{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T22:52:11Z","timestamp":1784069531745,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1145\/3555041.3589682","type":"proceedings-article","created":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T16:25:14Z","timestamp":1685982314000},"page":"91-94","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Proactively Screening Machine Learning Pipelines with ARGUSEYES"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4722-5840","authenticated-orcid":false,"given":"Sebastian","family":"Schelter","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9884-9517","authenticated-orcid":false,"given":"Stefan","family":"Grafberger","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9156-1561","authenticated-orcid":false,"given":"Shubha","family":"Guha","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6462-3579","authenticated-orcid":false,"given":"Bojan","family":"Karlas","sequence":"additional","affiliation":[{"name":"Harvard University, Boston, MA, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-7505","authenticated-orcid":false,"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,6,5]]},"reference":[{"key":"e_1_3_2_3_1_1","volume-title":"The State of Data Science","author":"Anaconda 0.","year":"2020","unstructured":"Anaconda.com. 2020. The State of Data Science 2020. https:\/\/www.anaconda.com\/state-of-data-science-2020."},{"key":"e_1_3_2_3_2_1","unstructured":"Irene Chen et al. 2018. Why is my classifier discriminatory? NeurIPS (2018)."},{"key":"e_1_3_2_3_3_1","unstructured":"Franccois Chollet et al. 2015. Keras. https:\/\/keras.io."},{"key":"e_1_3_2_3_4_1","doi-asserted-by":"crossref","unstructured":"Stefan Grafberger et al. 2022. Data distribution debugging in machine learning pipelines. VLDB Journal (2022).","DOI":"10.1145\/3448016.3452759"},{"key":"e_1_3_2_3_5_1","doi-asserted-by":"crossref","unstructured":"Todd J Green et al. 2007. Provenance semirings. PODS (2007).","DOI":"10.1145\/1265530.1265535"},{"key":"e_1_3_2_3_6_1","doi-asserted-by":"crossref","unstructured":"Ruoxi Jia et al. 2019. Efficient task-specific data valuation for nearest neighbor algorithms. VLDB (2019).","DOI":"10.14778\/3342263.3342637"},{"key":"e_1_3_2_3_7_1","unstructured":"Sayash Kapoor et al. 2022. Leakage and the Reproducibility Crisis in ML-based Science. arXiv preprint arXiv:2207.07048 (2022)."},{"key":"e_1_3_2_3_8_1","unstructured":"Curtis G Northcutt et al. 2021. Pervasive label errors in test sets destabilize machine learning benchmarks. NeurIPS (2021)."},{"key":"e_1_3_2_3_9_1","doi-asserted-by":"crossref","unstructured":"Neoklis Polyzotis et al. 2017. Data management challenges in production machine learning. SIGMOD (2017).","DOI":"10.1145\/3035918.3054782"},{"key":"e_1_3_2_3_10_1","unstructured":"Sebastian Schelter et al. 2015. On challenges in machine learning model management. IEEE Data Engineering Bullettin (2015)."},{"key":"e_1_3_2_3_11_1","unstructured":"Sebastian Schelter et al. 2022. Screening Native ML Pipelines with ?ArgusEyes\". CIDR (2022)."},{"key":"e_1_3_2_3_12_1","doi-asserted-by":"crossref","unstructured":"Joaquin Vanschoren et al. 2014. OpenML: networked science in machine learning. KDD (2014).","DOI":"10.1145\/2641190.2641198"},{"key":"e_1_3_2_3_13_1","doi-asserted-by":"crossref","unstructured":"Doris Xin et al. 2021. Production machine learning pipelines: Empirical analysis and optimization opportunities. SIGMOD (2021).","DOI":"10.1145\/3448016.3457566"},{"key":"e_1_3_2_3_14_1","first-page":"4","article-title":"2018. Accelerating the machine learning lifecycle with MLflow","volume":"41","author":"Matei Zaharia","year":"2018","unstructured":"Matei Zaharia et al. 2018. Accelerating the machine learning lifecycle with MLflow. IEEE Data Engineering Bullettin, Vol. 41, 4 (2018), 39--45.","journal-title":"IEEE Data Engineering Bullettin"}],"event":{"name":"SIGMOD\/PODS '23: International Conference on Management of Data","location":"Seattle WA USA","acronym":"SIGMOD\/PODS '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Companion of the 2023 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3555041.3589682","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3555041.3589682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T18:43:58Z","timestamp":1750272238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3555041.3589682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":14,"alternative-id":["10.1145\/3555041.3589682","10.1145\/3555041"],"URL":"https:\/\/doi.org\/10.1145\/3555041.3589682","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]},"assertion":[{"value":"2023-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}