{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T01:46:23Z","timestamp":1792460783728,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,25]],"date-time":"2019-06-25T00:00:00Z","timestamp":1561420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["387872445"],"award-info":[{"award-number":["387872445"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,25]]},"DOI":"10.1145\/3299869.3324956","type":"proceedings-article","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T17:41:43Z","timestamp":1560879703000},"page":"865-882","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":124,"title":["Raha"],"prefix":"10.1145","author":[{"given":"Mohammad","family":"Mahdavi","sequence":"first","affiliation":[{"name":"TU Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziawasch","family":"Abedjan","sequence":"additional","affiliation":[{"name":"TU Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raul","family":"Castro Fernandez","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":"QCRI, HBKU, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Stonebraker","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Tang","sequence":"additional","affiliation":[{"name":"QCRI, HBKU, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,6,25]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994518"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0389-y"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Ziawasch Abedjan John Morcos Ihab F Ilyas Mourad Ouzzani Paolo Papotti and Michael Stonebraker. 2016b. DataXFormer: A robust transformation discovery system. In ICDE. 1134--1145.  Ziawasch Abedjan John Morcos Ihab F Ilyas Mourad Ouzzani Paolo Papotti and Michael Stonebraker. 2016b. DataXFormer: A robust transformation discovery system. In ICDE. 1134--1145.","DOI":"10.1109\/ICDE.2016.7498319"},{"key":"e_1_3_2_2_4_1","volume-title":"Foundations of databases: the logical level","author":"Abiteboul Serge","unstructured":"Serge Abiteboul , Richard Hull , and Victor Vianu . 1995. Foundations of databases: the logical level . Addison-Wesley Longman Publishing Co., Inc. Serge Abiteboul, Richard Hull, and Victor Vianu. 1995. Foundations of databases: the logical level .Addison-Wesley Longman Publishing Co., Inc."},{"key":"e_1_3_2_2_5_1","volume-title":"Data clustering: algorithms and applications","author":"Aggarwal Charu C","unstructured":"Charu C Aggarwal and Chandan K Reddy . 2013. Data clustering: algorithms and applications . CRC Press . Charu C Aggarwal and Chandan K Reddy. 2013. Data clustering: algorithms and applications .CRC Press."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850578.2850579"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"S\u00f6ren Auer Christian Bizer Georgi Kobilarov Jens Lehmann Richard Cyganiak and Zachary Ives. 2007. DBpedia: A nucleus for a web of open data. In ISWC. 722--735.   S\u00f6ren Auer Christian Bizer Georgi Kobilarov Jens Lehmann Richard Cyganiak and Zachary Ives. 2007. DBpedia: A nucleus for a web of open data. In ISWC. 722--735.","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-008-0098-x"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2011.5767864"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/3204028.3204032"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2008.4497460"},{"key":"e_1_3_2_2_12_1","unstructured":"Andrei Z Broder. 1997. On the resemblance and containment of documents. In Compression and complexity of sequences . 21--29.   Andrei Z Broder. 1997. On the resemblance and containment of documents. In Compression and complexity of sequences . 21--29."},{"key":"e_1_3_2_2_13_1","unstructured":"Olivier Chapelle Jason Weston and Bernhard Sch\u00f6lkopf. 2003. Cluster kernels for semi-supervised learning. In NIPS. 601--608.   Olivier Chapelle Jason Weston and Bernhard Sch\u00f6lkopf. 2003. Cluster kernels for semi-supervised learning. In NIPS. 601--608."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/3007263.3007320"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536258.2536262"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544847"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749431"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Michele Dallachiesa Amr Ebaid Ahmed Eldawy Ahmed Elmagarmid Ihab F Ilyas Mourad Ouzzani and Nan Tang. 2013. NADEEF: a commodity data cleaning system. In SIGMOD. 541--552.  Michele Dallachiesa Amr Ebaid Ahmed Eldawy Ahmed Elmagarmid Ihab F Ilyas Mourad Ouzzani and Nan Tang. 2013. NADEEF: a commodity data cleaning system. In SIGMOD. 541--552.","DOI":"10.1145\/2463676.2465327"},{"key":"e_1_3_2_2_19_1","unstructured":"Sanjib Das AnHai Doan Paul Suganthan G. C. Chaitanya Gokhale and Pradap Konda. 2015. The Magellan Data Repository. https:\/\/sites.google.com\/site\/anhaidgroup\/projects\/data .  Sanjib Das AnHai Doan Paul Suganthan G. C. Chaitanya Gokhale and Pradap Konda. 2015. The Magellan Data Repository. https:\/\/sites.google.com\/site\/anhaidgroup\/projects\/data ."},{"key":"e_1_3_2_2_20_1","volume-title":"Ziawasch Abedjan, Sibo Wang, Michael Stonebraker, Ahmed K Elmagarmid, Ihab F Ilyas, Samuel Madden, Mourad Ouzzani, and Nan Tang.","author":"Deng Dong","year":"2017","unstructured":"Dong Deng , Raul Castro Fernandez , Ziawasch Abedjan, Sibo Wang, Michael Stonebraker, Ahmed K Elmagarmid, Ihab F Ilyas, Samuel Madden, Mourad Ouzzani, and Nan Tang. 2017 . The data civilizer system. In CIDR . Dong Deng, Raul Castro Fernandez, Ziawasch Abedjan, Sibo Wang, Michael Stonebraker, Ahmed K Elmagarmid, Ihab F Ilyas, Samuel Madden, Mourad Ouzzani, and Nan Tang. 2017. The data civilizer system. In CIDR ."},{"key":"e_1_3_2_2_21_1","volume-title":"Trifacta wrangler","author":"Enterprise Trifacta Wrangler","year":"2015","unstructured":"Trifacta Wrangler Enterprise . 2016. Trifacta wrangler ( 2015 ). Trifacta Wrangler Enterprise. 2016. Trifacta wrangler (2015)."},{"key":"e_1_3_2_2_22_1","volume-title":"et almbox","author":"Ester Martin","year":"1996","unstructured":"Martin Ester , Hans-Peter Kriegel , J\u00f6rg Sander , Xiaowei Xu , et almbox . 1996 . A density-based algorithm for discovering clusters in large spatial databases with noise. In SIGKDD. 226--231. Martin Ester, Hans-Peter Kriegel, J\u00f6rg Sander, Xiaowei Xu, et almbox. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In SIGKDD. 226--231."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1366102.1366103"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2010.154"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(89)90002-3"},{"key":"e_1_3_2_2_26_1","article-title":"Greedy function approximation: a gradient boosting machine","author":"Friedman Jerome H","year":"2001","unstructured":"Jerome H Friedman . 2001 . Greedy function approximation: a gradient boosting machine . Annals of statistics, 1189--1232. Jerome H Friedman. 2001. Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189--1232.","journal-title":"Annals of statistics, 1189--1232."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915242"},{"key":"e_1_3_2_2_28_1","unstructured":"Jean-Nicholas Hould. 2017. Craft Beers Dataset. https:\/\/www.kaggle.com\/nickhould\/craft-cans . Version 1.  Jean-Nicholas Hould. 2017. Craft Beers Dataset. https:\/\/www.kaggle.com\/nickhould\/craft-cans . Version 1."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Richard M Karp. 1972. Reducibility among combinatorial problems. In Complexity of computer computations . 85--103.  Richard M Karp. 1972. Reducibility among combinatorial problems. In Complexity of computer computations . 85--103.","DOI":"10.1007\/978-1-4684-2001-2_9"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.219"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"e_1_3_2_2_33_1","volume-title":"Rayyan--a web and mobile app for systematic reviews. Systematic reviews","author":"Ouzzani Mourad","unstructured":"Mourad Ouzzani , Hossam Hammady , Zbys Fedorowicz , and Ahmed Elmagarmid . 2016. Rayyan--a web and mobile app for systematic reviews. Systematic reviews , Vol. 5 , 1, 210. Mourad Ouzzani, Hossam Hammady, Zbys Fedorowicz, and Ahmed Elmagarmid. 2016. Rayyan--a web and mobile app for systematic reviews. Systematic reviews, Vol. 5, 1, 210."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915203"},{"key":"e_1_3_2_2_35_1","volume-title":"et almbox","author":"Pedregosa Fabian","year":"2011","unstructured":"Fabian Pedregosa , Ga\u00ebl Varoquaux , Alexandre Gramfort , Vincent Michel , Bertrand Thirion , Olivier Grisel , Mathieu Blondel , Peter Prettenhofer , Ron Weiss , Vincent Dubourg , et almbox . 2011 . Scikit-learn : Machine learning in Python. JMLR , Vol. 12 , Oct, 2825--2830. Fabian Pedregosa, Ga\u00ebl Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et almbox. 2011. Scikit-learn: Machine learning in Python. JMLR, Vol. 12, Oct, 2825--2830."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s007780100057"},{"key":"e_1_3_2_2_38_1","first-page":"3","article-title":"Data cleaning: Problems and current approaches","volume":"23","author":"Rahm Erhard","year":"2000","unstructured":"Erhard Rahm and Hong Hai Do . 2000 . Data cleaning: Problems and current approaches . DE , Vol. 23 , 4, 3 -- 13 . Erhard Rahm and Hong Hai Do. 2000. Data cleaning: Problems and current approaches. DE, Vol. 23, 4, 3--13.","journal-title":"DE"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"e_1_3_2_2_40_1","volume-title":"Encyclopedia of machine learning","author":"Sammut Claude","unstructured":"Claude Sammut and Geoffrey I Webb . 2011. Encyclopedia of machine learning . Springer Science & Business Media . Claude Sammut and Geoffrey I Webb. 2011. Encyclopedia of machine learning .Springer Science & Business Media."},{"key":"e_1_3_2_2_41_1","volume-title":"Introduction to information retrieval","author":"Sch\u00fctze Hinrich","unstructured":"Hinrich Sch\u00fctze , Christopher D Manning , and Prabhakar Raghavan . 2008. Introduction to information retrieval . Cambridge University Press . Hinrich Sch\u00fctze, Christopher D Manning, and Prabhakar Raghavan. 2008. Introduction to information retrieval .Cambridge University Press."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/2977797.2977807"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Chen Sun Abhinav Shrivastava Saurabh Singh and Abhinav Gupta. 2017. Revisiting unreasonable effectiveness of data in deep learning era. In ICCV . 843--852.  Chen Sun Abhinav Shrivastava Saurabh Singh and Abhinav Gupta. 2017. Revisiting unreasonable effectiveness of data in deep learning era. In ICCV . 843--852.","DOI":"10.1109\/ICCV.2017.97"},{"key":"e_1_3_2_2_44_1","volume-title":"A dictionary of statistics 3e","author":"Upton Graham","unstructured":"Graham Upton and Ian Cook . 2014. A dictionary of statistics 3e . Oxford University Press . Graham Upton and Ian Cook. 2014. A dictionary of statistics 3e .Oxford University Press."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3221269.3223028"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.14778\/1952376.1952378"}],"event":{"name":"SIGMOD\/PODS '19: International Conference on Management of Data","location":"Amsterdam Netherlands","acronym":"SIGMOD\/PODS '19","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2019 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3299869.3324956","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3299869.3324956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:43:23Z","timestamp":1750207403000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3299869.3324956"}},"subtitle":["A Configuration-Free Error Detection System"],"short-title":[],"issued":{"date-parts":[[2019,6,25]]},"references-count":45,"alternative-id":["10.1145\/3299869.3324956","10.1145\/3299869"],"URL":"https:\/\/doi.org\/10.1145\/3299869.3324956","relation":{},"subject":[],"published":{"date-parts":[[2019,6,25]]},"assertion":[{"value":"2019-06-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}