{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T12:01:17Z","timestamp":1759147277810,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":50,"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\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,9]]},"DOI":"10.1145\/3650203.3663333","type":"proceedings-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T20:13:23Z","timestamp":1717013603000},"page":"51-61","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Reactive Dataflow for Inflight Error Handling in ML Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4525-9791","authenticated-orcid":false,"given":"Abhilash","family":"Jindal","sequence":"first","affiliation":[{"name":"IIT Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2322-4527","authenticated-orcid":false,"given":"Kaustubh","family":"Beedkar","sequence":"additional","affiliation":[{"name":"IIT Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5465-3685","authenticated-orcid":false,"given":"Vishal","family":"Singh","sequence":"additional","affiliation":[{"name":"IIT Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0413-141X","authenticated-orcid":false,"given":"J. Nausheen","family":"Mohammed","sequence":"additional","affiliation":[{"name":"IIT Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6529-1546","authenticated-orcid":false,"given":"Tushar","family":"Singla","sequence":"additional","affiliation":[{"name":"IIT Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2099-0465","authenticated-orcid":false,"given":"Aman","family":"Gupta","sequence":"additional","affiliation":[{"name":"IIT Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8289-5930","authenticated-orcid":false,"given":"Keerti","family":"Choudhary","sequence":"additional","affiliation":[{"name":"IIT Delhi, India"}]}],"member":"320","published-online":{"date-parts":[[2024,6,9]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI'16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI'16). USENIX Association, 265--283."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-46678-0_5"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476377"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536222.2536229"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824076"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3190664"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/3598581.3598599"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/16856.16861"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Konstantin Bulatov Ekaterina Emelianova Daniil Tropin Natalya Skoryukina Yulia Chernyshova Alexander Sheshkus Sergey Usilin Zuheng Ming Jean-Christophe Burie Muzzamil Luqman and Vladimir Arlazarov. 2021. MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis. https:\/\/doi.org\/10.48550\/arXiv.2107.00396","DOI":"10.48550\/arXiv.2107.00396"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_11_1","volume-title":"Apache flink: Stream and batch processing in a single engine. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering 36, 4","author":"Carbone Paris","year":"2015","unstructured":"Paris Carbone, Asterios Katsifodimos, Stephan Ewen, Volker Markl, Seif Haridi, and Kostas Tzoumas. 2015. Apache flink: Stream and batch processing in a single engine. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering 36, 4 (2015)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454166"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"e_1_3_2_1_14_1","unstructured":"Confluent [n.d.]. Confluent's ksqldb. https:\/\/www.confluent.io\/product\/ksqldb\/."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362738"},{"volume-title":"MapReduce: Simplified Data Processing on Large Clusters (OSDI'04)","author":"Dean Jeffrey","key":"e_1_3_2_1_16_1","unstructured":"Jeffrey Dean and Sanjay Ghemawat. 2004. MapReduce: Simplified Data Processing on Large Clusters (OSDI'04). USENIX Association, 10."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_18_1","unstructured":"EasyOCR [n.d.]. EasyOCR. https:\/\/github.com\/JaidedAI\/EasyOCR."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350245"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2904789"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Yash Goyal Tejas Khot Douglas Summers-Stay Dhruv Batra and Devi Parikh. 2017. Making the V in VQA matter: Elevating the role of image understanding in visual question answering (CVPR'17). 6904--6913.","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884813"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3264586"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation (OSDI'18)","author":"Hsieh Kevin","year":"2018","unstructured":"Kevin Hsieh, Ganesh Ananthanarayanan, Peter Bodik, Shivaram Venkataraman, Paramvir Bahl, Matthai Philipose, Phillip B. Gibbons, and Onur Mutlu. 2018. Focus: Querying Large Video Datasets with Low Latency and Low Cost. In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation (OSDI'18). USENIX Association, 269--286."},{"key":"e_1_3_2_1_25_1","unstructured":"HuggingFace [n. d.]. HuggingFace Pipelines. https:\/\/huggingface.co\/docs\/transformers\/main_classes\/pipelines."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063576.2063816"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850595"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1272996.1273005"},{"key":"e_1_3_2_1_29_1","volume-title":"2019 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). IEEE, 29--38","author":"Jatowt Adam","year":"2019","unstructured":"Adam Jatowt, Mickael Coustaty, Nhu-Van Nguyen, Antoine Doucet, et al. 2019. Deep statistical analysis of OCR errors for effective post-OCR processing. In 2019 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). IEEE, 29--38."},{"key":"e_1_3_2_1_30_1","volume-title":"TinyBERT: Distilling BERT for Natural Language Understanding. CoRR abs\/1909.10351","author":"Jiao Xiaoqi","year":"2019","unstructured":"Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, and Qun Liu. 2019. TinyBERT: Distilling BERT for Natural Language Understanding. CoRR abs\/1909.10351 (2019). arXiv:1909.10351 http:\/\/arxiv.org\/abs\/1909.10351"},{"key":"e_1_3_2_1_31_1","first-page":"481","article-title":"Model assertions for monitoring and improving ML models","volume":"2","author":"Kang Daniel","year":"2020","unstructured":"Daniel Kang, Deepti Raghavan, Peter Bailis, and Matei Zaharia. 2020. Model assertions for monitoring and improving ML models. Proceedings of Machine Learning and Systems 2 (2020), 481--496.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR, 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-language transformer without convolution or region supervision. In International Conference on Machine Learning. PMLR, 5583--5594."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3377369.3377381"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_35_1","volume-title":"A survey of appearance models in visual object tracking. ACM transactions on Intelligent Systems and Technology (TIST) 4, 4","author":"Li Xi","year":"2013","unstructured":"Xi Li, Weiming Hu, Chunhua Shen, Zhongfei Zhang, Anthony Dick, and Anton Van Den Hengel. 2013. A survey of appearance models in visual object tracking. ACM transactions on Intelligent Systems and Technology (TIST) 4, 4 (2013), 1--48."},{"key":"e_1_3_2_1_36_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692 (2019). arXiv:1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522738"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915246"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.779"},{"key":"e_1_3_2_1_42_1","volume-title":"Parameswaran","author":"Shankar Shreya","year":"2022","unstructured":"Shreya Shankar, Rolando Garcia, Joseph M. Hellerstein, and Aditya G. Parameswaran. 2022. Operationalizing Machine Learning: An Interview Study. arXiv:2209.09125 [cs.SE]"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"e_1_3_2_1_44_1","volume-title":"International Conference on Machine Learning","volume":"139","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herve Jegou. 2021. Training data-efficient image transformers and distillation through attention. In International Conference on Machine Learning, Vol. 139. 10347--10357."},{"key":"e_1_3_2_1_45_1","volume-title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision. arXiv:2006.03677 [cs.CV]","author":"Wu Bichen","year":"2020","unstructured":"Bichen Wu, Chenfeng Xu, Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Zhicheng Yan, Masayoshi Tomizuka, Joseph Gonzalez, Kurt Keutzer, and Peter Vajda. 2020. Visual Transformers: Token-based Image Representation and Processing for Computer Vision. arXiv:2006.03677 [cs.CV]"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"e_1_3_2_1_47_1","unstructured":"Yiheng Xu Minghao Li Lei Cui Shaohan Huang Furu Wei and Ming Zhou. 2019. LayoutLM: Pre-training of Text and Layout for Document Image Understanding."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation","author":"Zaharia Matei","year":"2012","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J. Franklin, Scott Shenker, and Ion Stoica. 2012. Resilient Distributed Datasets: A Fault-Tolerant Abstraction for in-Memory Cluster Computing. In Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (San Jose, CA) (NSDI'12). USENIX Association, 1 pages."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/568271.223848"}],"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":["Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650203.3663333","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650203.3663333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:32Z","timestamp":1750291412000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650203.3663333"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,9]]},"references-count":50,"alternative-id":["10.1145\/3650203.3663333","10.1145\/3650203"],"URL":"https:\/\/doi.org\/10.1145\/3650203.3663333","relation":{},"subject":[],"published":{"date-parts":[[2024,6,9]]},"assertion":[{"value":"2024-06-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}