{"id":"W4412426567","doi":"10.2196/74085","title":"ChatGPT-4’s Level of Dermatological Knowledge Based on Board Examination Review Questions and Bloom’s Taxonomy","year":2025,"lang":"en","type":"article","venue":"JMIR Dermatology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Medicine; Dermatology; Computer science; World Wide Web","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":[0.0001729259,0.0001190133,0.0004066272,0.0002380145,0.00007940616,0.0000045968,0.0000622745,0.0001855869,0.00007186805],"category_scores_gemma":[0.0003833108,0.0001038793,0.00005533198,0.0002836495,0.0001641338,0.00003996443,0.00002132964,0.0001838582,0.0000420775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004983984,"about_ca_system_score_gemma":0.0002844523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003862552,"about_ca_topic_score_gemma":0.00004146761,"domain_scores_codex":[0.9988358,0.0001984934,0.0004880213,0.0002235013,0.00007732308,0.0001768335],"domain_scores_gemma":[0.9989395,0.0003862092,0.000110894,0.0002466547,0.0002372926,0.00007946979],"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":[0.0002283449,0.002551095,0.2888987,0.02258592,0.00009675593,0.00008018101,0.0008953995,0.000005552876,0.0004998176,0.0422565,0.0987424,0.5431593],"study_design_scores_gemma":[0.0008795048,0.0006857975,0.5427806,0.01581948,0.0005196182,0.0009304257,0.0007803375,0.00993507,0.03534545,0.002424622,0.389289,0.0006101077],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7491563,0.0419918,0.01635952,0.1399928,0.001538608,0.007145703,0.00004066737,0.0002896409,0.043485],"genre_scores_gemma":[0.9928281,0.001385096,0.0006670846,0.004211021,0.00002857431,0.0005281428,0.00003441004,0.000006247679,0.0003113539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5425492,"threshold_uncertainty_score":0.4236074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.276929403774977,"score_gpt":0.4607815919129726,"score_spread":0.1838521881379956,"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."}}