{"id":"W2061509267","doi":"10.1097/00001888-200310001-00020","title":"Differential Weighting of Errors on a Test of Clinical Reasoning Skills","year":2003,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Weighting; Test (biology); Item response theory; Differential (mechanical device); Differential item functioning; Computer science; Statistics; Psychology; Mathematics; Artificial intelligence; Medicine; Psychometrics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02071224,0.0006534272,0.0006029972,0.00364105,0.0002583104,0.001236739,0.0006324967,0.0009110126,0.0019269],"category_scores_gemma":[0.1619124,0.0002359681,0.0005595899,0.001422301,0.000918467,0.001363355,0.002742724,0.0008357869,0.0002686867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000752774,"about_ca_system_score_gemma":0.0005195769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001243129,"about_ca_topic_score_gemma":0.001343601,"domain_scores_codex":[0.9775944,0.01215297,0.002114635,0.001464853,0.006217738,0.0004553521],"domain_scores_gemma":[0.8418251,0.1221202,0.01827557,0.008966411,0.007750897,0.001061817],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002290944,0.0004510477,0.7573307,0.0002750113,0.0007050562,0.0001519595,0.00180821,0.005028172,0.002811749,0.001396182,0.0006699266,0.227081],"study_design_scores_gemma":[0.0001354703,0.001880239,0.9582715,0.0002485131,0.0004683884,0.001477506,0.001432493,0.01994855,0.0079704,0.00645335,0.001632079,0.00008157911],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9842438,0.0002624319,0.01320736,0.000169144,0.00001615931,0.0000708349,0.0001656469,0.00005295497,0.001811695],"genre_scores_gemma":[0.9934247,0.00007971564,0.005963171,0.00004613213,0.000009034227,0.00003209345,0.0001651529,0.0000136914,0.0002664151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9792877,"threshold_uncertainty_score":0.1095381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4836205860473455,"score_gpt":0.5582844268692446,"score_spread":0.07466384082189909,"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."}}