{"id":"https://openalex.org/W3177040676","doi":"https://doi.org/10.1109/tit.2022.3176778","title":"Data Deduplication With Random Substitutions","display_name":"Data Deduplication With Random Substitutions","publication_year":2022,"publication_date":"2022-05-25","ids":{"openalex":"https://openalex.org/W3177040676","doi":"https://doi.org/10.1109/tit.2022.3176778","mag":"3177040676"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2022.3176778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2022.3176778","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.00490","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086990183","display_name":"Hao Lou","orcid":"https://orcid.org/0000-0002-6133-2987"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Lou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6133-2987","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011621481","display_name":"Farzad Farnoud","orcid":"https://orcid.org/0000-0002-8684-4487"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farzad Farnoud","raw_affiliation_strings":["Department of Electrical and Computer Engineering and the Department of Computer Science, University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8684-4487","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Department of Computer Science, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8556,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7342615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"68","issue":"10","first_page":"6941","last_page":"6963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T11478","display_name":"Caching and Content Delivery","score":0.9909999966621399,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/data-deduplication","display_name":"Data deduplication","score":0.9416697025299072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.698243260383606},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5762089490890503},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5155741572380066},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.49259477853775024},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.47813880443573},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47756677865982056},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.46499931812286377},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3777303099632263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.262245237827301},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17763164639472961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10660508275032043}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9416697025299072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698243260383606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5762089490890503},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5155741572380066},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.49259477853775024},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.47813880443573},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47756677865982056},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.46499931812286377},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3777303099632263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.262245237827301},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17763164639472961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10660508275032043},{"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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tit.2022.3176778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2022.3176778","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2107.00490","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.00490","pdf_url":"https://arxiv.org/pdf/2107.00490","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.00490","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.00490","pdf_url":"https://arxiv.org/pdf/2107.00490","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[{"id":"https://openalex.org/G3201248366","display_name":null,"funder_award_id":"CIF-1755773","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3724219808","display_name":null,"funder_award_id":"1755773","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3177040676.pdf","grobid_xml":"https://content.openalex.org/works/W3177040676.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1474119323","https://openalex.org/W1491961545","https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W1969335064","https://openalex.org/W1971212200","https://openalex.org/W2056980397","https://openalex.org/W2073370301","https://openalex.org/W2110322986","https://openalex.org/W2119172358","https://openalex.org/W2128777897","https://openalex.org/W2168909179","https://openalex.org/W2285144687","https://openalex.org/W2475932436","https://openalex.org/W2909864759","https://openalex.org/W2916595918","https://openalex.org/W2944693735","https://openalex.org/W2962814541","https://openalex.org/W2998583855","https://openalex.org/W3080836056","https://openalex.org/W3102843100","https://openalex.org/W4298072523","https://openalex.org/W6605032692","https://openalex.org/W6628632004","https://openalex.org/W6634463810","https://openalex.org/W6636190696","https://openalex.org/W6696105951"],"related_works":["https://openalex.org/W4291327800","https://openalex.org/W2950721324","https://openalex.org/W3044766408","https://openalex.org/W2051867864","https://openalex.org/W2808817673","https://openalex.org/W2007540612","https://openalex.org/W4256251096","https://openalex.org/W2317248932","https://openalex.org/W19023560","https://openalex.org/W2311946325"],"abstract_inverted_index":{"Data":[0],"deduplication":[1,20,48,100,156],"saves":[2],"storage":[3,34],"space":[4],"by":[5],"identifying":[6],"and":[7,26,92,126,158],"removing":[8],"repeats":[9,55],"in":[10,31,53,64,74,87],"the":[11,45,89,93,108,119,145,153,166,169,175,178],"data":[12,19,51],"stream.":[13],"Compared":[14],"with":[15,80,144],"traditional":[16],"compression":[17,184],"methods,":[18],"schemes":[21],"are":[22,27,56,68,96,124],"more":[23],"computationally":[24],"efficient":[25],"thus":[28],"widely":[29],"used":[30],"large":[32],"scale":[33],"systems.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"provide":[40],"an":[41],"information-theoretic":[42],"analysis":[43],"of":[44,47,135,141,147,168,177],"performance":[46],"algorithms":[49,86],"on":[50],"streams":[52],"which":[54,65],"not":[57,115],"exact.":[58],"We":[59,150],"introduce":[60],"a":[61,75,81,132,138],"source":[62,110,142,162],"model":[63,111,148],"probabilistic":[66],"substitutions":[67],"considered.":[69],"More":[70],"precisely,":[71],"each":[72],"symbol":[73],"repeated":[76],"string":[77,171],"is":[78,102],"substituted":[79],"given":[82],"edit":[83,120],"probability.":[84,121],"Deduplication":[85],"both":[88],"fixed-length":[90,99],"scheme":[91,95],"variable-length":[94,155],"studied.":[97],"The":[98],"algorithm":[101,157],"shown":[103,127],"to":[104,128,174,182],"be":[105],"unsuitable":[106],"for":[107,137],"proposed":[109,125],"as":[112,161],"it":[113],"does":[114],"take":[116],"into":[117],"account":[118],"Two":[122],"modifications":[123],"have":[129],"performances":[130],"within":[131],"constant":[133],"factor":[134],"optimal":[136],"specific":[139],"class":[140],"models":[143],"knowledge":[146],"parameters.":[149],"also":[151],"study":[152],"conventional":[154],"show":[159],"that":[160],"entropy":[163],"becomes":[164],"smaller,":[165],"size":[167],"compressed":[170],"vanishes":[172],"relative":[173],"length":[176],"uncompressed":[179],"string,":[180],"leading":[181],"high":[183],"ratios.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
