{"id":"W4386439692","doi":"10.2196/48039","title":"Performance of ChatGPT on the Peruvian National Licensing Medical Examination: Cross-Sectional Study","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"United States Medical Licensing Examination; Context (archaeology); Medical education; Psychology; Sample (material); Medicine; Family medicine; Medical school; Geography","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00306813,0.0001165539,0.0001588992,0.0002666164,0.0002803432,0.00002522428,0.0001813201,0.0002195198,0.002981639],"category_scores_gemma":[0.005329604,0.00008414851,0.00006132304,0.0008408066,0.0002203871,0.0001084443,0.0000328335,0.0004712473,0.0004461397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002067092,"about_ca_system_score_gemma":0.003862767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001108197,"about_ca_topic_score_gemma":0.00002654794,"domain_scores_codex":[0.9959685,0.0001563765,0.0006333968,0.0002808541,0.002740596,0.0002203165],"domain_scores_gemma":[0.9978727,0.0006395556,0.0001433134,0.0002345889,0.0008183283,0.0002915773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001019106,0.00190857,0.8899977,0.0001236309,0.00002678791,0.000002754525,0.006034661,0.000007882884,0.00003006065,0.001202067,0.006633855,0.09393018],"study_design_scores_gemma":[0.00009911461,0.0004417657,0.9869615,0.0001952671,0.000007335447,0.0000343304,0.003348769,0.006882749,0.0002538632,0.0001085371,0.001591853,0.00007486899],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9771051,0.00001946363,0.000004240311,0.01703433,0.001638604,0.0007735202,0.000001354763,0.00007089298,0.003352445],"genre_scores_gemma":[0.994211,0.00005071315,0.00001145266,0.002336337,0.001885182,0.0003052073,0.000089857,0.00001540924,0.001094889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0969639,"threshold_uncertainty_score":0.9979298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1491671043030322,"score_gpt":0.4935031896576396,"score_spread":0.3443360853546074,"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."}}