{"id":"https://openalex.org/W2125530761","doi":"https://doi.org/10.1145/1458082.1458259","title":"Scaling up duplicate detection in graph data","display_name":"Scaling up duplicate detection in graph data","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2125530761","doi":"https://doi.org/10.1145/1458082.1458259","mag":"2125530761"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458259","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","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/A5087589863","display_name":"Melanie Herschel","orcid":"https://orcid.org/0009-0007-9821-5921"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Melanie Herschel","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso-Plattner-Institut, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087589863"],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":2.5447,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89907278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1325","last_page":"1326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9898999929428101,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646644711494446},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7431623935699463},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5861344933509827},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5457879304885864},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5198719501495361},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48990005254745483},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42665284872055054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34735095500946045},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2946270704269409},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22584033012390137},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17270693182945251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0995393693447113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646644711494446},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7431623935699463},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5861344933509827},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5457879304885864},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5198719501495361},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48990005254745483},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42665284872055054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34735095500946045},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2946270704269409},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22584033012390137},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17270693182945251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0995393693447113},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458259","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1689241477","https://openalex.org/W2024770506","https://openalex.org/W2087183379","https://openalex.org/W2099813268","https://openalex.org/W2107976925","https://openalex.org/W2108991785","https://openalex.org/W2148019918","https://openalex.org/W2164456230"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W141820298","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W3151146928"],"abstract_inverted_index":{"Duplicate":[0],"detection":[1,41,58],"determines":[2],"different":[3],"representations":[4,21],"of":[5,17],"real-world":[6,56],"objects":[7],"in":[8],"a":[9,33],"database.":[10],"Recent":[11],"research":[12,35],"has":[13,36,44],"considered":[14],"the":[15,27],"use":[16],"relationships":[18,31],"among":[19],"object":[20],"to":[22],"improve":[23],"duplicate":[24,40,57],"detection.":[25],"In":[26],"general":[28],"case":[29],"where":[30],"form":[32],"graph,":[34],"mainly":[37],"focused":[38],"on":[39],"quality/effectiveness.":[42],"Scalability":[43],"been":[45],"neglected":[46],"so":[47],"far,":[48],"even":[49],"though":[50],"it":[51],"is":[52],"crucial":[53],"for":[54],"large":[55],"tasks.":[59]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
