{"id":"W4405205056","doi":"10.2196/63881","title":"InfectA-Chat, an Arabic Large Language Model for Infectious Diseases: Comparative Analysis","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Arabic; Natural language processing; Coronavirus disease 2019 (COVID-19); Linguistics; Infectious disease (medical specialty); World Wide Web; Medicine","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":[0.005315137,0.001608881,0.0008784056,0.001903107,0.0006975021,0.001374734,0.00119079,0.00113403,0.00511625],"category_scores_gemma":[0.01546666,0.0003111594,0.00159011,0.0009251834,0.0003506515,0.002451739,0.001182007,0.00215454,0.001486099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002088583,"about_ca_system_score_gemma":0.001599335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02063747,"about_ca_topic_score_gemma":0.01740645,"domain_scores_codex":[0.9975985,0.001639296,0.0001396131,0.0003352134,0.0001603998,0.0001269729],"domain_scores_gemma":[0.9840376,0.01396052,0.0002765165,0.0004779582,0.0009164548,0.000331043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004666002,0.00162222,0.07155626,0.001590996,0.001715174,0.000683451,0.0008474986,0.4965186,0.002518428,0.008009051,0.04164756,0.3686247],"study_design_scores_gemma":[0.00006182942,0.0002275379,0.004328094,0.00004103358,0.0001369158,0.00009023047,0.0002126391,0.9896724,0.0004763335,0.002913263,0.001808051,0.00003163309],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7081289,0.01464756,0.2385081,0.003841052,0.001008286,0.0008684202,0.01343248,0.006237396,0.01332779],"genre_scores_gemma":[0.9137856,0.001230463,0.06916729,0.0004732234,0.0001715612,0.0005509485,0.01173442,0.0002773457,0.002609131],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02063747,"threshold_uncertainty_score":0.0410347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08991564170273754,"score_gpt":0.4769013428451054,"score_spread":0.3869857011423679,"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."}}