{"id":"W4281288662","doi":"10.1101/2022.05.19.492613","title":"Succinct <i>k</i> -mer Sets Using Subset Rank Queries on the Spectral Burrows-Wheeler Transform <sup>*</sup>","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Academy of Finland","keywords":"Substring; Lossless compression; String (physics); Suffix tree; Combinatorics; Data structure; Mathematics; Entropy (arrow of time); Computer science; Data compression; Discrete mathematics; Theoretical computer science; Algorithm","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":[0.002017503,0.0007800934,0.002238515,0.002339814,0.001145628,0.003320055,0.002058186,0.001412198,0.003971048],"category_scores_gemma":[0.01459461,0.0005429747,0.0008639449,0.004426709,0.00132788,0.007712572,0.003868827,0.001514259,0.001835992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001390854,"about_ca_system_score_gemma":0.001459743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001800893,"about_ca_topic_score_gemma":0.002316849,"domain_scores_codex":[0.9961548,0.0005961478,0.0004204414,0.0004489329,0.002034219,0.0003453722],"domain_scores_gemma":[0.9908553,0.003587184,0.0007347098,0.003335977,0.001114249,0.0003725839],"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":[0.00310189,0.001162243,0.01141804,0.000727909,0.0001435257,0.001280268,0.002314268,0.1461083,0.1008,0.1845219,0.03709513,0.5113265],"study_design_scores_gemma":[0.0001738085,0.0004762372,0.001317492,0.00006284567,0.0000414833,0.0005956601,0.0009714188,0.8156393,0.04944918,0.119679,0.01150898,0.00008457687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3737959,0.0007744455,0.5968926,0.001928853,0.0001444038,0.0007078745,0.006104815,0.009540889,0.01011019],"genre_scores_gemma":[0.6428116,0.0002861309,0.3423958,0.0003920314,0.0001289917,0.0004354026,0.009305037,0.0005453241,0.003699633],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003971048,"threshold_uncertainty_score":0.01328444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0207605215181029,"score_gpt":0.2306598103537979,"score_spread":0.209899288835695,"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."}}