{"id":"W2514834349","doi":"10.1097/sla.0000000000001931","title":"Setting Performance Standards for Technical and Nontechnical Competence in General Surgery","year":2016,"lang":"en","type":"article","venue":"Annals of Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal College of Physicians and Surgeons of Canada; University of Calgary; Western University; University of Toronto","funders":"","keywords":"Medicine; Competence (human resources); Credibility; Receiver operating characteristic; Laparoscopic cholecystectomy; Gold standard (test); Medical physics; Statistics; Surgery; Radiology; Social psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.002135186,0.00009823883,0.0004632428,0.0001801834,0.00003140735,0.000005303523,0.00002971211,0.00009198044,0.00004394234],"category_scores_gemma":[0.001446282,0.00006677351,0.0001533102,0.0001651988,0.0001403607,0.0001063391,0.00002578356,0.00007932477,8.63602e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001576692,"about_ca_system_score_gemma":0.0001550574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004366627,"about_ca_topic_score_gemma":0.000002194171,"domain_scores_codex":[0.998745,0.00003017789,0.0004928026,0.000195287,0.0002643767,0.0002723705],"domain_scores_gemma":[0.9963501,0.003113238,0.0001018933,0.0001277773,0.0001990876,0.0001078791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000663386,0.00007253819,0.7356705,0.0001385976,0.00001517899,0.00001890254,0.00001184234,0.000003543786,0.002054588,0.0002364245,0.001191066,0.2599234],"study_design_scores_gemma":[0.001057264,0.0000802177,0.9720018,0.001438865,0.00001071721,0.0000386856,0.00001348164,0.0005736885,0.007976469,0.0001614369,0.01646313,0.0001842791],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958296,0.0002226258,0.0004131731,0.002759206,0.00006081886,0.000140936,0.00002748468,0.0000433375,0.0005027705],"genre_scores_gemma":[0.998437,0.000474925,0.0004163254,0.0005241534,0.00007444403,0.00001660822,0.000006292925,0.00001216187,0.00003810082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2597392,"threshold_uncertainty_score":0.2722945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2560157991108771,"score_gpt":0.3885659162547141,"score_spread":0.1325501171438371,"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."}}