{"id":"W4404654665","doi":"10.2196/58375","title":"Performance of Plug-In Augmented ChatGPT and Its Ability to Quantify Uncertainty: Simulation Study on the German Medical Board Examination","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; German; Engineering; Psychology; Computer science; Geography; World Wide Web; Archaeology","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":[],"consensus_categories":[],"category_scores_codex":[0.002147995,0.0001215996,0.0001953646,0.0002498684,0.00007286932,0.00001920362,0.0001037047,0.0001706514,0.0004679445],"category_scores_gemma":[0.003009146,0.00008539636,0.00003017804,0.000498422,0.00007065729,0.0001048454,0.00002685895,0.0003827115,0.00005423362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002326884,"about_ca_system_score_gemma":0.001318625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003150365,"about_ca_topic_score_gemma":0.0001439518,"domain_scores_codex":[0.9977033,0.0002209953,0.000533392,0.0003347612,0.001023959,0.0001836651],"domain_scores_gemma":[0.9984276,0.0007775897,0.00006281284,0.0002346269,0.0002101851,0.0002871666],"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":[0.000371376,0.003822573,0.1201478,0.00113041,0.00002943896,0.000006787893,0.05130229,0.0001686029,0.0002884328,0.001726643,0.0008787796,0.8201269],"study_design_scores_gemma":[0.0001221178,0.001130192,0.7162778,0.001539074,0.00002840128,0.000005958932,0.004884524,0.2740592,0.0005902674,0.0001359732,0.001107781,0.00011869],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9661497,0.0001342261,0.00002751318,0.03105135,0.0008102436,0.001630605,9.931065e-7,0.00003866419,0.0001567122],"genre_scores_gemma":[0.9979184,0.00005382462,0.00000604261,0.001132941,0.0003706685,0.0003600529,0.00002464348,0.00001256337,0.0001208441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8200082,"threshold_uncertainty_score":0.5123664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1048683091182641,"score_gpt":0.4949827552047562,"score_spread":0.390114446086492,"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."}}