{"id":"https://openalex.org/W3080836056","doi":"https://doi.org/10.1109/isit44484.2020.9174380","title":"Data Deduplication with Random Substitutions","display_name":"Data Deduplication with Random Substitutions","publication_year":2020,"publication_date":"2020-06-01","ids":{"openalex":"https://openalex.org/W3080836056","doi":"https://doi.org/10.1109/isit44484.2020.9174380","mag":"3080836056"},"language":"en","primary_location":{"id":"doi:10.1109/isit44484.2020.9174380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit44484.2020.9174380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-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/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":["University of Virginia,Electrical and Computer Engineering,VA,USA","Electrical and Computer Engineering, University of Virginia, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Electrical and Computer Engineering,VA,USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Electrical and Computer Engineering, University of Virginia, 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":["University of Virginia,Electrical and Computer Engineering,VA,USA","Electrical and Computer Engineering, University of Virginia, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Electrical and Computer Engineering,VA,USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Electrical and Computer Engineering, University of Virginia, 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":0.4862,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68383021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2377","last_page":"2382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9954000115394592,"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"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9951000213623047,"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/data-deduplication","display_name":"Data deduplication","score":0.9486526846885681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694892406463623},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.620002806186676},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5860650539398193},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5223661065101624},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5148695707321167},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4685066044330597},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40723326802253723},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23973849415779114},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1793096661567688},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1336289346218109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11972817778587341}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9486526846885681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694892406463623},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.620002806186676},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5860650539398193},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5223661065101624},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5148695707321167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4685066044330597},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40723326802253723},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23973849415779114},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1793096661567688},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1336289346218109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11972817778587341},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit44484.2020.9174380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit44484.2020.9174380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W2099111195","https://openalex.org/W2110322986","https://openalex.org/W2168909179","https://openalex.org/W2210387432","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/W3102843100","https://openalex.org/W6634463810","https://openalex.org/W6636190696","https://openalex.org/W6696105951"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W4244492201","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W4291327800","https://openalex.org/W2950721324","https://openalex.org/W2007540612"],"abstract_inverted_index":{"Data":[0],"deduplication":[1,26,52],"saves":[2],"storage":[3],"space":[4],"by":[5],"identifying":[6],"and":[7,55,78],"removing":[8],"repeats":[9,32],"in":[10,41],"the":[11,23,67,75,85,88,94,97],"data":[12,29],"stream.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17],"provide":[18],"an":[19],"information-theoretic":[20],"analysis":[21],"of":[22,25,50,64,69,87,96],"performance":[24,59],"algorithms":[27],"with":[28,66],"streams":[30],"where":[31],"are":[33,45,53],"not":[34],"exact.":[35],"We":[36,72],"introduce":[37],"a":[38,61],"source":[39],"model":[40],"which":[42],"probabilistic":[43],"substitutions":[44],"considered.":[46],"Two":[47],"modified":[48],"versions":[49],"fixed-length":[51],"studied":[54],"proven":[56],"to":[57,93],"have":[58],"within":[60],"constant":[62],"factor":[63],"optimal":[65],"knowledge":[68],"repeat":[70],"length.":[71],"also":[73],"study":[74],"variable-length":[76],"scheme":[77],"show":[79],"that":[80],"as":[81],"entropy":[82],"becomes":[83],"smaller,":[84],"size":[86],"compressed":[89],"string":[90],"vanishes":[91],"relative":[92],"length":[95],"uncompressed":[98],"string.":[99]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
