{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006512764,0.001238839,0.0008114321,0.0008092661,0.0005211182,0.00125713,0.001263432,0.001639449,0.003731204],"category_scores_gemma":[0.02804293,0.0003702064,0.001111494,0.0007758471,0.0009870229,0.001432322,0.001439658,0.002163567,0.0009045851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002406296,"about_ca_system_score_gemma":0.001873148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05646367,"about_ca_topic_score_gemma":0.03142737,"domain_scores_codex":[0.9975303,0.00153902,0.00009932905,0.0003649114,0.0002509413,0.0002156011],"domain_scores_gemma":[0.9756932,0.02104743,0.000755631,0.0008998913,0.001053705,0.0005502045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002442996,0.00060297,0.06474847,0.0005346682,0.0002748674,0.0004600553,0.0004908323,0.8700653,0.0009921073,0.003449831,0.01523052,0.04070741],"study_design_scores_gemma":[0.0001498317,0.0003850306,0.008755329,0.00005082378,0.00005142385,0.00006771706,0.0001793253,0.9855295,0.0008852398,0.002052913,0.001857651,0.00003518198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9573094,0.0009230045,0.02459362,0.001877259,0.0002045813,0.0002399486,0.005767675,0.002884142,0.006200362],"genre_scores_gemma":[0.9779808,0.0001494882,0.01399121,0.000321174,0.00003960189,0.0001979309,0.005291854,0.0001630259,0.001864851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05646367,"threshold_uncertainty_score":0.11227,"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."}}