{"id":"https://openalex.org/W1998817683","doi":"https://doi.org/10.1145/1534530.1534539","title":"The design of a similarity based deduplication system","display_name":"The design of a similarity based deduplication system","publication_year":2009,"publication_date":"2009-05-04","ids":{"openalex":"https://openalex.org/W1998817683","doi":"https://doi.org/10.1145/1534530.1534539","mag":"1998817683"},"language":"en","primary_location":{"id":"doi:10.1145/1534530.1534539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1534530.1534539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SYSTOR 2009: The Israeli Experimental Systems Conference","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/A5022081536","display_name":"Lior Aronovich","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167072","display_name":"IBM (Brazil)","ror":"https://ror.org/05thm6q88","country_code":"BR","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210167072"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["BR","US"],"is_corresponding":true,"raw_author_name":"Lior Aronovich","raw_affiliation_strings":["IBM Corp","IBM Corporation#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Corp","institution_ids":["https://openalex.org/I4210167072"]},{"raw_affiliation_string":"IBM Corporation#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069503968","display_name":"Ron Asher","orcid":"https://orcid.org/0000-0001-7672-6527"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210167072","display_name":"IBM (Brazil)","ror":"https://ror.org/05thm6q88","country_code":"BR","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210167072"]}],"countries":["BR","US"],"is_corresponding":false,"raw_author_name":"Ron Asher","raw_affiliation_strings":["IBM Corp","IBM Corporation#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Corp","institution_ids":["https://openalex.org/I4210167072"]},{"raw_affiliation_string":"IBM Corporation#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083255118","display_name":"Eitan Bachmat","orcid":"https://orcid.org/0000-0001-7153-100X"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Eitan Bachmat","raw_affiliation_strings":["Ben-Gurion U"],"affiliations":[{"raw_affiliation_string":"Ben-Gurion U","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031417905","display_name":"Haim Bitner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haim Bitner","raw_affiliation_strings":["Marvell Corp"],"affiliations":[{"raw_affiliation_string":"Marvell Corp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037427953","display_name":"Michael Hirsch","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210167072","display_name":"IBM (Brazil)","ror":"https://ror.org/05thm6q88","country_code":"BR","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210167072"]}],"countries":["BR","US"],"is_corresponding":false,"raw_author_name":"Michael Hirsch","raw_affiliation_strings":["IBM Corp","IBM Corporation#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Corp","institution_ids":["https://openalex.org/I4210167072"]},{"raw_affiliation_string":"IBM Corporation#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059517520","display_name":"Shmuel T. Klein","orcid":"https://orcid.org/0000-0002-9478-3303"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shmuel T. Klein","raw_affiliation_strings":["Bar-Ilan U","Bar-Ilan U.#TAB#"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan U","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan U.#TAB#","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022081536"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210167072"],"apc_list":null,"apc_paid":null,"fwci":7.4151,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.97121905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9976999759674072,"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":0.9976000189781189,"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":0.9721928834915161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7908239364624023},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7267490029335022},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6639177799224854},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6131781935691833},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5669698715209961},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5622018575668335},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5295102596282959},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.42679327726364136},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41177135705947876},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.330894410610199},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3277643322944641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16421961784362793},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16207566857337952},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11439239978790283},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07871043682098389}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9721928834915161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908239364624023},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7267490029335022},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6639177799224854},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6131781935691833},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5669698715209961},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5622018575668335},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5295102596282959},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.42679327726364136},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41177135705947876},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.330894410610199},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3277643322944641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16421961784362793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16207566857337952},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11439239978790283},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07871043682098389},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1534530.1534539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1534530.1534539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SYSTOR 2009: The Israeli Experimental Systems Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1491429571","https://openalex.org/W1514735749","https://openalex.org/W1536700701","https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W1614703486","https://openalex.org/W1972418517","https://openalex.org/W1985108724","https://openalex.org/W1991800036","https://openalex.org/W1997657677","https://openalex.org/W2001496424","https://openalex.org/W2004286258","https://openalex.org/W2007842132","https://openalex.org/W2047142051","https://openalex.org/W2052899946","https://openalex.org/W2053449578","https://openalex.org/W2059513841","https://openalex.org/W2081193615","https://openalex.org/W2107745473","https://openalex.org/W2122290452","https://openalex.org/W2123845384","https://openalex.org/W2132069633","https://openalex.org/W2132627996","https://openalex.org/W2134826720","https://openalex.org/W2148885851","https://openalex.org/W2152565070","https://openalex.org/W2533248932","https://openalex.org/W3137072739","https://openalex.org/W6682205557"],"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/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W3044766408","https://openalex.org/W2374324126","https://openalex.org/W1565658545"],"abstract_inverted_index":{"We":[0],"describe":[1],"some":[2],"of":[3,13,63,74],"the":[4,11,33,44,72],"design":[5,22],"choices":[6],"that":[7,37],"were":[8,27],"made":[9],"during":[10],"development":[12],"a":[14,57,60],"fast,":[15],"scalable,":[16],"inline,":[17],"deduplication":[18,35,58,75],"device.":[19],"The":[20,41],"system's":[21],"goals":[23],"and":[24,68],"how":[25,51,83],"they":[26],"achieved":[28],"are":[29,77],"presented.":[30],"This":[31],"is":[32,66,80],"firs":[34],"device":[36],"uses":[38],"similarity":[39,52,64,86],"matching.":[40],"paper":[42],"provides":[43],"following":[45],"original":[46],"research":[47],"contributions:":[48],"we":[49],"show":[50],"signatures":[53,65],"can":[54],"serve":[55],"in":[56,71],"scheme;":[59],"novel":[61],"type":[62],"presented":[67],"its":[69],"advantages":[70],"context":[73],"requirements":[76],"explained.":[78],"It":[79],"also":[81],"shown":[82],"to":[84],"combine":[85],"matching":[87],"schemes":[88],"with":[89],"byte":[90,92],"by":[91],"comparison":[93],"or":[94],"hash":[95],"based":[96],"identity":[97],"schemes.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
