{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003277475,0.0004194301,0.0004379796,0.001188418,0.0008113045,0.0007479806,0.000549342,0.001106539,0.002972494],"category_scores_gemma":[0.009236403,0.0004942425,0.0006803316,0.001276091,0.001087034,0.001288722,0.0007272422,0.0007312117,0.000763707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006212345,"about_ca_system_score_gemma":0.0005252085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004743745,"about_ca_topic_score_gemma":0.006474903,"domain_scores_codex":[0.9984762,0.0005689321,0.0002157778,0.0003006336,0.0002528076,0.0001855905],"domain_scores_gemma":[0.9943202,0.001811414,0.002075486,0.0004050391,0.0007451237,0.0006427975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.004891527,0.001510562,0.9844794,0.0001357053,0.0002740024,0.0002115175,0.001162342,0.00002805072,0.0002383002,0.0001606374,0.0003901446,0.006517935],"study_design_scores_gemma":[0.0003711072,0.008693025,0.9868006,0.00006416616,0.0001449941,0.0005747991,0.002248679,0.00006602099,0.0001546171,0.0001361568,0.0007210554,0.00002472977],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.999005,0.0004198938,0.00006267384,0.0000299432,0.00001664135,0.00005269524,0.000143801,7.969965e-7,0.0002685091],"genre_scores_gemma":[0.9984468,0.0002895086,0.0002514661,0.0001427546,0.00003512704,0.0001164625,0.000470399,0.000001600165,0.0002458514],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004743745,"threshold_uncertainty_score":0.01733321,"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."}}