{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:55:38Z","timestamp":1757620538346,"version":"3.44.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s11222-025-10701-y","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T13:25:06Z","timestamp":1753968306000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimal F-score Matching for Bipartite Record Linkage"],"prefix":"10.1007","volume":"35","author":[{"given":"Eric A.","family":"Bai","sequence":"first","affiliation":[]},{"given":"Olivier","family":"Binette","sequence":"additional","affiliation":[]},{"given":"Jerome P.","family":"Reiter","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,31]]},"reference":[{"key":"10701_CR1","unstructured":"Bates, D., Maechler, M., Jagan, M.: Matrix: Sparse and Dense Matrix Classes and Methods. R package version 1.6-1 (2023)"},{"key":"10701_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2022.107474","volume":"172","author":"B Betancourt","year":"2022","unstructured":"Betancourt, B., Sosa, J., Rodr\u00edguez, A.: A prior for record linkage based on allelic partitions. Comput. Stat. Data Anal. 172, 107474 (2022)","journal-title":"Comput. Stat. Data Anal."},{"issue":"6","key":"10701_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3418896","volume":"53","author":"V Christophides","year":"2020","unstructured":"Christophides, V., Efthymiou, V., Palpanas, T., Papadakis, G., Stefanidis, K.: An overview of end-to-end entity resolution for big data. ACM Comput. Surveys (CSUR) 53(6), 1\u201342 (2020)","journal-title":"ACM Comput. Surveys (CSUR)"},{"issue":"4","key":"10701_CR4","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1080\/10618600.2018.1458624","volume":"27","author":"NM Dalzell","year":"2018","unstructured":"Dalzell, N.M., Reiter, J.P.: Regression modeling and file matching using possibly erroneous matching variables. J. Comput. Graph. Stat. 27(4), 728\u2013738 (2018)","journal-title":"J. Comput. Graph. Stat."},{"key":"10701_CR5","volume-title":"Customer Data Integration: Reaching a Single Version of the Truth","author":"J Dych\u00e9","year":"2006","unstructured":"Dych\u00e9, J., Levy, E.: Customer Data Integration: Reaching a Single Version of the Truth. John Wiley & Sons, New York (2006)"},{"issue":"2","key":"10701_CR6","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1017\/S0003055418000783","volume":"113","author":"T Enamorado","year":"2019","unstructured":"Enamorado, T., Fifield, B., Imai, K.: Using a probabilistic model to assist merging of large-scale administrative records. Am. Polit. Sci. Rev. 113(2), 353\u2013371 (2019)","journal-title":"Am. Polit. Sci. Rev."},{"key":"10701_CR7","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"IP Fellegi","year":"1969","unstructured":"Fellegi, I.P., Sunter, A.B.: A theory for record linkage. J. Am. Stat. Assoc. 64, 1183\u20131210 (1969)","journal-title":"J. Am. Stat. Assoc."},{"key":"10701_CR8","unstructured":"Fogel, R.W., Costa, D.L., Haines, M., Lee, C., Nguyen, L., Pope, C., Rosenberg, I., Scrimshaw, N., Trussell, J., Wilson, S., et\u00a0al.: .Aging of veterans of the union army: Version m-5. Chicago: Center for Population Economics, University of Chicago Graduate School of Business, Department of Economics, Brigham Young University, and the National Bureau of Economic Research (2000)"},{"issue":"1","key":"10701_CR9","first-page":"185","volume":"4","author":"M Fortini","year":"2001","unstructured":"Fortini, M., Liseo, B., Nuccitelli, A., Scanu, M.: On Bayesian record linkage. Research Off. Stat. 4(1), 185\u2013198 (2001)","journal-title":"Research Off. Stat."},{"key":"10701_CR10","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1214\/21-BA1297","volume":"17","author":"S Guha","year":"2022","unstructured":"Guha, S., Reiter, J.P., Mercatanti, A.: Bayesian causal inference with bipartite record linkage. Bayesian Anal. 17, 1275\u20131299 (2022)","journal-title":"Bayesian Anal."},{"key":"10701_CR11","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1080\/01621459.2012.726889","volume":"108","author":"R Gutman","year":"2013","unstructured":"Gutman, R., Afendulis, C.C., Zaslavsky, A.M.: A Bayesian procedure for file linking to analyze end-of-life medical costs. J. Am. Stat. Assoc. 108, 34\u201347 (2013)","journal-title":"J. Am. Stat. Assoc."},{"key":"10701_CR12","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/s11222-017-9746-6","volume":"28","author":"D Hand","year":"2018","unstructured":"Hand, D., Christen, P.: A note on using the F-measure for evaluating record linkage algorithms. Stat. Comput. 28, 539\u2013547 (2018)","journal-title":"Stat. Comput."},{"key":"10701_CR13","unstructured":"Jansche, M.: A maximum expected utility framework for binary sequence labeling. In A.\u00a0Zaenen and A.\u00a0van\u00a0den Bosch (Eds.), Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, Prague, Czech Republic, pp. 736\u2013743. Association for Computational Linguistics (2007)"},{"issue":"406","key":"10701_CR14","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1080\/01621459.1989.10478785","volume":"84","author":"MA Jaro","year":"1989","unstructured":"Jaro, M.A.: Advances in record-linkage methodology as applied to matching the 1985 census of Tampa, Florida. J. Am. Stat. Assoc. 84(406), 414\u2013420 (1989)","journal-title":"J. Am. Stat. Assoc."},{"key":"10701_CR15","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1146\/annurev-publhealth-031210-100700","volume":"32","author":"DP Jutte","year":"2011","unstructured":"Jutte, D.P., Roos, L.L., Brownell, M.D.: Administrative record linkage as a tool for public health research. Annu. Rev. Public Health 32, 91\u2013108 (2011)","journal-title":"Annu. Rev. Public Health"},{"key":"10701_CR16","doi-asserted-by":"crossref","unstructured":"Kundinger, B., Reiter, J.P., Steorts, R.C.: Efficient and scalable bipartite matching with fast beta linkage (fabl). Bayesian Analysis, forthcoming (2025)","DOI":"10.1214\/24-BA1427"},{"key":"10701_CR17","unstructured":"McVeigh, B.S., Spahn, B.T., Murray, J.S.: Scaling Bayesian probabilistic record linkage with post-hoc blocking: an application to the California Great Registers. arXiv preprint arXiv:1905.05337 (2019)"},{"key":"10701_CR18","unstructured":"Papadakis, G., Efthymiou, V., Thanos, E., Hassanzadeh, O.: Bipartite graph matching algorithms for clean-clean entity resolution: an empirical evaluation. arXiv preprint arXiv:2112.14030 (2021)"},{"key":"10701_CR19","unstructured":"Ramshaw, L., Tarjan, R.E.: On minimum-cost assignments in unbalanced bipartite graphs. Technical report, HP Labs, Report HPL-2012-40R1 (2012)"},{"issue":"518","key":"10701_CR20","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1080\/01621459.2016.1148612","volume":"112","author":"M Sadinle","year":"2017","unstructured":"Sadinle, M.: Bayesian estimation of bipartite matchings for record linkage. J. Am. Stat. Assoc. 112(518), 600\u2013612 (2017)","journal-title":"J. Am. Stat. Assoc."},{"key":"10701_CR21","doi-asserted-by":"crossref","unstructured":"Sadinle, M.: BRL: Beta Record Linkage. R package version 0.1.0 (2020)","DOI":"10.32614\/CRAN.package.BRL"},{"key":"10701_CR22","unstructured":"Sariyar, M., Borg, A.: RecordLinkage: Record Linkage Functions for Linking and Deduplicating Data Sets. R package version 0.4-12.4 (2022)"},{"key":"10701_CR23","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1214\/15-BA965SI","volume":"10","author":"RC Steorts","year":"2015","unstructured":"Steorts, R.C.: Entity resolution with empirically motivated priors. Bayesian Anal. 10, 849\u2013875 (2015)","journal-title":"Bayesian Anal."},{"key":"10701_CR24","doi-asserted-by":"publisher","first-page":"1648","DOI":"10.1080\/01621459.2015.1105807","volume":"111","author":"RC Steorts","year":"2016","unstructured":"Steorts, R.C., Hall, R., Fienberg, S.E.: A Bayesian approach to graphical record linkage and de-duplication. J. Am. Stat. Assoc. 111, 1648\u20131659 (2016)","journal-title":"J. Am. Stat. Assoc."},{"key":"10701_CR25","doi-asserted-by":"publisher","first-page":"1553","DOI":"10.1214\/10-AOAS447","volume":"5","author":"A Tancredi","year":"2011","unstructured":"Tancredi, A., Liseo, B.: A hierarchical Bayesian approach to record linkage and population size problems. The Annals Appl. Stat. 5, 1553\u20131585 (2011)","journal-title":"The Annals Appl. Stat."},{"key":"10701_CR26","doi-asserted-by":"crossref","unstructured":"Tang, J., Reiter, J.P., Steorts, R.C.: Bayesian modeling for simultaneous regression and record linkage. In J.\u00a0Domingo-Ferrer and K.\u00a0Muralidhar (Eds.), Privacy in Statistical Databases, pp. 209 \u2013 223. Lecture Notes in Computer Science 12276, Cham, Switzerland: Springer (2020)","DOI":"10.1007\/978-3-030-57521-2_15"},{"key":"10701_CR27","unstructured":"Winkler, W.E., Thibaudeau, Y.: An application of the Fellegi-Sunter model of record linkage to the 1990 U.S. decennial census. Technical report, United States Bureau of the Census, Working Paper Number RR91-09 (1991)"},{"key":"10701_CR28","unstructured":"Wortman, J.P.H.: Record Linkage Methods with Applications to Causal Inference and Election Voting Data. Ph. D. thesis, Department of Statistical Science, Duke University (2019)"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-025-10701-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-025-10701-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-025-10701-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T09:31:37Z","timestamp":1757323897000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-025-10701-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":28,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10701"],"URL":"https:\/\/doi.org\/10.1007\/s11222-025-10701-y","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"type":"print","value":"0960-3174"},{"type":"electronic","value":"1573-1375"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"assertion":[{"value":"11 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"160"}}