{"id":"W4404717881","doi":"10.1186/s12909-024-06309-x","title":"Performance of ChatGPT and Bard on the medical licensing examinations varies across different cultures: a comparison study","year":2024,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"United States Medical Licensing Examination; Medicine; Asian americans; Family medicine; Significant difference; Medical education; Medical physics; Medical school; Internal medicine; Political science; Ethnic group","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":[0.007968981,0.0005439387,0.0006694308,0.001932221,0.0005997187,0.001700811,0.0007533456,0.0008553923,0.001743113],"category_scores_gemma":[0.03713687,0.0002951833,0.0008995904,0.001209773,0.00109762,0.00231766,0.002307208,0.0008498932,0.001414746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00110888,"about_ca_system_score_gemma":0.0008311266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01197368,"about_ca_topic_score_gemma":0.01367279,"domain_scores_codex":[0.9945266,0.002353871,0.0008212229,0.0007229798,0.001186081,0.0003892464],"domain_scores_gemma":[0.9776936,0.01053884,0.003331706,0.001885793,0.005075424,0.001474618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000416759,0.0003357332,0.9678054,0.0001235863,0.0001465526,0.0002198875,0.00897825,0.0001952972,0.0005503558,0.00009054197,0.0004606925,0.02067707],"study_design_scores_gemma":[0.00002480406,0.0007446234,0.983129,0.0001047966,0.0001088882,0.000486385,0.01099522,0.001522287,0.00133148,0.0001390304,0.001372005,0.00004146224],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983229,0.0001341255,0.0001496446,0.00006450569,0.00001604472,0.00002317581,0.0001401583,0.000007219312,0.001142261],"genre_scores_gemma":[0.9987171,0.0001482335,0.0003084255,0.00006661548,0.00001436652,0.00003327902,0.0002435648,0.00001102755,0.0004574297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01197368,"threshold_uncertainty_score":0.04214448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1546363183540944,"score_gpt":0.4981344811457172,"score_spread":0.3434981627916227,"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."}}