{"id":"W4384120659","doi":"10.1001/jamaophthalmol.2023.2754","title":"Performance of an Upgraded Artificial Intelligence Chatbot for Ophthalmic Knowledge Assessment","year":2023,"lang":"en","type":"letter","venue":"JAMA Ophthalmology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; University of Toronto; Western University","funders":"","keywords":"Medicine; Chatbot; Medical physics; Optometry; Artificial intelligence; Computer science","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009324517,0.0004655235,0.001083657,0.0006501836,0.0001831584,0.00003388762,0.0004776728,0.001880657,0.0003897666],"category_scores_gemma":[0.0004519915,0.0004550187,0.0003047191,0.0005466478,0.0003273689,0.0001633418,0.00008859016,0.001820351,0.0002751809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000310793,"about_ca_system_score_gemma":0.001271159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003106878,"about_ca_topic_score_gemma":0.000007081608,"domain_scores_codex":[0.9961792,0.0002392612,0.00146914,0.0008829162,0.0003687252,0.0008608192],"domain_scores_gemma":[0.996438,0.001091194,0.000569443,0.0009121305,0.0008136173,0.000175577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002435771,0.00283374,0.0103021,0.01842688,0.0007643232,0.004283341,0.004352559,0.0001561672,0.002871895,0.001019861,0.4055657,0.5469876],"study_design_scores_gemma":[0.001148115,0.1061333,0.05755005,0.009577623,0.003994861,0.05332593,0.01304371,0.1938557,0.2405641,0.09898833,0.2126825,0.00913582],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7996318,0.0001485089,0.000117148,0.190495,0.005200039,0.002042517,0.0001054628,0.0001174246,0.002142069],"genre_scores_gemma":[0.9551157,0.0001037383,0.002755912,0.02172289,0.01305293,0.000918258,0.002294079,0.0002046657,0.003831787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5378518,"threshold_uncertainty_score":0.9997901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3044060482541513,"score_gpt":0.4875269611308485,"score_spread":0.1831209128766972,"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."}}