{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T20:42:41Z","timestamp":1779223361918,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,21]],"date-time":"2022-05-21T00:00:00Z","timestamp":1653091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172202, 61872177, 61772259, 62172205, 61832009"],"award-info":[{"award-number":["62172202, 61872177, 61772259, 62172205, 61832009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,21]]},"DOI":"10.1145\/3510003.3510091","type":"proceedings-article","created":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T22:42:59Z","timestamp":1657060979000},"page":"2215-2227","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":48,"title":["Training data debugging for the fairness of machine learning software"],"prefix":"10.1145","author":[{"given":"Yanhui","family":"Li","sequence":"first","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linghan","family":"Meng","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Wu","sequence":"additional","affiliation":[{"name":"Momenta, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baowen","family":"Xu","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,7,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"1988. Heart Disease Data Set. https:\/\/archive.ics.uci.edu\/ml\/datasets\/heart+disease."},{"key":"e_1_3_2_1_2_1","unstructured":"1994. Statlog (German Credit Data) Data Set. https:\/\/archive.ics.uci.edu\/ml\/datasets\/statlog+(german+credit+data)."},{"key":"e_1_3_2_1_3_1","unstructured":"1996. Adult Data Set. https:\/\/archive.ics.uci.edu\/ml\/datasets\/adult."},{"key":"e_1_3_2_1_4_1","unstructured":"2011. The algorithm that beats your bank manager. https:\/\/www.forbes.com\/sites\/parmyolson\/2011\/03\/15\/the-algorithm-that-beats-your-bank-manager\/#15da2651ae99."},{"key":"e_1_3_2_1_5_1","unstructured":"2012. Bank Marketing Data Set. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Bank+Marketing."},{"key":"e_1_3_2_1_6_1","unstructured":"2014. Student Performance Data Set. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Student+Performance."},{"key":"e_1_3_2_1_7_1","unstructured":"2015. MEPS Data Set. https:\/\/meps.ahrq.gov\/mepsweb."},{"key":"e_1_3_2_1_8_1","unstructured":"2016. Amazon just showed us that unbiased algorithms can be inadvertently racist. https:\/\/www.businessinsider.com\/how-algorithms-can-be-racist-2016-4."},{"key":"e_1_3_2_1_9_1","unstructured":"2016. default of credit card clients Data Set. https:\/\/archive.ics.uci.edu\/ml\/datasets\/default+of+credit+card+clients."},{"key":"e_1_3_2_1_10_1","unstructured":"2017. compas-analysis. https:\/\/github.com\/propublica\/compas-analysis."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338937"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/smr.1672"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"e_1_3_2_1_14_1","first-page":"671","article-title":"Big data's disparate impact","volume":"104","author":"Barocas Solon","year":"2016","unstructured":"Solon Barocas and Andrew D Selbst. 2016. Big data's disparate impact. Calif. L. Rev. 104 (2016), 671.","journal-title":"Calif. L. Rev."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2942287"},{"key":"e_1_3_2_1_16_1","volume-title":"John T. Richards, Diptikalyan Saha, Prasanna Sattigeri, Moninder Singh, Kush R. Varshney, and Yunfeng Zhang.","author":"Bellamy Rachel K. E.","year":"2018","unstructured":"Rachel K. E. Bellamy, Kuntal Dey, Michael Hind, Samuel C. Hofman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia, Jacquelyn Martino, Sameep Mehta, Aleksandra Mojsilovic, Seema Nagar, Karthikeyan Natesan Ramamurthy, John T. Richards, Diptikalyan Saha, Prasanna Sattigeri, Moninder Singh, Kush R. Varshney, and Yunfeng Zhang. 2018. AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias. CoRR abs\/1810.01943 (2018). arXiv:1810.01943 http:\/\/arxiv.org\/abs\/1810.01943"},{"key":"e_1_3_2_1_17_1","volume-title":"A convex framework for fair regression. arXiv preprint arXiv:1706.02409","author":"Berk Richard","year":"2017","unstructured":"Richard Berk, Hoda Heidari, Shahin Jabbari, Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel, and Aaron Roth. 2017. A convex framework for fair regression. arXiv preprint arXiv:1706.02409 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409704"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409704"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3264838"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-010-0190-x"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468537"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409697"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3418932"},{"key":"e_1_3_2_1_25_1","volume-title":"Software engineering for fairness: A case study with hyperparameter optimization. arXiv preprint arXiv:1905.05786","author":"Chakraborty Joymallya","year":"2019","unstructured":"Joymallya Chakraborty, Tianpei Xia, Fahmid M Fahid, and Tim Menzies. 2019. Software engineering for fairness: A case study with hyperparameter optimization. arXiv preprint arXiv:1905.05786 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spl.2011.04.001"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"e_1_3_2_1_28_1","first-page":"267","article-title":"A clarification of some statistical issues in Watson v. Fort Worth Bank and Trust","volume":"29","author":"Gastwirth Joseph L","year":"1988","unstructured":"Joseph L Gastwirth. 1988. A clarification of some statistical issues in Watson v. Fort Worth Bank and Trust. Jurimetrics J. 29 (1988), 267.","journal-title":"Jurimetrics J."},{"key":"e_1_3_2_1_29_1","volume-title":"Equality of Opportunity in Supervised Learning. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of Opportunity in Supervised Learning. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5--10, 2016, Barcelona, Spain, Daniel D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett (Eds.). 3315--3323. https:\/\/proceedings.neurips.cc\/paper\/2016\/hash\/9d2682367c3935defcb1f9e247a97c0d-Abstract.html"},{"key":"e_1_3_2_1_30_1","volume-title":"A solution to the problem of separation in logistic regression. Statistics in medicine 21, 16","author":"Heinze Georg","year":"2002","unstructured":"Georg Heinze and Michael Schemper. 2002. A solution to the problem of separation in logistic regression. Statistics in medicine 21, 16 (2002), 2409--2419."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380329"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2018.8330212"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00045"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2870895"},{"key":"e_1_3_2_1_36_1","unstructured":"Jeanine Romano Jeffrey D Kromrey Jesse Coraggio Jeff Skowronek and Linda Devine. 2006. Exploring methods for evaluating group differences on the NSSE and other surveys: Are the t-test and Cohen's d indices the most appropriate choices. In annual meeting of the Southern Association for Institutional Research. Citeseer 1--51."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/3461535.3463474"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2006.1599417"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1002\/spe.798"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2447976.2447990"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2876537"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238165"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389696"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052660"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00129"},{"key":"e_1_3_2_1_47_1","volume-title":"Machine learning testing: Survey, landscapes and horizons","author":"Zhang Jie M","year":"2020","unstructured":"Jie M Zhang, Mark Harman, Lei Ma, and Yang Liu. 2020. Machine learning testing: Survey, landscapes and horizons. IEEE Transactions on Software Engineering (2020)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380331"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2009.32"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556777"}],"event":{"name":"ICSE '22: 44th International Conference on Software Engineering","location":"Pittsburgh Pennsylvania","acronym":"ICSE '22","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 44th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510003.3510091","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3510003.3510091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:23Z","timestamp":1750183823000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510003.3510091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,21]]},"references-count":50,"alternative-id":["10.1145\/3510003.3510091","10.1145\/3510003"],"URL":"https:\/\/doi.org\/10.1145\/3510003.3510091","relation":{},"subject":[],"published":{"date-parts":[[2022,5,21]]},"assertion":[{"value":"2022-07-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}