{"id":"W1991728049","doi":"10.1111/j.1745-3984.2009.00091.x","title":"The Hierarchy Consistency Index: Evaluating Person Fit for Cognitive Diagnostic Assessment","year":2009,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Statistic; Consistency (knowledge bases); Cognition; Hierarchy; Computer science; Item response theory; Goodness of fit; Psychology; Statistics; Cognitive psychology; Artificial intelligence; Mathematics; Machine learning; Psychometrics","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":[0.04028628,0.00142489,0.001466349,0.01138919,0.0009375611,0.002314147,0.001430061,0.001648258,0.001772447],"category_scores_gemma":[0.1837069,0.0004745412,0.002699914,0.005963977,0.001405267,0.003511467,0.002516699,0.001683503,0.000424212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001077442,"about_ca_system_score_gemma":0.001809147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002622323,"about_ca_topic_score_gemma":0.00264546,"domain_scores_codex":[0.9690507,0.0144768,0.003363532,0.002143691,0.01035103,0.0006143017],"domain_scores_gemma":[0.852834,0.1089663,0.01211604,0.01054813,0.01392554,0.001609993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007911876,0.0005154195,0.6703907,0.0005125803,0.00236406,0.0002868977,0.002571625,0.02628441,0.002915663,0.01352655,0.00456242,0.2752784],"study_design_scores_gemma":[0.0003054241,0.003031833,0.5715205,0.0004512722,0.0006600335,0.001472179,0.002647988,0.3432082,0.006256807,0.06007173,0.009700412,0.0006736076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4015845,0.0009301627,0.5818649,0.0004963723,0.0002626381,0.001224219,0.001572083,0.001693899,0.01037121],"genre_scores_gemma":[0.8808327,0.0001649726,0.1162176,0.0001153963,0.0000647169,0.001060524,0.001044006,0.0001872714,0.0003129323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04028628,"threshold_uncertainty_score":0.2130567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1652812041663947,"score_gpt":0.4007072928289228,"score_spread":0.2354260886625281,"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."}}