{"id":"W2054769520","doi":"10.1046/j.1365-2923.2002.01307.x","title":"Selecting performance assessment methods for experienced physicians","year":2002,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Competence (human resources); Psychology; Performance measurement; Health care; Medical education; Applied psychology; Medicine; Social psychology; Business","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009308217,0.0001167463,0.0001980666,0.0001386651,0.0002080223,0.00001818624,0.0001237528,0.0001372836,0.001603491],"category_scores_gemma":[0.004455872,0.0001067552,0.00005518432,0.0006292244,0.0001038973,0.0001287752,0.0000152769,0.0003252842,0.00002589864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002808526,"about_ca_system_score_gemma":0.0007366698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006690748,"about_ca_topic_score_gemma":4.157303e-7,"domain_scores_codex":[0.9985479,0.00005894998,0.0003739733,0.0002711982,0.0004765811,0.0002714638],"domain_scores_gemma":[0.9990847,0.000110717,0.0001108483,0.0002554337,0.0003760379,0.00006230501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005874376,0.0007013673,0.001573072,0.0001118211,0.00001227545,1.077951e-7,0.001486314,6.182229e-7,0.0006045531,0.0003641366,0.08056168,0.9145782],"study_design_scores_gemma":[0.001523245,0.0005840907,0.02055733,0.0006836788,0.0001145697,0.000095322,0.003918282,0.3298672,0.004743333,0.0002137358,0.6373329,0.0003664169],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6785888,0.0003212241,0.2430048,0.05550494,0.004811822,0.001335759,5.624394e-7,0.0002111552,0.01622097],"genre_scores_gemma":[0.5749948,0.00007154563,0.3901427,0.02917572,0.001438926,0.001047242,0.00008373164,0.00003025604,0.003015068],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9142118,"threshold_uncertainty_score":0.9993092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02833471414707524,"score_gpt":0.4741631180636334,"score_spread":0.4458284039165581,"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."}}