{"id":"W2052069113","doi":"10.1111/emip.12003","title":"Validating Student Score Inferences With Person‐Fit Statistic and Verbal Reports: A Person‐Fit Study for Cognitive Diagnostic Assessment","year":2013,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Science Education and Pedagogy","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Statistic; Test (biology); Cognition; Consistency (knowledge bases); Psychology; Test statistic; Cognitive psychology; Artificial intelligence; Statistical hypothesis testing; Computer science; Statistics; 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":[0.08252496,0.0007105224,0.0006651921,0.003607291,0.0009351211,0.002693391,0.001192899,0.001055906,0.0008172539],"category_scores_gemma":[0.2945027,0.0003556054,0.001281418,0.001769051,0.001666619,0.002989163,0.002508406,0.001471352,0.0002624767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001166442,"about_ca_system_score_gemma":0.001386578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007760533,"about_ca_topic_score_gemma":0.0009467518,"domain_scores_codex":[0.9239098,0.05379995,0.005892722,0.002748493,0.01261903,0.001029942],"domain_scores_gemma":[0.6410083,0.2684951,0.03050087,0.02487089,0.03317005,0.001954798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009294103,0.002313661,0.8463715,0.0001933491,0.000341152,0.0002560475,0.04219732,0.002293357,0.003571115,0.003513831,0.0004879736,0.09753134],"study_design_scores_gemma":[0.0004007524,0.01208487,0.7891465,0.0003264952,0.0003637416,0.001828944,0.0551682,0.09181581,0.0325597,0.01002203,0.005851921,0.0004310863],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9732102,0.00003408569,0.02506634,0.00005132459,0.00002006299,0.000382993,0.00005232499,0.00005180681,0.001130849],"genre_scores_gemma":[0.9825916,0.0000207554,0.01649977,0.00004412394,0.00000960189,0.0005984916,0.0000712949,0.00002091998,0.0001433559],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08252496,"threshold_uncertainty_score":0.4364389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3346735437565425,"score_gpt":0.504415793140177,"score_spread":0.1697422493836346,"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."}}