{"id":"https://openalex.org/W2134696992","doi":"https://doi.org/10.5555/644108.644250","title":"High-order entropy-compressed text indexes","display_name":"High-order entropy-compressed text indexes","publication_year":2003,"publication_date":"2003-01-12","ids":{"openalex":"https://openalex.org/W2134696992","doi":"https://doi.org/10.5555/644108.644250","mag":"2134696992"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.8553","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.8553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.di.unipi.it/~grossi/PAPERS/sodaconf03FINAL-LATEST.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1808/7192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006984021","display_name":"Roberto Grossi","orcid":"https://orcid.org/0000-0002-7985-4222","observed_orcids":["https://orcid.org/0000-0002-7985-4222"]},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Grossi","raw_affiliation_strings":["Universit\u00e0 di Pisa, Pisa,"],"raw_orcid":"https://orcid.org/0000-0002-7985-4222","affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Pisa, Pisa,","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602560","display_name":"Ankur Kumar Gupta","orcid":"https://orcid.org/0000-0001-8528-9509","observed_orcids":["https://orcid.org/0000-0001-8528-9509"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankur Gupta","raw_affiliation_strings":["Center for Geometric and Biological Computing, Durham, NC#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-8528-9509","affiliations":[{"raw_affiliation_string":"Center for Geometric and Biological Computing, Durham, NC#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003340402","display_name":"Jeffrey Scott Vitter","orcid":"https://orcid.org/0000-0001-7970-6118","observed_orcids":["https://orcid.org/0000-0001-7970-6118"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Scott Vitter","raw_affiliation_strings":["Purdue Univ., West LaFayette, IN"],"raw_orcid":"https://orcid.org/0000-0001-7970-6118","affiliations":[{"raw_affiliation_string":"Purdue Univ., West LaFayette, IN","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.4274,"has_fulltext":false,"cited_by_count":648,"citation_normalized_percentile":{"value":0.98907707,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"841","last_page":"850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11567","display_name":"semigroups and automata theory","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compressed-suffix-arrays","display_name":"compressed suffix arrays","score":0.9610000252723694},{"id":"https://openalex.org/keywords/text-indexing","display_name":"text indexing","score":0.7680000066757202},{"id":"https://openalex.org/keywords/entropy-compression","display_name":"entropy compression","score":0.7630000114440918},{"id":"https://openalex.org/keywords/space-time-tradeoff","display_name":"space-time tradeoff","score":0.6840000152587891},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"pattern matching","score":0.722000002861023},{"id":"https://openalex.org/keywords/space-efficient-data-structures","display_name":"space-efficient data structures","score":0.4860000014305115}],"concepts":[{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.7928715944290161},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6197661757469177},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6119643449783325},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.6084384322166443},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.59247225522995},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5825937986373901},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.5750304460525513},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.5372282266616821},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.4994802474975586},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49389511346817017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3405764102935791},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.33830124139785767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3085443377494812},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15845558047294617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07866320013999939},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.8553","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.8553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.di.unipi.it/~grossi/PAPERS/sodaconf03FINAL-LATEST.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.4235","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.4235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/~jsv/Papers/GGV03.entropy.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.603.8960","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.603.8960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/courses/cps296.5/spring03/presentations/sodaconf03.pdf","raw_type":"text"},{"id":"pmh:oai:arpi.unipi.it:11568/225936","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/225936","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:kuscholarworks.ku.edu:1808/7192","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1808/7192","pdf_url":null,"source":{"id":"https://openalex.org/S4377196285","display_name":"KU ScholarWorks (University of Kansas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I146416000","host_organization_name":"University of Kansas","host_organization_lineage":["https://openalex.org/I146416000"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"mag:2134696992","doi":"https://doi.org/10.5555/644108.644250","is_oa":false,"landing_page_url":"http://olivernash.org/2014/01/03/dna-of-a-password-disaster/docs/WaveletTree.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:kuscholarworks.ku.edu:1808/7192","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1808/7192","pdf_url":null,"source":{"id":"https://openalex.org/S4377196285","display_name":"KU ScholarWorks (University of Kansas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I146416000","host_organization_name":"University of Kansas","host_organization_lineage":["https://openalex.org/I146416000"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1492127831","https://openalex.org/W1546738280","https://openalex.org/W1573714593","https://openalex.org/W1603784832","https://openalex.org/W1975454935","https://openalex.org/W1985174631","https://openalex.org/W1986970296","https://openalex.org/W2013697960","https://openalex.org/W2056707490","https://openalex.org/W2057622603","https://openalex.org/W2088362495","https://openalex.org/W2114790712","https://openalex.org/W2121252285","https://openalex.org/W2125203709","https://openalex.org/W2142509031","https://openalex.org/W2149243190","https://openalex.org/W2155512447","https://openalex.org/W2158322625","https://openalex.org/W2158874082","https://openalex.org/W2160484851"],"related_works":["https://openalex.org/W2533248932","https://openalex.org/W2170899819","https://openalex.org/W2161488606","https://openalex.org/W2159647614","https://openalex.org/W2158874082","https://openalex.org/W2158322625","https://openalex.org/W2149243190","https://openalex.org/W2130080588","https://openalex.org/W2107082304","https://openalex.org/W2088386938","https://openalex.org/W2073921136","https://openalex.org/W2046038806","https://openalex.org/W2044014345","https://openalex.org/W1990061958","https://openalex.org/W1985174631","https://openalex.org/W1974033543","https://openalex.org/W1965853364","https://openalex.org/W1949346071","https://openalex.org/W1523949762","https://openalex.org/W1509727978"],"abstract_inverted_index":{"We":[0,39],"present":[1],"a":[2,19,112,135],"novel":[3],"implementation":[4],"of":[5,24,67,86,108],"compressed":[6,42],"suffix":[7,43],"arrays":[8,44],"exhibiting":[9],"new":[10],"tradeoffs":[11,150],"between":[12],"search":[13,140],"time":[14,141],"and":[15,127,149],"space":[16,98],"occupancy":[17],"for":[18],"given":[20],"text":[21,58,110,118,136],"(or":[22],"sequence)":[23],"n":[25],"symbols":[26],"over":[27],"an":[28],"alphabet":[29,129],",":[30],"where":[31],"each":[32],"symbol":[33],"is":[34,94,119,131],"encoded":[35],"by":[36],"lg|\u03a3|":[37,72,80],"bits.":[38,146],"show":[40],"that":[41,91,123,142],"use":[45],"just":[46],"nH_h":[47],"+":[48,73],"O(n":[49],"lg":[50,51],"n/lg_|\u03a3|":[52],"n)":[53],"bits,":[54],"while":[55],"retaining":[56],"full":[57],"indexing":[59],"functionalities,":[60],"such":[61],"as":[62],"searching":[63],"any":[64],"pattern":[65],"sequence":[66],"length":[68],"m":[69],"in":[70,97,153],"O(m":[71],"polylog(n))":[74],"time.":[75],"The":[76],"term":[77],"H_h":[78,124],"\u2264":[79],"denotes":[81],"the":[82,87,105,109,117,128,154],"hth-order":[83],"empirical":[84,106],"entropy":[85,107],"text,":[88],"which":[89],"means":[90],"our":[92],"index":[93,137],"nearly":[95],"optimal":[96],"apart":[99],"from":[100],"lower-order":[101],"terms,":[102],"achieving":[103],"asymptotically":[104],"(with":[111],"multiplicative":[113],"constant":[114],"1).":[115],"If":[116],"highly":[120],"compressible":[121],"so":[122],"=":[125],"o(1)":[126],"size":[130],"small,":[132],"we":[133],"obtain":[134],"with":[138],"o(m)":[139],"requires":[143],"only":[144],"o(n)":[145],"Further":[147],"results":[148],"are":[151],"reported":[152],"paper.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":36},{"year":2017,"cited_by_count":42},{"year":2016,"cited_by_count":33},{"year":2015,"cited_by_count":46},{"year":2014,"cited_by_count":47},{"year":2013,"cited_by_count":65},{"year":2012,"cited_by_count":66}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}