{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T14:48:54Z","timestamp":1758120534751,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,5,31]],"date-time":"2020-05-31T00:00:00Z","timestamp":1590883200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100007515","name":"National Science Foundation","doi-asserted-by":"publisher","award":["AITF 1535565"],"award-info":[{"award-number":["AITF 1535565"]}],"id":[{"id":"10.13039\/100007515","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,11]]},"DOI":"10.1145\/3318464.3380606","type":"proceedings-article","created":{"date-parts":[[2020,5,29]],"date-time":"2020-05-29T17:12:33Z","timestamp":1590772353000},"page":"257-268","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Sample Debiasing in the Themis Open World Database System"],"prefix":"10.1145","author":[{"given":"Laurel","family":"Orr","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Magdalena","family":"Balazinska","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Suciu","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,5,31]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"https:\/\/www.congress.gov\/115\/bills\/s760\/BILLS-115s760is.pdf.  https:\/\/www.congress.gov\/115\/bills\/s760\/BILLS-115s760is.pdf."},{"key":"e_1_3_2_2_2_1","unstructured":"http:\/\/infusecp.mimas.ac.uk.  http:\/\/infusecp.mimas.ac.uk."},{"key":"e_1_3_2_2_3_1","unstructured":"https:\/\/pdf.ic3.gov\/2017_IC3Report.pdf.  https:\/\/pdf.ic3.gov\/2017_IC3Report.pdf."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"https:\/\/dawn.cs.stanford.edu\/2018\/04\/11\/db-community\/.  https:\/\/dawn.cs.stanford.edu\/2018\/04\/11\/db-community\/.","DOI":"10.1055\/s-0043-123542"},{"key":"e_1_3_2_2_5_1","unstructured":"https:\/\/gitlab.cs.washington.edu\/uwdb\/project_themis_debias.  https:\/\/gitlab.cs.washington.edu\/uwdb\/project_themis_debias."},{"key":"e_1_3_2_2_6_1","unstructured":"https:\/\/www.transtats.bts.gov\/.  https:\/\/www.transtats.bts.gov\/."},{"key":"e_1_3_2_2_7_1","unstructured":"https:\/\/cran.r-project.org\/web\/packages\/nycflights13\/index.html.  https:\/\/cran.r-project.org\/web\/packages\/nycflights13\/index.html."},{"key":"e_1_3_2_2_8_1","unstructured":"https:\/\/data.bloomington.in.gov\/dataset\/traffic-data.  https:\/\/data.bloomington.in.gov\/dataset\/traffic-data."},{"key":"e_1_3_2_2_9_1","unstructured":"https:\/\/data.baltimorecity.gov\/Neighborhoods\/Education-and-Youth-2010--2013-Shape\/ifsa-6r6x\/about.  https:\/\/data.baltimorecity.gov\/Neighborhoods\/Education-and-Youth-2010--2013-Shape\/ifsa-6r6x\/about."},{"key":"e_1_3_2_2_10_1","volume-title":"An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivariate behavioral research, 46(3):399--424","author":"Austin P. C.","year":"2011","unstructured":"P. C. Austin . An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivariate behavioral research, 46(3):399--424 , 2011 . P. C. Austin. An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivariate behavioral research, 46(3):399--424, 2011."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asn028"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/0965-8564(96)00004-3"},{"key":"e_1_3_2_2_13_1","first-page":"93","volume-title":"Artificial Intelligence and Statistics","author":"Bhowmik A.","year":"2015","unstructured":"A. Bhowmik , J. Ghosh , and O. Koyejo . Generalized linear models for aggregated data . In Artificial Intelligence and Statistics , pages 93 -- 101 , 2015 . A. Bhowmik, J. Ghosh, and O. Koyejo. Generalized linear models for aggregated data. In Artificial Intelligence and Statistics, pages 93--101, 2015."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2780413.2780425"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247530"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3056097"},{"key":"e_1_3_2_2_17_1","first-page":"3","volume-title":"Data Engineering, 2006. ICDE'06. Proceedings of the 22nd International Conference on","author":"Chen B.-C.","year":"2006","unstructured":"B.-C. Chen , L. Chen , R. Ramakrishnan , and D. R. Musicant . Learning from aggregate views . In Data Engineering, 2006. ICDE'06. Proceedings of the 22nd International Conference on , pages 3 -- 3 . IEEE, 2006 . B.-C. Chen, L. Chen, R. Ramakrishnan, and D. R. Musicant. Learning from aggregate views. In Data Engineering, 2006. ICDE'06. Proceedings of the 22nd International Conference on, pages 3--3. IEEE, 2006."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1968.1054142"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87987-9_8"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_13"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177731829"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142483"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915249"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3294052.3322188"},{"key":"e_1_3_2_2_25_1","volume-title":"Idebench: A benchmark for interactive data exploration. arXiv preprint arXiv:1804.02593","author":"Eichmann P.","year":"2018","unstructured":"P. Eichmann , C. Binnig , T. Kraska , and E. Zgraggen . Idebench: A benchmark for interactive data exploration. arXiv preprint arXiv:1804.02593 , 2018 . P. Eichmann, C. Binnig, T. Kraska, and E. Zgraggen. Idebench: A benchmark for interactive data exploration. arXiv preprint arXiv:1804.02593, 2018."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2013.09.012"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"e_1_3_2_2_28_1","first-page":"179","volume-title":"ICML","volume":"98","author":"Friedman N.","year":"1998","unstructured":"N. Friedman , M. Goldszmidt , and T. J. Lee . Bayesian network classification with continuous attributes: Getting the best of both discretization and parametric fitting . In ICML , volume 98 , pages 179 -- 187 , 1998 . N. Friedman, M. Goldszmidt, and T. J. Lee. Bayesian network classification with continuous attributes: Getting the best of both discretization and parametric fitting. In ICML, volume 98, pages 179--187, 1998."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/2073796.2073820"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3115404.3115418"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375727"},{"key":"e_1_3_2_2_32_1","first-page":"2672","volume-title":"Advances in neural information processing systems","author":"Goodfellow I.","year":"2014","unstructured":"I. Goodfellow , J. Pouget-Abadie , M. Mirza , B. Xu , D. Warde-Farley , S. Ozair , A. Courville , and Y. Bengio . Generative adversarial nets . In Advances in neural information processing systems , pages 2672 -- 2680 , 2014 . I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Advances in neural information processing systems, pages 2672--2680, 2014."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s007780100054"},{"key":"e_1_3_2_2_34_1","article-title":"Learning from imbalanced data","author":"He H.","year":"2008","unstructured":"H. He and E. A. Garcia . Learning from imbalanced data . IEEE Transactions on Knowledge & Data Engineering, (9):1263--1284 , 2008 . H. He and E. A. Garcia. Learning from imbalanced data. IEEE Transactions on Knowledge & Data Engineering, (9):1263--1284, 2008.","journal-title":"IEEE Transactions on Knowledge & Data Engineering, (9):1263--1284"},{"key":"e_1_3_2_2_35_1","first-page":"149","volume-title":"Machine Intelligence and Pattern Recognition","author":"Henrion M.","year":"1988","unstructured":"M. Henrion . Propagating uncertainty in bayesian networks by probabilistic logic sampling . In Machine Intelligence and Pattern Recognition , volume 5 , pages 149 -- 163 . Elsevier , 1988 . M. Henrion. Propagating uncertainty in bayesian networks by probabilistic logic sampling. In Machine Intelligence and Pattern Recognition, volume 5, pages 149--163. Elsevier, 1988."},{"key":"e_1_3_2_2_36_1","first-page":"601","volume-title":"Advances in neural information processing systems","author":"Huang J.","year":"2007","unstructured":"J. Huang , A. Gretton , K. Borgwardt , B. Sch\u00f6lkopf , and A. J. Smola . Correcting sample selection bias by unlabeled data . In Advances in neural information processing systems , pages 601 -- 608 , 2007 . J. Huang, A. Gretton, K. Borgwardt, B. Sch\u00f6lkopf, and A. J. Smola. Correcting sample selection bias by unlabeled data. In Advances in neural information processing systems, pages 601--608, 2007."},{"key":"e_1_3_2_2_37_1","volume-title":"A review of matrix scaling and sinkhorn's normal form for matrices and positive maps. arXiv preprint arXiv:1609.06349","author":"Idel M.","year":"2016","unstructured":"M. Idel . A review of matrix scaling and sinkhorn's normal form for matrices and positive maps. arXiv preprint arXiv:1609.06349 , 2016 . M. Idel. A review of matrix scaling and sinkhorn's normal form for matrices and positive maps. arXiv preprint arXiv:1609.06349, 2016."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000045"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/1939047.1939070"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1201\/b10391"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.3141\/2255-03"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/543613.543644"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-018-0074-4"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.18564\/jasss.2768"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10480682"},{"key":"e_1_3_2_2_47_1","volume-title":"Carnegie-Mellon Univ Pittsburgh Pa School of Computer Science","author":"Margaritis D.","year":"2003","unstructured":"D. Margaritis . Learning bayesian network model structure from data. Technical report , Carnegie-Mellon Univ Pittsburgh Pa School of Computer Science , 2003 . D. Margaritis. Learning bayesian network model structure from data. Technical report, Carnegie-Mellon Univ Pittsburgh Pa School of Computer Science, 2003."},{"key":"e_1_3_2_2_48_1","first-page":"311","volume-title":"VLDB","author":"Margaritis D.","year":"2001","unstructured":"D. Margaritis , C. Faloutsos , and S. Thrun . Netcube: A scalable tool for fast data mining and compression . In VLDB , pages 311 -- 320 , 2001 . D. Margaritis, C. Faloutsos, and S. Thrun. Netcube: A scalable tool for fast data mining and compression. In VLDB, pages 311--320, 2001."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.5753"},{"issue":"3","key":"e_1_3_2_2_50_1","first-page":"3","article-title":"A handbook for building an approximate query engine","volume":"38","author":"Mozafari B.","year":"2015","unstructured":"B. Mozafari and N. Niu . A handbook for building an approximate query engine . IEEE Data Eng. Bull. , 38 ( 3 ): 3 -- 29 , 2015 . B. Mozafari and N. Niu. A handbook for building an approximate query engine. IEEE Data Eng. Bull., 38(3):3--29, 2015.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.14778\/3213880.3213882"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2007.50"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.14778\/3115404.3115419"},{"key":"e_1_3_2_2_56_1","volume-title":"Sample debiasing in the themis open world database system (extended version). arXiv preprint arXiv:2002.09799","author":"Orr L.","year":"2020","unstructured":"L. Orr , M. Balazinska , and D. Suciu . Sample debiasing in the themis open world database system (extended version). arXiv preprint arXiv:2002.09799 , 2020 . L. Orr, M. Balazinska, and D. Suciu. Sample debiasing in the themis open world database system (extended version). arXiv preprint arXiv:2002.09799, 2020."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064013"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183747"},{"key":"e_1_3_2_2_59_1","volume-title":"Reducing bias in observational studies using subclassification on the propensity score. Journal of the American statistical Association, 79(387):516--524","author":"Rosenbaum P. R.","year":"1984","unstructured":"P. R. Rosenbaum and D. B. Rubin . Reducing bias in observational studies using subclassification on the propensity score. Journal of the American statistical Association, 79(387):516--524 , 1984 . P. R. Rosenbaum and D. B. Rubin. Reducing bias in observational studies using subclassification on the propensity score. Journal of the American statistical Association, 79(387):516--524, 1984."},{"key":"e_1_3_2_2_60_1","volume-title":"Wiley Encyclopedia of Computer Science and Engineering","author":"Solow D.","year":"2007","unstructured":"D. Solow . Linear and nonlinear programming. Wiley Encyclopedia of Computer Science and Engineering , 2007 . D. Solow. Linear and nonlinear programming. Wiley Encyclopedia of Computer Science and Engineering, 2007."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2015.10.010"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-013-9232-8"},{"key":"e_1_3_2_2_63_1","first-page":"101","volume-title":"EDBT","author":"Vartak M.","year":"2016","unstructured":"M. Vartak , V. Raghavan , E. A. Rundensteiner , and S. Madden . Refinement driven processing of aggregation constrained queries . In EDBT , pages 101 -- 112 , 2016 . M. Vartak, V. Raghavan, E. A. Rundensteiner, and S. Madden. Refinement driven processing of aggregation constrained queries. In EDBT, pages 101--112, 2016."},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610505"},{"key":"e_1_3_2_2_65_1","first-page":"114","volume-title":"Proceedings of the twenty-first international conference on Machine learning","author":"Zadrozny B.","unstructured":"B. Zadrozny . Learning and evaluating classifiers under sample selection bias . In Proceedings of the twenty-first international conference on Machine learning , page 114 . ACM, 2004. B. Zadrozny. Learning and evaluating classifiers under sample selection bias. In Proceedings of the twenty-first international conference on Machine learning, page 114. ACM, 2004."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2576930"},{"key":"e_1_3_2_2_67_1","first-page":"325","volume-title":"International Conference on Machine Learning","author":"Zemel R.","year":"2013","unstructured":"R. Zemel , Y. Wu , K. Swersky , T. Pitassi , and C. Dwork . Learning fair representations . In International Conference on Machine Learning , pages 325 -- 333 , 2013 . R. Zemel, Y. Wu, K. Swersky, T. Pitassi, and C. Dwork. Learning fair representations. In International Conference on Machine Learning, pages 325--333, 2013."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588579"}],"event":{"name":"SIGMOD\/PODS '20: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"Portland OR USA","acronym":"SIGMOD\/PODS '20"},"container-title":["Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3318464.3380606","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3318464.3380606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:23Z","timestamp":1750199903000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3318464.3380606"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,31]]},"references-count":66,"alternative-id":["10.1145\/3318464.3380606","10.1145\/3318464"],"URL":"https:\/\/doi.org\/10.1145\/3318464.3380606","relation":{},"subject":[],"published":{"date-parts":[[2020,5,31]]},"assertion":[{"value":"2020-05-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}