{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:06:34Z","timestamp":1784012794957,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["1916505"],"award-info":[{"award-number":["1916505"]}]},{"name":"NSF","award":["1922658"],"award-info":[{"award-number":["1922658"]}]},{"name":"NSF","award":["2312930"],"award-info":[{"award-number":["2312930"]}]},{"name":"UL Research Institutes"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tkde.2024.3365524","type":"journal-article","created":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T00:02:05Z","timestamp":1707868925000},"page":"7368-7379","source":"Crossref","is-referenced-by-count":18,"title":["Automated Data Cleaning can Hurt Fairness in Machine Learning-Based Decision Making"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9156-1561","authenticated-orcid":false,"given":"Shubha","family":"Guha","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4678-5929","authenticated-orcid":false,"given":"Falaah Arif","family":"Khan","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1587-0450","authenticated-orcid":false,"given":"Julia","family":"Stoyanovich","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4722-5840","authenticated-orcid":false,"given":"Sebastian","family":"Schelter","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3488717"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3299887.3299891"},{"key":"ref3","first-page":"1","article-title":"Quantitative data cleaning for large databases","volume":"25","author":"Hellerstein","year":"2008","journal-title":"United Nations Econ. Commission Europe"},{"issue":"1","key":"ref4","first-page":"4","article-title":"Data errors: Symptoms, causes and origins","volume":"45","author":"Ilyas","year":"2022","journal-title":"IEEE Data Eng. Bull."},{"key":"ref5","first-page":"13","article-title":"CleanML: A benchmark for joint data cleaning and machine learning","volume-title":"Proc. IEEE Int. Conf. Data Eng.","author":"Li"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3506712"},{"key":"ref7","first-page":"395","article-title":"FairPrep: Promoting data to a first-class citizen in studies on fairness-enhancing interventions","volume-title":"Proc. 23rd Int. Conf. Extending Database Technol.","author":"Schelter"},{"key":"ref8","first-page":"3543","article-title":"Why is my classifier discriminatory?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"issue":"1","key":"ref9","first-page":"24","article-title":"From cleaning before ML to cleaning for ML","volume":"44","author":"Neutatz","year":"2021","journal-title":"IEEE Data Eng. Bull."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.14778\/3430915.3430917"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287589"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517886"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00056"},{"key":"ref15","first-page":"815","article-title":"Sample selection for fair and robust training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Roh"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517841"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-021-00699-w"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13197"},{"key":"ref19","article-title":"California consumer privacy act - frequently asked questions","year":"2024"},{"key":"ref20","article-title":"Proposal for a regulation of the european parliament and of the council laying down harmonised rules on artificial intelligence (artificial intelligence act) and amending certain union legislative acts","year":"2021"},{"key":"ref21","article-title":"Digital charter implementation act: An act to enact the consumer privacy protection act, the personal information and data protection tribunal act and the artificial intelligence and data act and to make consequential and related amendments to other acts","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3551624.3555286"},{"key":"ref23","first-page":"6478","article-title":"Retiring adult: New datasets for fair machine learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref24","article-title":"Protections against discrimination and other prohibited practices","year":"2024"},{"key":"ref25","article-title":"What the European commission is doing to protect your rights","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.4324\/9781315631011-38"},{"key":"ref28","first-page":"77","article-title":"Gender shades: Intersectional accuracy disparities in commercial gender classification","volume-title":"Proc. 1st Conf. Fairness Accountability Transparency","author":"Buolamwini"},{"key":"ref29","article-title":"Fairness definitions and their politics","volume-title":"Proc. ACM Conf. Fairness Accountability Transparency","author":"Narayanan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994518"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324956"},{"key":"ref32","article-title":"Pervasive label errors in test sets destabilize machine learning benchmarks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Northcutt"},{"key":"ref33","first-page":"1373","article-title":"Learning with confident examples: Rank pruning for robust classification with noisy labels","volume-title":"Proc. 33rd Conf. Uncertainty Artif. Intell.","author":"Northcutt"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14778\/2536258.2536262"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319888"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342637"},{"key":"ref38","article-title":"Data debugging with Shapley importance over end-to-end machine learning pipelines","author":"Karla\u0161","year":"2022"},{"key":"ref39","first-page":"927","article-title":"Fair classification with instance-dependent label noise","volume-title":"Proc. 1st Conf. Causal Learn. Reasoning","author":"Wu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313559"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/69\/10750897\/10433778-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10750897\/10433778.pdf?arnumber=10433778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T15:28:06Z","timestamp":1732721286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10433778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":41,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3365524","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}