{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T15:40:36Z","timestamp":1786635636977,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1145\/3735654.3735939","type":"proceedings-article","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T21:36:31Z","timestamp":1750628191000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards Automated Task-Aware Data Validation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1887-6630","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"first","affiliation":[{"name":"BIFOLD & TU Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4722-5840","authenticated-orcid":false,"given":"Sebastian","family":"Schelter","sequence":"additional","affiliation":[{"name":"BIFOLD & TU Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994518"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054772"},{"key":"e_1_3_2_1_3_1","volume-title":"Automatic Suggestion of Constraints. https:\/\/github.com\/awslabs\/deequ\/blob\/master\/src\/main\/scala\/com\/amazon\/deequ\/examples\/constraint_suggestion_example.md. [Online","year":"2025","unstructured":"Amazon. 2025. Automatic Suggestion of Constraints. https:\/\/github.com\/awslabs\/deequ\/blob\/master\/src\/main\/scala\/com\/amazon\/deequ\/examples\/constraint_suggestion_example.md. [Online; accessed March-2025]."},{"key":"e_1_3_2_1_4_1","unstructured":"Sijie Dong Soror Sahri Themis Palpanas and Qitong Wang. 2025. Automated Data Quality Validation in an End-to-End GNN Framework. (2025)."},{"key":"e_1_3_2_1_5_1","volume-title":"https:\/\/greatexpectations.io\/. [Online","author":"Expectations Great","year":"2025","unstructured":"Great Expectations. 2024. Great Expectations. https:\/\/greatexpectations.io\/. [Online; accessed January-2025]."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW67478.2025.00011"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319888"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196889"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3665939.3665957"},{"key":"e_1_3_2_1_10_1","unstructured":"Hoa Thi Le Angela Bonifati and Andrea Mauri. 2025. Graph Consistency Rule Mining with LLMs: an Exploratory Study. (2025)."},{"key":"e_1_3_2_1_11_1","volume-title":"Samuel Madden, Mourad Ouzzani, Michael Stonebraker, and Nan Tang.","author":"Mahdavi Mohammad","year":"2019","unstructured":"Mohammad Mahdavi, Ziawasch Abedjan, Raul Castro Fernandez, Samuel Madden, Mourad Ouzzani, Michael Stonebraker, and Nan Tang. 2019. Raha: A Configuration-Free Error Detection System. SIGMOD (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403205"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539145"},{"key":"e_1_3_2_1_14_1","first-page":"334","article-title":"Data validation for machine learning","volume":"1","author":"Polyzotis Neoklis","year":"2019","unstructured":"Neoklis Polyzotis, Martin Zinkevich, Sudip Roy, Eric Breck, and Steven Whang. 2019. Data validation for machine learning. MLSys 1 (2019), 334--347.","journal-title":"MLSys"},{"key":"e_1_3_2_1_15_1","unstructured":"Sergey Redyuk Zoi Kaoudi Volker Markl and Sebastian Schelter. 2021. Automating Data Quality Validation for Dynamic Data Ingestion.. In EDBT. 61--72."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229867"},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Extending Database Technology. https:\/\/api.semanticscholar.org\/CorpusID:232283615","author":"Schelter Sebastian","year":"2021","unstructured":"Sebastian Schelter, Tammo Rukat, and Felix Biessmann. 2021. JENGA - A Framework to Study the Impact of Data Errors on the Predictions of Machine Learning Models. In International Conference on Extending Database Technology. https:\/\/api.semanticscholar.org\/CorpusID:232283615"},{"key":"e_1_3_2_1_18_1","first-page":"68539","article-title":"Toolformer: Language models can teach themselves to use tools","volume":"36","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess\u00ec, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems 36 (2023), 68539--68551.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"AWS Glue Data Quality. https:\/\/docs.aws.amazon.com\/glue\/latest\/dg\/glue-data-quality.html. [Online","author":"Services Amazon Web","year":"2025","unstructured":"Amazon Web Services. 2024. AWS Glue Data Quality. https:\/\/docs.aws.amazon.com\/glue\/latest\/dg\/glue-data-quality.html. [Online; accessed January-2025]."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614786"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457250"},{"key":"e_1_3_2_1_22_1","unstructured":"Tensorflow. 2025. TensorFlow Data Validation - An Example of a Key Component of TensorFlow Extended. https:\/\/colab.research.google.com\/github\/tensorflow\/tfx\/blob\/master\/docs\/tutorials\/data_validation\/tfdv_basic.ipynb. [Online; accessed March-2025]."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599776"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380568"},{"key":"e_1_3_2_1_25_1","volume-title":"LLM-Powered Proactive Data Systems. arXiv preprint arXiv:2502.13016","author":"Zeighami Sepanta","year":"2025","unstructured":"Sepanta Zeighami, Yiming Lin, Shreya Shankar, and Aditya Parameswaran. 2025. LLM-Powered Proactive Data Systems. arXiv preprint arXiv:2502.13016 (2025)."}],"event":{"name":"SIGMOD\/PODS '25: International Conference on Management of Data","location":"Berlin Germany","acronym":"SIGMOD\/PODS '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Workshop on Data Management for End-to-End Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3735654.3735939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:28:40Z","timestamp":1755973720000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3735654.3735939"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":25,"alternative-id":["10.1145\/3735654.3735939","10.1145\/3735654"],"URL":"https:\/\/doi.org\/10.1145\/3735654.3735939","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"2025-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}