{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T03:05:08Z","timestamp":1776395108228,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CNS-1651570"],"award-info":[{"award-number":["CNS-1651570"]}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3517907","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"496-505","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Finding Label and Model Errors in Perception Data With Learned Observation Assertions"],"prefix":"10.1145","author":[{"given":"Daniel","family":"Kang","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Arechiga","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sudeep","family":"Pillai","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter D.","family":"Bailis","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matei","family":"Zaharia","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098021"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1147376.1147391"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920870"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066175"},{"key":"e_1_3_2_2_6_1","unstructured":"Chiao-Lun Cheng. 2019. Training Data - Quantity is no Panacea. (2019). https:\/\/scale.com\/blog\/training-data-quantity-is-no-panacea"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2912574"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680833270"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319888"},{"key":"e_1_3_2_2_10_1","volume-title":"NIPS MLSys Workshop .","author":"Hynes Nick","year":"2017","unstructured":"Nick Hynes, D Sculley, and Michael Terry. 2017. The data linter: Lightweight, automated sanity checking for ml data sets. In NIPS MLSys Workshop ."},{"key":"e_1_3_2_2_11_1","volume-title":"Model Assertions for Monitoring and Improving ML Model. MLSys","author":"Kang Daniel","year":"2020","unstructured":"Daniel Kang, Deepti Raghavan, Peter Bailis, and Matei Zaharia. 2020. Model Assertions for Monitoring and Improving ML Model. MLSys (2020)."},{"key":"e_1_3_2_2_12_1","unstructured":"Andrej Kaparthy. 2018. Building the Software 2.0 Stack. (2018)."},{"key":"e_1_3_2_2_13_1","unstructured":"R. Kesten M. Usman J. Houston T. Pandya K. Nadhamuni A. Ferreira M. Yuan B. Low A. Jain P. Ondruska S. Omari S. Shah A. Kulkarni A. Kazakova C. Tao L. Platinsky W. Jiang and V. Shet. 2019. Lyft Level 5 Perception Dataset 2020. https:\/\/level5.lyft.com\/dataset\/."},{"key":"e_1_3_2_2_14_1","volume-title":"Activeclean: Interactive data cleaning while learning convex loss models. arXiv preprint arXiv:1601.03797","author":"Krishnan Sanjay","year":"2016","unstructured":"Sanjay Krishnan, Jiannan Wang, Eugene Wu, Michael J Franklin, and Ken Goldberg. 2016. Activeclean: Interactive data cleaning while learning convex loss models. arXiv preprint arXiv:1601.03797 (2016)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.910572"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"e_1_3_2_2_17_1","volume-title":"Jose Maria Martinez Montiel, and Juan D Tardos","author":"Mur-Artal Raul","year":"2015","unstructured":"Raul Mur-Artal, Jose Maria Martinez Montiel, and Juan D Tardos. 2015. ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE transactions on robotics, Vol. 31, 5 (2015), 1147--1163."},{"key":"e_1_3_2_2_18_1","volume-title":"International Conference on Machine Learning. 4901--4911","author":"Odena Augustus","year":"2019","unstructured":"Augustus Odena, Catherine Olsson, David Andersen, and Ian Goodfellow. 2019. Tensorfuzz: Debugging neural networks with coverage-guided fuzzing. In International Conference on Machine Learning. 4901--4911."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00107"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054782"},{"key":"e_1_3_2_2_21_1","volume-title":"Data validation for machine learning. MLSys","author":"Polyzotis Neoklis","year":"2019","unstructured":"Neoklis Polyzotis, Martin Zinkevich, Sudip Roy, Eric Breck, and Steven Whang. 2019. Data validation for machine learning. MLSys (2019)."},{"key":"e_1_3_2_2_22_1","volume-title":"Factor Graph based 3D Multi-Object Tracking in Point Clouds. arXiv preprint arXiv:2008.05309","author":"P\u00f6schmann Johannes","year":"2020","unstructured":"Johannes P\u00f6schmann, Tim Pfeifer, and Peter Protzel. 2020. Factor Graph based 3D Multi-Object Tracking in Point Clouds. arXiv preprint arXiv:2008.05309 (2020)."},{"key":"e_1_3_2_2_23_1","first-page":"3","article-title":"Data cleaning: Problems and current approaches","volume":"23","author":"Rahm Erhard","year":"2000","unstructured":"Erhard Rahm and Hong Hai Do. 2000. Data cleaning: Problems and current approaches. IEEE Data Eng. Bull., Vol. 23, 4 (2000), 3--13.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-019-00552-1"},{"key":"e_1_3_2_2_25_1","volume-title":"Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:1702.00820","author":"Rekatsinas Theodoros","year":"2017","unstructured":"Theodoros Rekatsinas, Xu Chu, Ihab F Ilyas, and Christopher R\u00e9. 2017. Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:1702.00820 (2017)."},{"key":"e_1_3_2_2_27_1","unstructured":"Vinay Shet. 2019. Lyft Level 5 Self-Driving Perception Dataset Competition Now Open. https:\/\/medium.com\/wovenplanetlevel5\/lyft-level-5-self-driving-dataset-competition-now-open-97493e9f154a. (2019)."},{"key":"e_1_3_2_2_28_1","volume-title":"Leveraging organizational resources to adapt models to new data modalities. arXiv preprint arXiv:2008.09983","author":"Suri Sahaana","year":"2020","unstructured":"Sahaana Suri, Raghuveer Chanda, Neslihan Bulut, Pradyumna Narayana, Yemao Zeng, Peter Bailis, Sugato Basu, Girija Narlikar, Christopher R\u00e9, and Abishek Sethi. 2020. Leveraging organizational resources to adapt models to new data modalities. arXiv preprint arXiv:2008.09983 (2020)."},{"key":"e_1_3_2_2_29_1","unstructured":"Daisuke Wakabayashi. 2018. Self-Driving Uber Car Kills Pedestrian in Arizona Where Robots Roam. https:\/\/www.nytimes.com\/2018\/03\/19\/technology\/uber-driverless-fatality.html ."},{"key":"e_1_3_2_2_30_1","volume-title":"Lidar","author":"Wandinger Ulla","unstructured":"Ulla Wandinger. 2005. Introduction to lidar. In Lidar. Springer, 1--18."},{"key":"e_1_3_2_2_31_1","volume-title":"Nathaniel Hamilton, Xiaodong Yang, Joel Rosenfeld, and Taylor T Johnson.","author":"Xiang Weiming","year":"2018","unstructured":"Weiming Xiang, Patrick Musau, Ayana A Wild, Diego Manzanas Lopez, Nathaniel Hamilton, Xiaodong Yang, Joel Rosenfeld, and Taylor T Johnson. 2018. Verification for machine learning, autonomy, and neural networks survey. arXiv preprint arXiv:1810.01989 (2018)."},{"key":"e_1_3_2_2_32_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_2_33_1","volume-title":"Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection. arXiv preprint arXiv:1908.09492","author":"Zhu Benjin","year":"2019","unstructured":"Benjin Zhu, Zhengkai Jiang, Xiangxin Zhou, Zeming Li, and Gang Yu. 2019. Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection. arXiv preprint arXiv:1908.09492 (2019)."}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517907","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517907","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:06Z","timestamp":1750183806000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517907"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":32,"alternative-id":["10.1145\/3514221.3517907","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3517907","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}