{"id":"W2303187789","doi":"10.1002/bjs.10103","title":"Consensus-based training and assessment model for general surgery","year":2016,"lang":"en","type":"article","venue":"British journal of surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal College of Physicians and Surgeons of Canada; University of Toronto","funders":"","keywords":"Milestone; Likert scale; Medicine; Delphi method; Cronbach's alpha; Medical education; Scale (ratio); Delphi; Psychometrics; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001569212,0.00009272927,0.0005400316,0.0001623419,0.00007269154,0.00003574042,0.00002164417,0.00006652476,0.0000857246],"category_scores_gemma":[0.0008678285,0.00007588077,0.0003264939,0.00006976489,0.00007952748,0.00007708387,0.000005916195,0.0001203085,4.256215e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004030981,"about_ca_system_score_gemma":0.0006163183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003436298,"about_ca_topic_score_gemma":0.000001768097,"domain_scores_codex":[0.9987059,0.00005291007,0.0006179442,0.0001251416,0.00026289,0.0002352351],"domain_scores_gemma":[0.9956632,0.00349738,0.0002675806,0.00005456774,0.0002650551,0.0002522115],"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":[0.0003394196,0.0001041047,0.06053249,0.00005546667,0.0001051799,0.0009146178,0.00002825464,0.0002278161,0.0004258233,0.00007489399,0.003311823,0.9338801],"study_design_scores_gemma":[0.02275975,0.000272041,0.6758264,0.009174297,0.0004841643,0.01628989,0.0002781327,0.2316733,0.0006822245,0.002511921,0.0390241,0.001023864],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9812176,0.0005821012,0.01572573,0.001823669,0.0002501158,0.00008684687,0.00002151534,0.00001894455,0.0002734878],"genre_scores_gemma":[0.9919097,0.0002144224,0.006610112,0.0007686102,0.0002861102,0.000003775628,0.000004730369,0.0000212524,0.0001813324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9328563,"threshold_uncertainty_score":0.3094328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.159169954672242,"score_gpt":0.3455573251873434,"score_spread":0.1863873705151014,"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."}}