{"id":"W4409260121","doi":"10.52225/narra.v5i1.2371","title":"Chinese generative AI models (DeepSeek and Qwen) rival ChatGPT-4 in ophthalmology queries with excellent performance in Arabic and English","year":2025,"lang":"en","type":"article","venue":"Narra J","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Arabic; Generative grammar; Computer science; Natural language processing; Linguistics; Artificial intelligence; Ophthalmology; Medicine; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005116862,0.001593147,0.0008572621,0.001122783,0.000713024,0.002735612,0.001529008,0.001441104,0.004722724],"category_scores_gemma":[0.02539331,0.0003013972,0.001077038,0.0009927351,0.0008281388,0.003646429,0.002763773,0.002245455,0.001893631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001998798,"about_ca_system_score_gemma":0.003211098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03203566,"about_ca_topic_score_gemma":0.03115321,"domain_scores_codex":[0.9966292,0.001376339,0.0003160021,0.0006661295,0.0007946566,0.0002176277],"domain_scores_gemma":[0.9870134,0.009368107,0.0004275494,0.001308136,0.001271039,0.0006116584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004097,0.001251296,0.06792401,0.003190409,0.0007018103,0.001062602,0.005293545,0.1726874,0.01836671,0.01072685,0.04941941,0.665279],"study_design_scores_gemma":[0.0004699335,0.001663474,0.02356218,0.0003824958,0.0003046938,0.0006701861,0.003606247,0.8906787,0.02105277,0.01192287,0.04535758,0.0003289324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8452706,0.003313543,0.07312563,0.003112505,0.0005786117,0.001022986,0.005386698,0.02311048,0.0450788],"genre_scores_gemma":[0.9199101,0.0006941385,0.06069901,0.0009176095,0.00006225419,0.0003050022,0.007703042,0.0005658412,0.009142892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03203566,"threshold_uncertainty_score":0.06369835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04285039109542241,"score_gpt":0.3732398101649944,"score_spread":0.330389419069572,"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."}}