{"id":"W4413020649","doi":"10.1001/jamasurg.2025.2564","title":"Artificial Intelligence–Augmented Human Instruction and Surgical Simulation Performance","year":2025,"lang":"en","type":"letter","venue":"JAMA Surgery","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; McMaster University Medical Centre; Hamilton General Hospital; McGill University; Université Laval; Montreal Neurological Institute and Hospital","funders":"","keywords":"Medicine; Randomized controlled trial; TUTOR; Cognition; Computer-Assisted Instruction; Medical education; Physical therapy; Multimedia; Computer science; Surgery; Psychiatry","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004047326,0.0002757044,0.000614189,0.0005020066,0.0001854351,0.00008820908,0.00004363814,0.0008233649,0.0005953782],"category_scores_gemma":[0.0002101726,0.000252755,0.0002105893,0.000387732,0.0001136106,0.0001477045,0.00004000603,0.001277172,0.00002609256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000887795,"about_ca_system_score_gemma":0.00009586466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001452857,"about_ca_topic_score_gemma":7.768784e-7,"domain_scores_codex":[0.9979868,0.0001044919,0.0007124122,0.0004399067,0.0004438895,0.0003124791],"domain_scores_gemma":[0.9980263,0.001324536,0.0001877727,0.0002298368,0.0001454709,0.00008613393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004734357,0.00007311644,0.0171497,0.0007209514,0.0001702257,0.0007938407,0.00007227912,0.0007568423,0.000005798248,0.0001407825,0.04159947,0.9380435],"study_design_scores_gemma":[0.0004974859,0.00005432437,0.007331263,0.0008059536,0.0001430263,0.00006927163,0.00002683754,0.03894774,0.0001135269,0.000257639,0.9513942,0.0003587227],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8468032,0.0001178026,0.0002017851,0.1412632,0.001497377,0.0005180571,0.00002323924,0.0003069201,0.009268374],"genre_scores_gemma":[0.9302754,0.00006639277,0.00002756419,0.06335091,0.003657693,0.00001604675,0.001304804,0.00003033017,0.001270875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9376848,"threshold_uncertainty_score":0.9999925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07281064779881054,"score_gpt":0.3267840665355765,"score_spread":0.2539734187367659,"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."}}