{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01880088,0.0001626264,0.001060321,0.0005384595,0.00005752241,0.000003559243,0.0007777026,0.0002776865,0.0009386037],"category_scores_gemma":[0.7085304,0.00009448741,0.0001318957,0.001878116,0.0004229024,0.00006264285,0.00008593822,0.0008256743,0.00001474037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001028463,"about_ca_system_score_gemma":0.00006289245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002756439,"about_ca_topic_score_gemma":4.393438e-7,"domain_scores_codex":[0.9938087,0.0009836026,0.002760534,0.0005121593,0.001625678,0.0003093673],"domain_scores_gemma":[0.8720975,0.124923,0.001913753,0.0006100999,0.000266551,0.0001891127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000347088,0.00005329633,0.9043301,0.00001446278,0.00002324924,0.000004187815,0.0008445638,0.00000948172,0.003557271,0.005962529,0.006348426,0.07881775],"study_design_scores_gemma":[0.005248675,0.002588395,0.867434,0.002089374,0.0001393403,0.00005695189,0.006776743,0.001732312,0.01587486,0.0872156,0.0103851,0.0004586702],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9692438,0.0003628732,0.007671283,0.0003583598,0.001442707,0.0001198259,0.000003020966,0.00002182186,0.02077632],"genre_scores_gemma":[0.9929595,0.0001857912,0.005400791,0.0002164212,0.0003676423,0.000002078131,8.548216e-7,0.00001024207,0.0008567044],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6897295,"threshold_uncertainty_score":0.9999747,"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."}}