{"id":"W4399836757","doi":"10.48550/arxiv.2406.12022","title":"Constructing Ancestral Recombination Graphs through Reinforcement Learning","year":2024,"lang":"en","type":"preprint","venue":"Archipelago (University of Quebec in Montreal)","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Recombination; Reinforcement; Genealogy; Computer science; Artificial intelligence; Evolutionary biology; Biology; History; Psychology; Genetics; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002260233,0.0001920372,0.0002725301,0.0001012341,0.00008345,0.00001970034,0.0003047435,0.0002938555,0.00001391148],"category_scores_gemma":[0.00004419105,0.0002143943,0.0001927768,0.0001110139,0.000186637,0.000005288711,0.001111496,0.0005943887,0.000004662144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004881377,"about_ca_system_score_gemma":0.00009301995,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05220524,"about_ca_topic_score_gemma":0.1897,"domain_scores_codex":[0.9987977,0.0001320736,0.0002153941,0.0004893139,0.0001234081,0.0002421574],"domain_scores_gemma":[0.9994513,0.00003301082,0.0002172414,0.0002059416,0.00005163705,0.0000408409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006145911,0.0002157355,0.02714459,0.001132376,0.0005161272,0.0002241921,0.01178636,0.03958965,0.01754947,0.02353505,0.0005232762,0.8771686],"study_design_scores_gemma":[0.004999664,0.002200103,0.09523182,0.003415281,0.0004396778,0.00006305354,0.0881351,0.03860219,0.01004698,0.751737,0.001898846,0.003230293],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.98739,0.0003388801,0.001493232,0.000145991,0.0002228425,0.0001949054,0.000009061473,0.00002638178,0.01017873],"genre_scores_gemma":[0.9962119,0.0002833669,0.001999023,0.00001790606,0.00004665766,5.887823e-7,0.0003655194,0.000009364341,0.001065647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8739383,"threshold_uncertainty_score":0.9541062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01608044009283437,"score_gpt":0.2320508668493383,"score_spread":0.2159704267565039,"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."}}