{"id":"W2751021312","doi":"10.1016/j.jsurg.2017.08.007","title":"Developing the Blueprint for a General Surgery Technical Skills Certification Examination: A Validation Study","year":2017,"lang":"en","type":"article","venue":"Journal of surgical education","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal College of Physicians and Surgeons of Canada; St. Michael's Hospital; University of Toronto","funders":"","keywords":"Blueprint; Certification; Likert scale; Delphi method; Cronbach's alpha; Medical education; Medicine; Computer science; Psychology; Management; Psychometrics; Engineering; Artificial intelligence","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":[0.002532013,0.0001052992,0.0002876666,0.0001439205,0.0004110984,0.0001543621,0.0001594889,0.00007877504,0.0000654591],"category_scores_gemma":[0.001594149,0.00006792373,0.0002031229,0.000121417,0.0000649162,0.0002627806,0.00002507217,0.0001947389,0.000005204542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001747443,"about_ca_system_score_gemma":0.0005800865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007045154,"about_ca_topic_score_gemma":0.000001721442,"domain_scores_codex":[0.99846,0.0001301072,0.0007082198,0.000156081,0.0004098967,0.0001357092],"domain_scores_gemma":[0.9971508,0.0007962829,0.0007970982,0.0003122346,0.0008321531,0.0001114667],"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":[0.0007391538,0.00353749,0.1480675,0.00007472966,0.0001817576,0.00002890494,0.001291422,0.0001117722,0.0004451452,0.00898762,0.0006231918,0.8359113],"study_design_scores_gemma":[0.002097981,0.0001616913,0.9696867,0.0001438251,0.0001318191,0.0002513902,0.0006236836,0.0003093334,0.0006690211,0.0008682685,0.02494439,0.0001119277],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9850805,0.00004911489,0.002332111,0.0103034,0.0007396764,0.0006089821,6.009209e-7,0.0000153125,0.0008702641],"genre_scores_gemma":[0.996541,0.00004422775,0.001939961,0.0001281659,0.00100658,0.00005266381,0.00001394012,0.00001252964,0.0002609775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8357993,"threshold_uncertainty_score":0.3161878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1199120047110545,"score_gpt":0.4130103308792028,"score_spread":0.2930983261681483,"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."}}