{"id":"https://openalex.org/W4387951120","doi":"https://doi.org/10.1109/ccece58730.2023.10288834","title":"DedupBench: A Benchmarking Tool for Data Chunking Techniques","display_name":"DedupBench: A Benchmarking Tool for Data Chunking Techniques","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4387951120","doi":"https://doi.org/10.1109/ccece58730.2023.10288834"},"language":"en","primary_location":{"id":"doi:10.1109/ccece58730.2023.10288834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccece58730.2023.10288834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","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/A5101726185","display_name":"Alan Liu","orcid":"https://orcid.org/0000-0002-8884-6662"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Alan Liu","raw_affiliation_strings":["University of Waterloo,Canada","University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102571615","display_name":"Abdelrahman Baba","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdelrahman Baba","raw_affiliation_strings":["University of Waterloo,Canada","University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067377502","display_name":"Sreeharsha Udayashankar","orcid":"https://orcid.org/0000-0003-0804-1600"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sreeharsha Udayashankar","raw_affiliation_strings":["University of Waterloo,Canada","University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086918800","display_name":"Samer Al-Kiswany","orcid":"https://orcid.org/0000-0002-6429-9983"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]},{"id":"https://openalex.org/I4210099137","display_name":"Research Canada","ror":"https://ror.org/0103eqz62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210099137"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Samer Al-Kiswany","raw_affiliation_strings":["University of Waterloo,Canada","University of Waterloo, Canada","Acronis Research, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Acronis Research, Canada","institution_ids":["https://openalex.org/I4210099137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101726185"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":1.0003,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77919269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"469","last_page":"474"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9998000264167786,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9958000183105469,"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":0.9525649547576904},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.9338029623031616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8492461442947388},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.7085616588592529},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.46885403990745544},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4679291248321533},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33157169818878174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29947441816329956}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9525649547576904},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.9338029623031616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492461442947388},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.7085616588592529},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.46885403990745544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4679291248321533},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33157169818878174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29947441816329956},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccece58730.2023.10288834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccece58730.2023.10288834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W22807665","https://openalex.org/W1474119323","https://openalex.org/W1553098517","https://openalex.org/W1639305476","https://openalex.org/W1969335064","https://openalex.org/W1976024527","https://openalex.org/W1992637701","https://openalex.org/W2008185810","https://openalex.org/W2067081213","https://openalex.org/W2110322986","https://openalex.org/W2110824055","https://openalex.org/W2147853062","https://openalex.org/W2155729921","https://openalex.org/W2351279544","https://openalex.org/W2475932436","https://openalex.org/W2587323806","https://openalex.org/W2787300667","https://openalex.org/W2916086000","https://openalex.org/W2953498285","https://openalex.org/W2986445348","https://openalex.org/W4200376613","https://openalex.org/W4205095516","https://openalex.org/W4239670432","https://openalex.org/W4312554896","https://openalex.org/W6600884019","https://openalex.org/W6705331335","https://openalex.org/W6764791836"],"related_works":["https://openalex.org/W4285245558","https://openalex.org/W1437397736","https://openalex.org/W2048606985","https://openalex.org/W2375056709","https://openalex.org/W4301155776","https://openalex.org/W2012359782","https://openalex.org/W2952411620","https://openalex.org/W2348132657","https://openalex.org/W4387951120","https://openalex.org/W2254835506"],"abstract_inverted_index":{"Data":[0],"deduplication":[1,29,34,72,87,136,157],"is":[2,21,44],"a":[3,45,60,94,117],"technique":[4],"for":[5,41,71,78,98,138],"reducing":[6],"storage":[7],"space":[8],"by":[9,84],"identifying":[10],"and":[11,31,51,89,127],"eliminating":[12],"redundant":[13],"data.":[14,75],"The":[15],"division":[16],"of":[17,23,48,67,81,102],"files":[18],"into":[19],"chunks":[20],"one":[22],"the":[24,28,37,65,79,99,108,134,142,146],"key":[25],"steps":[26],"in":[27,53,107],"process":[30],"directly":[32],"impacts":[33],"effectiveness.":[35],"Despite":[36],"numerous":[38],"algorithms":[39,70,115],"available":[40],"chunking,":[42],"there":[43],"limited":[46],"understanding":[47],"their":[49,86],"strengths":[50],"weaknesses":[52],"virtual":[54],"machine":[55],"backup":[56],"environments.We":[57],"present":[58],"DedupBench,":[59],"framework":[61],"designed":[62],"to":[63,148],"assess":[64],"performance":[66],"different":[68],"chunking":[69,82,90,104,114,150],"on":[73,152],"user-specified":[74,153],"DedupBench":[76,92],"allows":[77],"evaluation":[80,123],"techniques":[83,105,151],"comparing":[85],"ratio":[88],"throughput.":[91],"incorporates":[93],"generic":[95],"design,":[96],"allowing":[97],"effortless":[100],"integration":[101],"additional":[103],"developed":[106],"future.We":[109],"evaluate":[110,149],"four":[111],"widely":[112],"used":[113],"using":[116],"VM-based":[118,139],"dataset":[119],"with":[120],"DedupBench.":[121],"Our":[122],"contrasts":[124],"earlier":[125],"studies":[126],"demonstrates":[128],"that":[129],"Asymmetric":[130],"Extremum":[131],"(AE)":[132],"has":[133],"best":[135],"efficiency":[137],"datasets":[140],"among":[141],"tested":[143],"algorithms,":[144],"highlighting":[145],"need":[147],"data":[154],"before":[155],"designing":[156],"systems.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}