{"id":"W4386438954","doi":"10.1007/s00404-023-07185-4","title":"Performance of ChatGPT in Israeli Hebrew OBGYN national residency examinations","year":2023,"lang":"en","type":"article","venue":"Archives of Gynecology and Obstetrics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Medicine; Human genetics; Hebrew; Family medicine; Gynecology; Genetics; Classics","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":[0.0002321013,0.00005112348,0.000155996,0.0006603691,0.00005010205,0.00000127868,0.00005104337,0.00006575978,0.00003318171],"category_scores_gemma":[0.004503486,0.00005008169,0.00002433915,0.0006835389,0.0001695524,0.00005486162,0.00002848898,0.0001164718,0.00001398999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001934894,"about_ca_system_score_gemma":0.0002662434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007600004,"about_ca_topic_score_gemma":0.00008357474,"domain_scores_codex":[0.9992502,0.00004071329,0.0003354481,0.0001195445,0.0001192683,0.0001347867],"domain_scores_gemma":[0.9950418,0.004643728,0.00008833312,0.00008738453,0.00009780657,0.00004087278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003993012,0.0001381719,0.8549498,0.0003323747,0.00001179347,0.000004620174,0.003844011,0.00006019734,0.0007285074,0.005541365,0.0002259248,0.1341233],"study_design_scores_gemma":[0.00008947586,0.0003649307,0.9857162,0.00006593084,0.000008948192,0.000004183608,0.001019888,0.003931908,0.003301837,0.005001186,0.0004529915,0.0000425351],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936525,0.0006416179,0.00001025895,0.000976317,0.0002759755,0.0001522587,0.000004806551,0.00001145524,0.004274817],"genre_scores_gemma":[0.9963788,0.002715412,0.0003907935,0.0001306304,0.00002589952,0.00001352902,0.0000239517,0.000004437295,0.0003165111],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1340807,"threshold_uncertainty_score":0.5391419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09443597876947529,"score_gpt":0.3797961080783587,"score_spread":0.2853601293088834,"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."}}