{"id":"W3099298482","doi":"10.1007/s00464-020-08152-9","title":"Development and prospective validation of a scoring system for the Basic Endoscopic Skills Training (BEST) box","year":2020,"lang":"en","type":"article","venue":"Surgical Endoscopy","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto General Hospital; University of Toronto; University Health Network","funders":"Society of American Gastrointestinal and Endoscopic Surgeons","keywords":"Medicine; Receiver operating characteristic; Endoscopy; Prospective cohort study; Retrospective cohort study; Logistic regression; Medical physics; Surgery; Internal medicine","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":[0.0002869864,0.0001391318,0.0003626771,0.00003820621,0.0001286489,0.00002131237,0.00005514171,0.00005791715,0.00004312416],"category_scores_gemma":[0.000223533,0.00009331987,0.00008378927,0.0002092263,0.00006563924,0.00005574702,0.00002976149,0.0001324717,0.000006468075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000485337,"about_ca_system_score_gemma":0.0001040499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003448007,"about_ca_topic_score_gemma":4.238466e-7,"domain_scores_codex":[0.9988387,0.0000347085,0.0003711197,0.0002779134,0.0002610033,0.0002165984],"domain_scores_gemma":[0.9987733,0.0007975434,0.0001050256,0.00009874754,0.00008056094,0.000144758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01299838,0.001159281,0.2090717,0.007019077,0.002526243,0.0005260492,0.1078517,0.001930448,0.006958406,0.08345938,0.00004304198,0.5664563],"study_design_scores_gemma":[0.190843,0.002263874,0.02197825,0.004030653,0.001029884,0.0001713764,0.03593943,0.02226592,0.5865508,0.000233296,0.1336363,0.001057268],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992569,0.0003640289,0.001860418,0.0004508917,0.000130784,0.0009650794,0.000005763111,0.000116138,0.003537915],"genre_scores_gemma":[0.996637,0.00001394269,0.002972377,0.00007175952,0.0001354747,0.0001006147,0.00001073869,0.00001837323,0.00003968597],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5795924,"threshold_uncertainty_score":0.3805474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0512484015725226,"score_gpt":0.3064515041708012,"score_spread":0.2552031025982786,"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."}}