{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00461829,0.0008094824,0.0005740446,0.0007206835,0.0007010511,0.00156931,0.001250511,0.001909991,0.001762795],"category_scores_gemma":[0.0139702,0.0003026429,0.000651253,0.001089961,0.0006758593,0.001900955,0.001034618,0.002257803,0.0005651063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001164005,"about_ca_system_score_gemma":0.001327258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02933111,"about_ca_topic_score_gemma":0.02360559,"domain_scores_codex":[0.9985477,0.0008746689,0.00006734644,0.000177005,0.0002115551,0.0001216458],"domain_scores_gemma":[0.9878662,0.009826418,0.000242251,0.0007769463,0.0009231029,0.0003650336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001628955,0.001687676,0.04696063,0.0004783704,0.0002942314,0.003127251,0.001084896,0.7692562,0.005055346,0.01613613,0.04275272,0.1115376],"study_design_scores_gemma":[0.0001167969,0.00013875,0.002004809,0.00001714932,0.00003172116,0.0001651098,0.0004102083,0.9853461,0.001800747,0.005740288,0.004202414,0.00002591762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.862384,0.001749414,0.1006225,0.01518647,0.0005406069,0.0003307802,0.005336524,0.002206828,0.01164293],"genre_scores_gemma":[0.9409381,0.0003934873,0.05263005,0.0005148529,0.0001809158,0.00007878485,0.002791252,0.0001410275,0.002331558],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02933111,"threshold_uncertainty_score":0.05832076,"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."}}