{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T14:30:32Z","timestamp":1768401032318,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,7,9]],"date-time":"2018-07-09T00:00:00Z","timestamp":1531094400000},"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":[[2018,7,9]]},"DOI":"10.1145\/3221269.3223028","type":"proceedings-article","created":{"date-parts":[[2018,7,10]],"date-time":"2018-07-10T16:26:42Z","timestamp":1531240002000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Metadata-driven error detection"],"prefix":"10.1145","author":[{"given":"Larysa","family":"Visengeriyeva","sequence":"first","affiliation":[{"name":"TU Berlin"}]},{"given":"Ziawasch","family":"Abedjan","sequence":"additional","affiliation":[{"name":"TU Berlin"}]}],"member":"320","published-online":{"date-parts":[[2018,7,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/2856318.2856328"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994518"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0389-y"},{"key":"e_1_3_2_1_4_1","volume-title":"Outlier analysis","author":"Aggarwal Charu C","unstructured":"Charu C Aggarwal . 2015. Outlier analysis . Springer . Charu C Aggarwal. 2015. Outlier analysis. Springer."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850578.2850579"},{"key":"e_1_3_2_1_6_1","unstructured":"Christopher M Bishop. 2006. Pattern recognition. Machine Learning.  Christopher M Bishop. 2006. Pattern recognition. Machine Learning."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066175"},{"key":"e_1_3_2_1_8_1","volume-title":"Empirical model-building and response surfaces","author":"Box George EP","unstructured":"George EP Box and Norman R Draper . 1987. Empirical model-building and response surfaces . John Wiley & Sons . George EP Box and Norman R Draper. 1987. Empirical model-building and response surfaces. John Wiley & Sons."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018054314350"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143865"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544847"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3115404.3115414"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465327"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the Conference on Innovative Data Systems Research (CIDR).","author":"Deng Dong","year":"2017","unstructured":"Dong Deng , Raul Castro Fernandez , Ziawasch Abedjan , Sibo Wang , Michael Stonebraker , Ahmed Elmagarmid , Ihab F Ilyasl , Samuel Madden , Mourad Ouzzani , and Nan Tang . 2017 . The Data Civilizer System . In Proceedings of the Conference on Innovative Data Systems Research (CIDR). Dong Deng, Raul Castro Fernandez, Ziawasch Abedjan, Sibo Wang, Michael Stonebraker, Ahmed Elmagarmid, Ihab F Ilyasl, Samuel Madden, Mourad Ouzzani, and Nan Tang. 2017. The Data Civilizer System. In Proceedings of the Conference on Innovative Data Systems Research (CIDR)."},{"key":"e_1_3_2_1_15_1","unstructured":"Wenfei Fan and Floris Geerts. 2012. Foundations of Data Quality Management.   Wenfei Fan and Floris Geerts. 2012. Foundations of Data Quality Management."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536360.2536363"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903730"},{"key":"e_1_3_2_1_18_1","unstructured":"John A Hartigan and JA Hartigan. 1975. Clustering algorithms.   John A Hartigan and JA Hartigan. 1975. Clustering algorithms."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2747646"},{"key":"e_1_3_2_1_21_1","volume-title":"SampleClean: Fast and Reliable Analytics on Dirty Data","author":"Krishnan Sanjay","unstructured":"Sanjay Krishnan , Jiannan Wang , Michael J Franklin , Ken Goldberg , Tim Kraska , Tova Milo , and Eugene Wu. 2015. SampleClean: Fast and Reliable Analytics on Dirty Data . IEEE Data Engineering Bulletin . Sanjay Krishnan, Jiannan Wang, Michael J Franklin, Ken Goldberg, Tim Kraska, Tova Milo, and Eugene Wu. 2015. SampleClean: Fast and Reliable Analytics on Dirty Data. IEEE Data Engineering Bulletin."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.14778\/2535568.2448943"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897350.2897352"},{"key":"e_1_3_2_1_24_1","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy Kevin P.","year":"2012","unstructured":"Kevin P. Murphy . 2012 . Machine Learning: A Probabilistic Perspective . The MIT Press . Kevin P. Murphy. 2012. Machine Learning: A Probabilistic Perspective. The MIT Press."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915203"},{"key":"e_1_3_2_1_26_1","volume-title":"Outlier Detection in Heterogeneous Datasets using Automatic Tuple Expansion","author":"Claudel Clement Pit","unstructured":"Clement Pit Claudel , Zelda Mariet , Rachael Harding , and Sam Madden . 2016. Outlier Detection in Heterogeneous Datasets using Automatic Tuple Expansion . Technical Report, MIT. Clement Pit Claudel, Zelda Mariet, Rachael Harding, and Sam Madden. 2016. Outlier Detection in Heterogeneous Datasets using Automatic Tuple Expansion. Technical Report, MIT."},{"key":"e_1_3_2_1_27_1","volume-title":"Data cleaning: Problems and current approaches","author":"Rahm Erhard","unstructured":"Erhard Rahm and Hong Hai Do. 2000. Data cleaning: Problems and current approaches . IEEE Data Engineering Bulletin . Erhard Rahm and Hong Hai Do. 2000. Data cleaning: Problems and current approaches. IEEE Data Engineering Bulletin."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the Conference on Innovative Data Systems Research (CIDR).","author":"Stonebraker Michael","year":"2013","unstructured":"Michael Stonebraker , Daniel Bruckner , Ihab F Ilyas , George Beskales , Mitch Cherniack , Stanley B Zdonik , Alexander Pagan , and Shan Xu . 2013 . Data Curation at Scale: The Data Tamer System .. In Proceedings of the Conference on Innovative Data Systems Research (CIDR). Michael Stonebraker, Daniel Bruckner, Ihab F Ilyas, George Beskales, Mitch Cherniack, Stanley B Zdonik, Alexander Pagan, and Shan Xu. 2013. Data Curation at Scale: The Data Tamer System.. In Proceedings of the Conference on Innovative Data Systems Research (CIDR)."},{"key":"e_1_3_2_1_30_1","volume-title":"Principles of Data Wrangling: Practical Techniques for Data Preparation. OReilly Media","author":"Tye Rattenbury","unstructured":"Rattenbury Tye , Hellerstein Joseph M., Heer Jeffrey , Kandel Sean , and Carreras Connor . 2017. Principles of Data Wrangling: Practical Techniques for Data Preparation. OReilly Media , Inc . Rattenbury Tye, Hellerstein Joseph M., Heer Jeffrey, Kandel Sean, and Carreras Connor. 2017. Principles of Data Wrangling: Practical Techniques for Data Preparation. OReilly Media, Inc."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"David H Wolpert. 1992. Stacked generalization. Neural networks.  David H Wolpert. 1992. Stacked generalization. Neural networks.","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2463706"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Zhi-Hua Zhou. 2012. Ensemble methods: foundations and algorithms.   Zhi-Hua Zhou. 2012. Ensemble methods: foundations and algorithms.","DOI":"10.1201\/b12207"}],"event":{"name":"SSDBM '18: 30th International Conference on Scientific and Statistical Database Management","location":"Bozen-Bolzano Italy","acronym":"SSDBM '18"},"container-title":["Proceedings of the 30th International Conference on Scientific and Statistical Database Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3221269.3223028","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3221269.3223028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:43:29Z","timestamp":1750286609000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3221269.3223028"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,9]]},"references-count":33,"alternative-id":["10.1145\/3221269.3223028","10.1145\/3221269"],"URL":"https:\/\/doi.org\/10.1145\/3221269.3223028","relation":{},"subject":[],"published":{"date-parts":[[2018,7,9]]},"assertion":[{"value":"2018-07-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}