{"id":"W4380575774","doi":"10.2196/46939","title":"Putting ChatGPT’s Medical Advice to the (Turing) Test: Survey Study","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":188,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Chatbot; Advice (programming); Test (biology); Turing; Turing test; Psychology; Computer science; Medicine; World Wide Web; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00444468,0.0001522384,0.0002287831,0.0002161102,0.0002881044,0.00003850698,0.0003379519,0.0002167311,0.001584746],"category_scores_gemma":[0.03081016,0.0001062474,0.00005236818,0.001553932,0.00007249638,0.00007234396,0.0001000188,0.0005971228,0.002390455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000150291,"about_ca_system_score_gemma":0.004052065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003649541,"about_ca_topic_score_gemma":0.002286448,"domain_scores_codex":[0.9965458,0.0002709654,0.0006290895,0.0004111255,0.001707637,0.000435381],"domain_scores_gemma":[0.9964395,0.001473637,0.00009675464,0.0005298211,0.0004116692,0.001048627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000389313,0.001701559,0.3267106,0.00007240292,0.00001659632,0.000013286,0.01331768,0.000001346671,0.000007082658,0.00003522026,0.1773783,0.480707],"study_design_scores_gemma":[0.000108499,0.0005074816,0.9369046,0.0003568229,0.00002544804,0.00005003465,0.01497232,0.001637027,0.00009340749,0.0002014381,0.04499341,0.0001495036],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8390821,0.00006066069,0.00002880311,0.1558567,0.002663264,0.001424722,0.000001965547,0.0002477651,0.0006339895],"genre_scores_gemma":[0.9814662,0.00004977244,0.00005820147,0.0122635,0.003028779,0.0008084499,0.0001190694,0.00002869755,0.002177286],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.610194,"threshold_uncertainty_score":0.999328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1311681862863586,"score_gpt":0.5029894972674881,"score_spread":0.3718213109811295,"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."}}