618,0.0010541525,0.00061107066,0.0002853962],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008993718,0.00018131237,0.0002833432,0.00022468477,0.000899116,0.00066762883,0.0009590128,0.000101481375,0.00042725386],"category_scores_gemma":[0.12659203,0.00011709404,0.000084957865,0.0003042845,0.00012449107,0.00023981175,0.000116172385,0.00019974861,0.00006889915],"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":[0.00023515623,0.0008246595,0.6559843,0.0000054352085,0.000031657633,0.0000027948975,0.0002034041,0.00018193609,0.0029831678,0.021024294,0.011818968,0.30670422],"study_design_scores_gemma":[0.0002782426,0.00016624843,0.79165953,0.000037541915,0.0000073885835,0.0000012310269,0.00017754298,0.000883112,0.00003165029,0.2050371,0.0015834254,0.00013697294],"about_ca_topic_score_codex":0.00006475648,"about_ca_topic_score_gemma":0.0000111033505,"teacher_disagreement_score":0.30656725,"about_ca_system_score_codex":0.00011523829,"about_ca_system_score_gemma":0.00011241763,"threshold_uncertainty_score":0.8807651},"labels":[],"label_agreement":null},{"id":"W2758319537","doi":"10.1177/0013164417719111","title":"Recommendations on the Sample Sizes for Multilevel Latent Class Models","year":2017,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":93,"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":"Latent class model; Sample size determination; Statistics; Sample (material); Rule of thumb; Nested set model; Computer science; Model selection; Econometrics; Data mining; Mathematics; Algorithm","score_opus":0.4657980968857349,"score_gpt":0.4110614061339838,"score_spread":0.05473669075175114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758319537","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":[0.00090321485,0.00006229416,0.8258319,0.16864838,0.00068179396,0.00029396,0.000015385918,0.000014341689,0.003548719],"genre_scores_gemma":[0.6427089,0.000034681107,0.35352576,0.0030580235,0.0001857965,0.00026979804,0.0000032732685,0.0000036718354,0.0002101295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99903244,0.00008753361,0.00014969266,0.00033682943,0.00023256535,0.00016091237],"domain_scores_gemma":[0.9986386,0.00050821464,0.00009706865,0.00051846396,0.00015595816,0.0000817043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009958328,0.000103753126,0.00009412987,0.000019593515,0.0008100831,0.00021982667,0.0005848045,0.000046488407,0.000055202883],"category_scores_gemma":[0.00046604022,0.00005898724,0.0000568991,0.000021782655,0.00006113881,0.0001328984,0.00005893615,0.00010074649,0.0000065701706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009863841,0.00025237058,0.000034567678,0.0000022970842,0.000011634513,4.1167418e-8,0.00012069426,0.0000063449143,0.0000720485,0.8193682,0.01352469,0.16659723],"study_design_scores_gemma":[0.00026966288,0.00012984339,0.025609717,0.000023633886,0.000005034115,0.000001867537,0.0000050695603,0.008538443,0.00006374146,0.95115304,0.014083711,0.000116213196],"about_ca_topic_score_codex":0.000009636351,"about_ca_topic_score_gemma":0.0000037386503,"teacher_disagreement_score":0.64180565,"about_ca_system_score_codex":0.000027519074,"about_ca_system_score_gemma":0.000030499,"threshold_uncertainty_score":0.6230586},"labels":[],"label_agreement":null},{"id":"W2904094333","doi":"10.1177/0013164418817801","title":"Centering in Multiple Regression Does Not Always Reduce Multicollinearity: How to Tell When Your Estimates Will Not Benefit From Centering","year":2018,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":24,"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":"Multicollinearity; Independence (probability theory); Regression; Econometrics; Correlation; Regression analysis; Statistics; Context (archaeology); Joint probability distribution; Linear regression; Mathematics; Random variable; Psychology","score_opus":0.4401330808779662,"score_gpt":0.45631741001503445,"score_spread":0.016184329137068243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904094333","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":[0.7580072,0.00006980141,0.23011817,0.009957203,0.000910658,0.0005304268,0.00016333142,0.00004689193,0.00019631122],"genre_scores_gemma":[0.55223364,0.0000134007605,0.44698256,0.00030282114,0.00029687476,0.000061975465,0.0000074822774,0.000012062281,0.00008915065],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99814177,0.00008707026,0.0003660934,0.00061392266,0.00044977968,0.0003413644],"domain_scores_gemma":[0.99850464,0.00068223383,0.00010556186,0.00025585736,0.00020883924,0.00024285178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055505196,0.0002398547,0.00030881268,0.00006649254,0.00019736972,0.00007175517,0.00017986962,0.00010424022,0.00022695556],"category_scores_gemma":[0.0025787444,0.00015887778,0.00004509485,0.00007319733,0.00008912567,0.00011689706,0.000102460406,0.00019659914,0.000010735073],"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":[0.0026115424,0.005733672,0.023533238,0.00025732408,0.00014203764,0.000018772418,0.0063826083,0.00007118119,0.74710953,0.033278763,0.003004601,0.17785674],"study_design_scores_gemma":[0.0024186987,0.00066033285,0.12978621,0.0013638438,0.000053096537,0.000010925946,0.0005371365,0.0041424953,0.054614488,0.7998605,0.0056628305,0.0008894669],"about_ca_topic_score_codex":0.0000459015,"about_ca_topic_score_gemma":0.00006389268,"teacher_disagreement_score":0.7665817,"about_ca_system_score_codex":0.00010771587,"about_ca_system_score_gemma":0.00001427016,"threshold_uncertainty_score":0.64788485},"labels":[],"label_agreement":null},{"id":"W2912880345","doi":"10.1177/0013164419829855","title":"Item Response Tree Models to Investigate Acquiescence and Extreme Response Styles in Likert-Type Rating Scales","year":2019,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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 British Columbia","funders":"","keywords":"Acquiescence; Psychology; Likert scale; Rating scale; Item response theory; Social psychology; Explanatory model; Scale (ratio); Psychometrics; Statistics; Developmental psychology; Mathematics","score_opus":0.7658315465227954,"score_gpt":0.4754891438004715,"score_spread":0.29034240272232387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912880345","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":[0.9806734,0.001268786,0.00048745607,0.015228469,0.0005318762,0.00037954934,0.0000036968634,0.000023802188,0.0014029617],"genre_scores_gemma":[0.97766954,0.00003598116,0.020057576,0.0014590727,0.00007116534,0.000034373865,7.394071e-7,0.0000075883386,0.00066395395],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99459946,0.0020998768,0.00070328,0.00092365936,0.0013216933,0.00035203845],"domain_scores_gemma":[0.9777385,0.020907745,0.00018337913,0.00044445347,0.00041189004,0.0003140045],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020367742,0.00020834063,0.00034326,0.0005136818,0.00014896784,0.00020200684,0.00043640914,0.00010592473,0.00019676384],"category_scores_gemma":[0.07539219,0.00014229825,0.000041515777,0.0015436438,0.00014544431,0.00021254118,0.00014607381,0.00020493782,0.000071364244],"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":[0.012252368,0.0007334612,0.7199343,0.000022084116,0.000024270359,0.000009036084,0.002987203,0.0004888008,0.12055857,0.0044619157,0.0080885375,0.13043948],"study_design_scores_gemma":[0.00042959917,0.00052879023,0.95204425,0.000092418275,0.000002373401,0.000017339034,0.001022192,0.0004757549,0.000088696965,0.04367717,0.0014187994,0.00020264281],"about_ca_topic_score_codex":0.000017110107,"about_ca_topic_score_gemma":0.000018075165,"teacher_disagreement_score":0.23210993,"about_ca_system_score_codex":0.00007438178,"about_ca_system_score_gemma":0.00009923058,"threshold_uncertainty_score":0.9323962},"labels":[],"label_agreement":null},{"id":"W2921505365","doi":"10.1177/0013164419834607","title":"Comparing Age- and Grade-Based Norms on the Woodcock–Johnson III Normative Update","year":2019,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Medical Education and Admissions","field":"Medicine","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":"Queen's University","funders":"","keywords":"Woodcock; Normative; Psychology; Developmental psychology; Statistics; Mathematics; Epistemology; Philosophy","score_opus":0.20948185716706838,"score_gpt":0.37079014919839487,"score_spread":0.1613082920313265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921505365","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":[0.8241476,0.0002527386,0.00003373111,0.15965371,0.00043934528,0.0004285384,0.0000016198405,0.0000171979,0.01502554],"genre_scores_gemma":[0.9752794,0.000049646664,0.00024610347,0.023455434,0.00016389388,0.000056228193,0.000021111346,0.0000050513295,0.00072313176],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9988141,0.000078126584,0.00020078354,0.00025657975,0.0004932211,0.00015717171],"domain_scores_gemma":[0.99901867,0.0001752605,0.00006115329,0.00018130583,0.00009289427,0.0004707454],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004762381,0.00012545437,0.00017715525,0.000048070804,0.00014693226,0.000027606628,0.00007069946,0.00005473819,0.0043481495],"category_scores_gemma":[0.00045862643,0.00006417257,0.00003910386,0.000111200105,0.00011017004,0.000023834824,0.000014421262,0.00027775764,0.00015550714],"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":[0.0022959267,0.02091114,0.19757876,0.0005231567,0.00047840073,0.00002016152,0.0055926032,0.000036430447,0.011871837,0.1748484,0.5429956,0.042847607],"study_design_scores_gemma":[0.0016770504,0.0004598754,0.9194391,0.00025941312,0.00002975506,0.000017437678,0.0004097112,0.00010271842,0.00015159229,0.0029806856,0.07432063,0.00015206863],"about_ca_topic_score_codex":0.0000071548584,"about_ca_topic_score_gemma":0.0000017516682,"teacher_disagreement_score":0.7218603,"about_ca_system_score_codex":0.00004382631,"about_ca_system_score_gemma":0.00012837505,"threshold_uncertainty_score":0.996562},"labels":[],"label_agreement":null},{"id":"W2941810097","doi":"10.1177/0013164419844305","title":"A Measurement Is a Choice and Stevens’ Scales of Measurement Do Not Help Make It: A Response to Chalmers","year":2019,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":51,"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":"Relevance (law); Confusion; Reliability (semiconductor); Task (project management); Psychology; Test (biology); Epistemology; Measure (data warehouse); Computer science; Philosophy; Psychoanalysis; Data mining; Economics","score_opus":0.4019735413709748,"score_gpt":0.46501596832292,"score_spread":0.06304242695194523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941810097","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":[0.8654582,0.0019629293,0.074543394,0.050391905,0.00093878753,0.0028994477,0.0001212043,0.00005439824,0.0036297555],"genre_scores_gemma":[0.9303914,0.000039154602,0.06733705,0.0017511874,0.00009553604,0.00017818066,7.38716e-7,0.000020471629,0.00018633992],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99571645,0.0004668012,0.0006232193,0.0007218259,0.0021025215,0.0003692013],"domain_scores_gemma":[0.9974847,0.00057435443,0.00018716995,0.00040186525,0.000986611,0.00036533803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005523759,0.00030085244,0.00048022298,0.00011474983,0.00010753549,0.00003501314,0.00017365301,0.000109445224,0.00029880527],"category_scores_gemma":[0.0035066635,0.00023171896,0.000086099455,0.00017304507,0.00011335172,0.000048590413,0.00007331889,0.00018734626,0.000024443352],"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":[0.011111347,0.011679055,0.010958944,0.0023659903,0.0010666955,0.000008094775,0.008864738,0.0000381653,0.42041537,0.22200553,0.026668362,0.28481773],"study_design_scores_gemma":[0.005245067,0.0045076814,0.5077362,0.0021748424,0.00024780122,0.00005365024,0.001456012,0.00007509607,0.004758426,0.4365331,0.03566463,0.0015475146],"about_ca_topic_score_codex":0.000009675781,"about_ca_topic_score_gemma":0.000018497629,"teacher_disagreement_score":0.49677724,"about_ca_system_score_codex":0.0002109827,"about_ca_system_score_gemma":0.000095377574,"threshold_uncertainty_score":0.9449225},"labels":[],"label_agreement":null},{"id":"W2978741138","doi":"10.1177/0013164419878861","title":"A Propensity Score Method for Investigating Differential Item Functioning in Performance Assessment","year":2019,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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":"Propensity score matching; Differential item functioning; Matching (statistics); Context (archaeology); Psychology; Proxy (statistics); Language proficiency; Aptitude; Set (abstract data type); Test (biology); Computer science; Psychometrics; Statistics; Natural language processing; Cognitive psychology; Item response theory; Machine learning; Developmental psychology; Mathematics; Mathematics education","score_opus":0.7918302834411759,"score_gpt":0.5152538123684256,"score_spread":0.2765764710727503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978741138","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":[0.96294296,0.00009228509,0.028875984,0.002306052,0.0014334372,0.0006194682,0.0000023359232,0.0000162645,0.0037111999],"genre_scores_gemma":[0.91398185,0.000005432166,0.08498016,0.000394821,0.0001832243,0.00012794166,0.0000035587364,0.000005118826,0.00031790035],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996895,0.00045508705,0.00059889053,0.000694811,0.0010831986,0.0002730183],"domain_scores_gemma":[0.9924827,0.006486253,0.00025280457,0.00026402014,0.0003992723,0.00011491624],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008982325,0.00014854893,0.00031122615,0.00022672406,0.00018812247,0.00015195916,0.00028145185,0.000077231074,0.0005146002],"category_scores_gemma":[0.015745478,0.00009559405,0.00006526914,0.00069003506,0.00004837473,0.0001399267,0.00007072685,0.00022765719,0.000017786266],"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":[0.00004068296,0.00019853181,0.89448565,0.00001800246,0.000008313528,8.898317e-8,0.000080550664,0.0000769228,0.0022882249,0.0016939376,0.00058374554,0.10052537],"study_design_scores_gemma":[0.00056374364,0.0003063206,0.9732747,0.00006251464,0.000004813251,0.000007357346,0.0001216014,0.003625702,0.000045814108,0.02100385,0.0008487372,0.00013481437],"about_ca_topic_score_codex":0.000013064756,"about_ca_topic_score_gemma":0.0000044994613,"teacher_disagreement_score":0.10039056,"about_ca_system_score_codex":0.000086678985,"about_ca_system_score_gemma":0.00007842275,"threshold_uncertainty_score":0.9925453},"labels":[],"label_agreement":null},{"id":"W3006067352","doi":"10.1177/0013164420903770","title":"The Role of Item Distributions on Reliability Estimation: The Case of Cronbach’s Coefficient Alpha","year":2020,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","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 British Columbia","funders":"","keywords":"Cronbach's alpha; Alpha (finance); Reliability (semiconductor); Random variable; Bounded function; Range (aeronautics); Code (set theory); Mathematics; Correlation coefficient; Applied mathematics; Computer science; Statistics; Discrete mathematics; Mathematical analysis; Physics; Psychometrics","score_opus":0.18206716658744782,"score_gpt":0.4010203161917416,"score_spread":0.2189531496042938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006067352","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":[0.4237261,0.00089577993,0.36764503,0.19488242,0.00031746316,0.0020634762,0.0013672549,0.000077960074,0.009024528],"genre_scores_gemma":[0.99771124,0.000008063186,0.0018999059,0.00018676865,0.000038981474,0.00011686735,0.000024201503,0.0000030168512,0.000010959205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886423,0.00012497997,0.00041186184,0.00018663092,0.0003085692,0.00010373208],"domain_scores_gemma":[0.99743646,0.0016987904,0.000170304,0.00023112482,0.00036430464,0.00009903152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005661449,0.000090759204,0.00011802765,0.000008208937,0.0003407011,0.000018956987,0.00013823697,0.000035708144,0.00016683858],"category_scores_gemma":[0.0040021525,0.00004859024,0.000054191063,0.00019205602,0.00033838098,0.000016262944,0.000022153346,0.00011376358,0.000012790549],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032608026,0.0006880193,0.000106356296,0.000014520436,0.00001277224,2.5552478e-7,0.00014170061,0.00004492588,0.000113022674,0.98409545,0.0063433326,0.008407051],"study_design_scores_gemma":[0.00051786756,0.00044254144,0.08398382,0.000037021164,0.00008536026,0.0000511788,0.00097227417,0.013109755,0.0010570885,0.8869734,0.012584866,0.00018485359],"about_ca_topic_score_codex":0.0000058762835,"about_ca_topic_score_gemma":0.000001989111,"teacher_disagreement_score":0.57398516,"about_ca_system_score_codex":0.000036409267,"about_ca_system_score_gemma":0.000040325544,"threshold_uncertainty_score":0.47912398},"labels":[],"label_agreement":null},{"id":"W3011484504","doi":"10.1177/0013164420911136","title":"Evaluating the Performances of Missing Data Handling Methods in Ability Estimation From Sparse Data","year":2020,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":79,"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":"Missing data; Imputation (statistics); Statistics; Cart; Data set; Regression; Mean squared error; Mathematics; Computer science; Regression analysis; Data mining; Engineering","score_opus":0.9728668887097844,"score_gpt":0.6848813766788585,"score_spread":0.2879855120309259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011484504","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":[0.77417326,0.0038595607,0.18871535,0.031227242,0.0007960083,0.00031966218,0.0000668081,0.000014520455,0.0008275712],"genre_scores_gemma":[0.58206,0.000018802491,0.41742325,0.00032239588,0.00014105071,0.0000051265974,0.000025828524,0.0000019239465,0.0000016321445],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995159,0.0016832638,0.0008591573,0.00085482793,0.0012891844,0.00015458126],"domain_scores_gemma":[0.9725879,0.025044374,0.00048813707,0.0014783576,0.00028937042,0.000111886424],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034227863,0.00010897554,0.00027378552,0.000068505775,0.00016486029,0.000117738804,0.0017610884,0.000049172486,0.00038912054],"category_scores_gemma":[0.19343059,0.00005919431,0.000023899705,0.000880895,0.00014556624,0.00029063175,0.0004866393,0.00020808633,0.0000062951767],"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":[0.00006719087,0.00014168471,0.055705838,0.000007987333,0.000010923625,1.3980345e-7,0.0004956385,0.00039277933,0.0021936726,0.00007479744,0.0007508764,0.9401585],"study_design_scores_gemma":[0.00024494663,0.00012189699,0.7066829,0.00003916008,0.00001452093,0.0000018449863,0.00049203116,0.23140287,0.000055214532,0.06028666,0.0005731066,0.0000848261],"about_ca_topic_score_codex":0.00007103551,"about_ca_topic_score_gemma":0.000005508873,"teacher_disagreement_score":0.94007367,"about_ca_system_score_codex":0.000018250435,"about_ca_system_score_gemma":0.0000888725,"threshold_uncertainty_score":0.99446565},"labels":[],"label_agreement":null},{"id":"W3131054533","doi":"10.1177/0013164421991211","title":"A Polytomous Scoring Approach to Handle Not-Reached Items in Low-Stakes Assessments","year":2021,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":27,"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":"Polytomous Rasch model; Test (biology); Psychology; Item response theory; Statistics; Psychometrics; Clinical psychology; Mathematics","score_opus":0.8074745264456583,"score_gpt":0.5362121694680764,"score_spread":0.27126235697758194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131054533","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":[0.93713295,0.000837971,0.011574955,0.004665763,0.0013810436,0.00027592535,0.0000067758424,0.000024406467,0.044100188],"genre_scores_gemma":[0.9603879,0.000015673659,0.03720906,0.0011900639,0.00022839507,0.00009169724,0.000004428037,0.000006149796,0.0008666293],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99588376,0.0005463748,0.0006411288,0.00091100374,0.0016660233,0.00035171985],"domain_scores_gemma":[0.9958897,0.0028805498,0.00013734675,0.00041161253,0.00043231816,0.00024845425],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062339017,0.00016906967,0.00032284716,0.0003166229,0.00014134067,0.0002513652,0.0003967074,0.00008678187,0.0003079576],"category_scores_gemma":[0.024780631,0.000119123935,0.00006979623,0.0017942928,0.00004971071,0.000100435085,0.000101123864,0.00021799983,0.000052279123],"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":[0.00026299368,0.0068651913,0.60213363,0.000039150185,0.00006509469,0.000019086287,0.0015204219,0.00034724153,0.015980277,0.009870173,0.010394881,0.35250184],"study_design_scores_gemma":[0.00047189937,0.000118640775,0.9807056,0.000050966966,0.0000041791145,0.00003056945,0.0008993396,0.00010445661,0.00026864008,0.014523715,0.0026331772,0.00018879495],"about_ca_topic_score_codex":0.000033230805,"about_ca_topic_score_gemma":0.000009581437,"teacher_disagreement_score":0.378572,"about_ca_system_score_codex":0.00009613525,"about_ca_system_score_gemma":0.00010268258,"threshold_uncertainty_score":0.9834341},"labels":[],"label_agreement":null},{"id":"W3162676432","doi":"10.1177/00131644211014261","title":"On the Performance of Semi- and Nonparametric Item Response Functions in Computer Adaptive Tests","year":2021,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computerized adaptive testing; Nonparametric statistics; Item response theory; Monotonic function; Parametric statistics; Selection (genetic algorithm); Statistics; Smoothing; Polynomial; Kernel (algebra); Mathematics; Function (biology); Differential item functioning; Sample (material); Computer science; Econometrics; Psychometrics; Artificial intelligence","score_opus":0.622595515931154,"score_gpt":0.4554608671959295,"score_spread":0.16713464873522454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162676432","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":[0.9896255,0.0006333599,0.0009820742,0.006915492,0.0004413631,0.0001077567,0.000003852081,0.0000044074495,0.0012861973],"genre_scores_gemma":[0.99457425,0.00003106523,0.004560649,0.0005937269,0.0000579684,0.000020695326,5.0279283e-7,0.000001992055,0.0001591387],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997507,0.00084376225,0.0003647408,0.0003788627,0.0007762909,0.00012938354],"domain_scores_gemma":[0.96394956,0.03525796,0.00012446489,0.00023803907,0.00036997927,0.00005997715],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006843746,0.00008755823,0.00016639222,0.0002377645,0.00011574148,0.000046187102,0.00015901077,0.00004705945,0.0002884709],"category_scores_gemma":[0.04094793,0.000047124497,0.00003251239,0.0017038857,0.00011478594,0.000042124477,0.000052019055,0.00016629374,0.000014020501],"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":[0.0011291389,0.0017933481,0.7719322,0.000010119425,0.00003712654,0.0000042892552,0.0004903547,0.00048765272,0.0018990113,0.0076980917,0.012308722,0.20220995],"study_design_scores_gemma":[0.0001961106,0.0004682621,0.9856955,0.0000345504,0.0000025709842,0.00001843871,0.0001719621,0.00061193964,0.000056810226,0.0122923115,0.00039156404,0.000060023915],"about_ca_topic_score_codex":0.0000030595845,"about_ca_topic_score_gemma":0.0000020803163,"teacher_disagreement_score":0.21376325,"about_ca_system_score_codex":0.000027924209,"about_ca_system_score_gemma":0.000054688324,"threshold_uncertainty_score":0.9671306},"labels":[],"label_agreement":null},{"id":"W3181535716","doi":"10.1177/00131644211023569","title":"The Importance of Thinking Multivariately When Setting Subscale Cutoff Scores","year":2021,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","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 British Columbia","funders":"","keywords":"Counterintuitive; Cutoff; Test (biology); Psychology; Mathematics; Value (mathematics); Econometrics; Psychometrics; Property (philosophy); Process (computing); Cognitive psychology; Statistics; Computer science; Epistemology","score_opus":0.1154940239194557,"score_gpt":0.335637612308858,"score_spread":0.22014358838940234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181535716","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":[0.18871115,0.010561527,0.56526923,0.21577072,0.0027662134,0.00097343227,0.000034239856,0.0004212847,0.015492195],"genre_scores_gemma":[0.8717427,0.00009614215,0.12692338,0.00094448443,0.0000908536,0.00005687463,0.000008892345,0.0000036238362,0.00013302962],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986185,0.00012536805,0.00028203466,0.00033407402,0.00049060833,0.00014944612],"domain_scores_gemma":[0.9987624,0.0002279764,0.00015323947,0.00043699355,0.00036844343,0.000050914627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010066108,0.00008445328,0.00009210178,0.000020456995,0.00023784056,0.000106180094,0.0004948961,0.000040664887,0.000037394177],"category_scores_gemma":[0.0004901616,0.000055450248,0.000032461987,0.00015380279,0.00008603011,0.00013569939,0.000110346526,0.00011372554,0.0000050966305],"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":[0.000014506218,0.0005885706,0.0801587,0.00002113916,0.0000349354,0.000002234899,0.0008780784,0.0000016798473,0.016977688,0.83888346,0.018091043,0.044347957],"study_design_scores_gemma":[0.00015563464,0.0000459229,0.7286816,0.000049762984,0.000003856598,0.000020945314,0.000060125258,0.00011977054,0.007573583,0.2554416,0.007719437,0.00012774098],"about_ca_topic_score_codex":0.000003886345,"about_ca_topic_score_gemma":0.0000075214525,"teacher_disagreement_score":0.68303156,"about_ca_system_score_codex":0.000035797566,"about_ca_system_score_gemma":0.00008852758,"threshold_uncertainty_score":0.22611955},"labels":[],"label_agreement":null},{"id":"W4205671165","doi":"10.1177/00131644211069406","title":"Effects of Response Option Order on Likert-Type Psychometric Properties and Reactions","year":2022,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Psychology; Item response theory; Equivalence (formal languages); Likert scale; Valence (chemistry); Psychometrics; Statistics; Econometrics; Social psychology; Cognitive psychology; Clinical psychology; Developmental psychology; Mathematics","score_opus":0.4480482305994032,"score_gpt":0.380515059367472,"score_spread":0.0675331712319312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205671165","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":[0.9823012,0.005284495,0.000017444168,0.007540274,0.0019284176,0.00047719697,0.000007783278,0.000032179316,0.0024110295],"genre_scores_gemma":[0.99644166,0.00016487662,0.00014751148,0.00085262314,0.00010914595,0.00050765194,0.0000041088842,0.000009595687,0.001762801],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978597,0.00060134626,0.00031642758,0.00050098106,0.0004976636,0.0002238663],"domain_scores_gemma":[0.9990863,0.0003166582,0.00012553262,0.00018414533,0.0001766229,0.000110732464],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008765614,0.00018202458,0.00022082064,0.00018570687,0.0004005652,0.000015496144,0.00012563613,0.000077887315,0.0014643287],"category_scores_gemma":[0.000333156,0.00012734067,0.000047382662,0.000683166,0.00018047413,0.0000299978,0.00005344726,0.00031278373,0.00004167688],"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":[0.062482715,0.072099365,0.14167935,0.0004010764,0.001051039,0.000036416965,0.009513748,0.00005156256,0.17588036,0.07525282,0.12233829,0.33921328],"study_design_scores_gemma":[0.0008830947,0.0037594289,0.959358,0.000025274485,0.000033608638,0.000036916073,0.00031706213,5.518771e-7,0.00006279442,0.0023727014,0.032971036,0.00017954013],"about_ca_topic_score_codex":0.00003825482,"about_ca_topic_score_gemma":9.3967697e-7,"teacher_disagreement_score":0.81767863,"about_ca_system_score_codex":0.0000611709,"about_ca_system_score_gemma":0.000016314967,"threshold_uncertainty_score":0.9994485},"labels":[],"label_agreement":null},{"id":"W4213257957","doi":"10.1177/0013164411430486","title":"Erratum","year":2011,"lang":"en","type":"erratum","venue":"Educational and Psychological Measurement","topic":"Psychological and Temporal Perspectives Research","field":"Psychology","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":"Psychology","score_opus":0.34380546116296895,"score_gpt":0.42857137976583604,"score_spread":0.08476591860286709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213257957","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":[0.0006716329,0.01746622,0.000023269184,0.006344909,0.049512595,0.00054123596,0.000054978806,0.000095221825,0.9252899],"genre_scores_gemma":[0.09598975,0.0010014134,0.00027455264,0.0021852986,0.007121929,0.0007843952,0.00024865524,0.00007380086,0.8923202],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954989,0.00043665722,0.0005684129,0.0015802813,0.0011178917,0.00079785474],"domain_scores_gemma":[0.99795806,0.000097686236,0.00023089536,0.0007401312,0.0004356295,0.0005375665],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009416424,0.0005854125,0.00058837817,0.00023425846,0.00025339428,0.000081730504,0.0006828838,0.0010663229,0.046140704],"category_scores_gemma":[0.00024213857,0.00042021298,0.00024190747,0.00033377908,0.0005452869,0.000060393555,0.00012741625,0.0021247524,0.0031204815],"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":[0.00018353389,0.0028309384,0.00044126326,0.00003094715,0.00020577427,0.000022785947,0.00042841918,6.4499295e-9,0.00001603549,0.037242085,0.9496117,0.008986476],"study_design_scores_gemma":[0.00040392092,0.0007606575,0.24678484,0.00007950515,0.00003329017,0.000064941836,0.00014992284,1.385699e-7,4.582128e-7,0.07977683,0.67147076,0.0004747429],"about_ca_topic_score_codex":0.00012514956,"about_ca_topic_score_gemma":0.000013426942,"teacher_disagreement_score":0.278141,"about_ca_system_score_codex":0.00015454629,"about_ca_system_score_gemma":0.00012694215,"threshold_uncertainty_score":0.99982494},"labels":[],"label_agreement":null},{"id":"W4241133324","doi":"10.1177/0013164408318769","title":"Invariance of the Measurement Model Underlying the Wechsler Adult Intelligence Scale—III in the United States and Canada","year":2008,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":19,"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 Calgary; BC Mental Health & Substance Use Services; University of British Columbia","funders":"","keywords":"Measurement invariance; Psychology; Normative; Latent variable; Statistics; Wechsler Adult Intelligence Scale; Latent variable model; Psychometrics; Test (biology); Item response theory; Sample (material); Level of measurement; Scale (ratio); Structural equation modeling; Confirmatory factor analysis; Intelligence quotient; Set (abstract data type); Developmental psychology; Mathematics; Cognition","score_opus":0.774923581148864,"score_gpt":0.45804181837841057,"score_spread":0.3168817627704534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241133324","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":[0.96222126,0.0007389672,0.0045650764,0.029871343,0.00041380667,0.00034085818,0.000005527182,0.000004234898,0.0018388983],"genre_scores_gemma":[0.9947783,0.0003060373,0.0012929233,0.0034996686,0.00002763794,0.00004115962,6.9669665e-7,0.0000027746923,0.000050808372],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958607,0.0006781541,0.0005608786,0.0003682035,0.0023231697,0.00020889378],"domain_scores_gemma":[0.9942394,0.004319829,0.00023925022,0.0004255618,0.0007146728,0.000061306026],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007498812,0.00012756891,0.00017472502,0.00010612731,0.0004578927,0.00006990846,0.0008071734,0.00004294246,0.000044169556],"category_scores_gemma":[0.011314486,0.00005164614,0.00003720569,0.0012218592,0.00036664694,0.000046701243,0.000076788405,0.00025650876,9.1845874e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005817134,0.002728,0.60254395,0.000066747045,0.00017558994,0.000007137921,0.03024107,0.0353913,0.0015205914,0.05160478,0.115647614,0.15949148],"study_design_scores_gemma":[0.00018102667,0.000052931195,0.8781536,0.000045605895,0.000007049359,0.00002423589,0.003622827,0.0033897357,0.000030163477,0.11315146,0.0012346548,0.00010670043],"about_ca_topic_score_codex":0.06767186,"about_ca_topic_score_gemma":0.07233101,"teacher_disagreement_score":0.27560964,"about_ca_system_score_codex":0.000094466515,"about_ca_system_score_gemma":0.00026293856,"threshold_uncertainty_score":0.9970136},"labels":[],"label_agreement":null},{"id":"W4280512083","doi":"10.1177/00131644221096431","title":"Investigating Confidence Intervals of Item Parameters When Some Item Parameters Take Priors in the 2PL and 3PL Models","year":2022,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Prior probability; Statistics; Covariance; Mathematics; Marginal likelihood; Standard error; Maximum a posteriori estimation; Restricted maximum likelihood; Confidence interval; Maximization; Econometrics; Estimation theory; Bayesian probability; Maximum likelihood; Mathematical optimization","score_opus":0.7746316401685195,"score_gpt":0.4702359430135424,"score_spread":0.3043956971549771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280512083","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":[0.98511964,0.0018402857,0.0008312443,0.010600177,0.0005452365,0.00037517658,0.0000115426965,0.000010250942,0.0006664614],"genre_scores_gemma":[0.97977746,0.000040009527,0.017461604,0.002493347,0.000035332832,0.00014311963,0.0000019140934,0.0000047691265,0.000042419782],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946089,0.0017463363,0.0008830011,0.000637042,0.0018579947,0.00026677235],"domain_scores_gemma":[0.97878104,0.02004546,0.0004731324,0.00039338897,0.00018303085,0.00012396321],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014992902,0.00016609456,0.00033732684,0.00028774372,0.00025263015,0.00013276079,0.00076303375,0.000050983894,0.00015560084],"category_scores_gemma":[0.033697523,0.00010132279,0.0000762804,0.0008384688,0.00031142333,0.00018015526,0.00017340796,0.0003550547,0.0000019877266],"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":[0.00023467712,0.002024971,0.6112234,0.000080849124,0.00012788101,0.000009019919,0.030685198,0.003942939,0.0034168414,0.0716163,0.015133082,0.26150483],"study_design_scores_gemma":[0.0003095533,0.00035247408,0.42479387,0.000042608957,0.0000088082115,0.00003338373,0.006246823,0.0009158573,0.000027968323,0.56667495,0.0004472166,0.00014648198],"about_ca_topic_score_codex":0.00007540542,"about_ca_topic_score_gemma":0.0000047174863,"teacher_disagreement_score":0.49505866,"about_ca_system_score_codex":0.0000527837,"about_ca_system_score_gemma":0.000057721656,"threshold_uncertainty_score":0.97444206},"labels":[],"label_agreement":null},{"id":"W4288758431","doi":"10.1177/00131644221104220","title":"Supervised Classes, Unsupervised Mixing Proportions: Detection of Bots in a Likert-Type Questionnaire","year":2022,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mahalanobis distance; Cutoff; Sample (material); Statistics; Likert scale; Computer science; Calibration; Sample size determination; Mixture model; Artificial intelligence; Mathematics","score_opus":0.26873442613628207,"score_gpt":0.39222254678309215,"score_spread":0.12348812064681008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288758431","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":[0.9930046,0.0006488898,0.0027558007,0.002031524,0.00044594333,0.00051220367,0.00002065914,0.000099561265,0.00048082246],"genre_scores_gemma":[0.99281573,0.000021795498,0.0065687075,0.00010686591,0.000046460427,0.00035479298,0.000028165749,0.000008481312,0.000049014696],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984796,0.00028097315,0.0003989543,0.00024624937,0.00046556507,0.00012866585],"domain_scores_gemma":[0.9992567,0.00019596113,0.00011640697,0.00015320841,0.00022780607,0.000049956412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014335747,0.00010382205,0.00015654086,0.00013877903,0.00017205007,0.000012788474,0.00009768427,0.00004895828,0.0008092291],"category_scores_gemma":[0.0011921774,0.00009280968,0.000037781432,0.00036285506,0.0000442143,0.00005229746,0.000029213263,0.0001877497,0.0000024844765],"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":[0.002614918,0.03839879,0.36395493,0.0016836012,0.00035091452,0.000015858035,0.009824151,0.0003757777,0.14080848,0.09760879,0.052325018,0.29203877],"study_design_scores_gemma":[0.0008792763,0.0010020375,0.6636363,0.00026616163,0.000027385382,0.00005106574,0.0006229338,0.0004660399,0.0013644062,0.32880208,0.0025055353,0.00037674588],"about_ca_topic_score_codex":0.000056310077,"about_ca_topic_score_gemma":0.000029421213,"teacher_disagreement_score":0.2996814,"about_ca_system_score_codex":0.00013866684,"about_ca_system_score_gemma":0.000075936856,"threshold_uncertainty_score":0.8860491},"labels":[],"label_agreement":null},{"id":"W4292454731","doi":"10.1177/00131644221111402","title":"Comparing the Psychometric Properties of a Scale Across Three Likert and Three Alternative Formats: An Application to the Rosenberg Self-Esteem Scale","year":2022,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"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 British Columbia; York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Likert scale; Scale (ratio); Psychology; Acquiescence; Psychometrics; Computer science; Statistics; Clinical psychology; Mathematics","score_opus":0.591184351862449,"score_gpt":0.45387219246827853,"score_spread":0.13731215939417046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292454731","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":[0.9779297,0.0017751893,0.007975584,0.009972205,0.00068857084,0.00078893185,0.000014563971,0.000025375724,0.00082988775],"genre_scores_gemma":[0.9951015,0.00002672862,0.0033231962,0.00081094896,0.0001980831,0.00049852143,0.0000016809445,0.000006980927,0.000032345255],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99604917,0.0005336209,0.0006255085,0.0006173582,0.0018815403,0.0002928206],"domain_scores_gemma":[0.99674594,0.0017151909,0.00034031452,0.0006231512,0.0004328222,0.0001425498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010270857,0.00016913941,0.00027794982,0.0001887728,0.0011151234,0.00020199463,0.0010873383,0.00003749097,0.0000613215],"category_scores_gemma":[0.002605751,0.00008082662,0.00006370349,0.0021125332,0.0001937653,0.00014712945,0.00036815283,0.00027278278,0.0000098052205],"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":[0.00030191784,0.0018111689,0.6910167,0.000016888824,0.000062741245,1.5629739e-7,0.007792927,0.0007335208,0.0014972468,0.0018559487,0.0024653976,0.2924454],"study_design_scores_gemma":[0.00029115545,0.00043989194,0.96248525,0.000011238328,0.000010642204,0.000029495588,0.0030856687,0.0014810095,0.000055523156,0.02649871,0.0054790545,0.00013235639],"about_ca_topic_score_codex":0.0001230757,"about_ca_topic_score_gemma":0.00022022164,"teacher_disagreement_score":0.29231304,"about_ca_system_score_codex":0.000067689616,"about_ca_system_score_gemma":0.000033088,"threshold_uncertainty_score":0.85767406},"labels":[],"label_agreement":null},{"id":"W4321330224","doi":"10.1177/00131644231155804","title":"The Impact of Measurement Model Misspecification on Coefficient Omega Estimates of Composite Reliability","year":2023,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Omega; Statistics; Reliability (semiconductor); Mathematics; Econometrics; Scale (ratio); Population; Factor analysis; Composite index; Hierarchical database model; Computer science; Physics; Thermodynamics; Demography; Data mining; Composite indicator","score_opus":0.7526933176330004,"score_gpt":0.5302071217753532,"score_spread":0.22248619585764717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321330224","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":[0.9833092,0.00057841645,0.0061979233,0.0045854147,0.000490271,0.00037015407,0.000020462876,0.000027818583,0.0044203154],"genre_scores_gemma":[0.99677193,0.000074178315,0.0029869552,0.000031013224,0.000044048786,0.00003463157,0.0000028982795,0.00000445835,0.00004989232],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9954539,0.0003919173,0.0008555696,0.00047883106,0.002588518,0.00023125112],"domain_scores_gemma":[0.98896104,0.008310819,0.000455873,0.0005967426,0.0015598639,0.0001156689],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015923006,0.00014768315,0.00028514175,0.00021525029,0.00024132397,0.000055055905,0.00051286095,0.000057795412,0.00005803184],"category_scores_gemma":[0.039014056,0.00007235716,0.00016005035,0.0013736675,0.0002544428,0.000036835947,0.000055143053,0.00012480891,0.000023081742],"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":[0.0018076261,0.007374702,0.29549968,0.00006804936,0.00026130117,8.026783e-7,0.0014435269,0.1672411,0.07724416,0.026172886,0.10040194,0.32248423],"study_design_scores_gemma":[0.00021794262,0.00039686152,0.87487763,0.00003247514,0.000006602136,0.0000013399334,0.00010997382,0.009941641,0.00045286625,0.11369736,0.00018477312,0.000080561964],"about_ca_topic_score_codex":0.000017748744,"about_ca_topic_score_gemma":7.2654734e-7,"teacher_disagreement_score":0.57937795,"about_ca_system_score_codex":0.00011724166,"about_ca_system_score_gemma":0.00009104267,"threshold_uncertainty_score":0.96908075},"labels":[],"label_agreement":null},{"id":"W4378220707","doi":"10.1177/00131644231165520","title":"The Accuracy of Bayesian Model Fit Indices in Selecting Among Multidimensional Item Response Theory Models","year":2023,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision 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":"McGill University","funders":"","keywords":"Curse of dimensionality; Nested set model; Deviance information criterion; Bayesian probability; Item response theory; Statistics; Bayesian information criterion; Computer science; Mathematics; Econometrics; Bayesian inference; Data mining; Psychometrics","score_opus":0.7180011966789275,"score_gpt":0.5115401562574108,"score_spread":0.2064610404215167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378220707","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":[0.98656976,0.0005475775,0.004657246,0.0061954604,0.00038982581,0.00022976089,0.0000054340594,0.000025566824,0.0013793798],"genre_scores_gemma":[0.9950299,0.000060155722,0.0042201187,0.00021428376,0.000056138437,0.000057729783,0.0000011307201,0.000005704479,0.00035482424],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99526614,0.0015899941,0.00076584576,0.00051529985,0.0015489646,0.000313745],"domain_scores_gemma":[0.92431265,0.07451524,0.00035820733,0.0003234392,0.00038367088,0.00010680149],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033753507,0.00013762357,0.00022747666,0.0004037244,0.0003423304,0.000076383476,0.0004799435,0.00008811115,0.00007409475],"category_scores_gemma":[0.13423745,0.00007556276,0.000073150906,0.0019417796,0.00020311681,0.00015600638,0.0001087669,0.00024115978,0.000010825334],"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":[0.0037242302,0.0014483021,0.47417554,0.000024233801,0.0001051602,0.00000752765,0.0055283713,0.06979506,0.0051349415,0.070539236,0.019744718,0.3497727],"study_design_scores_gemma":[0.00020682527,0.00006301989,0.6286461,0.000028522638,0.0000024775977,0.000002911229,0.0007493426,0.04117201,0.000026461355,0.3288742,0.00014860446,0.000079551886],"about_ca_topic_score_codex":0.00001190186,"about_ca_topic_score_gemma":0.000010142141,"teacher_disagreement_score":0.34969312,"about_ca_system_score_codex":0.00004232831,"about_ca_system_score_gemma":0.00010527906,"threshold_uncertainty_score":0.9949541},"labels":[],"label_agreement":null},{"id":"W4388140417","doi":"10.1177/00131644231202949","title":"Comparing RMSEA-Based Indices for Assessing Measurement Invariance in Confirmatory Factor Models","year":2023,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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":"York University","funders":"","keywords":"Structural equation modeling; Confirmatory factor analysis; Mathematics; Goodness of fit; Statistics","score_opus":0.9282427079429465,"score_gpt":0.5543654165441689,"score_spread":0.37387729139877757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388140417","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":[0.9347901,0.0010865417,0.048337452,0.007699773,0.0019406482,0.0007530217,0.0000146997545,0.000095104806,0.005282701],"genre_scores_gemma":[0.9898903,0.000014055745,0.009096093,0.0005831067,0.0001556268,0.00021281437,0.00000510135,0.000008370866,0.000034557524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9953379,0.0004935041,0.0007831517,0.0007400192,0.0022366408,0.00040880954],"domain_scores_gemma":[0.9921908,0.0063786656,0.0003024663,0.00030728488,0.0006512982,0.00016950656],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013993557,0.00019045633,0.00037542733,0.0005678244,0.0002572484,0.0002998393,0.0004941294,0.00010225235,0.00013893096],"category_scores_gemma":[0.02272173,0.00013594676,0.000085629945,0.0014480755,0.000097597345,0.00024312137,0.00005408397,0.00019587151,0.00002928321],"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":[0.00024310275,0.0014651378,0.8307145,0.00010556007,0.00006048222,0.0000046144964,0.0009188183,0.0061347275,0.0034590296,0.012275587,0.017682029,0.12693639],"study_design_scores_gemma":[0.00077007787,0.00007291818,0.88264036,0.00008748665,0.0000044623025,0.0000017222519,0.00037162757,0.008063969,0.000047565063,0.105673514,0.0020794913,0.00018682107],"about_ca_topic_score_codex":0.00001956253,"about_ca_topic_score_gemma":0.00001836127,"teacher_disagreement_score":0.12674958,"about_ca_system_score_codex":0.00014762382,"about_ca_system_score_gemma":0.0001702269,"threshold_uncertainty_score":0.9855103},"labels":[],"label_agreement":null},{"id":"W4406779237","doi":"10.1177/00131644241308528","title":"A Comparison of the Next Eigenvalue Sufficiency Test to Other Stopping Rules for the Number of Factors in Factor Analysis","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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":"Université TÉLUQ","funders":"","keywords":"Curse of dimensionality; Exploratory factor analysis; Statistics; Mathematics; Test (biology); Eigenvalues and eigenvectors; Sample (material); Computer science; Identification (biology); Hull; Factor (programming language); Algorithm; Psychometrics; Engineering","score_opus":0.7892882399583666,"score_gpt":0.5763748813874294,"score_spread":0.21291335857093718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406779237","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":[0.98106676,0.00048721407,0.011769974,0.0040275,0.00049336936,0.00034590758,0.000026399499,0.000003040176,0.0017798134],"genre_scores_gemma":[0.99672085,0.000004135899,0.002855303,0.00022195924,0.000023633147,0.000034547687,4.3928267e-7,0.0000016707749,0.00013748967],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978908,0.00024994955,0.0006447368,0.00031174166,0.00075848075,0.00014433819],"domain_scores_gemma":[0.9801772,0.018841805,0.00025476416,0.0003372872,0.00035233548,0.000036600948],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034076837,0.0000938237,0.00031134248,0.0002438046,0.00013278014,0.000041190553,0.0005979179,0.00004614795,0.00034241067],"category_scores_gemma":[0.041079074,0.000040634226,0.00015274648,0.0026956133,0.00011173182,0.000027219354,0.000060527218,0.00008909927,0.0000019000447],"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":[0.000015870377,0.00046240963,0.98393613,0.0000042783604,0.00004103419,4.284838e-9,0.0005440089,0.00015701875,0.00063241704,0.002754586,0.00053681177,0.010915437],"study_design_scores_gemma":[0.000109033106,0.000045431145,0.9860746,0.000020825766,0.00003156988,1.03727224e-7,0.001541307,0.00018134816,0.00015823527,0.010484605,0.001305158,0.000047728998],"about_ca_topic_score_codex":0.00008247871,"about_ca_topic_score_gemma":0.000035138597,"teacher_disagreement_score":0.03767139,"about_ca_system_score_codex":0.000030799503,"about_ca_system_score_gemma":0.00005177184,"threshold_uncertainty_score":0.96699834},"labels":[],"label_agreement":null},{"id":"W4407928271","doi":"10.1177/00131644251319047","title":"Shortening Psychological Scales: Semantic Similarity Matters","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","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":"University of Alberta","funders":"","keywords":"Similarity (geometry); Sentence; Semantic similarity; Scale (ratio); Computer science; Natural language processing; Sample (material); Artificial intelligence; Embedding; Correlation; Information retrieval; Mathematics","score_opus":0.6635170864862416,"score_gpt":0.5275220275597801,"score_spread":0.13599505892646158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407928271","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":[0.759869,0.0025673837,0.06129149,0.11446027,0.005202896,0.00059770915,0.000010885766,0.0001384848,0.05586191],"genre_scores_gemma":[0.97600085,0.000051089955,0.015218386,0.007644137,0.00017794794,0.000056597855,0.0000026868083,0.000005075284,0.00084322976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99565524,0.00065781776,0.0008245712,0.0010659363,0.0013931545,0.00040326157],"domain_scores_gemma":[0.9921536,0.006434592,0.00018756608,0.00056176644,0.0004642158,0.0001983021],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00783861,0.00023309265,0.00039648573,0.0004035595,0.00037368556,0.00025648423,0.00073129724,0.00016762014,0.0010992244],"category_scores_gemma":[0.021034056,0.00014825634,0.00014160456,0.0015640837,0.00027925638,0.00010343034,0.00013450641,0.00035483117,0.00009916684],"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":[0.00015834553,0.001835996,0.42708433,0.000027072721,0.00007493682,0.0000065455715,0.00012342165,0.000025490906,0.0012898165,0.021281336,0.24013582,0.30795687],"study_design_scores_gemma":[0.00030649104,0.00012462701,0.787795,0.000045357123,0.000012111469,0.000021479738,0.0002035467,0.00006445942,0.0000124420485,0.20212162,0.009130483,0.00016240907],"about_ca_topic_score_codex":0.000008676394,"about_ca_topic_score_gemma":0.0000033818892,"teacher_disagreement_score":0.36071065,"about_ca_system_score_codex":0.00006525017,"about_ca_system_score_gemma":0.000030093039,"threshold_uncertainty_score":0.9998139},"labels":[],"label_agreement":null},{"id":"W4416195809","doi":"10.1177/00131644251389891","title":"Reliability as Projection in Operator-Theoretic Test Theory: Conditional Expectation, Hilbert Space Geometry, and Implications for Psychometric Practice","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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 British Columbia","funders":"","keywords":"Reliability (semiconductor); Projection (relational algebra); Mathematical proof; Hilbert space; Complement (music); Statistical hypothesis testing; Space (punctuation); Conditional expectation; Perspective (graphical)","score_opus":0.3733883313779877,"score_gpt":0.5068659574544272,"score_spread":0.13347762607643948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416195809","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":[0.7334268,0.004177211,0.081816785,0.14007856,0.0017684805,0.0025692962,0.00006686148,0.000064875036,0.036031134],"genre_scores_gemma":[0.9790429,0.00015350645,0.017885314,0.0015141807,0.00012305488,0.00066619326,0.0000146166585,0.0000059449408,0.00059428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9966762,0.00072557625,0.00071638374,0.00094528217,0.00067791087,0.00025862546],"domain_scores_gemma":[0.95057714,0.047050066,0.00027696564,0.0004145866,0.0015478114,0.0001334011],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012101807,0.00018442587,0.00027800893,0.0009963759,0.00036956207,0.00021354124,0.0002977102,0.00012768533,0.0002456322],"category_scores_gemma":[0.32103285,0.00013252051,0.000061372666,0.0037613162,0.00025048474,0.00023322941,0.000051410807,0.00020457178,0.000013550942],"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":[0.00031641612,0.0021127516,0.4150243,0.00002828673,0.00003305205,1.820009e-7,0.00031305867,0.00001762933,0.0006144523,0.50302887,0.015670482,0.06284052],"study_design_scores_gemma":[0.00041003787,0.00018194487,0.54774636,0.000014484978,0.000011346308,0.000013740486,0.0005551404,0.000016846549,0.000012313065,0.44424412,0.006706484,0.00008720127],"about_ca_topic_score_codex":0.00002137415,"about_ca_topic_score_gemma":0.000003787007,"teacher_disagreement_score":0.30893105,"about_ca_system_score_codex":0.00014692631,"about_ca_system_score_gemma":0.00016170299,"threshold_uncertainty_score":0.68468636},"labels":[],"label_agreement":null},{"id":"W4417427433","doi":"10.1177/00131644251393483","title":"From Linear Geometry to Nonlinear and Information-Geometric Settings in Test Theory: Bregman Projections as a Unifying Framework","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","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":"Bregman divergence; Nonlinear system; Hilbert space; Projection (relational algebra); Regular polygon; Reliability (semiconductor); Statistical hypothesis testing; Space (punctuation); Information geometry","score_opus":0.3273493193826945,"score_gpt":0.4780451314572261,"score_spread":0.1506958120745316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417427433","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":[0.9125359,0.0012527809,0.03357979,0.03878924,0.0014262393,0.00063343265,0.000043721153,0.000051476196,0.011687394],"genre_scores_gemma":[0.903976,0.000076760625,0.08863826,0.006647179,0.0002766061,0.0000971403,0.00000860051,0.0000046630876,0.0002747508],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972195,0.00030925198,0.00071217975,0.0005544957,0.00093757844,0.00026700323],"domain_scores_gemma":[0.97482055,0.023876686,0.00019157269,0.00037294472,0.00055376283,0.0001844526],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006965682,0.0001703374,0.00027901176,0.0018338719,0.00028287838,0.00028233533,0.00037695753,0.00014689563,0.00035503414],"category_scores_gemma":[0.21938342,0.00012111362,0.000045638513,0.0069537843,0.000094729905,0.00030278793,0.00014470425,0.00036421805,0.00008496165],"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":[0.00014418375,0.00092099025,0.46303105,0.000022905408,0.000045467677,0.0000013658318,0.0014034162,0.000057253208,0.00012467502,0.023860395,0.010863899,0.49952438],"study_design_scores_gemma":[0.00026581218,0.00015228173,0.74267113,0.00010731186,0.000007871962,0.000005242238,0.0014758051,0.000065096545,0.000016404601,0.22270276,0.03239162,0.00013865979],"about_ca_topic_score_codex":0.000104383806,"about_ca_topic_score_gemma":0.0000051559127,"teacher_disagreement_score":0.49938574,"about_ca_system_score_codex":0.00007499878,"about_ca_system_score_gemma":0.00010764068,"threshold_uncertainty_score":0.78719205},"labels":[],"label_agreement":null}]}