{"id":"W4399295484","doi":"10.1007/s11336-024-09977-2","title":"The InterModel Vigorish as a Lens for Understanding (and Quantifying) the Value of Item Response Models for Dichotomously Coded Items","year":2024,"lang":"en","type":"article","venue":"Psychometrika","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Jacobs Foundation; Leverhulme Trust","keywords":"Item response theory; Value (mathematics); Computer science; Psychometrics; Statistics; Econometrics; Mathematics","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","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03122411,0.0002688855,0.0005257612,0.001461841,0.000788054,0.001108833,0.001349117,0.0001510038,0.00001247079],"category_scores_gemma":[0.1525028,0.0001379966,0.0004150012,0.005397151,0.0003538592,0.0003772599,0.0001679579,0.0002854938,0.000005543578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001063042,"about_ca_system_score_gemma":0.0001205317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003403075,"about_ca_topic_score_gemma":0.00001296569,"domain_scores_codex":[0.9955651,0.000712048,0.001179524,0.0008567,0.001107727,0.0005788572],"domain_scores_gemma":[0.6946864,0.3036663,0.0003793724,0.000845233,0.0003253244,0.00009733842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.008523574,0.0001507435,0.001812718,0.0002540374,0.0005619668,0.000006199442,0.007686683,0.001390827,0.00476689,0.6612574,0.05422121,0.2593677],"study_design_scores_gemma":[0.0008244172,0.0005203453,0.0006028161,0.0001331376,0.00005510078,0.00002738534,0.005567334,0.3545919,0.0002505862,0.596819,0.04039027,0.0002177237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1475065,0.008243239,0.8343368,0.004104012,0.002690886,0.001336426,0.0001220704,0.0001004867,0.001559561],"genre_scores_gemma":[0.986743,0.0005730536,0.01083564,0.0002158,0.0001605795,0.0001971636,0.000001865864,0.00004594227,0.001226941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8392365,"threshold_uncertainty_score":0.9999281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6941929902442963,"score_gpt":0.5167567847765115,"score_spread":0.1774362054677847,"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."}}