{"id":"W4396621042","doi":"10.21203/rs.3.rs-4244182/v1","title":"Advancing Real-time Pandemic Forecasting Using Large Language Models: A COVID-19 Case Study","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Data science; Artificial intelligence; Population; Machine learning; Intersection (aeronautics); Big data; Pandemic; Time series; Operations research; Data mining; Coronavirus disease 2019 (COVID-19); Geography; Disease; Infectious disease (medical specialty); Medicine; Engineering; Cartography","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":[0.007653128,0.0005706525,0.001118804,0.00117941,0.0004847479,0.0002555117,0.000481233,0.0003741412,0.0004359992],"category_scores_gemma":[0.004578128,0.0005347105,0.0003548343,0.001039949,0.0001464699,0.000147808,0.005372544,0.003481386,0.0001916082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002733106,"about_ca_system_score_gemma":0.00450758,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01291615,"about_ca_topic_score_gemma":0.002818402,"domain_scores_codex":[0.9921623,0.001437407,0.0008012422,0.001777279,0.002152103,0.001669698],"domain_scores_gemma":[0.9944062,0.001139289,0.0001856609,0.002153439,0.0006792942,0.001436098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"case_report","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001538806,0.00288683,0.07271005,0.04511269,0.001769467,0.7789885,0.04964963,0.02374598,0.00295479,0.00008498457,0.01115718,0.009401141],"study_design_scores_gemma":[0.003683426,0.0006488928,0.0002763022,0.006268112,0.0005189482,0.008173896,0.07285772,0.9039329,0.00001771038,0.001744396,0.0008805566,0.0009971531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9840347,0.003826936,0.0006424948,0.0001665781,0.0001871287,0.004983682,0.003267878,0.0009692039,0.001921452],"genre_scores_gemma":[0.9950144,0.0002050763,0.001451778,0.00008288704,0.000720104,0.0003700926,0.001003833,0.0002452122,0.0009065946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8801869,"threshold_uncertainty_score":0.9997104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1755556517200205,"score_gpt":0.4866044541106803,"score_spread":0.3110488023906598,"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."}}