{"id":"https://openalex.org/W2035415465","doi":"https://doi.org/10.1109/msst.2012.6232381","title":"Estimation of deduplication ratios in large data sets","display_name":"Estimation of deduplication ratios in large data sets","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2035415465","doi":"https://doi.org/10.1109/msst.2012.6232381","mag":"2035415465"},"language":"en","primary_location":{"id":"doi:10.1109/msst.2012.6232381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2012.6232381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)","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/A5036936298","display_name":"Danny Harnik","orcid":"https://orcid.org/0009-0000-0614-6543"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Danny Harnik","raw_affiliation_strings":["IBM Research, Haifa, Israel","IBM Research Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059227880","display_name":"Oded Margalit","orcid":"https://orcid.org/0000-0002-2026-2601"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Oded Margalit","raw_affiliation_strings":["IBM Research, Haifa, Israel","IBM Research Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026549255","display_name":"Dalit Naor","orcid":"https://orcid.org/0009-0007-9628-312X"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dalit Naor","raw_affiliation_strings":["IBM Research, Haifa, Israel","IBM Research Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004291203","display_name":"Dmitriy V. Sotnikov","orcid":"https://orcid.org/0000-0002-4993-0685"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dmitry Sotnikov","raw_affiliation_strings":["IBM Research, Haifa, Israel","IBM Research Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077710649","display_name":"Gil Vernik","orcid":"https://orcid.org/0009-0008-4236-5733"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gil Vernik","raw_affiliation_strings":["IBM Research, Haifa, Israel","IBM Research Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036936298"],"corresponding_institution_ids":["https://openalex.org/I4210167297"],"apc_list":null,"apc_paid":null,"fwci":6.3333,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96665852,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9958999752998352,"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/T11106","display_name":"Data Management and Algorithms","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9743689298629761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8799536228179932},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6239655613899231},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6231741905212402},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.54713374376297},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.521540641784668},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4341890215873718},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41294345259666443},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3591461777687073},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3266572952270508},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11560383439064026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08088859915733337}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9743689298629761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8799536228179932},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6239655613899231},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6231741905212402},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.54713374376297},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.521540641784668},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4341890215873718},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41294345259666443},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3591461777687073},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3266572952270508},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11560383439064026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08088859915733337},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msst.2012.6232381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2012.6232381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.361.4525","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.361.4525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://storageconference.org/2012/Papers/17.Deduplication.Estimation.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1521407587","https://openalex.org/W1785933978","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W2005731313","https://openalex.org/W2025051251","https://openalex.org/W2058991275","https://openalex.org/W2080745194","https://openalex.org/W2081037744","https://openalex.org/W2083695892","https://openalex.org/W2103012681","https://openalex.org/W2103126020","https://openalex.org/W2107745473","https://openalex.org/W2110322986","https://openalex.org/W2112400233","https://openalex.org/W2120396387","https://openalex.org/W2134786002","https://openalex.org/W2135348622","https://openalex.org/W2163336450","https://openalex.org/W2170990775","https://openalex.org/W2500232297","https://openalex.org/W4233413206","https://openalex.org/W6600228218","https://openalex.org/W6602837329","https://openalex.org/W6608138927","https://openalex.org/W6631269574","https://openalex.org/W6676700842","https://openalex.org/W6676862906","https://openalex.org/W6679775555"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W1982579475"],"abstract_inverted_index":{"We":[0,114,144],"study":[1,101],"the":[2,7,42,70,88,110,149,160,180,215,238,244,264,282],"problem":[3],"of":[4,41,148,151,172,184,193,207,218,237,243,255,263,284],"accurately":[5],"estimating":[6,281],"data":[8,19,43,112,181,188,232,265],"reduction":[9,182],"ratio":[10,183],"achieved":[11,252],"by":[12],"deduplication":[13,60,97,142,290,306],"and":[14,36,92,98,135,162,165,275,299],"compression":[15],"on":[16,103,169,229],"a":[17,26,56,116,170,185,196,230,289],"specific":[18],"set.":[20,113],"This":[21],"turns":[22],"out":[23],"to":[24,47,52,67,87,156,273,286,294,305],"be":[25,48,106],"challenging":[27],"task":[28],"-":[29],"It":[30],"has":[31],"been":[32],"shown":[33],"both":[34],"empirically":[35],"analytically":[37],"that":[38,226],"essentially":[39],"all":[40,69],"at":[44,194],"hand":[45],"needs":[46],"inspected":[49],"in":[50,75,83,248],"order":[51],"come":[53],"up":[54],"with":[55,96,130,139,190],"accurate":[57],"estimation":[58,228],"when":[59,65,108],"is":[61,270],"involved.":[62],"Moreover,":[63],"even":[64],"permitted":[66],"inspect":[68],"data,":[71],"there":[72],"are":[73,125],"challenges":[74],"devising":[76],"an":[77],"efficient,":[78],"yet":[79,128],"accurate,":[80,127],"method.":[81],"Efficiency":[82],"this":[84,249],"case":[85,217],"refers":[86],"demanding":[89],"CPU,":[90],"memory":[91,133],"disk":[93,212],"usage":[94],"associated":[95,138],"compression.":[99],"Our":[100,123,268],"focuses":[102],"what":[104],"can":[105],"done":[107],"scanning":[109],"entire":[111],"present":[115],"novel":[117],"two-phased":[118],"framework":[119,222],"for":[120,277],"such":[121],"estimations.":[122],"techniques":[124,158],"provably":[126],"run":[129],"very":[131],"low":[132],"requirements":[134],"avoid":[136],"overheads":[137],"maintaining":[140],"large":[141,231],"tables.":[143],"give":[145],"formal":[146],"proofs":[147],"correctness":[150],"our":[152,167,221],"algorithm,":[153],"compare":[154],"it":[155],"existing":[157],"from":[159,266],"database":[161],"streaming":[163],"literature":[164],"evaluate":[166],"technique":[168,269],"number":[171,283],"real":[173],"world":[174],"workloads.":[175],"For":[176,241],"example,":[177],"we":[178,246,251],"estimate":[179],"7":[186],"TB":[187],"set":[189,233],"accuracy":[191,253],"guarantees":[192],"most":[195,236],"1%":[197],"relative":[198,257],"error":[199,258],"while":[200,259],"using":[201],"as":[202,204],"little":[203],"1":[205],"MB":[206],"RAM":[208],"(and":[209],"no":[210],"additional":[211],"access).":[213],"In":[214],"interesting":[216],"full-file":[219],"deduplication,":[220],"readily":[223],"accepts":[224],"optimizations":[225],"allow":[227],"without":[234],"reading":[235,260],"actual":[239],"data.":[240],"one":[242],"workloads":[245],"used":[247],"work":[250],"guarantee":[254],"2%":[256],"only":[261],"27%":[262],"disk.":[267],"practical,":[271],"simple":[272],"implement,":[274],"useful":[276],"multiple":[278],"scenarios,":[279],"including":[280],"disks":[285],"buy,":[287],"choosing":[288],"technique,":[291],"deciding":[292],"whether":[293],"dedupe":[295,298],"or":[296],"not":[297],"conducting":[300],"large-scale":[301],"academic":[302],"studies":[303],"related":[304],"ratios.":[307]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}