{"id":"W4307097012","doi":"10.31234/osf.io/2hswm","title":"The Accuracy of Bayesian Model Fit Indices in Selecting Among Multidimensional Item Response Theory Models","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Curse of dimensionality; Nested set model; Deviance information criterion; Bayesian probability; Statistics; Bayesian information criterion; Computer science; Mathematics; Econometrics; Bayesian inference; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08064235,0.0003691746,0.0008072144,0.001603481,0.0005887263,0.0002633315,0.002946002,0.00030084,0.0004253298],"category_scores_gemma":[0.3559909,0.0002228574,0.0003324643,0.002859266,0.0002491321,0.0003195599,0.004452301,0.001709071,0.00000282446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001422081,"about_ca_system_score_gemma":0.0006285955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003268239,"about_ca_topic_score_gemma":0.00009045767,"domain_scores_codex":[0.9858357,0.007505068,0.002165267,0.001274989,0.002625221,0.0005937546],"domain_scores_gemma":[0.5638254,0.4316352,0.002221118,0.001765752,0.0004253942,0.0001271036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00096442,0.00006817231,0.02498579,0.00001263391,0.0000407014,0.000009724324,0.001876866,0.9252487,0.00008298154,0.005815946,0.0006041173,0.04028994],"study_design_scores_gemma":[0.0001855293,0.00002756299,0.01975949,0.00004711564,0.000007173511,0.000002588858,0.003370882,0.6753852,0.00006049969,0.3008852,0.00007997403,0.000188767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8364999,0.0007147972,0.1544564,0.0005350118,0.0005969097,0.0005609536,0.00003431002,0.00007445938,0.006527289],"genre_scores_gemma":[0.9330993,0.00007577239,0.06407924,0.0001438796,0.00003246078,0.00009090805,0.000003053905,0.00002771147,0.002447678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4241302,"threshold_uncertainty_score":0.9466721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4788933920804174,"score_gpt":0.4867495426273737,"score_spread":0.007856150546956375,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}