{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T23:15:21Z","timestamp":1792278921139,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,6,26]],"date-time":"2016-06-26T00:00:00Z","timestamp":1466899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSERC","award":["19579"],"award-info":[{"award-number":["19579"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,6,26]]},"DOI":"10.1145\/2882903.2912574","type":"proceedings-article","created":{"date-parts":[[2016,6,16]],"date-time":"2016-06-16T19:01:52Z","timestamp":1466103712000},"page":"2201-2206","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":421,"title":["Data Cleaning"],"prefix":"10.1145","author":[{"given":"Xu","family":"Chu","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ihab F.","family":"Ilyas","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjay","family":"Krishnan","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2016,6,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Trifacta. http:\/\/www.trifacta.com.  Trifacta. http:\/\/www.trifacta.com."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2436823"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732967.2732975"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850587"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/1287369.1287420"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2007.27"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2737786"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2011.5767864"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1147376.1147391"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920870"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544854"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687695"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066175"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2007.367920"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816641"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610520"},{"key":"e_1_3_2_1_17_1","volume-title":"PAKDD","author":"Chawla S.","year":"2006","unstructured":"S. Chawla and P. Sun . Outlier detection: Principles, techniques and applications . In PAKDD , 2006 . S. Chawla and P. Sun. Outlier detection: Principles, techniques and applications. In PAKDD, 2006."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623617"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2011.5767833"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536258.2536262"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544847"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749431"},{"key":"e_1_3_2_1_24_1","volume-title":"Estimating the impact of unknown unknowns on aggregate query results. CoRR, abs\/1507.05591","author":"Chung Y.","year":"2015","unstructured":"Y. Chung , M. L. Mortensen , C. Binnig , and T. Kraska . Estimating the impact of unknown unknowns on aggregate query results. CoRR, abs\/1507.05591 , 2015 . Y. Chung, M. L. Mortensen, C. Binnig, and T. Kraska. Estimating the impact of unknown unknowns on aggregate query results. CoRR, abs\/1507.05591, 2015."},{"key":"e_1_3_2_1_25_1","first-page":"315","volume-title":"PVLDB","author":"Cong G.","year":"2007","unstructured":"G. Cong , W. Fan , F. Geerts , X. Jia , and S. Ma . Improving data quality: Consistency and accuracy . In PVLDB , pages 315 -- 326 . VLDB Endowment , 2007 . G. Cong, W. Fan, F. Geerts, X. Jia, and S. Ma. Improving data quality: Consistency and accuracy. In PVLDB, pages 315--326. VLDB Endowment, 2007."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465327"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.100"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1316689.1316741"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2746539.2746580"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920867"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989373"},{"key":"e_1_3_2_1_32_1","unstructured":"Gartner. Forecast: The internet of things worldwide. https:\/\/www.gartner.com\/doc\/2625419\/forecast-internet-things-worldwide-.  Gartner. Forecast: The internet of things worldwide. https:\/\/www.gartner.com\/doc\/2625419\/forecast-internet-things-worldwide-."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536360.2536363"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2463691"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588576"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453900"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824122"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/2856318.2856331"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661885"},{"key":"e_1_3_2_1_40_1","volume-title":"United Nations Economic Commission for Europe (UNECE)","author":"Hellerstein J. M.","year":"2008","unstructured":"J. M. Hellerstein . Quantitative data cleaning for large databases . United Nations Economic Commission for Europe (UNECE) , 2008 . J. M. Hellerstein. Quantitative data cleaning for large databases. United Nations Economic Commission for Europe (UNECE), 2008."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000045"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2006.8"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/1182635.1164143"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872875"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2747646"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1514894.1514901"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367527"},{"key":"e_1_3_2_1_48_1","volume-title":"Tutorial at SIGKDD","author":"Kriegel H.-P.","year":"2010","unstructured":"H.-P. Kriegel , P. Kr\u00f6ger , and A. Zimek . Outlier detection techniques . In Tutorial at SIGKDD , 2010 . H.-P. Kriegel, P. Kr\u00f6ger, and A. Zimek. Outlier detection techniques. In Tutorial at SIGKDD, 2010."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645740"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824037"},{"issue":"3","key":"e_1_3_2_1_51_1","first-page":"59","article-title":"Fast and reliable analytics on dirty data","volume":"38","author":"Krishnan S.","year":"2015","unstructured":"S. Krishnan , J. Wang , M. J. Franklin , K. Goldberg , T. Kraska , T. Milo , and E. Wu. Sampleclean : Fast and reliable analytics on dirty data . IEEE Data Eng. Bull. , 38 ( 3 ): 59 -- 75 , 2015 . S. Krishnan, J. Wang, M. J. Franklin, K. Goldberg, T. Kraska, T. Milo, and E. Wu. Sampleclean: Fast and reliable analytics on dirty data. IEEE Data Eng. Bull., 38(3):59--75, 2015.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_52_1","volume-title":"Arxiv: http:\/\/arxiv.org\/pdf\/1601.03797.pdf","author":"Krishnan S.","year":"2015","unstructured":"S. Krishnan , J. Wang , E. Wu , M. J. Franklin , and K. Goldberg . Activeclean: Interactive data cleaning while learning convex loss models . In Arxiv: http:\/\/arxiv.org\/pdf\/1601.03797.pdf , 2015 . S. Krishnan, J. Wang, E. Wu, M. J. Franklin, and K. Goldberg. Activeclean: Interactive data cleaning while learning convex loss models. In Arxiv: http:\/\/arxiv.org\/pdf\/1601.03797.pdf, 2015."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-05813-9_29"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2063691"},{"key":"e_1_3_2_1_55_1","volume-title":"CASE","author":"Mahler J.","year":"2014","unstructured":"J. Mahler , S. Krishnan , M. Laskey , S. Sen , A. Murali , B. Kehoe , S. Patil , J. Wang , M. Franklin , P. Abbeel , and K. Y. Goldberg . Learning accurate kinematic control of cable-driven surgical robots using data cleaning and gaussian process regression . In CASE , 2014 . J. Mahler, S. Krishnan, M. Laskey, S. Sen, A. Murali, B. Kehoe, S. Patil, J. Wang, M. Franklin, P. Abbeel, and K. Y. Goldberg. Learning accurate kinematic control of cable-driven surgical robots using data cleaning and gaussian process regression. In CASE, 2014."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000044"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807178"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989376"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735471.2735474"},{"key":"e_1_3_2_1_60_1","unstructured":"A. Parameswaran H. Garcia-Molina H. Park N. Polyzotis A. Ramesh and J. Widom. Crowdscreen: Algorithms for filtering data with humans.  A. Parameswaran H. Garcia-Molina H. Park N. Polyzotis A. Ramesh and J. Widom. Crowdscreen: Algorithms for filtering data with humans."},{"key":"e_1_3_2_1_61_1","volume-title":"Answering queries using humans, algorithms and databases","author":"Parameswaran A.","year":"2011","unstructured":"A. Parameswaran and N. Polyzotis . Answering queries using humans, algorithms and databases . 2011 . A. Parameswaran and N. Polyzotis. Answering queries using humans, algorithms and databases. 2011."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610503"},{"key":"e_1_3_2_1_63_1","volume-title":"Data cleaning: Problems and current approaches","author":"Rahm E.","year":"2000","unstructured":"E. Rahm and H. H. Do . Data cleaning: Problems and current approaches . IEEE Data Eng. Bull ., 23(4), 2000 . E. Rahm and H. H. Do. Data cleaning: Problems and current approaches. IEEE Data Eng. Bull., 23(4), 2000."},{"key":"e_1_3_2_1_64_1","first-page":"381","volume-title":"VLDB","author":"Raman V.","year":"2001","unstructured":"V. Raman and J. M. Hellerstein . Potter's wheel: An interactive data cleaning system . In VLDB , pages 381 -- 390 , 2001 . V. Raman and J. M. Hellerstein. Potter's wheel: An interactive data cleaning system. In VLDB, pages 381--390, 2001."},{"key":"e_1_3_2_1_65_1","volume-title":"Robust regression and outlier detection","author":"Rousseeuw P. J.","year":"2005","unstructured":"P. J. Rousseeuw and A. M. Leroy . Robust regression and outlier detection , volume 589 . John Wiley & Sons , 2005 . P. J. Rousseeuw and A. M. Leroy. Robust regression and outlier detection, volume 589. John Wiley & Sons, 2005."},{"key":"e_1_3_2_1_66_1","volume-title":"Controlling bias in adaptive data analysis using information theory. CoRR, abs\/1511.05219","author":"Russo D.","year":"2015","unstructured":"D. Russo and J. Zou . Controlling bias in adaptive data analysis using information theory. CoRR, abs\/1511.05219 , 2015 . D. Russo and J. Zou. Controlling bias in adaptive data analysis using information theory. CoRR, abs\/1511.05219, 2015."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536258.2536259"},{"key":"e_1_3_2_1_68_1","series-title":"Series B (Methodological)","volume-title":"The interpretation of interaction in contingency tables. Journal of the Royal Statistical Society","author":"Simpson E. H.","year":"1951","unstructured":"E. H. Simpson . The interpretation of interaction in contingency tables. Journal of the Royal Statistical Society . Series B (Methodological) , 1951 . E. H. Simpson. The interpretation of interaction in contingency tables. Journal of the Royal Statistical Society. Series B (Methodological), 1951."},{"key":"e_1_3_2_1_69_1","volume-title":"CIDR","author":"Stonebraker M.","year":"2013","unstructured":"M. Stonebraker , D. Bruckner , I. F. Ilyas , G. Beskales , M. Cherniack , S. B. Zdonik , A. Pagan , and S. Xu . Data curation at scale: The data tamer system . In CIDR , 2013 . M. Stonebraker, D. Bruckner, I. F. Ilyas, G. Beskales, M. Cherniack, S. B. Zdonik, A. Pagan, and S. Xu. Data curation at scale: The data tamer system. In CIDR, 2013."},{"key":"e_1_3_2_1_70_1","first-page":"187","volume-title":"PVLDB","author":"Subramaniam S.","year":"2006","unstructured":"S. Subramaniam , T. Palpanas , D. Papadopoulos , V. Kalogeraki , and D. Gunopulos . Online outlier detection in sensor data using non-parametric models . In PVLDB , pages 187 -- 198 , 2006 . S. Subramaniam, T. Palpanas, D. Papadopoulos, V. Kalogeraki, and D. Gunopulos. Online outlier detection in sensor data using non-parametric models. In PVLDB, pages 187--198, 2006."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816736"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566721"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816655"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350263"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610505"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465280"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610494"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536336.2536337"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536354.2536356"},{"key":"e_1_3_2_1_80_1","volume-title":"ICML","author":"Xiao H.","year":"2015","unstructured":"H. Xiao , B. Biggio , G. Brown , G. Fumera , C. Eckert , and F. Roli . Is feature selection secure against training data poisoning ? In ICML , 2015 . H. Xiao, B. Biggio, G. Brown, G. Fumera, C. Eckert, and F. Roli. Is feature selection secure against training data poisoning? In ICML, 2015."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2463706"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.14778\/1952376.1952378"}],"event":{"name":"SIGMOD\/PODS'16: International Conference on Management of Data","location":"San Francisco California USA","acronym":"SIGMOD\/PODS'16","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2016 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2882903.2912574","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2882903.2912574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:55:53Z","timestamp":1750222553000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2882903.2912574"}},"subtitle":["Overview and Emerging Challenges"],"short-title":[],"issued":{"date-parts":[[2016,6,26]]},"references-count":81,"alternative-id":["10.1145\/2882903.2912574","10.1145\/2882903"],"URL":"https:\/\/doi.org\/10.1145\/2882903.2912574","relation":{},"subject":[],"published":{"date-parts":[[2016,6,26]]},"assertion":[{"value":"2016-06-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}