{"id":"W2315264017","doi":"10.1097/sla.0000000000001620","title":"Implementing and Evaluating a National Certification Technical Skills Examination","year":2016,"lang":"en","type":"article","venue":"Annals of Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Sinai Hospital","funders":"","keywords":"Certification; Medicine; Cronbach's alpha; Competence (human resources); Checklist; Reliability (semiconductor); Rating scale; Maintenance of Certification; Medical education; Medical physics; Psychometrics; Clinical psychology; Psychology; Management","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":[0.002119272,0.00005484941,0.0001471723,0.0001410022,0.00004619945,0.000007301484,0.000015658,0.00004217192,0.0001976154],"category_scores_gemma":[0.002226318,0.00003863248,0.00005976545,0.0001378226,0.00004442259,0.0001082081,0.00001935399,0.0000329964,0.000004547418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001068918,"about_ca_system_score_gemma":0.00004505969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002388507,"about_ca_topic_score_gemma":6.682498e-7,"domain_scores_codex":[0.9989852,0.00005401597,0.0003335488,0.0001358007,0.0003449285,0.0001465165],"domain_scores_gemma":[0.9979249,0.001440903,0.000138067,0.00006601411,0.0003748263,0.00005524224],"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":[0.00003489724,0.0001108883,0.1111419,0.00002747215,0.00002233109,0.00000136261,0.00004687231,9.282472e-7,0.02713921,0.001130628,0.0001799333,0.8601635],"study_design_scores_gemma":[0.0004671399,0.00002886546,0.9902313,0.0002011703,0.00001076572,0.000008387227,0.00003677879,0.0002740654,0.005819265,0.0006694864,0.002190008,0.00006274594],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947858,0.0000571917,0.0002608058,0.002163468,0.00002534009,0.00008867463,0.000007232981,0.00003242661,0.002579038],"genre_scores_gemma":[0.9991928,0.00004784465,0.0002653092,0.0002957955,0.00006034543,0.000007200219,0.00002381622,0.000006705681,0.000100233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8790894,"threshold_uncertainty_score":0.2665272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4304403721875084,"score_gpt":0.4635618905539116,"score_spread":0.03312151836640315,"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."}}