{"id":"W4307979298","doi":"10.1101/2022.10.29.514266","title":"Expanding the stdpopsim species catalog, and lessons learned for realistic genome simulations","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; Science for Life Laboratory; Knut och Alice Wallenbergs Stiftelse; Brown University; Deutsche Forschungsgemeinschaft; University of Edinburgh; Robertson Foundation; National Institutes of Health; National Science Foundation","keywords":"Inference; Computer science; Population; Data science; Genome; Crossover; Sophistication; Obstacle; Benchmarking; Data mining; Biology; Machine learning; Artificial intelligence; Geography; Genetics; Gene","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":[0.0112406,0.001291188,0.001461585,0.002978892,0.001246781,0.003830867,0.007292818,0.002094788,0.01285629],"category_scores_gemma":[0.04120421,0.001534196,0.00225265,0.003726777,0.001159533,0.007622238,0.005424419,0.004897298,0.005420698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001670734,"about_ca_system_score_gemma":0.003522739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007281039,"about_ca_topic_score_gemma":0.007121877,"domain_scores_codex":[0.9970781,0.0009984281,0.0003031186,0.000384985,0.001046192,0.0001892165],"domain_scores_gemma":[0.9792143,0.009226484,0.0006427888,0.005064433,0.004373657,0.001478196],"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":[0.0008317489,0.0002992749,0.02472491,0.002956647,0.0004210759,0.0008929475,0.001251083,0.3261091,0.008115628,0.1487647,0.2102695,0.2753635],"study_design_scores_gemma":[0.0002884835,0.0001581685,0.00265647,0.001150474,0.0001321252,0.0004160113,0.0002380326,0.4937792,0.006491455,0.1051014,0.3893369,0.0002511736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06709579,0.006931121,0.7542894,0.0119461,0.002181966,0.0004695834,0.03436591,0.0898121,0.03290799],"genre_scores_gemma":[0.1095779,0.004204313,0.8145161,0.002094137,0.0003325722,0.0008215266,0.04799934,0.01813473,0.002319409],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01285629,"threshold_uncertainty_score":0.05944669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03119683748765339,"score_gpt":0.2814751036992191,"score_spread":0.2502782662115657,"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."}}