{"id":"W4386292753","doi":"10.1093/bjs/znad258.077","title":"828 Real-Time Artificial Intelligence Instruction in Comparison to Human Expert Instruction in Surgical Technical Skills Teaching – a Randomized Controlled Trial","year":2023,"lang":"en","type":"article","venue":"British journal of surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"CLIPS; Task (project management); Medicine; Repetition (rhetorical device); Randomized controlled trial; Baseline (sea); Medical physics; Surgery","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":[0.008167992,0.0001750842,0.002458093,0.001237718,0.0001078669,0.00008811943,0.00008254705,0.0002137442,0.0001859071],"category_scores_gemma":[0.004839273,0.0001687151,0.0006750034,0.0008609951,0.0001079017,0.0002117645,0.00003248616,0.0008567776,0.00001804644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001892026,"about_ca_system_score_gemma":0.0001322872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002393233,"about_ca_topic_score_gemma":0.00005888597,"domain_scores_codex":[0.994899,0.0009427984,0.00289437,0.0002550533,0.0006574925,0.000351333],"domain_scores_gemma":[0.995877,0.003103222,0.0005468509,0.00009904015,0.0001379812,0.0002358538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.6643866,0.00073032,0.002187511,0.00001261715,0.00007617567,0.002547543,0.0003376755,0.000883005,0.0005946822,0.0002291678,0.00011716,0.3278975],"study_design_scores_gemma":[0.9749506,0.0002637784,0.01311656,0.002203159,0.00007267304,0.002797218,0.0006456726,0.004001596,0.000147112,0.0009483351,0.0005256922,0.0003275816],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962814,0.00008429491,0.0001098867,0.0003110248,0.0009010495,0.001081629,0.000001115973,0.00007571709,0.001153845],"genre_scores_gemma":[0.9984748,0.0002510192,0.0002785914,0.00004583652,0.0008115884,0.00005588217,0.00001636812,0.00002358029,0.00004234088],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3275699,"threshold_uncertainty_score":0.6880001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05352652917610808,"score_gpt":0.3593577191866574,"score_spread":0.3058311900105493,"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."}}