{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:32:48Z","timestamp":1775838768508,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,26]],"date-time":"2017-06-26T00:00:00Z","timestamp":1498435200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1139158"],"award-info":[{"award-number":["CCF-1139158"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["SN10040 DE-SC0012463"],"award-info":[{"award-number":["SN10040 DE-SC0012463"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-12-2-0331"],"award-info":[{"award-number":["FA8750-12-2-0331"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,6,26]]},"DOI":"10.1145\/2882903.2899409","type":"proceedings-article","created":{"date-parts":[[2016,6,16]],"date-time":"2016-06-16T15:01:52Z","timestamp":1466089312000},"page":"2117-2120","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":59,"title":["ActiveClean"],"prefix":"10.1145","author":[{"given":"Sanjay","family":"Krishnan","sequence":"first","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael J.","family":"Franklin","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Vancouver, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugene","family":"Wu","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,6,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"U. Berkeley. Berkeley data analytics stack. https:\/\/amplab.cs.berkeley.edu\/software\/."},{"key":"e_1_3_2_1_2_1","volume-title":"Tupleware: Distributed machine learning on small clusters","author":"Crotty A.","year":"2014","unstructured":"A. Crotty, A. Galakatos, and T. Kraska. Tupleware: Distributed machine learning on small clusters. In IEEE Data Eng. Bull., 2014."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588576"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824122"},{"key":"e_1_3_2_1_5_1","unstructured":"G. Inc. Tensorflow. https:\/\/www.tensorflow.org\/."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824037"},{"issue":"3","key":"e_1_3_2_1_7_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.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_8_1","unstructured":"S. Krishnan J. Wang E. Wu M. J. Franklin and K. Goldberg. Activeclean: Interactive data cleaning while learning convex loss models. http:\/\/arxiv.org\/abs\/1601.03797v1."},{"key":"e_1_3_2_1_9_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."},{"key":"e_1_3_2_1_10_1","unstructured":"P. Spark. Pyspark. https:\/\/spark.apache.org\/docs\/0.9.0\/python-programming-guide.html."},{"key":"e_1_3_2_1_11_1","volume-title":"JMLR","author":"der Maaten L. Van","year":"2008","unstructured":"L. Van der Maaten and G. Hinton. Visualizing data using t-sne. In JMLR, 2008."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610505"},{"key":"e_1_3_2_1_13_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."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2463706"},{"key":"e_1_3_2_1_15_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\/2882903.2899409","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2882903.2899409","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2882903.2899409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:18:24Z","timestamp":1763457504000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2882903.2899409"}},"subtitle":["An Interactive Data Cleaning Framework For Modern Machine Learning"],"short-title":[],"issued":{"date-parts":[[2016,6,26]]},"references-count":15,"alternative-id":["10.1145\/2882903.2899409","10.1145\/2882903"],"URL":"https:\/\/doi.org\/10.1145\/2882903.2899409","relation":{},"subject":[],"published":{"date-parts":[[2016,6,26]]},"assertion":[{"value":"2016-06-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}