{"id":"https://openalex.org/W4415368421","doi":"https://doi.org/10.1109/isit63088.2025.11195582","title":"Fragmentation in Data Deduplication Systems II: The Jump Metric","display_name":"Fragmentation in Data Deduplication Systems II: The Jump Metric","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4415368421","doi":"https://doi.org/10.1109/isit63088.2025.11195582"},"language":null,"primary_location":{"id":"doi:10.1109/isit63088.2025.11195582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit63088.2025.11195582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5015402300","display_name":"Yun-Han Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun-Han Li","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051523017","display_name":"Jin Sima","orcid":"https://orcid.org/0000-0003-4588-9790"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin Sima","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046640187","display_name":"Ilan Shomorony","orcid":"https://orcid.org/0000-0001-5077-2269"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilan Shomorony","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084947882","display_name":"Olgica Milenkovi\u0107","orcid":"https://orcid.org/0000-0002-1871-4912"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olgica Milenkovic","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015402300"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42987093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.998199999332428,"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":0.998199999332428,"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":0.9872999787330627,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.977400004863739,"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":0.8650000095367432},{"id":"https://openalex.org/keywords/jump","display_name":"Jump","score":0.6509000062942505},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.642799973487854},{"id":"https://openalex.org/keywords/fragmentation","display_name":"Fragmentation (computing)","score":0.5414000153541565},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.35409998893737793},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.33239999413490295}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8650000095367432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6765000224113464},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.6509000062942505},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.642799973487854},{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5065000057220459},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26649999618530273},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C529754248","wikidata":"https://www.wikidata.org/wiki/Q1054772","display_name":"Data recovery","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit63088.2025.11195582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit63088.2025.11195582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5918033806","display_name":null,"funder_award_id":"19-56384","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1999333545","https://openalex.org/W2012359782","https://openalex.org/W2122423206","https://openalex.org/W2344760497","https://openalex.org/W2475932436","https://openalex.org/W2780813414","https://openalex.org/W2916595918","https://openalex.org/W2963294730","https://openalex.org/W3177040676"],"related_works":[],"abstract_inverted_index":{"Data":[0],"deduplication":[1,26,62],"refers":[2],"to":[3,12,29,81,112],"a":[4,107,134],"collection":[5],"of":[6,36,58,88,100,106,129,142],"data":[7,15,34,82,144],"processing":[8],"strategies":[9],"that":[10,109,153],"aim":[11],"remove":[13],"repeated":[14],"chunks":[16,35],"stored":[17,42],"by":[18,147],"different":[19],"users.":[20],"Despite":[21],"providing":[22],"excellent":[23],"storage":[24],"savings,":[25],"can":[27,163],"lead":[28],"severe":[30],"file":[31,39,108],"fragmentation":[32,66],"issues:":[33],"the":[37,47,86,92,97,103,114,118,127,139],"same":[38],"may":[40],"be":[41],"at":[43],"distal":[44],"locations":[45],"on":[46,117,126],"server,":[48],"making":[49],"reconstruction":[50,104],"time-consuming.":[51],"Here,":[52],"we":[53,90],"continue":[54],"our":[55],"analytical":[56],"study":[57],"uncoded":[59],"and":[60,123,132,157],"coded":[61,158],"methods":[63],"with":[64],"reduced":[65],"levels.":[67],"We":[68,120,149],"model":[69],"files":[70],"as":[71],"self-avoiding":[72],"(simple)":[73],"paths":[74],"in":[75,160],"specialized":[76],"graphs":[77],"whose":[78],"nodes":[79],"correspond":[80],"chunks.":[83],"To":[84],"measure":[85],"level":[87],"fragmentation,":[89,131],"introduce":[91],"jump":[93,130,140,165],"metric":[94],"which":[95],"captures":[96],"worst-case":[98],"number":[99,141],"times":[101],"during":[102],"process":[105],"one":[110],"has":[111],"change":[113],"readout":[115],"location":[116],"server.":[119],"derive":[121],"lower":[122],"upper":[124],"bounds":[125],"degree":[128],"provide":[133],"new":[135],"algorithm":[136],"for":[137],"computing":[138],"hierarchical":[143],"structures":[145],"captured":[146],"trees.":[148],"also":[150],"present":[151],"examples":[152],"show":[154],"how":[155],"repetition":[156],"redundancy":[159],"chunk":[161],"stores":[162],"reduce":[164],"fragmentation.":[166]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-21T00:00:00"}