{"id":"W4410516993","doi":"10.1038/s43856-025-00903-w","title":"Hidden challenges in evaluating spillover risk of zoonotic viruses using machine learning models","year":2025,"lang":"en","type":"article","venue":"Communications Medicine","topic":"Zoonotic diseases and public health","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Precursory Research for Embryonic Science and Technology; Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Spillover effect; Computer science; Artificial intelligence; Virology; Machine learning; Biology; Economics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001859011,0.0001492142,0.0005307472,0.0004764882,0.00014812,0.000004993708,0.0003914577,0.00008089697,0.0001453816],"category_scores_gemma":[0.002615638,0.0001244908,0.00006667945,0.0006039234,0.0002232198,0.0001015249,0.0002521162,0.0005294962,0.000003411528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001477817,"about_ca_system_score_gemma":0.0004495555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002860649,"about_ca_topic_score_gemma":0.0003928998,"domain_scores_codex":[0.9980542,0.0005083009,0.0007030719,0.0002179,0.0002845348,0.0002319825],"domain_scores_gemma":[0.9970145,0.0008828486,0.000266052,0.001470224,0.000236962,0.0001293746],"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":[0.0004619154,0.001741669,0.1805535,0.002292545,0.0005748929,0.000009919879,0.009411605,0.007092079,0.00152778,0.08667105,0.0001694628,0.7094936],"study_design_scores_gemma":[0.003835455,0.0004184792,0.03273258,0.003375268,0.0006454435,0.000009113858,0.005207116,0.9408052,0.00002653134,0.008541586,0.00424473,0.0001585094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7430531,0.1534401,0.002372885,0.02363059,0.0002103103,0.001150625,0.00001795643,0.0001178767,0.07600656],"genre_scores_gemma":[0.9689706,0.02250861,0.007789682,0.0004667499,0.00004614965,0.00002002811,0.00003579752,0.00001829224,0.000144091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9337131,"threshold_uncertainty_score":0.5076588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3328424760754218,"score_gpt":0.4448740010224857,"score_spread":0.1120315249470639,"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."}}