{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:10:03Z","timestamp":1755864603117,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":24,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Education and Research","award":["BIFOLD24B"],"award-info":[{"award-number":["BIFOLD24B"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,9]]},"DOI":"10.1145\/3626246.3654745","type":"proceedings-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T10:26:39Z","timestamp":1716459999000},"page":"528-531","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PLUTUS: Understanding Data Distribution Tailoring for Machine Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3945-925X","authenticated-orcid":false,"given":"Jiwon","family":"Chang","sequence":"first","affiliation":[{"name":"University of Rochester, Rochester, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1295-0460","authenticated-orcid":false,"given":"Christina","family":"Dionysio","sequence":"additional","affiliation":[{"name":"Technsiche Universit\u00e4t Berlin, Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4710-8719","authenticated-orcid":false,"given":"Fatemeh","family":"Nargesian","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1344-3663","authenticated-orcid":false,"given":"Matthias","family":"Boehm","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Berlin, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,6,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. Dash Enterprise: The Premier Data App Platform for Python. https:\/\/plotly.com\/dash."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551858"},{"key":"e_1_3_2_1_3_1","unstructured":"Matthias Boehm et al. 2020. SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle. In CIDR."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/3523210.3523223"},{"volume-title":"SIGKDD. ACM","author":"Chen Tianqi","key":"e_1_3_2_1_5_1","unstructured":"Tianqi Chen and Carlos Guestrin. 2016. XGBoost: A Scalable Tree Boosting System. In SIGKDD. ACM, San Francisco California USA, 785--794. https:\/\/doi. org\/10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_6_1","volume-title":"Ki Hyun Tae, and Steven Euijong Whang","author":"Chung Yeounoh","year":"2019","unstructured":"Yeounoh Chung, Tim Kraska, Neoklis Polyzotis, Ki Hyun Tae, and Steven Euijong Whang. 2019. Slice Finder: Automated Data Slicing for Model Validation. In ICDE."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2916074"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Sam Corbett-Davies Emma Pierson Avi Feller Sharad Goel and Aziz Huq. 2017. Algorithmic decision making and the cost of fairness. In SIGKDD. 797--806.","DOI":"10.1145\/3097983.3098095"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824127"},{"key":"e_1_3_2_1_10_1","volume-title":"Ozdaglar","author":"Fallah Alireza","year":"2022","unstructured":"Alireza Fallah, Ali Makhdoumi, Azarakhsh Malekian, and Asuman E. Ozdaglar. 2022. Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms. In EC. 1141."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735461.2735467"},{"key":"e_1_3_2_1_12_1","first-page":"1","article-title":"Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels","volume":"408","author":"Jochen G\u00f6rtler","year":"2022","unstructured":"Jochen G\u00f6rtler et al. 2022. Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels. In CHI. 408:1--408:13. https:\/\/doi.org\/10. 1145\/3491102.3501823","journal-title":"CHI."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Zhongjun Jin Mengjing Xu Chenkai Sun Abolfazl Asudeh and H. V. Jagadish. 2020. MithraCoverage: A System for Investigating Population Bias for Intersectional Fairness. In SIGMOD. 2721--2724. https:\/\/doi.org\/10.1145\/3318464.3384689","DOI":"10.1145\/3318464.3384689"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.318"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3467861.3467872"},{"key":"e_1_3_2_1_16_1","volume-title":"Lundberg and Su-In Lee","author":"Scott","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In NeurIPS. 4765--4774."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Supun Nakandala Arun Kumar and Yannis Papakonstantinou. 2019. Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations. In SIGMOD. 1589--1606. https:\/\/doi.org\/10.1145\/3299869.3319874","DOI":"10.1145\/3299869.3319874"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Fatemeh Nargesian Abolfazl Asudeh and H. V. Jagadish. 2021. Tailoring Data Source Distributions for Fairness-aware Data Integration. PVLDB 14 11 (2021).","DOI":"10.14778\/3476249.3476299"},{"key":"e_1_3_2_1_19_1","volume-title":"Steven Euijong Whang, and Martin Zinkevich","author":"Polyzotis Neoklis","year":"2017","unstructured":"Neoklis Polyzotis, Sudip Roy, Steven Euijong Whang, and Martin Zinkevich. 2017. Data Management Challenges in Production Machine Learning. In SIGMOD."},{"key":"e_1_3_2_1_20_1","unstructured":"Propublica. [n. d.]. Machine Bias Series. https:\/\/www.propublica.org\/series\/ machine-bias."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Marco T\u00falio Ribeiro Sameer Singh and Carlos Guestrin. 2016. \"Why Should I Trust You?\": Explaining the Predictions of Any Classifier. In SIGKDD. 1135--1144. https:\/\/doi.org\/10.1145\/2939672.2939778","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Svetlana Sagadeeva and Matthias Boehm. 2021. SliceLine: Fast Linear-Algebrabased Slice Finding for ML Model Debugging. In SIGMOD. ACM 2290--2299.","DOI":"10.1145\/3448016.3457323"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452792"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-"}],"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":["Companion of the 2024 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626246.3654745","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626246.3654745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:30:33Z","timestamp":1755862233000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626246.3654745"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,9]]},"references-count":24,"alternative-id":["10.1145\/3626246.3654745","10.1145\/3626246"],"URL":"https:\/\/doi.org\/10.1145\/3626246.3654745","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"}}]}}