{"id":"https://openalex.org/W1978089967","doi":"https://doi.org/10.1145/2063576.2063967","title":"Collection-based compression using discovered long matching strings","display_name":"Collection-based compression using discovered long matching strings","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W1978089967","doi":"https://doi.org/10.1145/2063576.2063967","mag":"1978089967"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057941712","display_name":"Andrew Peel","orcid":"https://orcid.org/0000-0002-9914-3508"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Andrew Peel","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia","The University of Melbourne, Melbourne, Australia;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia;","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087794199","display_name":"Anthony Wirth","orcid":"https://orcid.org/0000-0003-3746-6704"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Anthony Wirth","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia","The University of Melbourne, Melbourne, Australia;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia;","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia","The University of Melbourne, Melbourne, Australia;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia;","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":1.3489,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80223338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2361","last_page":"2364"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973999857902527,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/computer-science","display_name":"Computer science","score":0.7876314520835876},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.7308644652366638},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6905484795570374},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5444025993347168},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.5428429245948792},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5192915797233582},{"id":"https://openalex.org/keywords/file-size","display_name":"File size","score":0.4700034260749817},{"id":"https://openalex.org/keywords/texture-compression","display_name":"Texture compression","score":0.42292842268943787},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.41385120153427124},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3459433317184448},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32276129722595215},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.2774942219257355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1551477015018463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13851800560951233},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09647029638290405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876314520835876},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.7308644652366638},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6905484795570374},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5444025993347168},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.5428429245948792},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5192915797233582},{"id":"https://openalex.org/C2776029614","wikidata":"https://www.wikidata.org/wiki/Q1146367","display_name":"File size","level":2,"score":0.4700034260749817},{"id":"https://openalex.org/C54243161","wikidata":"https://www.wikidata.org/wiki/Q39333","display_name":"Texture compression","level":5,"score":0.42292842268943787},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.41385120153427124},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3459433317184448},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32276129722595215},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2774942219257355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1551477015018463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13851800560951233},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09647029638290405},{"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/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"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/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"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":1,"locations":[{"id":"doi:10.1145/2063576.2063967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1819656317","https://openalex.org/W1947728686","https://openalex.org/W1972418517","https://openalex.org/W2050140640","https://openalex.org/W2053003009","https://openalex.org/W2127963296","https://openalex.org/W2141641405","https://openalex.org/W2164215197"],"related_works":["https://openalex.org/W2388481516","https://openalex.org/W2161302774","https://openalex.org/W2766695209","https://openalex.org/W3209669196","https://openalex.org/W2011090518","https://openalex.org/W4386918011","https://openalex.org/W2953482628","https://openalex.org/W2103127675","https://openalex.org/W2945049259","https://openalex.org/W4211074971"],"abstract_inverted_index":{"Many":[0],"collections":[1],"of":[2,39,63,127],"data":[3],"contain":[4,13],"items":[5],"that":[6,87],"are":[7,23,47],"inherently":[8],"similar.":[9],"For":[10],"example,":[11],"archives":[12],"files":[14,46,96],"with":[15,69,80,141],"incremental":[16],"changes":[17],"between":[18],"releases.":[19],"Long-range":[20],"inter-file":[21],"similarities":[22],"not":[24],"exploited":[25],"by":[26,49],"standard":[27,118],"approaches":[28],"to":[29,51,112],"compression.":[30],"We":[31,85],"investigate":[32],"compression":[33,43,75,92,100,109,126,139],"using":[34,117],"similarity":[35],"from":[36],"all":[37],"parts":[38],"a":[40,56,135],"collection,":[41],"collection-based":[42],"(CBC).":[44],"Input":[45],"delta-encoded":[48],"reference":[50],"long":[52],"string":[53],"matches":[54],"in":[55],"source":[57],"collection.":[58],"The":[59,131],"expected":[60],"space":[61],"requirement":[62],"our":[64,88,120],"encoding":[65],"algorithm":[66],"is":[67,78,134],"sublinear":[68],"the":[70,74,81,125],"collection":[71],"size,":[72],"and":[73,102],"time":[76],"complexity":[77],"linear":[79],"input":[82,95],"file":[83,115],"size.":[84],"show":[86],"scheme":[89,121],"achieves":[90,122],"better":[91],"for":[93],"large":[94],"than":[97],"existing":[98,142],"differential":[99],"systems,":[101],"scales":[103],"better.":[104],"Also,":[105],"we":[106],"achieve":[107],"significant":[108],"improvement":[110,137],"compared":[111],"compressing":[113],"each":[114],"individually":[116],"utilities:":[119],"several":[123],"times":[124],"gzip":[128],"or":[129],"7-zip.":[130],"overall":[132],"result":[133],"dramatic":[136],"on":[138],"available":[140],"approaches.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
