{"id":"W4378528433","doi":"10.2196/47305","title":"Performance of the Large Language Model ChatGPT on the National Nurse Examinations in Japan: Evaluation Study","year":2023,"lang":"en","type":"article","venue":"JMIR Nursing","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Multiple choice; Test (biology); Certification; Specialty; Reading (process); Simple (philosophy); Medicine; Nursing; Psychology; Medical education; Family medicine; Linguistics; Political science","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":[0.001178786,0.00005462521,0.00007248898,0.0001392493,0.0001577525,0.000006733522,0.00007409824,0.00003612868,0.00003629897],"category_scores_gemma":[0.0003235594,0.00003481641,0.00002627712,0.0006092751,0.00003895521,0.00006031106,0.00000623499,0.0001502911,0.00003069836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002278881,"about_ca_system_score_gemma":0.0001905741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002917407,"about_ca_topic_score_gemma":0.00004617146,"domain_scores_codex":[0.9989144,0.00009640043,0.000209284,0.0001137159,0.0005315706,0.0001345866],"domain_scores_gemma":[0.9994161,0.0001378071,0.00006501651,0.0001644942,0.0001977996,0.00001875661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001936969,0.003835901,0.278502,0.0001027269,0.0000255968,8.172792e-7,0.476648,0.01805271,0.004078722,0.004388154,0.005850887,0.2083208],"study_design_scores_gemma":[0.00007380347,0.0001070293,0.4505526,0.0002339573,0.00001238757,8.471129e-7,0.03863883,0.5085675,0.00141485,0.0003588111,0.000008481079,0.00003095835],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901037,0.00001310567,0.00000326634,0.005698953,0.0002526224,0.001173554,0.000003088313,0.00001876222,0.002733],"genre_scores_gemma":[0.9990888,0.000002575921,0.000006967606,0.000204952,0.0001088578,0.0001922184,0.00001281845,0.000007746945,0.0003750573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4905148,"threshold_uncertainty_score":0.1419772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2435107861828159,"score_gpt":0.5128631239450444,"score_spread":0.2693523377622285,"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."}}