{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001304883,0.0009786795,0.0007976218,0.000328665,0.001235883,0.0009903675,0.003603725,0.0004207249,0.0003879532],"category_scores_gemma":[0.00008182825,0.0007934486,0.0003817462,0.0009865935,0.0002220528,0.00077969,0.002025513,0.002002476,0.00007118937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004804974,"about_ca_system_score_gemma":0.0008823775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002376326,"about_ca_topic_score_gemma":0.00000303955,"domain_scores_codex":[0.9945852,0.0004410052,0.0007843614,0.001847418,0.001246205,0.001095849],"domain_scores_gemma":[0.995163,0.000224966,0.0004384852,0.003586703,0.0002523101,0.0003345434],"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":[0.001813924,0.006459122,0.01940034,0.004251389,0.004875503,0.005423077,0.004652525,0.1311302,0.4366749,0.3059908,0.07849037,0.0008378639],"study_design_scores_gemma":[0.003630333,0.0006964903,0.02637275,0.001762746,0.0004836385,0.000001588223,0.000102373,0.5489165,0.1932013,0.0003122841,0.2168346,0.007685458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.900915,0.001735877,0.08556395,0.003197664,0.003418396,0.002308571,0.001383146,0.001340307,0.00013713],"genre_scores_gemma":[0.9733172,0.0003158336,0.02399977,0.001251653,0.0006520773,0.0002698752,0.000003056258,0.0001765429,0.00001398865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4177862,"threshold_uncertainty_score":0.9994516,"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."}}