{"id":"https://openalex.org/W2046020929","doi":"https://doi.org/10.1145/1066157.1066168","title":"Reference reconciliation in complex information spaces","display_name":"Reference reconciliation in complex information spaces","publication_year":2005,"publication_date":"2005-06-14","ids":{"openalex":"https://openalex.org/W2046020929","doi":"https://doi.org/10.1145/1066157.1066168","mag":"2046020929"},"language":"en","primary_location":{"id":"doi:10.1145/1066157.1066168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","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/A5001402526","display_name":"Xin Luna Dong","orcid":"https://orcid.org/0009-0000-8667-322X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Dong","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067621853","display_name":"Alon Halevy","orcid":"https://orcid.org/0000-0002-8717-7356"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Halevy","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034699810","display_name":"Jayant Madhavan","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayant Madhavan","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001402526"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":54.4489,"has_fulltext":false,"cited_by_count":526,"citation_normalized_percentile":{"value":0.99965845,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.9771999716758728,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9678999781608582,"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":0.7755818963050842},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6257883310317993},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5957743525505066},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5937546491622925},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5685701966285706},{"id":"https://openalex.org/keywords/prime","display_name":"Prime (order theory)","score":0.5138192772865295},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5111759305000305},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.4984898567199707},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.49498647451400757},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4912411570549011},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45069438219070435},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32201462984085083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.183370441198349},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15627381205558777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755818963050842},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6257883310317993},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5957743525505066},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5937546491622925},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5685701966285706},{"id":"https://openalex.org/C184992742","wikidata":"https://www.wikidata.org/wiki/Q7243229","display_name":"Prime (order theory)","level":2,"score":0.5138192772865295},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5111759305000305},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.4984898567199707},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.49498647451400757},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4912411570549011},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45069438219070435},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32201462984085083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.183370441198349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15627381205558777},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1066157.1066168","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.108.3413","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.108.3413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://data.cs.washington.edu/semex/reconciliation_sigmod.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.319.3579","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.319.3579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/sigmodpods05/sigmod/pdf/p85-dong.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.473.9158","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.473.9158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://pal.sri.com/CALOfiles/cstore/PAL-publications/calo/2005/p85-dong.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W46452414","https://openalex.org/W73146770","https://openalex.org/W115704860","https://openalex.org/W130948412","https://openalex.org/W177885090","https://openalex.org/W1485156179","https://openalex.org/W1559390933","https://openalex.org/W1581262234","https://openalex.org/W1603243937","https://openalex.org/W1646278814","https://openalex.org/W1673955757","https://openalex.org/W2015720094","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2050071106","https://openalex.org/W2052390074","https://openalex.org/W2055405704","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2085099553","https://openalex.org/W2097730395","https://openalex.org/W2105423800","https://openalex.org/W2111625757","https://openalex.org/W2112175905","https://openalex.org/W2112912553","https://openalex.org/W2120772360","https://openalex.org/W2135223301","https://openalex.org/W2154785834","https://openalex.org/W2159481891","https://openalex.org/W2162630660","https://openalex.org/W2164456230","https://openalex.org/W4250633719","https://openalex.org/W4254734767","https://openalex.org/W4285719527","https://openalex.org/W6637623960","https://openalex.org/W6669040500","https://openalex.org/W6674476871","https://openalex.org/W6676669657","https://openalex.org/W6683373780"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297"],"abstract_inverted_index":{"Reference":[0],"reconciliation":[1,91,116],"is":[2,71,78],"the":[3,20,76,86,100],"problem":[4],"of":[5,12,38,67,84,151],"identifying":[6],"when":[7],"different":[8],"references":[9,28,49,103,128],"(i.e.,":[10],"sets":[11],"attribute":[13,62,131],"values)":[14],"in":[15],"a":[16,30,35,69,81,148,166],"dataset":[17,169],"correspond":[18],"to":[19,29,51,79,104,118,160],"same":[21],"real-world":[22],"entity.":[23],"Most":[24],"previous":[25],"literature":[26],"assumed":[27],"single":[31],"class":[32],"that":[33,136],"had":[34],"fair":[36],"number":[37],"attributes":[39],"(e.g.,":[40],"research":[41],"publications).":[42],"We":[43],"consider":[44],"complex":[45],"information":[46,87,114,153],"spaces:":[47],"our":[48,162],"belong":[50],"multiple":[52],"related":[53],"classes":[54],"and":[55,121,142,155],"each":[56],"reference":[57,109],"may":[58],"have":[59],"very":[60],"few":[61],"values.":[63,132],"A":[64],"prime":[65],"example":[66],"such":[68],"space":[70],"Personal":[72],"Information":[73],"Management,":[74],"where":[75],"goal":[77],"provide":[80],"coherent":[82],"view":[83],"all":[85],"on":[88,147,165],"one's":[89],"desktop.Our":[90],"algorithm":[92,163],"has":[93],"three":[94],"principal":[95],"features.":[96],"First,":[97],"we":[98,112,125,138],"exploit":[99],"associations":[101],"between":[102,115],"design":[105],"new":[106],"methods":[107,146],"for":[108],"comparison.":[110],"Second,":[111],"propagate":[113],"decisions":[117],"accumulate":[119],"positive":[120],"negative":[122],"evidences.":[123],"Third,":[124],"gradually":[126],"enrich":[127],"by":[129],"merging":[130],"Our":[133],"experiments":[134],"show":[135],"(1)":[137],"considerably":[139],"improve":[140],"precision":[141],"recall":[143],"over":[144],"standard":[145,167],"diverse":[149],"set":[150],"personal":[152],"datasets,":[154],"(2)":[156],"there":[157],"are":[158],"advantages":[159],"using":[161],"even":[164],"citation":[168],"benchmark.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":35},{"year":2015,"cited_by_count":25},{"year":2014,"cited_by_count":40},{"year":2013,"cited_by_count":35},{"year":2012,"cited_by_count":30}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}