{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010134,0.0002009027,0.001000382,0.0004577975,0.0000878786,0.00001452101,0.00006571158,0.0001568185,0.00002328842],"category_scores_gemma":[0.2987177,0.0001605318,0.00009100023,0.0002539108,0.0001366393,0.00008532769,0.00005543635,0.001245504,0.000001480803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001224132,"about_ca_system_score_gemma":0.00008523024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007095012,"about_ca_topic_score_gemma":0.000128682,"domain_scores_codex":[0.9966112,0.0008564653,0.001272391,0.0004546724,0.0004677145,0.0003375366],"domain_scores_gemma":[0.9701877,0.02893237,0.0002499026,0.000233477,0.0001293705,0.0002671295],"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":[0.0006440417,0.0003927576,0.2854784,0.00004942815,0.00002550893,0.00001668038,0.004799709,0.001152367,0.0001805466,0.00006288536,0.0003836677,0.706814],"study_design_scores_gemma":[0.01170434,0.004476918,0.9438555,0.01309862,0.0001236192,0.00002066662,0.00170776,0.005312531,0.00007763032,0.0000201512,0.0193664,0.0002358657],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916499,0.0003050359,0.004727954,0.002067563,0.0001364428,0.0006933308,0.00001018203,0.00006166493,0.000347923],"genre_scores_gemma":[0.971014,0.000155355,0.02717347,0.0008130218,0.0003422496,0.00002483322,0.00005340285,0.00003109112,0.0003925621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7065781,"threshold_uncertainty_score":0.7071895,"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."}}