{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T20:08:07Z","timestamp":1779048487717,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T00:00:00Z","timestamp":1780099200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,31]]},"DOI":"10.1145\/3807899.3808688","type":"proceedings-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:58:38Z","timestamp":1778615918000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["End-to-End Auditing of ML Pipelines through Data Provenance and Model Explainability"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4634-6564","authenticated-orcid":false,"given":"Pasquale Leonardo","family":"Lazzaro","sequence":"first","affiliation":[{"name":"Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7772-2680","authenticated-orcid":false,"given":"Elia","family":"Guglielmi","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0978-2446","authenticated-orcid":false,"given":"Paolo","family":"Missier","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Birmingham, Birmingham, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1484-3693","authenticated-orcid":false,"given":"Riccardo","family":"Torlone","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44503-X_20"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000006"},{"key":"e_1_3_2_1_3_1","volume-title":"The Faiss library. arXiv preprint arXiv:2401.08281","author":"Douze Matthijs","year":"2024","unstructured":"Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazar\u00e9, Maria Lomeli, Lucas Hosseini, and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. arXiv preprint arXiv:2401.08281 (2024)."},{"key":"e_1_3_2_1_4_1","first-page":"2823","article-title":"Automating and Optimizing Data-Centric What-If Analyses on Native Machine Learning Pipelines","volume":"16","author":"Grafberger Stefan","year":"2023","unstructured":"Stefan Grafberger, Shubha Guha, Paul Groth, and Sebastian Schelter. 2023. Automating and Optimizing Data-Centric What-If Analyses on Native Machine Learning Pipelines. Proceedings of the VLDB Endowment 16, 11 (2023), 2823\u20132836.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-025-01209-3"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning(ICML).","author":"Koh P. W.","unstructured":"P. W. Koh and P. Liang. 2017. Understanding black-box predictions via influence functions. In International Conference on Machine Learning(ICML)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 28th International Conference on Extending Database Technology (EDBT). OpenProceedings.org","author":"Lazzaro P. L.","unstructured":"P. L. Lazzaro, M. Lazzaro, P. Missier, and R. Torlone. 2025. PROLIT: Supporting the Transparency of Data Preparation Pipelines through Narratives over Data Provenance. In Proceedings of the 28th International Conference on Extending Database Technology (EDBT). OpenProceedings.org, Barcelona, Spain."},{"key":"e_1_3_2_1_9_1","unstructured":"S. M. Lundberg and S. I. Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (NeurIPS). [10] Luc Moreau Paolo Missier et al. 2013. PROV-DM: The PROV Data Model. W3C Recommendation. https:\/\/www.w3.org\/TR\/prov-dm\/"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the Workshops of the EDBT\/ICDT 2021 Joint Conference.","author":"Phani Arnab","year":"2021","unstructured":"Arnab Phani. 2021. What Information is Required for Explainable AI? A Provenance-based Research Agenda and Future Challenges. In Proceedings of the Workshops of the EDBT\/ICDT 2021 Joint Conference."},{"key":"e_1_3_2_1_11_1","unstructured":"G. Pruthi F. Liu S. Kale and M. Sundararajan. 2020. Estimating training data influence by tracing gradient descent. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_12_1","volume-title":"Automated Documentation of End-to-End Experiments in Data Science. In 2019 IEEE 35th International Conference on Data Engineering (ICDE). IEEE.","author":"Redyuk Sergey","year":"2019","unstructured":"Sergey Redyuk. 2019. Automated Documentation of End-to-End Experiments in Data Science. In 2019 IEEE 35th International Conference on Data Engineering (ICDE). IEEE."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939502.2939516"},{"key":"e_1_3_2_1_14_1","unstructured":"Doris Xin et al. 2021. LineaPy: Data Lineage for Python. In https:\/\/github.com\/LineaLabs\/lineapy."}],"event":{"name":"SIGMOD\/PODS '26: International Conference on Management of Data","location":"Bengaluru India","acronym":"DEEM '26","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Data Management for End-to-End Machine Learning"],"original-title":[],"deposited":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T19:58:53Z","timestamp":1779047933000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3807899.3808688"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,30]]},"references-count":14,"alternative-id":["10.1145\/3807899.3808688","10.1145\/3807899"],"URL":"https:\/\/doi.org\/10.1145\/3807899.3808688","relation":{},"subject":[],"published":{"date-parts":[[2026,5,30]]},"assertion":[{"value":"2026-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}