{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001425484,0.001864522,0.001306913,0.002958134,0.0009892659,0.002728013,0.003156722,0.00139676,0.01172838],"category_scores_gemma":[0.01049573,0.000674082,0.001183526,0.005527081,0.0008319772,0.005204842,0.002825141,0.001459591,0.009990982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001218862,"about_ca_system_score_gemma":0.002029138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004174903,"about_ca_topic_score_gemma":0.004722442,"domain_scores_codex":[0.9973056,0.0003239557,0.0003185788,0.0005826634,0.001187341,0.0002817315],"domain_scores_gemma":[0.9957851,0.001675823,0.0001873929,0.001404611,0.0008226947,0.0001243598],"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":[0.00106103,0.0003683611,0.003677849,0.0006084001,0.0001316296,0.0002716707,0.0005827782,0.0151985,0.05444314,0.01978066,0.07431727,0.8295587],"study_design_scores_gemma":[0.0004214426,0.000333428,0.003594089,0.0001131044,0.0001174308,0.0009968999,0.000539702,0.6994799,0.1470694,0.05719844,0.08995713,0.0001789656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07064389,0.001970453,0.7643266,0.0008769244,0.0005591449,0.0003580142,0.005568511,0.139444,0.01625254],"genre_scores_gemma":[0.1576209,0.0004543996,0.8091441,0.0004443542,0.0002116209,0.0003967331,0.01606559,0.007228633,0.008433697],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01172838,"threshold_uncertainty_score":0.03923535,"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."}}