{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:49:09Z","timestamp":1750308549325,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,8,4]],"date-time":"2017-08-04T00:00:00Z","timestamp":1501804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,8,4]]},"DOI":"10.1145\/3097983.3097999","type":"proceedings-article","created":{"date-parts":[[2017,8,4]],"date-time":"2017-08-04T18:35:54Z","timestamp":1501871754000},"page":"95-103","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["A Minimal Variance Estimator for the Cardinality of Big Data Set Intersection"],"prefix":"10.1145","author":[{"given":"Reuven","family":"Cohen","sequence":"first","affiliation":[{"name":"Technion, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liran","family":"Katzir","sequence":"additional","affiliation":[{"name":"Technion, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aviv","family":"Yehezkel","sequence":"additional","affiliation":[{"name":"Technion, Haifa, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2007.369032"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247504"},{"key":"e_1_3_2_2_3_1","first-page":"21","volume-title":"IEEE Compression and Complexity of Sequences","author":"Broder A. Z.","year":"1997","unstructured":"A. Z. Broder . On the resemblance and containment of documents . In IEEE Compression and Complexity of Sequences 1997 , pages 21 -- 29 . A. Z. Broder. On the resemblance and containment of documents. In IEEE Compression and Complexity of Sequences 1997, pages 21--29."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45123-4_1"},{"key":"e_1_3_2_2_5_1","volume-title":"Syntactic clustering of the web. Computer Networks, 29(8--13):1157--1166","author":"Broder A. Z.","year":"1997","unstructured":"A. Z. Broder , S. C. Glassman , M. S. Manasse , and G. Zweig . Syntactic clustering of the web. Computer Networks, 29(8--13):1157--1166 , 1997 . A. Z. Broder, S. C. Glassman, M. S. Manasse, and G. Zweig. Syntactic clustering of the web. Computer Networks, 29(8--13):1157--1166, 1997."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.46298\/dmtcs.3492"},{"key":"e_1_3_2_2_7_1","volume-title":"Scandinavian Journal of Statistics","author":"Clifford P.","year":"2011","unstructured":"P. Clifford and I. A. Cosma . A statistical analysis of probabilistic counting algorithms . Scandinavian Journal of Statistics , 2011 . P. Clifford and I. A. Cosma. A statistical analysis of probabilistic counting algorithms. Scandinavian Journal of Statistics, 2011."},{"key":"e_1_3_2_2_8_1","first-page":"428","volume-title":"DS-7","author":"Clifton C.","year":"1997","unstructured":"C. Clifton , E. Housman , and A. Rosenthal . Experience with a combined approach to attribute-matching across heterogeneous databases . In DS-7 , pages 428 -- 451 , 1997 . C. Clifton, E. Housman, and A. Rosenthal. Experience with a combined approach to attribute-matching across heterogeneous databases. In DS-7, pages 428--451, 1997."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453884"},{"key":"e_1_3_2_2_10_1","volume-title":"A minimal variance estimator for the cardinality of big data set intersection. CoRR, abs\/1606.00996","author":"Cohen R.","year":"2016","unstructured":"R. Cohen , L. Katzir , and A. Yehezkel . A minimal variance estimator for the cardinality of big data set intersection. CoRR, abs\/1606.00996 , 2016 . R. Cohen, L. Katzir, and A. Yehezkel. A minimal variance estimator for the cardinality of big data set intersection. CoRR, abs\/1606.00996, 2016."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/564691.564719"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.46298\/dmtcs.3545"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0000(85)90041-8"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972979.9"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2007.142"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dam.2008.06.020"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009761603038"},{"key":"e_1_3_2_2_18_1","first-page":"71","volume-title":"ACSC","author":"K\u00f6hler H.","year":"2010","unstructured":"H. K\u00f6hler . Estimating set intersection using small samples . In ACSC , pages 71 -- 78 , 2010 . H. K\u00f6hler. Estimating set intersection using small samples. In ACSC, pages 71--78, 2010."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.46298\/dmtcs.2780"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1353343.1353418"},{"issue":"4","key":"e_1_3_2_2_21_1","first-page":"14","article-title":"Matching algorithms within a duplicate detection system","volume":"23","author":"Monge A. E.","year":"2000","unstructured":"A. E. Monge . Matching algorithms within a duplicate detection system . IEEE Data Eng. Bull. , 23 ( 4 ): 14 -- 20 , 2000 . A. E. Monge. Matching algorithms within a duplicate detection system. IEEE Data Eng. Bull., 23(4):14--20, 2000.","journal-title":"IEEE Data Eng. Bull."},{"issue":"4","key":"e_1_3_2_2_22_1","first-page":"3","article-title":"Problems and current approaches","volume":"23","author":"Rahm E.","year":"2000","unstructured":"E. Rahm and H. H. Do . Data cleaning : Problems and current approaches . IEEE Data Eng. Bull. , 23 ( 4 ): 3 -- 13 , 2000 . E. Rahm and H. H. Do. Data cleaning: Problems and current approaches. IEEE Data Eng. Bull., 23(4):3--13, 2000.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/b97553"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939772"}],"event":{"name":"KDD '17: The 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Halifax NS Canada","acronym":"KDD '17"},"container-title":["Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3097983.3097999","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3097983.3097999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:03:42Z","timestamp":1750273422000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3097983.3097999"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,4]]},"references-count":24,"alternative-id":["10.1145\/3097983.3097999","10.1145\/3097983"],"URL":"https:\/\/doi.org\/10.1145\/3097983.3097999","relation":{},"subject":[],"published":{"date-parts":[[2017,8,4]]},"assertion":[{"value":"2017-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}