{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T20:28:07Z","timestamp":1791318487569,"version":"4.3.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,5,27]],"date-time":"2015-05-27T00:00:00Z","timestamp":1432684800000},"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":[[2015,5,27]]},"DOI":"10.1145\/2723372.2747646","type":"proceedings-article","created":{"date-parts":[[2015,6,2]],"date-time":"2015-06-02T05:35:02Z","timestamp":1433223302000},"page":"1215-1230","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":114,"title":["BigDansing"],"prefix":"10.1145","author":[{"given":"Zuhair","family":"Khayyat","sequence":"first","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ihab F.","family":"Ilyas","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alekh","family":"Jindal","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"Madden","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mourad","family":"Ouzzani","sequence":"additional","affiliation":[{"name":"Qatar Computing Research Institute, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Papotti","sequence":"additional","affiliation":[{"name":"Qatar Computing Research Institute, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jorge-Arnulfo","family":"Quian\u00e9-Ruiz","sequence":"additional","affiliation":[{"name":"Qatar Computing Research Institute, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Tang","sequence":"additional","affiliation":[{"name":"Qatar Computing Research Institute, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si","family":"Yin","sequence":"additional","affiliation":[{"name":"Qatar Computing Research Institute, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2015,5,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Shark (Hive on Spark). https:\/\/github.com\/amplab\/shark.  Shark (Hive on Spark). https:\/\/github.com\/amplab\/shark."},{"key":"e_1_3_2_1_2_1","unstructured":"TPC-H benchmark version 2.14.4. http:\/\/www.tpc.org\/tpch\/.  TPC-H benchmark version 2.14.4. http:\/\/www.tpc.org\/tpch\/."},{"key":"e_1_3_2_1_3_1","volume-title":"Data Quality: Concepts, Methodologies and Techniques","author":"Batini C.","year":"2006","unstructured":"C. Batini and M. Scannapieco . Data Quality: Concepts, Methodologies and Techniques . Springer , 2006 . C. Batini and M. Scannapieco. Data Quality: Concepts, Methodologies and Techniques. Springer, 2006."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920870"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066175"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544847"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465327"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_3_2_1_9_1","volume-title":"VLDB","author":"DeWitt D. J.","year":"1991","unstructured":"D. J. DeWitt , J. F. Naughton , and D. A. Schneider . An evaluation of non-equijoin algorithms . In VLDB , 1991 . D. J. DeWitt, J. F. Naughton, and D. A. Schneider. An evaluation of non-equijoin algorithms. In VLDB, 1991."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2371176"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1366102.1366103"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2631923"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989373"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.82"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1976.10481472"},{"key":"e_1_3_2_1_16_1","volume-title":"http:\/\/www.gartner.com\/","author":"Friedman T.","year":"2013","unstructured":"T. Friedman . Magic quadrant for data quality tools. http:\/\/www.gartner.com\/ , 2013 . T. Friedman. Magic quadrant for data quality tools. http:\/\/www.gartner.com\/, 2013."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536360.2536363"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816654"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113269"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/1978665.1978670"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465258"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/309847.309954"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1514894.1514901"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367527"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807184"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807178"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989423"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"issue":"4","key":"e_1_3_2_1_29_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_1_30_1","volume-title":"Accelerate your PostgreSQL System and Avoid the Common Pitfalls that Can Slow it Down","author":"Smith G.","year":"2010","unstructured":"G. Smith . Postgre SQL 9.0 High Performance : Accelerate your PostgreSQL System and Avoid the Common Pitfalls that Can Slow it Down . Packt Publishing , 2010 . G. Smith. PostgreSQL 9.0 High Performance: Accelerate your PostgreSQL System and Avoid the Common Pitfalls that Can Slow it Down. Packt Publishing, 2010."},{"issue":"3","key":"e_1_3_2_1_31_1","article-title":"Gartner warns firms of 'dirty data","volume":"41","author":"Swartz N.","year":"2007","unstructured":"N. Swartz . Gartner warns firms of 'dirty data '. Information Management Journal , 41 ( 3 ), 2007 . N. Swartz. Gartner warns firms of 'dirty data'. Information Management Journal, 41(3), 2007.","journal-title":"Information Management Journal"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687609"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816736"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816655"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610505"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610494"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2484425.2484427"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465288"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2463706"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/1952376.1952378"},{"key":"e_1_3_2_1_41_1","volume-title":"HotCloud","author":"Zaharia M.","year":"2010","unstructured":"M. Zaharia , M. Chowdhury , M. J. Franklin , S. Shenker , and I. Stoica . Spark: Cluster computing with working sets . In HotCloud , 2010 . M. Zaharia, M. Chowdhury, M. J. Franklin, S. Shenker, and I. Stoica. Spark: Cluster computing with working sets. In HotCloud, 2010."}],"event":{"name":"SIGMOD\/PODS'15: International Conference on Management of Data","location":"Melbourne Victoria Australia","acronym":"SIGMOD\/PODS'15","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2723372.2747646","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2723372.2747646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:16:38Z","timestamp":1750227398000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2723372.2747646"}},"subtitle":["A System for Big Data Cleansing"],"short-title":[],"issued":{"date-parts":[[2015,5,27]]},"references-count":41,"alternative-id":["10.1145\/2723372.2747646","10.1145\/2723372"],"URL":"https:\/\/doi.org\/10.1145\/2723372.2747646","relation":{},"subject":[],"published":{"date-parts":[[2015,5,27]]},"assertion":[{"value":"2015-05-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}