{"id":"W4379140845","doi":"10.1016/j.jpurol.2023.05.018","title":"ChatGPT and large language model (LLM) chatbots: The current state of acceptability and a proposal for guidelines on utilization in academic medicine","year":2023,"lang":"en","type":"review","venue":"Journal of Pediatric Urology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":214,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Medicine; Guideline; MEDLINE; English language; Medical record; Medical education; Artificial intelligence; Computer science; Pathology; Psychology; Internal medicine","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":[0.002778833,0.0001750185,0.001015777,0.000521532,0.00003824576,0.000003220182,0.0001137099,0.0001882624,0.000006286818],"category_scores_gemma":[0.003056144,0.00009815399,0.00009959497,0.0003562484,0.00008705924,0.00004835501,0.00003823765,0.0008163886,9.350969e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000598488,"about_ca_system_score_gemma":0.001043834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001977563,"about_ca_topic_score_gemma":0.00005279571,"domain_scores_codex":[0.9974679,0.0001767526,0.001722767,0.0001972451,0.0002171276,0.0002181979],"domain_scores_gemma":[0.9974038,0.0008101609,0.001152601,0.0001435527,0.000395616,0.00009428497],"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":[0.000122837,0.00007620788,0.0003944217,0.005314208,0.0000333222,0.000002653631,0.002096485,0.00001035706,2.22456e-7,0.0000702967,0.0008338823,0.9910451],"study_design_scores_gemma":[0.003672753,0.01909655,0.003909507,0.009528157,0.01983648,0.0008255757,0.004045398,0.05069554,0.00001405164,0.07030156,0.8167,0.001374406],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01302884,0.9804986,0.0008435078,0.003920506,0.0006025321,0.001066905,0.00003066779,0.000005812423,0.000002643452],"genre_scores_gemma":[0.002463405,0.9952681,0.0000934171,0.000148243,0.001930516,0.00003613884,0.00002041791,0.00002212146,0.00001760796],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9896707,"threshold_uncertainty_score":0.4002603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.455626065115204,"score_gpt":0.5717565975105738,"score_spread":0.1161305323953699,"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."}}