{"id":"W4376167123","doi":"10.48550/arxiv.2305.05893","title":"Acceleration of FM-index Queries Through Prefix-free Parsing","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Human Genome Research Institute; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Directorate for Biological Sciences; National Institutes of Health; National Science Foundation","keywords":"Prefix; Computer science; Parsing; Word (group theory); Suffix; Suffix array; Search engine indexing; Trie; Sorting; Suffix tree; Character (mathematics); Index (typography); String (physics); Code (set theory); Artificial intelligence; Data structure; Algorithm; Programming language; Set (abstract data type); Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001901505,0.0002551202,0.0003421625,0.0001665391,0.0001789918,0.0001459831,0.002421939,0.0002591133,0.00001638483],"category_scores_gemma":[0.00004838711,0.0002772439,0.0001483167,0.0005152064,0.0001073054,0.001135542,0.005396281,0.0003771513,0.00002954941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009969083,"about_ca_system_score_gemma":0.000162624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006995339,"about_ca_topic_score_gemma":0.00009128395,"domain_scores_codex":[0.998288,0.0001054542,0.0002582607,0.0009189009,0.0001574744,0.0002719427],"domain_scores_gemma":[0.9972966,0.00009922827,0.0003477196,0.002009623,0.0001733608,0.00007346318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000146962,0.0002985554,0.007555917,0.0005295199,0.0002531178,0.0003712196,0.002194369,0.404451,0.0003588138,0.5704709,0.008079992,0.005289662],"study_design_scores_gemma":[0.000509119,0.00007333725,0.004168377,0.000284656,0.00003922878,0.000002586313,0.0001150496,0.7687211,0.0009805739,0.223454,0.001193052,0.0004588879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04952979,0.00004912683,0.9476355,0.0001318304,0.0009297671,0.0002160984,0.00005286925,0.0003305697,0.001124491],"genre_scores_gemma":[0.9861384,0.0002347198,0.01265394,0.00003418414,0.00009558377,7.670572e-7,0.00005527293,0.00001955138,0.0007675756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9366086,"threshold_uncertainty_score":0.999968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1616371602638194,"score_gpt":0.2160245113640064,"score_spread":0.05438735110018697,"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."}}