{"id":"https://openalex.org/W7215959900","doi":"https://doi.org/10.48550/arxiv.2610.00566","title":"Probabilistic linkage with graphs: leveraging cluster structure to improve the accuracy of entity resolution at scale","display_name":"Probabilistic linkage with graphs: leveraging cluster structure to improve the accuracy of entity resolution at scale","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215959900","doi":"https://doi.org/10.48550/arxiv.2610.00566"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.00566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00566","pdf_url":"https://arxiv.org/pdf/2610.00566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.00566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012610633","display_name":"Evelyn Lauren","orcid":"https://orcid.org/0000-0002-0333-110X","observed_orcids":["https://orcid.org/0000-0002-0333-110X"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I192619145","display_name":"University of the Witwatersrand","ror":"https://ror.org/03rp50x72","country_code":"ZA","type":"education","lineage":["https://openalex.org/I192619145"]}],"countries":["US","ZA"],"is_corresponding":false,"raw_author_name":"Lauren, Evelyn","raw_affiliation_strings":["Department of Biostatistics , Boston University School of Public Health , Boston , MA , USA","Health Economics and Epidemiology Research Office , Faculty of Health Sciences , University of the Witwatersrand , Johannesburg , South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics , Boston University School of Public Health , Boston , MA , USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Health Economics and Epidemiology Research Office , Faculty of Health Sciences , University of the Witwatersrand , Johannesburg , South Africa","institution_ids":["https://openalex.org/I192619145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078526061","display_name":"Laura Forsberg White","orcid":"https://orcid.org/0000-0002-0588-8235","observed_orcids":["https://orcid.org/0000-0002-0588-8235"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"White, Laura","raw_affiliation_strings":["Department of Biostatistics , Boston University School of Public Health , Boston , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics , Boston University School of Public Health , Boston , MA , USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038658089","display_name":"Trevor Graham Bell","orcid":"https://orcid.org/0000-0003-2630-7513","observed_orcids":["https://orcid.org/0000-0003-2630-7513"]},"institutions":[{"id":"https://openalex.org/I107920810","display_name":"National Health Laboratory Service","ror":"https://ror.org/00znvbk37","country_code":"ZA","type":"government","lineage":["https://openalex.org/I107920810"]},{"id":"https://openalex.org/I4387155312","display_name":"National Institute for Communicable Diseases","ror":"https://ror.org/007wwmx82","country_code":"ZA","type":"government","lineage":["https://openalex.org/I4387155312"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Bell, Trevor Graham","raw_affiliation_strings":["National Institute for Communicable Diseases , National Health Laboratory Service , Johannesburg , South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute for Communicable Diseases , National Health Laboratory Service , Johannesburg , South Africa","institution_ids":["https://openalex.org/I107920810","https://openalex.org/I4387155312"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039166958","display_name":"Jacob H. Bor","orcid":"https://orcid.org/0000-0002-5112-8536","observed_orcids":["https://orcid.org/0000-0002-5112-8536"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bor, Jacob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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/T13546","display_name":"Census and Population Estimation","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11539","display_name":"Survey Methodology and Nonresponse","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-record-linkage","display_name":"probabilistic record linkage","score":0.9480000138282776},{"id":"https://openalex.org/keywords/entity-resolution","display_name":"entity resolution","score":0.9980000257492065},{"id":"https://openalex.org/keywords/graph-clustering","display_name":"graph clustering","score":0.7900000214576721},{"id":"https://openalex.org/keywords/transitive-closure","display_name":"transitive closure","score":0.7950000166893005},{"id":"https://openalex.org/keywords/louvain-algorithm","display_name":"Louvain algorithm","score":0.6549999713897705},{"id":"https://openalex.org/keywords/leiden-algorithm","display_name":"Leiden algorithm","score":0.9739999771118164},{"id":"https://openalex.org/keywords/label-propagation","display_name":"label propagation","score":0.9480000138282776},{"id":"https://openalex.org/keywords/markov-clustering","display_name":"Markov clustering","score":0.8420000076293945},{"id":"https://openalex.org/keywords/administrative-data","display_name":"administrative data","score":0.8769999742507935},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.31200000643730164}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7145000100135803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062000036239624},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6976000070571899},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6830999851226807},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6412000060081482},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.5849000215530396},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.5152999758720398},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.4878000020980835},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.27000001072883606},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.00566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00566","pdf_url":"https://arxiv.org/pdf/2610.00566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2610.00566","doi":"https://doi.org/10.48550/arxiv.2610.00566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.00566","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.00566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00566","pdf_url":"https://arxiv.org/pdf/2610.00566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215959900.pdf","grobid_xml":"https://content.openalex.org/works/W7215959900.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1981877370","https://openalex.org/W1995541812","https://openalex.org/W2015953751","https://openalex.org/W2033947830","https://openalex.org/W2034190452","https://openalex.org/W2047940964","https://openalex.org/W2073471108","https://openalex.org/W2095293504","https://openalex.org/W2102763740","https://openalex.org/W2124209874","https://openalex.org/W2128366083","https://openalex.org/W2132202037","https://openalex.org/W2142074194","https://openalex.org/W2164998314","https://openalex.org/W2898696130","https://openalex.org/W2973207699","https://openalex.org/W3004300812","https://openalex.org/W3048871918","https://openalex.org/W3092962901","https://openalex.org/W4226285323","https://openalex.org/W4242744113","https://openalex.org/W4294243456"],"related_works":["https://openalex.org/W2808219196","https://openalex.org/W7098832611","https://openalex.org/W2790417993","https://openalex.org/W2765590357","https://openalex.org/W4402404993","https://openalex.org/W2602742489","https://openalex.org/W822439496","https://openalex.org/W2343236305","https://openalex.org/W36024057","https://openalex.org/W4280528717"],"abstract_inverted_index":{"Probabilistic":[0],"record":[1],"linkage":[2,83,138,154],"identifies":[3],"records":[4],"belonging":[5],"to":[6,21,52,81,137,158,161,170],"the":[7,60,65,91,150,181],"same":[8,92],"entity":[9,105,116,182],"even":[10],"when":[11],"identifiers":[12],"are":[13],"incomplete":[14],"or":[15],"imperfect,":[16],"and":[17,56,118,128,132,185],"is":[18],"increasingly":[19],"used":[20],"conduct":[22],"population-level":[23],"inferences":[24],"from":[25,59,87,120],"administrative":[26],"data":[27],"at":[28,191],"scale.":[29,192],"Linkage":[30],"produces":[31],"noisy":[32],"pairwise":[33],"links":[34],"that":[35,77],"must":[36],"then":[37],"be":[38],"resolved":[39],"into":[40,188],"distinct":[41,69],"individuals.":[42],"The":[43,164],"standard":[44],"approach,":[45],"transitive":[46,162],"closure,":[47],"applies":[48],"a":[49],"fixed":[50],"threshold":[51],"each":[53],"link":[54],"independently":[55],"assigns":[57],"clusters":[58],"resulting":[61],"connected":[62],"components.":[63],"However,":[64],"risk":[66],"of":[67],"merging":[68],"individuals":[70],"grows":[71],"with":[72],"population":[73],"size,":[74],"motivating":[75],"approaches":[76],"use":[78],"graph":[79],"structure":[80],"improve":[82],"accuracy.":[84],"Clustering":[85],"algorithms":[86,111,141,166],"adjacent":[88,121],"fields":[89,122],"solve":[90],"graph-clustering":[93],"task":[94],"in":[95,115,180],"other":[96],"domains,":[97],"yet":[98],"have":[99],"never":[100],"been":[101],"systematically":[102],"evaluated":[103,108],"for":[104],"resolution.":[106],"We":[107],"eleven":[109],"clustering":[110,176],"--":[112,123,142,147],"five":[113],"established":[114],"resolution":[117,183],"six":[119],"across":[124],"three":[125,165],"simulated":[126],"datasets":[127],"one":[129],"real-world":[130],"dataset,":[131],"propose":[133],"an":[134],"adaptation":[135],"tailored":[136],"graphs.":[139],"Cross-field":[140],"Leiden,":[143],"Louvain,":[144],"label":[145],"propagation":[146],"were":[148],"among":[149],"most":[151],"accurate,":[152],"reducing":[153],"error":[155],"by":[156],"up":[157,169],"66%":[159],"relative":[160],"closure.":[163],"also":[167],"ran":[168],"40":[171],"times":[172],"faster":[173],"than":[174],"Markov":[175],"(a":[177],"leading":[178],"approach":[179],"literature)":[184],"integrate":[186],"directly":[187],"existing":[189],"pipelines":[190]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}