{"id":"https://openalex.org/W2576893748","doi":"https://doi.org/10.1109/isit.2017.8006827","title":"An Information-Theoretic Analysis of Deduplication","display_name":"An Information-Theoretic Analysis of Deduplication","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2576893748","doi":"https://doi.org/10.1109/isit.2017.8006827","mag":"2576893748"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2017.8006827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2017.8006827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1701.04451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069438536","display_name":"Urs Niesen","orcid":"https://orcid.org/0000-0002-2938-228X"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Urs Niesen","raw_affiliation_strings":["Qualcomm\u2019s New Jersey Research Center, Bridgewater, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Qualcomm\u2019s New Jersey Research Center, Bridgewater, NJ, USA","institution_ids":["https://openalex.org/I4210087596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5069438536"],"corresponding_institution_ids":["https://openalex.org/I4210087596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00852305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"65","issue":"9","first_page":"1738","last_page":"1742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9991000294685364,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9986000061035156,"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/T10237","display_name":"Cryptography and Data Security","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.980133056640625},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.8694140911102295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8134742975234985},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4275355935096741},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4187389314174652},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3434234857559204},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.24872907996177673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11148807406425476}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.980133056640625},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.8694140911102295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134742975234985},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4275355935096741},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4187389314174652},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3434234857559204},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.24872907996177673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11148807406425476},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/isit.2017.8006827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2017.8006827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"doi:10.1109/tit.2019.2916037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2019.2916037","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:1701.04451","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.04451","pdf_url":"https://arxiv.org/pdf/1701.04451","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":"","raw_type":null},{"id":"doi:10.48550/arxiv.1701.04451","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1701.04451","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2576893748","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1701.04451","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.04451","pdf_url":"https://arxiv.org/pdf/1701.04451","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":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2576893748.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W200233886","https://openalex.org/W1474119323","https://openalex.org/W1490390347","https://openalex.org/W1491942965","https://openalex.org/W1491961545","https://openalex.org/W1609518033","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W1975868314","https://openalex.org/W2044492449","https://openalex.org/W2056980397","https://openalex.org/W2094224023","https://openalex.org/W2096798913","https://openalex.org/W2101398931","https://openalex.org/W2106981684","https://openalex.org/W2107745473","https://openalex.org/W2109420392","https://openalex.org/W2113641473","https://openalex.org/W2119631914","https://openalex.org/W2128777897","https://openalex.org/W2133470506","https://openalex.org/W2156719566","https://openalex.org/W2161628678","https://openalex.org/W2162486070","https://openalex.org/W2344760497","https://openalex.org/W2555411750","https://openalex.org/W2949677291","https://openalex.org/W2963294730","https://openalex.org/W3100895107","https://openalex.org/W3150003982","https://openalex.org/W4233121052","https://openalex.org/W4243055721","https://openalex.org/W4246164361","https://openalex.org/W6608138927","https://openalex.org/W6629455298","https://openalex.org/W6636190696","https://openalex.org/W6675802084","https://openalex.org/W6683597717","https://openalex.org/W6683941882","https://openalex.org/W6793350840"],"related_works":["https://openalex.org/W2963294730","https://openalex.org/W2946343007","https://openalex.org/W1998817683","https://openalex.org/W2920476195","https://openalex.org/W2083695892","https://openalex.org/W2907754081","https://openalex.org/W2133676910","https://openalex.org/W2156468933","https://openalex.org/W2164625277","https://openalex.org/W2184015804","https://openalex.org/W2443621726","https://openalex.org/W2103906418","https://openalex.org/W2184554052","https://openalex.org/W1976190464","https://openalex.org/W1972694312","https://openalex.org/W2183291039","https://openalex.org/W3170830440","https://openalex.org/W42232109","https://openalex.org/W2312689340","https://openalex.org/W2031250218"],"abstract_inverted_index":{"Deduplication":[0],"finds":[1],"and":[2,13,17,25,73,77,104],"removes":[3],"long-range":[4],"data":[5,56],"duplicates.":[6],"It":[7,58,69,85],"is":[8,46,112],"commonly":[9],"used":[10],"in":[11],"cloud":[12],"enterprise":[14],"server":[15],"settings":[16],"has":[18],"been":[19],"successfully":[20],"applied":[21],"to":[22,65,114],"primary,":[23],"backup,":[24],"archival":[26],"storage.":[27],"Despite":[28],"its":[29,36],"practical":[30],"importance":[31,97],"as":[32],"a":[33,60,80],"source-coding":[34],"technique,":[35],"analysis":[37,54,89],"from":[38],"the":[39,66,96],"point":[40],"of":[41,43,55,90,98],"view":[42],"information":[44],"theory":[45],"missing.":[47],"This":[48],"paper":[49],"provides":[50,87],"such":[51],"an":[52,88],"information-theoretic":[53],"deduplication.":[57],"introduces":[59,79],"new":[61],"source":[62,102],"model":[63],"adapted":[64],"deduplication":[67,75,83,93,105,110],"setting.":[68],"formalizes":[70],"both":[71],"fixed":[72],"variable-length":[74],"schemes,":[76],"it":[78],"novel,":[81],"multi-chunk":[82,109],"scheme.":[84],"then":[86],"these":[91],"three":[92],"variants,":[94],"emphasizing":[95],"boundary":[99],"synchronization":[100],"between":[101],"blocks":[103],"chunks.":[106],"The":[107],"proposed":[108],"scheme":[111],"shown":[113],"be":[115],"order":[116],"optimal":[117],"under":[118],"fairly":[119],"mild":[120],"assumptions.":[121]},"counts_by_year":[],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}