{"id":"W4385329931","doi":"10.1515/cclm-2023-0765","title":"Chatbot GPT can be grossly inaccurate","year":2023,"lang":"en","type":"letter","venue":"Clinical Chemistry and Laboratory Medicine (CCLM)","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"","keywords":"Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008851111,0.0008008945,0.0007206437,0.001277415,0.004550909,0.005494499,0.002289993,0.02486109,0.05640803],"category_scores_gemma":[0.08650217,0.0008198911,0.0007044751,0.000640878,0.00246563,0.007184721,0.004059638,0.01536402,0.05279623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00361578,"about_ca_system_score_gemma":0.002668539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00768367,"about_ca_topic_score_gemma":0.009887564,"domain_scores_codex":[0.9900267,0.003295109,0.0006207176,0.0007162406,0.004041011,0.001300303],"domain_scores_gemma":[0.9415831,0.04477426,0.001655139,0.002879588,0.006804201,0.002303738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008137789,0.00001960863,0.0003990439,0.00003487086,0.00000559521,0.0007983477,0.0004516536,0.0002540879,0.000378974,0.01330271,0.970365,0.01390875],"study_design_scores_gemma":[0.00004961493,0.00005444879,0.0006687127,0.0002211663,0.00001767306,0.0009761932,0.0008532443,0.006255977,0.0008115466,0.03833467,0.9516956,0.00006130261],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.002330097,0.0004235248,0.01443125,0.8616238,0.01840675,0.0000894556,0.000575713,0.003653243,0.09846622],"genre_scores_gemma":[0.05210128,0.0004662541,0.008297887,0.7295063,0.01431804,0.000235754,0.0006026953,0.001545843,0.1929259],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.05640803,"threshold_uncertainty_score":0.1887036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3206781854294226,"score_gpt":0.4929426255778536,"score_spread":0.172264440148431,"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."}}