{"id":"https://openalex.org/W3197696349","doi":"https://doi.org/10.1109/isit45174.2021.9517909","title":"Asymptotic Analysis of Data Deduplication with a Constant Number of Substitutions","display_name":"Asymptotic Analysis of Data Deduplication with a Constant Number of Substitutions","publication_year":2021,"publication_date":"2021-07-12","ids":{"openalex":"https://openalex.org/W3197696349","doi":"https://doi.org/10.1109/isit45174.2021.9517909","mag":"3197696349"},"language":"en","primary_location":{"id":"doi:10.1109/isit45174.2021.9517909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit45174.2021.9517909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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 Hassanzadeh","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":0.481,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67284382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3296","last_page":"3301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9943000078201294,"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/T11017","display_name":"Chaos-based Image/Signal Encryption","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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9794753789901733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7728803753852844},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5566577911376953},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5180951952934265},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4479823708534241},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3548508286476135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18529388308525085},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.164107084274292}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9794753789901733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728803753852844},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5566577911376953},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5180951952934265},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4479823708534241},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3548508286476135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18529388308525085},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.164107084274292},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit45174.2021.9517909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit45174.2021.9517909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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":25,"referenced_works":["https://openalex.org/W38366299","https://openalex.org/W1491961545","https://openalex.org/W1553098517","https://openalex.org/W1576397915","https://openalex.org/W1608647889","https://openalex.org/W1929726975","https://openalex.org/W1969335064","https://openalex.org/W2004286258","https://openalex.org/W2093274905","https://openalex.org/W2110322986","https://openalex.org/W2110824055","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/W2998583855","https://openalex.org/W3080836056","https://openalex.org/W4298072523","https://openalex.org/W6634463810","https://openalex.org/W6640146480","https://openalex.org/W6696105951","https://openalex.org/W6757813481"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2074021203","https://openalex.org/W2144348063","https://openalex.org/W4296125805","https://openalex.org/W1982579475"],"abstract_inverted_index":{"Data":[0],"deduplication":[1,23,46,49,94,106],"has":[2],"gained":[3],"attention":[4],"in":[5,14,64],"large-scale":[6],"storage":[7],"systems":[8],"due":[9],"to":[10],"the":[11,18,42,52,88,92,104],"explosive":[12],"growth":[13],"digital":[15],"data.":[16],"Recently,":[17],"information-theoretic":[19],"aspects":[20],"of":[21,44,54,56,70,81],"conventional":[22],"algorithms":[24,30,50],"have":[25,34],"been":[26,35],"studied":[27],"and":[28,47,103],"novel":[29],"with":[31,73],"better":[32],"performance":[33],"proposed.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"study":[41],"performances":[43],"variable-length":[45,93],"multi-chunk":[48,105],"from":[51],"point":[53],"view":[55],"information":[57],"theory.":[58],"We":[59,84],"consider":[60],"a":[61,78],"source":[62,66,90],"model":[63],"which":[65],"strings":[67],"are":[68],"composed":[69],"repeated":[71],"blocks":[72],"each":[74],"data":[75],"block":[76],"containing":[77],"constant":[79],"number":[80],"substitution":[82],"edits.":[83],"show":[85],"that":[86],"over":[87],"proposed":[89],"model,":[91],"algorithm":[95,107],"can":[96],"achieve":[97],"asymptotically":[98],"arbitrarily":[99],"large":[100],"compression":[101],"ratio":[102],"is":[108],"order":[109],"optimal":[110],"under":[111],"mild":[112],"conditions.":[113]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
