{"id":"https://openalex.org/W7220904664","doi":"https://doi.org/10.48550/arxiv.2610.10500","title":"Taxonomic Classification with Tag Arrays","display_name":"Taxonomic Classification with Tag Arrays","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220904664","doi":"https://doi.org/10.48550/arxiv.2610.10500"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.10500","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.10500","pdf_url":"https://arxiv.org/pdf/2610.10500","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.10500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013172801","display_name":"Travis Gagie","orcid":"https://orcid.org/0000-0003-3689-327X","observed_orcids":["https://orcid.org/0000-0003-3689-327X"]},"institutions":[{"id":"https://openalex.org/I4405268203","display_name":"Centre for Biotechnology and Bioengineering","ror":"https://ror.org/0066thn33","country_code":"CL","type":"facility","lineage":["https://openalex.org/I4405268203"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Gagie, Travis","raw_affiliation_strings":["CeBiB -Center for Biotechnology and Bioengineering , Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CeBiB -Center for Biotechnology and Bioengineering , Chile","institution_ids":["https://openalex.org/I4405268203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157961618","display_name":"Gonzalo Navarro","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405268203","display_name":"Centre for Biotechnology and Bioengineering","ror":"https://ror.org/0066thn33","country_code":"CL","type":"facility","lineage":["https://openalex.org/I4405268203"]},{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Navarro, Gonzalo","raw_affiliation_strings":["CeBiB -Center for Biotechnology and Bioengineering , Chile","Department of Computer Science , University of Chile , Santiago , Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CeBiB -Center for Biotechnology and Bioengineering , Chile","institution_ids":["https://openalex.org/I4405268203"]},{"raw_affiliation_string":"Department of Computer Science , University of Chile , Santiago , Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9390000104904175,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9390000104904175,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0575999990105629,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/taxonomic-classification","display_name":"taxonomic classification","score":0.9549999833106995},{"id":"https://openalex.org/keywords/maximal-exact-matches","display_name":"maximal exact matches","score":0.6990000009536743},{"id":"https://openalex.org/keywords/16s-rrna","display_name":"16S rRNA","score":0.8769999742507935},{"id":"https://openalex.org/keywords/burrows-wheeler-transform","display_name":"Burrows-Wheeler transform","score":0.7789999842643738},{"id":"https://openalex.org/keywords/nanopore-reads","display_name":"nanopore reads","score":0.5910000205039978},{"id":"https://openalex.org/keywords/silva","display_name":"SILVA","score":0.5130000114440918},{"id":"https://openalex.org/keywords/k-mer-indexing","display_name":"k-mer indexing","score":0.4169999957084656}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7312999963760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6241999864578247},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.5372999906539917},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.5353999733924866},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4339999854564667},{"id":"https://openalex.org/C2780422015","wikidata":"https://www.wikidata.org/wiki/Q402152","display_name":"Ancestor","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33399999141693115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C48702757","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Biological classification","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2778328004","wikidata":"https://www.wikidata.org/wiki/Q122422","display_name":"Squamata","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.10500","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.10500","pdf_url":"https://arxiv.org/pdf/2610.10500","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.10500","doi":"https://doi.org/10.48550/arxiv.2610.10500","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.10500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.10500","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.10500","pdf_url":"https://arxiv.org/pdf/2610.10500","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220904664.pdf","grobid_xml":"https://content.openalex.org/works/W7220904664.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4389363634","https://openalex.org/W4401034109","https://openalex.org/W7161691638"],"related_works":["https://openalex.org/W7221064640","https://openalex.org/W4413508788","https://openalex.org/W4391800639","https://openalex.org/W4416373688","https://openalex.org/W4399164936","https://openalex.org/W7213223817","https://openalex.org/W5935772","https://openalex.org/W4378803010","https://openalex.org/W4399724822","https://openalex.org/W4385073184"],"abstract_inverted_index":{"Taxonomic":[0],"classifiers":[1],"based":[2],"on":[3,73,79,119,187,222,251,262,272],"exact":[4,49],"matches":[5,9],"differ":[6],"in":[7,13,100,129,139,148,164,214,288,299],"which":[8,311],"they":[10],"use":[11,293],"and":[12,54,125,170,182,210,226,237,241,259],"how":[14,172],"each":[15,40,47,101,130,294],"match":[16,50],"splits":[17,56],"its":[18,273],"credit":[19,29,59,90],"among":[20],"the":[21,31,43,67,74,93,98,104,143,149,159,167,191,223,263,315],"taxa":[22],"containing":[23],"it:":[24],"Kraken~2":[25],"gives":[26,46],"a":[27,57,62,120,133,194,212,303,308],"$k$-mer's":[28],"to":[30,85,92,109,142,317],"lowest":[32],"common":[33,177],"ancestor":[34],"of":[35,42,66,95,97,145,161,166,171,190,302,305,314],"those":[36],"taxa,":[37],"SPUMONI~2":[38],"labels":[39],"position":[41],"read,":[44],"Tagger":[45],"maximal":[48],"(MEM)":[51],"one":[52,217,289,300],"label,":[53],"Cliffy":[55],"match's":[58],"evenly":[60],"over":[61],"roughly":[63],"logarithmic":[64],"sample":[65],"taxa.":[68],"We":[69,113,157],"compare":[70],"these":[71],"schemes":[72],"same":[75,224],"long":[76,115,176,285],"MEMs,":[77,297],"mainly":[78],"short":[80],"16S":[81],"rRNA":[82],"reads":[83,225,278,316],"classified":[84],"genera":[86],"with":[87,117,132,175,197,216,307,320],"SILVA,":[88],"where":[89,282],"proportional":[91,141],"number":[94,144,160],"occurrences":[96,128],"MEM":[99,286],"taxon":[102,131],"is":[103,229],"most":[105,199],"accurate,":[106],"by":[107],"1.0":[108],"6.8":[110],"percentage":[111,243],"points.":[112],"compute":[114],"MEMs":[116],"Boyer--Moore--Li":[118,306],"run-length":[121,135],"compressed":[122,136],"suffix":[123],"array,":[124,138],"count":[126],"their":[127,318],"complete,":[134],"tag":[137,146,162],"time":[140],"runs":[147,163,169],"MEM's":[150],"BWT":[151,168],"interval,":[152],"without":[153],"locating":[154],"any":[155],"occurrence.":[156],"bound":[158],"terms":[165],"often":[173],"suffixes":[174],"prefixes":[178],"have":[179,193],"different":[180],"tags,":[181],"show":[183],"that":[184],"tags":[185],"constant":[186],"$d$":[188],"blocks":[189],"text":[192],"macro":[195],"scheme":[196],"at":[198,219],"$r":[200],"+":[201],"2d$":[202],"phrases.":[203],"On":[204,276],"SILVA":[205],"our":[206],"index":[207],"takes":[208,257],"1.44\\,GB":[209],"classifies":[211],"read":[213],"66\\,$\u03bc$s":[215],"thread":[218],"93.8\\%":[220],"accuracy;":[221],"server,":[227,264],"it":[228,256],"14":[230],"times":[231,239],"smaller":[232],"than":[233,247],"Cliffy's":[234,248,269],"undigested":[235],"index,":[236],"4.4":[238],"faster":[240],"8":[242],"points":[244],"more":[245],"accurate":[246],"LCA":[249,270],"query":[250,271],"it.":[252],"Over":[253],"minimizer":[254],"digests":[255],"0.49\\,GB":[258],"reaches":[260],"92.5\\%;":[261],"92.1\\%":[265],"against":[266],"84.2\\%":[267],"for":[268],"digested":[274],"index.":[275],"nanopore":[277],"from":[279],"whole":[280],"genomes,":[281],"almost":[283],"every":[284],"occurs":[287],"species,":[290],"we":[291],"instead":[292],"read's":[295],"longest":[296],"found":[298],"pass":[301],"variant":[304],"$k$-mer":[309],"filter,":[310],"assigns":[312],"99.6\\%":[313],"species":[319],"no":[321],"length":[322],"threshold.":[323]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-09T00:00:00"}