{"id":"W2979396087","doi":"10.1002/bjs.11359","title":"Development and evaluation of the General Surgery Objective Structured Assessment of Technical Skill (GOSATS)","year":2019,"lang":"en","type":"article","venue":"British journal of surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Mount Sinai Hospital; University of Toronto","funders":"Royal College of Physicians and Surgeons of Canada","keywords":"Medicine; Summative assessment; Cronbach's alpha; Reliability (semiconductor); Specialty; Medical physics; Certification; Formative assessment; Medical education; Family medicine; Psychometrics; Clinical psychology; Psychology; Mathematics education","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.01179974,0.0004833369,0.0003645729,0.001066623,0.0001916951,0.0005897999,0.0005866851,0.0003269173,0.0006083437],"category_scores_gemma":[0.02075228,0.000239298,0.0006502393,0.0003702604,0.0004635084,0.000392339,0.001065212,0.0003752456,0.0002977253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006802843,"about_ca_system_score_gemma":0.002086211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001677767,"about_ca_topic_score_gemma":0.003066707,"domain_scores_codex":[0.9929871,0.003951677,0.0006678151,0.000377896,0.001825488,0.0001899941],"domain_scores_gemma":[0.9891021,0.003020312,0.001451823,0.0005260031,0.005201698,0.0006980641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002630008,0.001533606,0.6278417,0.0005223207,0.0002358392,0.0002703855,0.002188117,0.004780879,0.01612473,0.0005156583,0.001754885,0.3416019],"study_design_scores_gemma":[0.000383948,0.01574914,0.9553752,0.0002339574,0.0001962036,0.0006861658,0.0009437989,0.01294722,0.008172239,0.0003211303,0.004935515,0.00005547175],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9843073,0.0002424886,0.01022348,0.0001104359,0.00006408209,0.002136689,0.000354045,0.00008860475,0.00247292],"genre_scores_gemma":[0.950948,0.0003102131,0.04493835,0.00007550215,0.00002399338,0.001798089,0.0009383402,0.00002510818,0.0009423039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01179974,"threshold_uncertainty_score":0.06240374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05304400114586332,"score_gpt":0.3363322992370958,"score_spread":0.2832882980912325,"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."}}