{"id":"https://openalex.org/W2167011595","doi":"https://doi.org/10.1007/11890591_5","title":"Unsupervised Duplicate Detection Using Sample Non-duplicates","display_name":"Unsupervised Duplicate Detection Using Sample Non-duplicates","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2167011595","doi":"https://doi.org/10.1007/11890591_5","mag":"2167011595"},"language":"en","primary_location":{"id":"doi:10.1007/11890591_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11890591_5","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5017098065","display_name":"Patrick Lehti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133470","display_name":"Fraunhofer Institute for Secure Information Technology","ror":"https://ror.org/03qt2gs44","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210133470","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Patrick Lehti","raw_affiliation_strings":["Fraunhofer IPSI, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPSI, Darmstadt, Germany","institution_ids":["https://openalex.org/I4210133470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037943398","display_name":"P\u00e9ter Fankhauser","orcid":"https://orcid.org/0000-0001-7128-9188"},"institutions":[{"id":"https://openalex.org/I4210133470","display_name":"Fraunhofer Institute for Secure Information Technology","ror":"https://ror.org/03qt2gs44","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210133470","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Fankhauser","raw_affiliation_strings":["Fraunhofer IPSI, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPSI, Darmstadt, Germany","institution_ids":["https://openalex.org/I4210133470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017098065"],"corresponding_institution_ids":["https://openalex.org/I4210133470"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.14638609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9868000149726868,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9803000092506409,"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":0.8175349235534668},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6163293719291687},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5872735977172852},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5833841562271118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5731824636459351},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5605651140213013},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.546317458152771},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.48195216059684753},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46228742599487305},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.44024550914764404},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2646036148071289},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07736930251121521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8175349235534668},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6163293719291687},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5872735977172852},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5833841562271118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5731824636459351},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5605651140213013},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.546317458152771},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.48195216059684753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46228742599487305},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.44024550914764404},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2646036148071289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07736930251121521},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/11890591_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11890591_5","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:fraunhofer.de:N-59609","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-59609.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IPSI","raw_type":"Book Article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/212118","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/212118","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"book article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W46452414","https://openalex.org/W80619934","https://openalex.org/W92894758","https://openalex.org/W95995957","https://openalex.org/W115704860","https://openalex.org/W128740895","https://openalex.org/W130948412","https://openalex.org/W154872207","https://openalex.org/W1484228408","https://openalex.org/W1497443639","https://openalex.org/W1519440323","https://openalex.org/W1520363973","https://openalex.org/W1557365335","https://openalex.org/W1559390933","https://openalex.org/W1566649662","https://openalex.org/W1569123402","https://openalex.org/W1581262234","https://openalex.org/W1593045043","https://openalex.org/W1612155886","https://openalex.org/W1647671624","https://openalex.org/W1660390307","https://openalex.org/W1742677423","https://openalex.org/W1761401273","https://openalex.org/W1774330103","https://openalex.org/W1898496839","https://openalex.org/W1975723136","https://openalex.org/W1979629649","https://openalex.org/W1981276685","https://openalex.org/W2007709031","https://openalex.org/W2023448865","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2038281398","https://openalex.org/W2046020929","https://openalex.org/W2049633694","https://openalex.org/W2049855118","https://openalex.org/W2052390074","https://openalex.org/W2055405704","https://openalex.org/W2058755145","https://openalex.org/W2063408112","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2085099553","https://openalex.org/W2097730395","https://openalex.org/W2102350406","https://openalex.org/W2102443632","https://openalex.org/W2112912553","https://openalex.org/W2120772360","https://openalex.org/W2121947440","https://openalex.org/W2122410182","https://openalex.org/W2127218421","https://openalex.org/W2129598390","https://openalex.org/W2131576956","https://openalex.org/W2133236963","https://openalex.org/W2139956879","https://openalex.org/W2140095548","https://openalex.org/W2150698190","https://openalex.org/W2153635508","https://openalex.org/W2153977007","https://openalex.org/W2154785834","https://openalex.org/W2155406434","https://openalex.org/W2159481891","https://openalex.org/W2161600801","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2167081989","https://openalex.org/W2169948249","https://openalex.org/W2170902582","https://openalex.org/W2171574281","https://openalex.org/W2623293810","https://openalex.org/W2999905431","https://openalex.org/W4214671568","https://openalex.org/W4230502578","https://openalex.org/W4253845435","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3183633970","https://openalex.org/W2900794075","https://openalex.org/W3208309985","https://openalex.org/W2026253357","https://openalex.org/W2695951553","https://openalex.org/W2775464024","https://openalex.org/W2117320694","https://openalex.org/W3108696707","https://openalex.org/W3201151379","https://openalex.org/W73805934"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"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"}
