{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004198944,0.0001011866,0.0001303092,0.0001155191,0.0005550703,0.0002334841,0.0004748007,0.00001993072,0.00001366766],"category_scores_gemma":[0.007341212,0.00007000956,0.0001281228,0.0002321692,0.00005754289,0.000413838,0.00002253157,0.000161823,0.000003397437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003027019,"about_ca_system_score_gemma":0.00225328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001706401,"about_ca_topic_score_gemma":0.000003498966,"domain_scores_codex":[0.9977563,0.0001402136,0.0003797745,0.0001721257,0.001314553,0.0002370377],"domain_scores_gemma":[0.9932671,0.002800136,0.0004387652,0.0001203639,0.00325746,0.0001161974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007603015,0.001114014,0.010724,0.00002977175,0.0002356174,0.000004667561,0.003519446,0.0002007189,0.004232158,0.0816862,0.008263847,0.8899136],"study_design_scores_gemma":[0.001607031,0.001908273,0.8999675,0.0007508715,0.00009794776,0.00009858675,0.002374199,0.006202675,0.0005211028,0.08420184,0.001996834,0.0002731636],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08587495,0.004212194,0.6740158,0.2208119,0.004737523,0.001773295,0.000006910279,0.0000199529,0.008547397],"genre_scores_gemma":[0.9887915,0.0000294264,0.009702053,0.0009985249,0.0003714122,0.00003303161,4.985511e-7,0.000002662263,0.00007092646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9029165,"threshold_uncertainty_score":0.8788646,"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."}}