{"id":"https://openalex.org/W4410564994","doi":"https://doi.org/10.1145/3729426","title":"Physical vs. Logical Indexing with IDEA: Inverted Deduplication-Aware Index","display_name":"Physical vs. Logical Indexing with IDEA: Inverted Deduplication-Aware Index","publication_year":2025,"publication_date":"2025-05-21","ids":{"openalex":"https://openalex.org/W4410564994","doi":"https://doi.org/10.1145/3729426"},"language":"en","primary_location":{"id":"doi:10.1145/3729426","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729426","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3729426","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111428994","display_name":"A J Levi","orcid":"https://orcid.org/0009-0008-5854-1957"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Asaf Levi","raw_affiliation_strings":["Computer Science, Technion Israel Institute of Technology","computer science, Technion Israel Institute of Technology, Haifa, Israel"],"raw_orcid":"https://orcid.org/0009-0008-5854-1957","affiliations":[{"raw_affiliation_string":"Computer Science, Technion Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"computer science, Technion Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091766663","display_name":"Philip Shilane","orcid":"https://orcid.org/0000-0003-1235-0502"},"institutions":[{"id":"https://openalex.org/I4210149435","display_name":"DELL (United States)","ror":"https://ror.org/05rejmm18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149435"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Shilane","raw_affiliation_strings":["Dell Technologies","Dell Technologies,  Newtown, United States"],"raw_orcid":"https://orcid.org/0000-0003-1235-0502","affiliations":[{"raw_affiliation_string":"Dell Technologies","institution_ids":["https://openalex.org/I4210149435"]},{"raw_affiliation_string":"Dell Technologies,  Newtown, United States","institution_ids":["https://openalex.org/I4210149435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000600007","display_name":"Sarai Sheinvald","orcid":"https://orcid.org/0000-0002-0524-7390"},"institutions":[{"id":"https://openalex.org/I231622532","display_name":"Braude College of Engineering Karmiel","ror":"https://ror.org/004af2v94","country_code":"IL","type":"education","lineage":["https://openalex.org/I231622532"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sarai Sheinvald","raw_affiliation_strings":["Software Engineering, Ort Braude College of Engineering","Software engineering, Ort Braude College of Engineering, Karmiel, Israel"],"raw_orcid":"https://orcid.org/0000-0002-0524-7390","affiliations":[{"raw_affiliation_string":"Software Engineering, Ort Braude College of Engineering","institution_ids":["https://openalex.org/I231622532"]},{"raw_affiliation_string":"Software engineering, Ort Braude College of Engineering, Karmiel, Israel","institution_ids":["https://openalex.org/I231622532"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045808821","display_name":"Gala Yadgar","orcid":"https://orcid.org/0000-0003-2701-0260"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gala Yadgar","raw_affiliation_strings":["Computer Science, Technion Israel Institute of Technology","Computer Science, Technion Israel Institute of Technology, Haifa, Israel"],"raw_orcid":"https://orcid.org/0000-0003-2701-0260","affiliations":[{"raw_affiliation_string":"Computer Science, Technion Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Computer Science, Technion Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2161,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8826967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"21","issue":"4","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9990000128746033,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9990000128746033,"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.8781793117523193},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8036682605743408},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.7502671480178833},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6984694600105286},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.6950834393501282},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.47895270586013794},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4374883472919464},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2744261622428894},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.126491516828537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8781793117523193},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8036682605743408},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.7502671480178833},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6984694600105286},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.6950834393501282},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.47895270586013794},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4374883472919464},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2744261622428894},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.126491516828537}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3729426","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729426","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3729426","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729426","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G945566956","display_name":null,"funder_award_id":"807/20","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W120798314","https://openalex.org/W178328500","https://openalex.org/W1594511758","https://openalex.org/W1972418517","https://openalex.org/W1995152885","https://openalex.org/W1995735274","https://openalex.org/W2020498246","https://openalex.org/W2038807029","https://openalex.org/W2099966806","https://openalex.org/W2125203709","https://openalex.org/W2125671345","https://openalex.org/W2144577446","https://openalex.org/W2238991082","https://openalex.org/W2294581520","https://openalex.org/W2406547600","https://openalex.org/W2518235607","https://openalex.org/W2734941459","https://openalex.org/W3037854022","https://openalex.org/W4231934124","https://openalex.org/W4298005108","https://openalex.org/W6779791889"],"related_works":["https://openalex.org/W2393932274","https://openalex.org/W2102493899","https://openalex.org/W2145657320","https://openalex.org/W1505866794","https://openalex.org/W4282568653","https://openalex.org/W2187610212","https://openalex.org/W2527247821","https://openalex.org/W2123678380","https://openalex.org/W4237510188","https://openalex.org/W1973126996"],"abstract_inverted_index":{"In":[0,111,149],"the":[1,6,44,85,93,113,129,134,154,168,179,191,218,227],"realm":[2],"of":[3,22,40,50,98,136,156,220],"information":[4],"retrieval,":[5],"need":[7],"to":[8,66,92,128,133,167,178,235,246],"maintain":[9],"reliable":[10],"term-indexing":[11],"has":[12],"grown":[13],"more":[14],"acute":[15],"in":[16,82,90,181],"recent":[17],"years,":[18],"with":[19,64,77],"vast":[20],"amounts":[21],"ever-growing":[23],"online":[24],"data":[25,28,55,60,76,95],"used":[26],"for":[27,250],"mining":[29],"and":[30,34,105,107,125,174,194,205,230,237,240,248,252],"natural":[31],"language":[32],"processing,":[33],"searched":[35],"by":[36,144,233,244],"a":[37,67,157],"large":[38],"number":[39],"search-engine":[41],"users.":[42],"At":[43],"same":[45],"time,":[46],"an":[47],"increasing":[48],"portion":[49],"primary":[51],"storage":[52,104,147],"systems":[53],"employ":[54],"deduplication,":[56],"where":[57],"duplicate":[58],"logical":[59,94],"chunks":[61,170],"are":[62],"replaced":[63],"references":[65],"unique":[68,169],"physical":[69,130],"copy.":[70],"We":[71],"show":[72],"that":[73,160,171,223],"indexing":[74,140,231],"deduplicated":[75],"deduplication-oblivious":[78],"mechanisms":[79],"might":[80],"result":[81,203],"extreme":[83],"inefficiencies:":[84],"index":[86,118,192,228],"size":[87,229],"would":[88,120],"increase":[89],"proportion":[91],"size,":[96],"regardless":[97],"its":[99],"duplication":[100],"ratio,":[101],"consuming":[102],"excessive":[103],"memory":[106],"slowing":[108],"down":[109],"lookups.":[110],"addition,":[112],"logically":[114],"sequential":[115],"accesses":[116,127],"during":[117],"creation":[119],"be":[121],"transformed":[122],"into":[123],"random":[124],"redundant":[126],"chunks.":[131],"Indeed,":[132],"best":[135],"our":[137],"knowledge,":[138],"term":[139],"is":[141,184],"not":[142],"supported":[143],"any":[145],"deduplicating":[146],"system.":[148],"this":[150],"article,":[151],"we":[152],"propose":[153],"design":[155,188],"deduplication-aware":[158],"term-index":[159],"addresses":[161],"these":[162],"challenges.":[163],"IDEA":[164,224],"maps":[165,175],"terms":[166],"contain":[172],"them,":[173],"each":[176],"chunk":[177],"files":[180],"which":[182],"it":[183],"contained.":[185],"This":[186],"basic":[187],"concept":[189],"improves":[190],"performance":[193],"can":[195,225],"support":[196],"advanced":[197],"functionalities":[198],"such":[199],"as":[200],"inline":[201],"indexing,":[202],"ranking,":[204],"proximity":[206],"search.":[207],"Our":[208],"prototype":[209],"implementation":[210],"based":[211],"on":[212],"Lucene":[213],"(the":[214],"search":[215],"engine":[216],"at":[217],"core":[219],"Elasticsearch)":[221],"shows":[222],"reduce":[226,241],"time":[232],"up":[234,245],"73%":[236],"94%,":[238],"respectively,":[239],"term-lookup":[242],"latency":[243],"82%":[247],"59%":[249],"single":[251],"multi-term":[253],"queries,":[254],"respectively.":[255]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
