{"id":"W4408212176","doi":"10.1055/a-2551-2131","title":"Solving Complex Pediatric Surgical Case Studies: A Comparative Analysis of Copilot, ChatGPT-4, and Experienced Pediatric Surgeons' Performance","year":2025,"lang":"en","type":"article","venue":"European Journal of Pediatric Surgery","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Medicine; General surgery; Pediatric Surgeon; Pediatric surgery; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004354933,0.0004091875,0.003189271,0.003197459,0.0002169722,0.00004294056,0.0001686247,0.00007072358,0.0001025911],"category_scores_gemma":[0.001197357,0.0003191079,0.001442232,0.004514843,0.0001945582,0.0002213298,0.0001359999,0.0004548595,0.000007024521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008431426,"about_ca_system_score_gemma":0.0003774527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000806664,"about_ca_topic_score_gemma":0.000001256526,"domain_scores_codex":[0.9950795,0.0011147,0.002163837,0.0004056598,0.0007405003,0.0004957644],"domain_scores_gemma":[0.9892221,0.008010964,0.001197892,0.0003531443,0.0008143314,0.000401563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004895238,0.000234089,0.9706943,0.0004216336,0.001447124,0.02078845,0.001823702,0.00009170458,0.000006029247,0.0000365484,0.003216153,0.0007507674],"study_design_scores_gemma":[0.002660245,0.0004079269,0.9682542,0.0000594897,0.01539565,0.00525959,0.002927889,0.0003219584,0.00001860722,0.00000135199,0.004206532,0.0004865812],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9804112,0.01640033,0.0000562308,0.0001579333,0.0006482506,0.0001922549,0.00001036445,0.0000320645,0.002091401],"genre_scores_gemma":[0.9753308,0.02282109,0.0002074674,0.0001080632,0.001247551,0.000003362854,0.00000769707,0.00002351372,0.0002504061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01552886,"threshold_uncertainty_score":0.9999261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06479984516485819,"score_gpt":0.3323002339807762,"score_spread":0.267500388815918,"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."}}