{"id":"W4296169238","doi":"10.31234/osf.io/q3djt","title":"The InterModel Vigorish as a lens for understanding (and quantifying) the value of item response models for dichotomously coded items","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Jacobs Foundation; Leverhulme Trust","keywords":"Value (mathematics); Lens (geology); Computer science; Optics; Physics; Machine learning","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":[0.06385863,0.003495404,0.002321632,0.0120575,0.001914741,0.009290637,0.004545199,0.004109757,0.006003649],"category_scores_gemma":[0.2542094,0.001492723,0.00343474,0.008523395,0.01108777,0.01319158,0.008906125,0.01384753,0.001027683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004490256,"about_ca_system_score_gemma":0.002968303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002677785,"about_ca_topic_score_gemma":0.002483805,"domain_scores_codex":[0.9335698,0.05246679,0.001754003,0.003880205,0.007790416,0.0005386523],"domain_scores_gemma":[0.7489275,0.2149274,0.01085095,0.01989985,0.004373186,0.001021064],"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":[0.000106606,0.0001223422,0.009716785,0.0005211852,0.000533535,0.0002011468,0.00406424,0.04323322,0.001223621,0.8503508,0.002860486,0.08706606],"study_design_scores_gemma":[0.00002433914,0.0001485409,0.003059336,0.0003469043,0.0000675017,0.0001797313,0.0004676739,0.09835699,0.0009986067,0.8897082,0.006538111,0.0001039014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008082087,0.001061963,0.9815117,0.001948024,0.0001160051,0.0001165695,0.0002418817,0.0003418736,0.006580037],"genre_scores_gemma":[0.2533269,0.0009626562,0.7418496,0.001095721,0.000321878,0.0008899168,0.0003498761,0.0003265752,0.0008769617],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06385863,"threshold_uncertainty_score":0.3377208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7894785360017323,"score_gpt":0.5272314517039378,"score_spread":0.2622470842977945,"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."}}