{"id":"https://openalex.org/W2073053905","doi":"https://doi.org/10.1145/2741948.2741952","title":"Deriving and comparing deduplication techniques using a model-based classification","display_name":"Deriving and comparing deduplication techniques using a model-based classification","publication_year":2015,"publication_date":"2015-04-13","ids":{"openalex":"https://openalex.org/W2073053905","doi":"https://doi.org/10.1145/2741948.2741952","mag":"2073053905"},"language":"en","primary_location":{"id":"doi:10.1145/2741948.2741952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2741948.2741952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049694671","display_name":"J\u00fcrgen Kaiser","orcid":null},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Kaiser","raw_affiliation_strings":["Johannes Gutenberg University Mainz","Johannes Gutenberg University Mainz#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Johannes Gutenberg University Mainz#TAB#","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011466225","display_name":"Andr\u00e9 Brinkmann","orcid":"https://orcid.org/0000-0003-3083-2775"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Brinkmann","raw_affiliation_strings":["Johannes Gutenberg University Mainz","Johannes Gutenberg University Mainz#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Johannes Gutenberg University Mainz#TAB#","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024794786","display_name":"Tim S\u00fc\u00df","orcid":"https://orcid.org/0000-0001-9935-798X"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim S\u00fc\u00df","raw_affiliation_strings":["Johannes Gutenberg University Mainz","Johannes Gutenberg University Mainz#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Johannes Gutenberg University Mainz#TAB#","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003807012","display_name":"Dirk Meister","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158349","display_name":"Pure Storage (United States)","ror":"https://ror.org/058x40223","country_code":"US","type":"company","lineage":["https://openalex.org/I4210158349"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dirk Meister","raw_affiliation_strings":["Pure Storage"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pure Storage","institution_ids":["https://openalex.org/I4210158349"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3237,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79622954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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":0.9994000196456909,"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":0.991599977016449,"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/T11478","display_name":"Caching and Content Delivery","score":0.9866999983787537,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.954775333404541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8045827746391296},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5202880501747131},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5085028409957886},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4315423369407654},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18254345655441284},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06288430094718933}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.954775333404541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045827746391296},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5202880501747131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5085028409957886},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4315423369407654},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18254345655441284},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06288430094718933}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2741948.2741952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2741948.2741952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth European Conference on Computer Systems","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":32,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W12581771","https://openalex.org/W69510097","https://openalex.org/W120798314","https://openalex.org/W178328500","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1418704970","https://openalex.org/W1445823765","https://openalex.org/W1576397915","https://openalex.org/W1929726975","https://openalex.org/W1969126835","https://openalex.org/W1997349095","https://openalex.org/W2016947394","https://openalex.org/W2028546326","https://openalex.org/W2029433591","https://openalex.org/W2096670209","https://openalex.org/W2110322986","https://openalex.org/W2111238480","https://openalex.org/W2112671267","https://openalex.org/W2123845384","https://openalex.org/W2126381420","https://openalex.org/W2133806194","https://openalex.org/W2134792144","https://openalex.org/W2147407897","https://openalex.org/W2149509741","https://openalex.org/W2149993626","https://openalex.org/W2153158407","https://openalex.org/W2156468933","https://openalex.org/W2281363974","https://openalex.org/W6607453207","https://openalex.org/W6634463810"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2144348063","https://openalex.org/W2074021203"],"abstract_inverted_index":{"Data":[0],"deduplication":[1],"has":[2],"been":[3,15],"a":[4,9,30],"hot":[5],"research":[6],"topic":[7],"and":[8],"large":[10],"number":[11],"of":[12,27],"systems":[13,18],"have":[14],"developed.":[16],"These":[17],"are":[19],"usually":[20],"seen":[21],"as":[22],"an":[23],"inherently":[24],"linked":[25],"set":[26],"characteristics.":[28],"However,":[29],"detailed":[31],"analysis":[32],"shows":[33],"independent":[34],"concepts":[35],"that":[36],"can":[37],"be":[38],"used":[39],"in":[40],"other":[41],"systems.":[42]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}