{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05162802,0.0003749113,0.0008666332,0.0005922845,0.001438226,0.0008681284,0.002778058,0.0002475415,0.00004387714],"category_scores_gemma":[0.1574129,0.0001907311,0.000604486,0.000984287,0.000378894,0.0001728443,0.002294213,0.0006608466,7.301172e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002037774,"about_ca_system_score_gemma":0.0003517904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002098331,"about_ca_topic_score_gemma":0.00004812156,"domain_scores_codex":[0.9931052,0.002029026,0.001651919,0.00116763,0.001479224,0.0005670294],"domain_scores_gemma":[0.6700534,0.3264472,0.001369064,0.001579514,0.0004666036,0.00008418837],"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":[0.01247417,0.0001390195,0.0009310549,0.0002620847,0.0005851378,0.000005068742,0.01071053,0.07331079,0.0009597045,0.8480988,0.02469818,0.02782549],"study_design_scores_gemma":[0.0004104993,0.0002007668,0.0000778955,0.00004375583,0.00003988302,0.000007586921,0.01278464,0.4542351,0.00005779597,0.5278077,0.004167982,0.0001663363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08947357,0.001065103,0.8979254,0.003265182,0.001964434,0.00260198,0.0002456916,0.000074915,0.003383728],"genre_scores_gemma":[0.9545238,0.0003507257,0.04029158,0.0003727729,0.0001054572,0.0008074385,0.00000834051,0.00005720997,0.003482687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8650502,"threshold_uncertainty_score":0.9998618,"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."}}