{"id":"W1977281256","doi":"10.1207/s15328015tlm1701_3","title":"Use of \"Standardized Examinees\" to Screen for Standardized-Patient Scoring Bias in a Clinical Skills Examination","year":2005,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"College of Physicians and Surgeons of Ontario","funders":"","keywords":"Standardized test; Medicine; Psychology; Physical examination; Medical education; Medical physics; Family medicine; Radiology; Mathematics education","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01890972,0.0004001289,0.0003103468,0.00110598,0.0003586643,0.0004266308,0.0004878576,0.0004736671,0.00131372],"category_scores_gemma":[0.06583658,0.0002684135,0.0003153536,0.0003931162,0.0009403945,0.0006139928,0.001102447,0.000494873,0.0002418684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003405913,"about_ca_system_score_gemma":0.000689911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004221637,"about_ca_topic_score_gemma":0.001183082,"domain_scores_codex":[0.9844594,0.009847973,0.002102381,0.0008962676,0.002428669,0.0002653005],"domain_scores_gemma":[0.9458505,0.02561444,0.01242736,0.005025673,0.009591674,0.001490384],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009218401,0.0004479626,0.9572614,0.0001238241,0.0001148452,0.0001982865,0.001205618,0.0003306117,0.006588509,0.0002162406,0.000503095,0.0320877],"study_design_scores_gemma":[0.0001918909,0.00583651,0.9792692,0.00006047346,0.00007552194,0.001446574,0.0005485498,0.002303351,0.008627908,0.0001287729,0.001478842,0.00003235865],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934672,0.0001272927,0.004381319,0.00007563695,0.00003615056,0.0005080927,0.00005024956,0.00004081312,0.001313451],"genre_scores_gemma":[0.9893836,0.00005361566,0.009529529,0.00006922579,0.00001418452,0.0005459363,0.0001111212,0.000008984068,0.0002838382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9810903,"threshold_uncertainty_score":0.1000054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08751713581490382,"score_gpt":0.4095279154759775,"score_spread":0.3220107796610737,"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."}}