{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T01:57:25Z","timestamp":1769738245362,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":90,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4500703"],"award-info":[{"award-number":["2022YFB4500703"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332012"],"award-info":[{"award-number":["62332012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472245"],"award-info":[{"award-number":["62472245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alibaba Research Intern Program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3718958.3750513","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:54:11Z","timestamp":1756313651000},"page":"527-540","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SkeletonHunter: Diagnosing and Localizing Network Failures in Containerized Large Model Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9104-6316","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"},{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9882-9279","authenticated-orcid":false,"given":"Kun","family":"Qian","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7286-122X","authenticated-orcid":false,"given":"Zhenhua","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4443-8170","authenticated-orcid":false,"given":"Tianyin","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5850-7132","authenticated-orcid":false,"given":"Yunhao","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1785-448X","authenticated-orcid":false,"given":"Weicheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hang Zhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9946-3641","authenticated-orcid":false,"given":"Yun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1155-1871","authenticated-orcid":false,"given":"Jiakang","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5404-797X","authenticated-orcid":false,"given":"Shuhong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5713-7225","authenticated-orcid":false,"given":"Xue","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2496-0661","authenticated-orcid":false,"given":"Hongfei","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2679-4983","authenticated-orcid":false,"given":"Fei","family":"Feng","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4352-7497","authenticated-orcid":false,"given":"Ennan","family":"Zhai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2014. Virtual eXtensible Local Area Network (VXLAN): A Framework for Overlaying Virtualized Layer 2 Networks over Layer 3 Networks. https:\/\/datatracker.ietf.org\/doc\/html\/rfc7348. (2014)."},{"key":"e_1_3_2_1_2_1","unstructured":"2018. Lognormal Distribution. https:\/\/www.sciencedirect.com\/topics\/engineering\/lognormal-distribution. (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"IEEE Standard for a Precision Clock Synchronization Protocol for Networked Measurement and Control Systems","year":"2019","unstructured":"2020. IEEE Standard for a Precision Clock Synchronization Protocol for Networked Measurement and Control Systems. IEEE Std 1588-2019 (2020), 1\u2013499."},{"key":"e_1_3_2_1_4_1","unstructured":"2022. Doubling All2all Performance with NVIDIA Collective Communication Library 2.12. https:\/\/developer.nvidia.com\/blog\/doubling-all2all-performance-with-nvidia-collective-communication-library-2-12\/. (2022)."},{"key":"e_1_3_2_1_5_1","unstructured":"2023. NVIDIA DGX SuperPOD: Next Generation Scalable Infrastructure for AI Leadership. https:\/\/docs.nvidia.com\/https:\/docs.nvidia.com\/dgx-superpod-reference-architecture-dgx-h100.pdf. (2023)."},{"key":"e_1_3_2_1_6_1","unstructured":"2024. Container Network Interface (CNI). https:\/\/kubernetes.io\/docs\/concepts\/extend-kubernetes\/compute-storage-net\/network-plugins\/. (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"2024. Dynolog: A Performance Monitoring Daemon for Heterogeneous CPU-GPU Systems. https:\/\/github.com\/facebookincubator\/dynolog. (2024)."},{"key":"e_1_3_2_1_8_1","unstructured":"2024. GPT-3 Powers the Next Generation of Apps. https:\/\/openai.com\/index\/gpt-3-apps\/. (2024)."},{"key":"e_1_3_2_1_9_1","unstructured":"2024. Networking Overview. https:\/\/docs.docker.com\/engine\/network\/. (2024)."},{"key":"e_1_3_2_1_10_1","unstructured":"2025. Azure Machine Learning Documentation. https:\/\/learn.microsoft.com\/en-us\/azure\/machine-learning\/?view=azureml-api-1. (2025)."},{"key":"e_1_3_2_1_11_1","unstructured":"2025. Configuring Distributed Training for PyTorch. https:\/\/cloud.google.com\/ai-platform\/training\/docs\/distributed-pytorch. (2025)."},{"key":"e_1_3_2_1_12_1","unstructured":"2025. The Container Security Platform. https:\/\/gvisor.dev\/. (2025)."},{"key":"e_1_3_2_1_13_1","unstructured":"2025. DataParallel \u2014 PyTorch 2.7 Documentation. https:\/\/docs.pytorch.org\/docs\/stable\/generated\/torch.nn.DataParallel.html. (2025)."},{"key":"e_1_3_2_1_14_1","unstructured":"2025. DeepSeek-V3. https:\/\/github.com\/deepseek-ai\/DeepSeek-V3. (2025)."},{"key":"e_1_3_2_1_15_1","unstructured":"2025. Docker Containers for Training and Deploying Models. https:\/\/docs.aws.amazon.com\/sagemaker\/latest\/dg\/docker-containers.html. (2025)."},{"key":"e_1_3_2_1_16_1","unstructured":"2025. Environment Variables \u2014 NCCL 2.25.1 Documentation. https:\/\/docs.nvidia.com\/deeplearning\/nccl\/user-guide\/docs\/env.html#nccl-ib-timeout. (2025)."},{"key":"e_1_3_2_1_17_1","unstructured":"2025. Industry Leading Open-Source AI | Llama by Meta. https:\/\/www.llama.com\/. (2025)."},{"key":"e_1_3_2_1_18_1","unstructured":"2025. Microsoft\/Msccl: Microsoft Collective Communication Library. https:\/\/github.com\/microsoft\/msccl. (2025)."},{"key":"e_1_3_2_1_19_1","unstructured":"2025. Mixtral of Experts a High Quality Sparse Mixture-of-Experts. https:\/\/mistral.ai\/news\/mixtral-of-experts\/. (2025)."},{"key":"e_1_3_2_1_20_1","unstructured":"2025. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl. (2025)."},{"key":"e_1_3_2_1_21_1","unstructured":"2025. Openucx\/Ucc. UCX. (2025)."},{"key":"e_1_3_2_1_22_1","unstructured":"2025. Qwen3. https:\/\/github.com\/QwenLM\/Qwen3. (2025)."},{"key":"e_1_3_2_1_23_1","unstructured":"2025. Realtime Compute for Apache Flink - Alibaba Cloud. https:\/\/www.alibabacloud.com\/product\/realtime-compute. (2025)."},{"key":"e_1_3_2_1_24_1","unstructured":"2025. Simple Log Service. https:\/\/www.alibabacloud.com\/help\/en\/sls\/. (2025)."},{"key":"e_1_3_2_1_25_1","unstructured":"2025. The Speed of Containers the Security of VMs. https:\/\/katacontainers.io\/. (2025)."},{"key":"e_1_3_2_1_26_1","unstructured":"2025. TensorFlow. https:\/\/www.tensorflow.org\/. (2025)."},{"key":"e_1_3_2_1_27_1","unstructured":"2025. Torch.Profiler \u2014 PyTorch 2.7 Documentation. https:\/\/docs.pytorch.org\/docs\/stable\/profiler.html. (2025)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1977.10770"},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of USENIX NSDI. 419\u2013435","author":"Arzani Behnaz","year":"2018","unstructured":"Behnaz Arzani, Selim Ciraci, Luiz Chamon, Yibo Zhu, Hongqiang (Harry) Liu, Jitu Padhye, Boon Thau Loo, and Geoff Outhred. 2018. 007: Democratically Finding the Cause of Packet Drops. In Proc. of USENIX NSDI. 419\u2013435."},{"key":"e_1_3_2_1_30_1","volume-title":"Boon Thau Loo","author":"Arzani Behnaz","year":"2016","unstructured":"Behnaz Arzani, Selim Ciraci, Boon Thau Loo, Assaf Schuster, and Geoff Outhred. 2016. Taking the Blame Game Out of Data Centers Operations with NetPoirot. In Proc. of ACM SIGCOMM. 440\u2013453."},{"key":"e_1_3_2_1_31_1","volume-title":"Parameter Estimation and Inverse Problems","author":"Aster Richard C","unstructured":"Richard C Aster, Brian Borchers, and Clifford H Thurber. 2018. Parameter Estimation and Inverse Problems. Elsevier."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405894"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"e_1_3_2_1_34_1","volume-title":"Proc. of USENIX NSDI.","author":"B\u00fchler Tobias","year":"2023","unstructured":"Tobias B\u00fchler, Romain Jacob, Ingmar Poese, and Laurent Vanbever. 2023. Enhancing Global Network Monitoring with Magnifier. In Proc. of USENIX NSDI."},{"key":"e_1_3_2_1_35_1","volume-title":"Ports","author":"Burke Matthew","year":"2021","unstructured":"Matthew Burke, Sowmya Dharanipragada, Shannon Joyner, Adriana Szekeres, Jacob Nelson, Irene Zhang, and Dan R. K. Ports. 2021. PRISM: Rethinking the RDMA Interface for Distributed Systems. In Proc. of ACM SOSP. 228\u2013242."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523720"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731410"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672256"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Jianbo Dong Bin Luo Jun Zhang Pengcheng Zhang Fei Feng Yikai Zhu Ang Liu Zian Chen Yi Shi Hairong Jiao Gang Lu Yu Guan Ennan Zhai Wencong Xiao Hanyu Zhao Man Yuan Siran Yang Xiang Li Jiamang Wang Rui Men Jianwei Zhang Chang Zhou Dennis Cai Yuan Xie and Binzhang Fu. 2025. Enhancing Large-Scale AI Training Efficiency: The C4 Solution for Real-Time Anomaly Detection and Communication Optimization. (2025). arXiv:cs\/2406.04594 https:\/\/arxiv.org\/abs\/2406.04594","DOI":"10.1109\/HPCA61900.2025.00095"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2086696.2086719"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405851"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.fl.24.010192.002143"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"e_1_3_2_1_44_1","volume-title":"Woodall","author":"Gabriel Edgar","year":"2004","unstructured":"Edgar Gabriel, Graham E. Fagg, George Bosilca, Thara Angskun, Jack J. Dongarra, Jeffrey M. Squyres, Vishal Sahay, Prabhanjan Kambadur, Brian Barrett, Andrew Lumsdaine, Ralph H. Castain, David J. Daniel, Richard L. Graham, and Timothy S. Woodall. 2004. Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation. In Proc. of Springer PVM\/MPI. 97\u2013104."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787496"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604877"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.33.2.25"},{"key":"e_1_3_2_1_50_1","volume-title":"Proc. of USENIX NSDI. 745\u2013760","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. 2024. MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs. In Proc. of USENIX NSDI. 745\u2013760."},{"key":"e_1_3_2_1_51_1","volume-title":"Proc. of USENIX ATC. 437\u2013450","author":"Kalia Anuj","unstructured":"Anuj Kalia, Michael Kaminsky, and David G. Andersen. 2016. Design Guidelines for High Performance RDMA Systems. In Proc. of USENIX ATC. 437\u2013450."},{"key":"e_1_3_2_1_52_1","volume-title":"Proc. of USENIX NSDI. 253\u2013268","author":"Kannan Pravein Govindan","year":"2021","unstructured":"Pravein Govindan Kannan, Nishant Budhdev, Raj Joshi, and Mun Choon Chan. 2021. Debugging Transient Faults in Data Centers Using Synchronized Network-Wide Packet Histories. In Proc. of USENIX NSDI. 253\u2013268."},{"key":"e_1_3_2_1_53_1","volume-title":"Proc. of USENIX NSDI. 421\u2013436","author":"Khandelwal Anurag","year":"2019","unstructured":"Anurag Khandelwal, Rachit Agarwal, and Ion Stoica. 2019. Confluo: Distributed Monitoring and Diagnosis Stack for High-Speed Networks. In Proc. of USENIX NSDI. 421\u2013436."},{"key":"e_1_3_2_1_54_1","volume-title":"Proc. of USENIX OSDI. 243\u2013259","author":"Lin Jiaxin","year":"2020","unstructured":"Jiaxin Lin, Kiran Patel, Brent E. Stephens, Anirudh Sivaraman, and Aditya Akella. 2020. PANIC: A High-Performance Programmable NIC for Multi-Tenant Networks. In Proc. of USENIX OSDI. 243\u2013259."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604869"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672264"},{"key":"e_1_3_2_1_57_1","volume-title":"Proc. of USENIX NSDI.","author":"Liu Wei","year":"2025","unstructured":"Wei Liu, Kun Qian, Zhenhua Li, Feng Qian, Tianyin Xu, Yunhao Liu, Yu Guan, Shuhong Zhu, Hongfei Xu, Lanlan Xi, Chao Qin, and Ennan Zhai. 2025. Mitigating Scalability Walls of RDMA-based Container Networks. In Proc. of USENIX NSDI."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934906"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533727"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.53"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1573-4412(05)80005-4"},{"key":"e_1_3_2_1_63_1","volume-title":"HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs.","author":"Panda Pranoy","year":"2024","unstructured":"Pranoy Panda, Ankush Agarwal, Chaitanya Devaguptapu, Manohar Kaul, and Prathosh A P. 2024. HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs. (2024). arXiv:cs.CL\/2406.06027 https:\/\/arxiv.org\/abs\/2406.06027"},{"key":"e_1_3_2_1_64_1","volume-title":"Proc. of USENIX ATC.","author":"Peng Yanghua","year":"2017","unstructured":"Yanghua Peng, Ji Yang, and Chuan Wu. 2017. deTector: A Topology-aware Monitoring System for Data Center Networks. In Proc. of USENIX ATC."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7249172"},{"key":"e_1_3_2_1_66_1","volume-title":"Proc. of USENIX NSDI.","author":"Pfaff Ben","year":"2015","unstructured":"Ben Pfaff, Justin Pettit, Teemu Koponen, Ethan J Jackson, Andy Zhou, Jarno Rajahalme, Jesse Gross, Alex Wang, Jonathan Stringer, Pravin Shelar, Keith Amidon, and Mart\u0131n Casado. 2015. The Design and Implementation of Open vSwitch. In Proc. of USENIX NSDI."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_2_1_68_1","volume-title":"Proc. of ACM SIGKDD. 3505\u20133506","author":"Rasley Jeff","year":"2020","unstructured":"Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. 2020. Deep-Speed: System Optimizations Enable Training Deep Learning Models with Over 100 Billion Parameters. In Proc. of ACM SIGKDD. 3505\u20133506."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626310"},{"key":"e_1_3_2_1_70_1","volume-title":"Proc. of USENIX NSDI. 595\u2013612","author":"Roy Arjun","unstructured":"Arjun Roy, Hongyi Zeng, Jasmeet Bagga, and Alex C. Snoeren. 2017. Passive Realtime Datacenter Fault Detection and Localization. In Proc. of USENIX NSDI. 595\u2013612."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544222"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672221"},{"key":"e_1_3_2_1_73_1","volume-title":"Proc. of ACM HotNets. 36\u201342","author":"Stephens Brent","unstructured":"Brent Stephens, Aditya Akella, and Michael M. Swift. 2018. Your Programmable NIC Should Be a Programmable Switch. In Proc. of ACM HotNets. 36\u201342."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589069"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604847"},{"key":"e_1_3_2_1_76_1","volume-title":"Proc. of USENIX OSDI. 233\u2013248","author":"Tammana Praveen","year":"2016","unstructured":"Praveen Tammana, Rachit Agarwal, and Myungjin Lee. 2016. Simplifying Data-center Network Debugging with Pathdump. In Proc. of USENIX OSDI. 233\u2013248."},{"key":"e_1_3_2_1_77_1","volume-title":"Proc. of USENIX NSDI. 453\u2013456","author":"Tammana Praveen","year":"2018","unstructured":"Praveen Tammana, Rachit Agarwal, and Myungjin Lee. 2018. Distributed Network Monitoring and Debugging with SwitchPointer. In Proc. of USENIX NSDI. 453\u2013456."},{"key":"e_1_3_2_1_78_1","volume-title":"Proc. of USENIX NSDI. 599\u2013614","author":"Tan Cheng","year":"2019","unstructured":"Cheng Tan, Ze Jin, Chuanxiong Guo, Tianrong Zhang, Haitao Wu, Karl Deng, Dongming Bi, and Dong Xiang. 2019. NetBouncer: Active Device and Link Failure Localization in Data Center Networks. In Proc. of USENIX NSDI. 599\u2013614."},{"key":"e_1_3_2_1_79_1","volume-title":"Sequential Analysis","author":"Wald Abraham","unstructured":"Abraham Wald. 2004. Sequential Analysis. Courier Corporation."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.319"},{"key":"e_1_3_2_1_81_1","volume-title":"Proc. of USENIX NSDI. 267\u2013285","author":"Wang Weitao","year":"2022","unstructured":"Weitao Wang, Xinyu Crystal Wu, Praveen Tammana, Ang Chen, and T S Eugene Ng. 2022. Closed-Loop Network Performance Monitoring and Diagnosis with SpiderMon. In Proc. of USENIX NSDI. 267\u2013285."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1978-0468306-4"},{"key":"e_1_3_2_1_83_1","volume-title":"Proc. of USENIX NSDI. 395\u2013420","author":"Wu Yang","year":"2019","unstructured":"Yang Wu, Ang Chen, and Linh Thi Xuan Phan. 2019. Zeno: Diagnosing Performance Problems with Temporal Provenance. In Proc. of USENIX NSDI. 395\u2013420."},{"key":"e_1_3_2_1_84_1","volume-title":"Proc. of USENIX ATC. 835\u2013850","author":"Xiong Yifan","year":"2024","unstructured":"Yifan Xiong, Yuting Jiang, Ziyue Yang, Lei Qu, Guoshuai Zhao, Shuguang Liu, Dong Zhong, Boris Pinzur, Jie Zhang, Yang Wang, Jithin Jose, Hossein Pourreza, Jeff Baxter, Kushal Datta, Prabhat Ram, Luke Melton, Joe Chau, Peng Cheng, Yongqiang Xiong, and Lidong Zhou. 2024. SuperBench: Improving Cloud AI Infrastructure Reliability with Proactive Validation. In Proc. of USENIX ATC. 835\u2013850."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604850"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695977"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604837"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3406214"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787483"},{"key":"e_1_3_2_1_90_1","volume-title":"Proc. of USENIX NSDI. 761\u2013774","author":"Zu Yazhou","year":"2024","unstructured":"Yazhou Zu, Alireza Ghaffarkhah, Hoang-Vu Dang, Brian Towles, Steven Hand, Safeen Huda, Adekunle Bello, Alexander Kolbasov, Arash Rezaei, Dayou Du, Steve Lacy, Hang Wang, Aaron Wisner, Chris Lewis, and Henri Bahini. 2024. Resiliency at Scale: Managing Google's TPUv4 Machine Learning Supercomputer. In Proc. of USENIX NSDI. 761\u2013774."}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","location":"S\u00e3o Francisco Convent Coimbra Portugal","acronym":"SIGCOMM '25","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2025 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718958.3750513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:57:26Z","timestamp":1756313846000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718958.3750513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":90,"alternative-id":["10.1145\/3718958.3750513","10.1145\/3718958"],"URL":"https:\/\/doi.org\/10.1145\/3718958.3750513","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}