{"id":"W4407568760","doi":"10.1101/2025.02.13.638012","title":"Developing Foundation Models for Predicting Viral Animal Host Range in Intelligent Surveillance","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Key Research and Development Program of China; Peking University; National Natural Science Foundation of China","keywords":"Host (biology); Foundation (evidence); Range (aeronautics); Computer science; Virology; Biology; Engineering; Political science; Ecology; Aerospace engineering","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":[0.001807633,0.0009111354,0.0007347209,0.001238676,0.0002877276,0.0007788496,0.0009468672,0.0009170378,0.001028048],"category_scores_gemma":[0.004674542,0.000459059,0.0008390572,0.0005453928,0.0005103888,0.001137548,0.0009093492,0.001054675,0.0002729373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008266014,"about_ca_system_score_gemma":0.0008649332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008099088,"about_ca_topic_score_gemma":0.009198934,"domain_scores_codex":[0.9995578,0.0001645261,0.00002502583,0.0001358622,0.00005753327,0.00005922657],"domain_scores_gemma":[0.9974177,0.00187645,0.0002411586,0.0001332756,0.0002456256,0.00008575346],"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":[0.00009818421,0.00005300496,0.01016982,0.00004217103,0.00006991432,0.0000663589,0.00003506161,0.9481863,0.001016327,0.001822883,0.001193087,0.03724697],"study_design_scores_gemma":[0.000002098133,0.000008987265,0.0002014531,0.000003424006,0.00000321946,0.000005578224,0.000002727972,0.9986176,0.0001030959,0.0009717171,0.00007848628,0.000001517672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2913818,0.001072675,0.6992992,0.001229689,0.00009461759,0.00008275273,0.001466761,0.002722807,0.00264965],"genre_scores_gemma":[0.9296609,0.0002276532,0.06701985,0.0002030691,0.00005996619,0.00009493029,0.001531991,0.00006511392,0.001136538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008099088,"threshold_uncertainty_score":0.01610386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03026296275175833,"score_gpt":0.2780579926039816,"score_spread":0.2477950298522233,"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."}}