{"id":"W3129775080","doi":"10.1101/2021.02.17.431713","title":"Compression for population genetic data through finite-state entropy","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Universities Space Research Association","keywords":"Computation; Computer science; Population; Data compression; Entropy (arrow of time); Conditional entropy; Genome-wide association study; Algorithm; Data mining; Principle of maximum entropy; Artificial intelligence; Biology; Genetics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009483678,0.0003545553,0.0004315922,0.001070432,0.0003420183,0.001056856,0.0008020584,0.0004203091,0.002788718],"category_scores_gemma":[0.005734285,0.0001604513,0.0003080868,0.001350613,0.0007898483,0.001602767,0.0009922349,0.0007392034,0.0006427467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005742222,"about_ca_system_score_gemma":0.000622768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001034971,"about_ca_topic_score_gemma":0.0008961324,"domain_scores_codex":[0.9993717,0.0001602162,0.00005805448,0.00008225765,0.0002805976,0.00004728429],"domain_scores_gemma":[0.9964752,0.001990489,0.0001479358,0.0009326478,0.0004074079,0.00004635825],"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":[0.0009397332,0.0001854702,0.003740752,0.000205163,0.0000692568,0.0003720528,0.0004142252,0.2402199,0.04586009,0.1343782,0.009675088,0.56394],"study_design_scores_gemma":[0.00004112577,0.00005294486,0.0005708286,0.00002379889,0.000009259615,0.000122649,0.00004176417,0.8931955,0.04700037,0.0558946,0.003030912,0.00001639525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08431086,0.0003124798,0.9090041,0.0005954578,0.0001232789,0.00005615645,0.0005603617,0.003046485,0.001990835],"genre_scores_gemma":[0.6317849,0.0003061125,0.3631067,0.0002010385,0.0001046687,0.0001621918,0.001586479,0.000264699,0.002483193],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002788718,"threshold_uncertainty_score":0.0093292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0347364983110735,"score_gpt":0.2617207467837306,"score_spread":0.2269842484726571,"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."}}