{"id":"W4200283550","doi":"10.1136/bmj-2021-067883","title":"“It’s not rocket science” and “It’s not brain surgery”—“It’s a walk in the park”: prospective comparative study","year":2021,"lang":"en","type":"article","venue":"BMJ","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Aerospace; Confidence interval; Recall; Test (biology); Psychology; Population; Cognition; Artificial intelligence; Medicine; Computer science; Cognitive psychology; Engineering; Psychiatry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003195609,0.0001622783,0.0004474252,0.0001434132,0.0002320117,0.0001058936,0.000109727,0.00004820155,0.000231004],"category_scores_gemma":[0.002120434,0.0001097261,0.00006460981,0.001080511,0.0002575642,0.0001325137,0.00008535674,0.0002879625,0.00003046949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009565882,"about_ca_system_score_gemma":0.0004924795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004662107,"about_ca_topic_score_gemma":0.0004847323,"domain_scores_codex":[0.9975777,0.0002974498,0.0004234068,0.0004699255,0.0009070974,0.0003243783],"domain_scores_gemma":[0.9972583,0.001893552,0.0000943999,0.0003018851,0.0003158404,0.0001360328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001851483,0.003175382,0.6362256,0.00006161304,0.0002461487,0.002184936,0.2518383,0.0000983701,0.0006026241,0.001156593,0.08524017,0.01731872],"study_design_scores_gemma":[0.004341679,0.0002228535,0.8808326,0.0001128636,0.00004192048,0.00009496761,0.07630364,0.001503557,0.0009668285,0.00006944512,0.03530015,0.0002095453],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8647678,0.00001680777,0.000008578981,0.1033592,0.0001386283,0.001110476,0.000005298162,0.00002790762,0.03056528],"genre_scores_gemma":[0.9783918,0.000003406976,0.00005418155,0.02056963,0.0001329117,0.00009877545,0.000006979628,0.000008930564,0.0007333951],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2446069,"threshold_uncertainty_score":0.4474501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1436219618460758,"score_gpt":0.4069361338212948,"score_spread":0.263314171975219,"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."}}