{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007303815,0.001439521,0.00150113,0.002407896,0.001322963,0.003539418,0.006637405,0.002248662,0.01451591],"category_scores_gemma":[0.02906414,0.001634663,0.002746994,0.003224471,0.001009881,0.006652138,0.004712123,0.00526557,0.006885825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001633489,"about_ca_system_score_gemma":0.003421169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00804657,"about_ca_topic_score_gemma":0.008680551,"domain_scores_codex":[0.9978168,0.0007470907,0.0002176611,0.0003032801,0.0007530625,0.0001621253],"domain_scores_gemma":[0.9905069,0.003959659,0.0003444235,0.002262852,0.002113012,0.0008131886],"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":[0.0007404828,0.0002899855,0.02141069,0.002618598,0.0004471582,0.0008270985,0.001050898,0.4197818,0.008863569,0.136872,0.2220094,0.1850883],"study_design_scores_gemma":[0.0002934597,0.0001250993,0.002188285,0.0007426241,0.0001253758,0.000365873,0.0001704415,0.5594345,0.00528487,0.09292155,0.3381096,0.0002381737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05449317,0.005739183,0.7509953,0.00889379,0.002324002,0.0004851669,0.04335849,0.09578385,0.03792697],"genre_scores_gemma":[0.1026513,0.004547125,0.7955598,0.002075686,0.0003746362,0.001115263,0.06729309,0.02305697,0.003326218],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01451591,"threshold_uncertainty_score":0.04856056,"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."}}