{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004399515,0.0005845394,0.0006335418,0.0001474552,0.0003829036,0.001145296,0.003753874,0.0003848575,0.00001804415],"category_scores_gemma":[0.0002621892,0.0005883615,0.0001431267,0.0004304612,0.00005002254,0.001276479,0.006806023,0.0005567713,0.00001931184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001270357,"about_ca_system_score_gemma":0.0004464467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002159218,"about_ca_topic_score_gemma":0.000003591114,"domain_scores_codex":[0.9956381,0.0001976679,0.0007312009,0.002184867,0.0006126027,0.0006355552],"domain_scores_gemma":[0.9926771,0.0002133081,0.0006241207,0.005770977,0.0004925846,0.0002219131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004216843,0.00413052,0.02286273,0.008224318,0.001932801,0.002053873,0.0004846983,0.06250963,0.8374557,0.01929816,0.03854012,0.002085738],"study_design_scores_gemma":[0.001177784,0.00008185397,0.05263597,0.00126358,0.00011738,7.601159e-8,0.000002004327,0.8786687,0.03576677,0.0001013081,0.02853476,0.001649798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05687993,0.002069721,0.935621,0.0001759554,0.002777037,0.0009292638,0.001055397,0.0004902523,0.000001450106],"genre_scores_gemma":[0.466226,0.0004679428,0.5323346,0.00023243,0.0004812197,0.0001374485,0.00003516426,0.00008098814,0.000004159828],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8161591,"threshold_uncertainty_score":0.9998916,"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."}}