{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06822349,0.003377473,0.002312759,0.01287156,0.001840469,0.008990797,0.004710865,0.003683526,0.00512439],"category_scores_gemma":[0.2588912,0.00145259,0.003352305,0.008172806,0.01055466,0.01176268,0.008864826,0.01294328,0.0007645561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004591252,"about_ca_system_score_gemma":0.002733175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002800541,"about_ca_topic_score_gemma":0.002717043,"domain_scores_codex":[0.9286821,0.05672723,0.001931351,0.004123631,0.007970611,0.0005649857],"domain_scores_gemma":[0.7408563,0.2244359,0.01089183,0.01876505,0.004096928,0.0009540351],"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":[0.0001387751,0.0001455194,0.01522599,0.0006455292,0.0007443209,0.0002562571,0.005555793,0.06020045,0.001471093,0.8008687,0.003140711,0.1116069],"study_design_scores_gemma":[0.00002878158,0.0002260792,0.005120441,0.0004587037,0.00009076324,0.0002530159,0.0007581969,0.1380652,0.001255662,0.8460252,0.007566858,0.0001510968],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01116043,0.001080024,0.9780441,0.001890289,0.000126675,0.0001390599,0.0002664681,0.000379103,0.006913937],"genre_scores_gemma":[0.3022411,0.000796666,0.693521,0.0008577247,0.0002823256,0.0009204251,0.0003280045,0.0002832077,0.0007695542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06822349,"threshold_uncertainty_score":0.3608046,"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."}}