{"id":"https://openalex.org/W1969046465","doi":"https://doi.org/10.1145/1198513.1198521","title":"When indexing equals compression","display_name":"When indexing equals compression","publication_year":2006,"publication_date":"2006-10-01","ids":{"openalex":"https://openalex.org/W1969046465","doi":"https://doi.org/10.1145/1198513.1198521","mag":"1969046465"},"language":"en","primary_location":{"id":"doi:10.1145/1198513.1198521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1198513.1198521","pdf_url":null,"source":{"id":"https://openalex.org/S137348503","display_name":"ACM Transactions on Algorithms","issn_l":"1549-6325","issn":["1549-6325","1549-6333"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074854108","display_name":"Luca Foschini","orcid":null},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Foschini","raw_affiliation_strings":["Scuola Superiore Sant'Anna, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scuola Superiore Sant'Anna, Pisa, Italy","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006984021","display_name":"Roberto Grossi","orcid":"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, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602560","display_name":"Ankur Gupta","orcid":"https://orcid.org/0000-0001-8528-9509"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Gupta","raw_affiliation_strings":["Duke University, Durham, North Carolina, NC","Duke University, Durham, North Carolina, NC#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, North Carolina, NC","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University, Durham, North Carolina, NC#TAB#","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003340402","display_name":"Jeffrey Scott Vitter","orcid":"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 University, West Lafayette, Indiana, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, Indiana, IN","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0089,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.95729022,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"2","issue":"4","first_page":"611","last_page":"639"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11309","display_name":"Music and Audio Processing","score":0.9653000235557556,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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-array","display_name":"Compressed suffix array","score":0.7263643741607666},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6894591450691223},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.6773777008056641},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6649118065834045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6616852879524231},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5390334725379944},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4935039281845093},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4876047670841217},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.45782288908958435},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41559216380119324},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.371252179145813},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.2859671115875244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23339667916297913},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.20967108011245728}],"concepts":[{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.7263643741607666},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6894591450691223},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.6773777008056641},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6649118065834045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6616852879524231},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5390334725379944},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4935039281845093},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4876047670841217},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45782288908958435},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41559216380119324},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.371252179145813},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.2859671115875244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23339667916297913},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.20967108011245728},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1198513.1198521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1198513.1198521","pdf_url":null,"source":{"id":"https://openalex.org/S137348503","display_name":"ACM Transactions on Algorithms","issn_l":"1549-6325","issn":["1549-6325","1549-6333"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:arpi.unipi.it:11568/101752","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/101752","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,"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/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W101935434","https://openalex.org/W938539187","https://openalex.org/W1489909987","https://openalex.org/W1510415214","https://openalex.org/W1573714593","https://openalex.org/W1608371561","https://openalex.org/W1638203394","https://openalex.org/W1742966691","https://openalex.org/W1860214409","https://openalex.org/W1909344111","https://openalex.org/W1968228074","https://openalex.org/W1975454935","https://openalex.org/W1975965284","https://openalex.org/W1985174631","https://openalex.org/W1986970296","https://openalex.org/W1990061958","https://openalex.org/W2013697960","https://openalex.org/W2029814178","https://openalex.org/W2030962049","https://openalex.org/W2046038806","https://openalex.org/W2047619746","https://openalex.org/W2054439442","https://openalex.org/W2072210981","https://openalex.org/W2083335299","https://openalex.org/W2088362495","https://openalex.org/W2088386938","https://openalex.org/W2093788424","https://openalex.org/W2100173929","https://openalex.org/W2114790712","https://openalex.org/W2116365500","https://openalex.org/W2121252285","https://openalex.org/W2122640893","https://openalex.org/W2134283755","https://openalex.org/W2134696992","https://openalex.org/W2149243190","https://openalex.org/W2152486057","https://openalex.org/W2156630914","https://openalex.org/W2158874082","https://openalex.org/W2159647614","https://openalex.org/W2160484851","https://openalex.org/W2170899819","https://openalex.org/W2610559255","https://openalex.org/W2621280964","https://openalex.org/W2911940095","https://openalex.org/W2995414748","https://openalex.org/W3042165818","https://openalex.org/W4230960895"],"related_works":["https://openalex.org/W2576782855","https://openalex.org/W2359436045","https://openalex.org/W153119118","https://openalex.org/W2608759984","https://openalex.org/W363060408","https://openalex.org/W2003608043","https://openalex.org/W2143531254","https://openalex.org/W2055795184","https://openalex.org/W2123393931","https://openalex.org/W2295072202"],"abstract_inverted_index":{"We":[0,55,82],"report":[1],"on":[2],"a":[3,49,59,74,85,96],"new":[4],"experimental":[5],"analysis":[6],"of":[7,17,43,52,80,88,104],"high-order":[8],"entropy-compressed":[9],"suffix":[10,89],"arrays,":[11],"which":[12],"retains":[13],"the":[14,30,44,53,70,105],"theoretical":[15],"performance":[16],"previous":[18],"work":[19],"and":[20,64],"represents":[21],"an":[22],"improvement":[23],"in":[24,95],"practice.":[25],"Our":[26],"experiments":[27],"indicate":[28],"that":[29,79,99,103],"resulting":[31],"text":[32,46,106],"index":[33],"offers":[34],"state-of-the-art":[35],"compression.":[36],"In":[37],"particular,":[38],"we":[39],"require":[40],"roughly":[41],"20%":[42],"original":[45],"size---without":[47],"requiring":[48],"separate":[50],"instance":[51],"text.":[54],"can":[56],"additionally":[57],"use":[58],"simple":[60],"notion":[61],"to":[62,78,102],"encode":[63],"decode":[65],"block-sorting":[66],"transforms":[67],"(such":[68],"as":[69],"Burrows--Wheeler":[71],"transform),":[72],"achieving":[73],"compression":[75],"ratio":[76],"comparable":[77,101],"bzip2.":[81],"also":[83],"provide":[84],"compressed":[86,108],"representation":[87],"trees":[90],"(and":[91],"their":[92],"associated":[93],"text)":[94],"total":[97],"space":[98],"is":[100],"alone":[107],"with":[109],"gzip.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":8}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}