{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T19:10:06Z","timestamp":1755976206013,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1845638, 1740305, 2008295, 2106197, 2103794"],"award-info":[{"award-number":["1845638, 1740305, 2008295, 2106197, 2103794"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,9]]},"DOI":"10.1145\/3665601.3669847","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T12:20:36Z","timestamp":1717762836000},"page":"26-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SET: Searching Effective Supervised Learning Augmentations in Large Tabular Data Repositories"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5604-2027","authenticated-orcid":false,"given":"Jiaxiang","family":"Liu","sequence":"first","affiliation":[{"name":"Columbia University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6613-0337","authenticated-orcid":false,"given":"Zezhou","family":"Huang","sequence":"additional","affiliation":[{"name":"Columbia University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4254-6688","authenticated-orcid":false,"given":"Eugene","family":"Wu","sequence":"additional","affiliation":[{"name":"Columbia University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,9]]},"reference":[{"volume-title":"d.]. 2012 New York City school level College Board SAT results for the graduating seniors of","year":"2010","key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. 2012 New York City school level College Board SAT results for the graduating seniors of 2010. https:\/\/data.cityofnewyork.us\/Education\/SAT-scores\/vtmi-3hwp."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. 2013 -2018 School Math Results. https:\/\/data.cityofnewyork.us\/Education\/2013-2018-School-Math-Results\/m27t-ht3h."},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. 2013-2019 Attendance Results - School. https:\/\/data.cityofnewyork.us\/Education\/2013-2019-Attendance-Results-School\/vww9-qguh\/."},{"key":"e_1_3_2_1_4_1","unstructured":"2022. NYC Open Data. https:\/\/opendata.cityofnewyork.us\/."},{"key":"e_1_3_2_1_5_1","unstructured":"2023. Google Dataset Search. https:\/\/datasetsearch.research.google.com\/."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2902251.2902280"},{"key":"e_1_3_2_1_7_1","volume-title":"ARDA: automatic relational data augmentation for machine learning. arXiv preprint arXiv:2003.09758","author":"Chepurko Nadiia","year":"2020","unstructured":"Nadiia Chepurko, Ryan Marcus, Emanuel Zgraggen, Raul\u00a0Castro Fernandez, Tim Kraska, and David Karger. 2020. ARDA: automatic relational data augmentation for machine learning. arXiv preprint arXiv:2003.09758 (2020)."},{"key":"e_1_3_2_1_8_1","unstructured":"Data.gov. 2024. Data.gov: The Home of the U.S. Government\u2019s Open Data. https:\/\/www.data.gov\/"},{"key":"e_1_3_2_1_9_1","volume-title":"2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE, 1001\u20131012","author":"Fernandez Raul\u00a0Castro","year":"2018","unstructured":"Raul\u00a0Castro Fernandez, Ziawasch Abedjan, Famien Koko, Gina Yuan, Samuel Madden, and Michael Stonebraker. 2018. Aurum: A data discovery system. In 2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE, 1001\u20131012."},{"key":"e_1_3_2_1_10_1","volume-title":"METAM: Goal-Oriented Data Discovery. arXiv preprint arXiv:2304.09068","author":"Galhotra Sainyam","year":"2023","unstructured":"Sainyam Galhotra, Yue Gong, and Raul\u00a0Castro Fernandez. 2023. METAM: Goal-Oriented Data Discovery. arXiv preprint arXiv:2304.09068 (2023)."},{"volume-title":"The elements of statistical learning: data mining, inference, and prediction. Vol.\u00a02","author":"Hastie Trevor","key":"e_1_3_2_1_11_1","unstructured":"Trevor Hastie, Robert Tibshirani, Jerome\u00a0H Friedman, and Jerome\u00a0H Friedman. 2009. The elements of statistical learning: data mining, inference, and prediction. Vol.\u00a02. Springer."},{"key":"e_1_3_2_1_12_1","volume-title":"Saibot: A Differentially Private Data Search Platform. arXiv preprint arXiv:2307.00432","author":"Huang Zezhou","year":"2023","unstructured":"Zezhou Huang, Jiaxiang Liu, Daniel Alabi, Raul\u00a0Castro Fernandez, and Eugene Wu. 2023. Saibot: A Differentially Private Data Search Platform. arXiv preprint arXiv:2307.00432 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"The Fast and the Private: Task-based Dataset Search. arXiv preprint arXiv:2308.05637","author":"Huang Zezhou","year":"2023","unstructured":"Zezhou Huang, Jiaxiang Liu, Haonan Wang, and Eugene Wu. 2023. The Fast and the Private: Task-based Dataset Search. arXiv preprint arXiv:2308.05637 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/3467861.3467872"},{"volume-title":"Procedia Computer Science","author":"Miloslavskaya Natalia","key":"e_1_3_2_1_15_1","unstructured":"Natalia Miloslavskaya and Alexander Tolstoy. 2016. Big Data, Fast Data and Data Lake Concepts. In Procedia Computer Science. Elsevier."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00264"},{"key":"e_1_3_2_1_17_1","first-page":"434","article-title":"FLAML: a fast and lightweight AutoML Library","volume":"3","author":"Wang Chi","year":"2021","unstructured":"Chi Wang, Qingyun Wu, Markus Weimer, and Erkang Zhu. 2021. FLAML: a fast and lightweight AutoML Library. Proceedings of Machine Learning and Systems 3 (2021), 434\u2013447.","journal-title":"Proceedings of Machine Learning and Systems"}],"event":{"name":"SIGMOD\/PODS '24: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"Santiago AA Chile","acronym":"SIGMOD\/PODS '24"},"container-title":["Proceedings of the Conference on Governance, Understanding and Integration of Data for Effective and Responsible AI"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665601.3669847","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665601.3669847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:35:42Z","timestamp":1755974142000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665601.3669847"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,9]]},"references-count":17,"alternative-id":["10.1145\/3665601.3669847","10.1145\/3665601"],"URL":"https:\/\/doi.org\/10.1145\/3665601.3669847","relation":{},"subject":[],"published":{"date-parts":[[2024,6,9]]},"assertion":[{"value":"2024-06-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}