{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T06:45:07Z","timestamp":1768286707598,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CCF-2047061"],"award-info":[{"award-number":["CCF-2047061"]}]},{"name":"Google Research","award":["Research Scholar Program"],"award-info":[{"award-number":["Research Scholar Program"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3517908","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"521-530","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Spine: Scaling up Programming-by-Negative-Example for String Filtering and Transformation"],"prefix":"10.1145","author":[{"given":"Chaoji","family":"Zuo","sequence":"first","affiliation":[{"name":"Rutgers University, Piscataway, NJ, USA"}]},{"given":"Sepehr","family":"Assadi","sequence":"additional","affiliation":[{"name":"Rutgers University, Piscataway, NJ, USA"}]},{"given":"Dong","family":"Deng","sequence":"additional","affiliation":[{"name":"Rutgers University, Piscataway, NJ, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"https:\/\/www.nytimes.com\/2014\/08\/18\/technology\/for-big-data-scientists-hurdle-to-insights-is-janitor-work.html."},{"key":"e_1_3_2_2_2_1","unstructured":"https:\/\/www.forbes.com\/sites\/gilpress\/2016\/03\/23\/data-preparation-most-time-consuming-least-enjoyable-data-science-task-survey-says."},{"key":"e_1_3_2_2_3_1","unstructured":"Informatica Advanced Data Transformation. https:\/\/www.informatica.com\/products\/dataintegration\/advanced-data-transformation.html."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2016.7498319"},{"key":"e_1_3_2_2_5_1","first-page":"9949","volume-title":"AAAI","author":"Aguas J. S.","year":"2020","unstructured":"J. S. Aguas, S. Jim\u00e9 nez, and A. Jonsson. Generalized planning with positive and negative examples. In AAAI, pages 9949--9956. AAAI Press, 2020."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(78)90683-6"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687686"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2737952"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2007.367920"},{"key":"e_1_3_2_2_10_1","volume-title":"ICLR","author":"Bunel R.","year":"2018","unstructured":"R. Bunel, M. J. Hausknecht, J. Devlin, R. Singh, and P. Kohli. Leveraging grammar and reinforcement learning for neural program synthesis. In ICLR, 2018."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389742"},{"issue":"2","key":"e_1_3_2_2_12_1","first-page":"10","article-title":"Biggorilla: An open-source ecosystem for data preparation and integration","volume":"41","author":"Chen C.","year":"2018","unstructured":"C. Chen, B. Golshan, A. Y. Halevy, W. Tan, and A. Doan. Biggorilla: An open-source ecosystem for data preparation and integration. IEEE Data Eng. Bull., 41(2):10--22, 2018.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385412.3385988"},{"key":"e_1_3_2_2_14_1","first-page":"189","volume-title":"COLING","author":"Contractor D.","year":"2010","unstructured":"D. Contractor, T. A. Faruquie, and L. V. Subramaniam. Unsupervised cleansing of noisy text. In C. Huang and D. Jurafsky, editors, COLING, pages 189--196, 2010."},{"key":"e_1_3_2_2_15_1","volume-title":"CIDR","author":"Deng D.","year":"2017","unstructured":"D. Deng, R. C. Fernandez, Z. Abedjan, S. Wang, M. Stonebraker, A. K. Elmagarmid, I. F. Ilyas, S. Madden, M. Ouzzani, and N. Tang. The data civilizer system. In CIDR, 2017."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00026"},{"key":"e_1_3_2_2_17_1","first-page":"990","volume-title":"ICML","author":"Devlin J.","year":"2017","unstructured":"J. Devlin, J. Uesato, S. Bhupatiraju, R. Singh, A. Mohamed, and P. Kohli. Robustfill: Neural program learning under noisy I\/O. In ICML, pages 990--998, 2017."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/540337"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(78)90562-4"},{"key":"e_1_3_2_2_20_1","unstructured":"M. Gualtieri. Deputize end-user developers to deliver business agility and reduce costs. 2019."},{"key":"e_1_3_2_2_21_1","first-page":"1","article-title":"Data quality considerations for big data and machine learning: Going beyond data cleaning and transformations","volume":"10","author":"Gudivada V.","year":"2017","unstructured":"V. Gudivada, A. Apon, and J. Ding. Data quality considerations for big data and machine learning: Going beyond data cleaning and transformations. International Journal on Advances in Software, 10:1--20, 07 2017.","journal-title":"International Journal on Advances in Software"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1926385.1926423"},{"issue":"8","key":"e_1_3_2_2_23_1","first-page":"97","article-title":"Spreadsheet data manipulation using examples","volume":"55","author":"Gulwani S.","year":"2012","unstructured":"S. Gulwani, W. R. Harris, and R. Singh. Spreadsheet data manipulation using examples. Commun., 55(8):97--105, 2012.","journal-title":"Commun."},{"key":"e_1_3_2_2_24_1","volume-title":"Program synthesis. Found. Trends Program. Lang., 4(1--2):1--119","author":"Gulwani S.","year":"2017","unstructured":"S. Gulwani, O. Polozov, and R. Singh. Program synthesis. Found. Trends Program. Lang., 4(1--2):1--119, 2017."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3231751.3231766"},{"issue":"11","key":"e_1_3_2_2_26_1","first-page":"2368","article-title":"Auto-transform: Learning-to-transform by patterns","volume":"13","author":"He Y.","year":"2020","unstructured":"Y. He, Z. Jin, and S. Chaudhuri. Auto-transform: Learning-to-transform by patterns. Proc. VLDB Endow., 13(11):2368--2381, 2020.","journal-title":"Proc. VLDB Endow."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3322485"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064034"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2594291.2594333"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421431"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2003.1260795"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/138027.138042"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380608"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401965"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/2977797.2977807"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21690-4_23"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/3149193.3149199"},{"key":"e_1_3_2_2_39_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."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983990.2984030"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2856767.2856791"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.541"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415900"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3115404.3115409"}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517908","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517908","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:06Z","timestamp":1750183806000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517908"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":44,"alternative-id":["10.1145\/3514221.3517908","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3517908","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}