{"id":"W4323047994","doi":"10.7554/elife.84874","title":"Expanding the stdpopsim species catalog, and lessons learned for realistic genome simulations","year":2023,"lang":"en","type":"article","venue":"eLife","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; National Human Genome Research Institute; 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; Process (computing); Benchmarking; Data mining; Biology; Machine learning; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001663083,0.00006856256,0.00006125787,0.00002641502,0.0002182807,0.00002594427,0.00008730569,0.00005273255,0.000006553888],"category_scores_gemma":[0.0002395935,0.0000552112,0.00003382936,0.00008330934,0.0000735573,0.000001314656,0.00007872873,0.0000345098,0.000008705643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008313648,"about_ca_system_score_gemma":0.00003855279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001183652,"about_ca_topic_score_gemma":0.0002217419,"domain_scores_codex":[0.9994803,0.00002033946,0.00009569139,0.0001686694,0.00008161715,0.0001533904],"domain_scores_gemma":[0.9996376,0.00004271715,0.00002961792,0.000188939,0.00006056949,0.0000405764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005405021,0.00003217804,0.004488944,0.00003977866,0.0001005789,0.00000127471,0.0006251871,0.0355368,0.9381799,0.005647648,0.0134624,0.001831239],"study_design_scores_gemma":[0.001834314,0.0003583095,0.3047312,0.0000188199,0.0001100113,0.00001631614,0.002223274,0.05273927,0.01787469,0.003006767,0.6163663,0.0007208061],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9809009,0.0003392029,0.01408946,0.002947193,0.0001362072,0.0002624624,0.0004246211,0.00004011714,0.0008598519],"genre_scores_gemma":[0.992373,0.0003780983,0.0001846167,0.0001902716,0.0001923454,0.00001801653,0.000767177,0.00001320258,0.005883229],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9203053,"threshold_uncertainty_score":0.2251447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05582397652275529,"score_gpt":0.343647141379384,"score_spread":0.2878231648566287,"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."}}