{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T09:03:21Z","timestamp":1784624601485,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"State Key Laboratory Of Networking And Switching Technology","award":["NST20250519"],"award-info":[{"award-number":["NST20250519"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,6]]},"DOI":"10.1145\/3820441.3820449","type":"proceedings-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T08:11:31Z","timestamp":1784621491000},"page":"51-58","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Argus: Scalable and Deterministic Network Fault Localization for AI Training Clusters"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0276-4538","authenticated-orcid":false,"given":"Yuxiang","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5614-3420","authenticated-orcid":false,"given":"Jiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3167-2413","authenticated-orcid":false,"given":"Xianyu","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0306-8430","authenticated-orcid":false,"given":"Yubo","family":"Ruan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1801-5704","authenticated-orcid":false,"given":"Yuxuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4441-3998","authenticated-orcid":false,"given":"Yingjie","family":"Duan","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8530-5259","authenticated-orcid":false,"given":"Shoushou","family":"Ren","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3215-888X","authenticated-orcid":false,"given":"Xianjun","family":"He","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4368-7751","authenticated-orcid":false,"given":"Junlong","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2068-5315","authenticated-orcid":false,"given":"Yuan","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3545-1122","authenticated-orcid":false,"given":"Tao","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"e_1_3_3_2_2_2","first-page":"419","volume-title":"15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Arzani Behnaz","year":"2018","unstructured":"Behnaz Arzani, Selim Ciraci, Luiz Chamon, Yibo Zhu, Hongqiang\u00a0Harry Liu, Jitu Padhye, Boon\u00a0Thau Loo, and Geoff Outhred. 2018. 007: Democratically finding the cause of packet drops. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). 419\u2013435."},{"key":"e_1_3_3_2_3_2","unstructured":"Broadcom SDK Contributors. 2018. Tomahawk Hash Implementation (hash.c). https:\/\/github.com\/jarsy\/bcm-sdk\/blob\/master\/src\/soc\/esw\/tomahawk\/hash.c. Accessed: 2026-03-04."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672256"},{"key":"e_1_3_3_2_5_2","first-page":"865","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Dong Jianbo","year":"2025","unstructured":"Jianbo Dong, Kun Qian, Pengcheng Zhang, Zhilong Zheng, Liang Chen, Fei Feng, Yichi Xu, Yikai Zhu, Gang Lu, Xue Li, et\u00a0al. 2025. Evolution of Aegis: Fault Diagnosis for { AI} Model Training Service in Production. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). 865\u2013881."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787496"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750515"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Vipul Harsh Tong Meng Kapil Agrawal and Philip\u00a0Brighten Godfrey. 2023. Flock: Accurate network fault localization at scale. Proceedings of the ACM on Networking 1 CoNEXT1 (2023) 1\u201322.","DOI":"10.1145\/3595289"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405877"},{"key":"e_1_3_3_2_11_2","unstructured":"Huawei. 2025. ns-3-ub: UnifiedBus Network Simulation Framework. https:\/\/gitcode.com\/open-usim\/ns-3-ub. Accessed: 2026-03-04."},{"key":"e_1_3_3_2_12_2","first-page":"745","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","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, et\u00a0al. 2024. { MegaScale} : Scaling large language model training to more than 10,000 { GPUs}. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 745\u2013760."},{"key":"e_1_3_3_2_13_2","first-page":"253","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Kannan Pravein\u00a0Govindan","year":"2021","unstructured":"Pravein\u00a0Govindan Kannan, Nishant Budhdev, Raj Joshi, and Mun\u00a0Choon Chan. 2021. Debugging transient faults in data centers using synchronized network-wide packet histories. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 253\u2013268."},{"key":"e_1_3_3_2_14_2","first-page":"287","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Kong Xinhao","year":"2022","unstructured":"Xinhao Kong, Yibo Zhu, Huaping Zhou, Zhuo Jiang, Jianxi Ye, Chuanxiong Guo, and Danyang Zhuo. 2022. Collie: Finding performance anomalies in { RDMA} subsystems. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 287\u2013305."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604827"},{"key":"e_1_3_3_2_16_2","first-page":"931","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li Qiang","year":"2023","unstructured":"Qiang Li, Yixiao Gao, Xiaoliang Wang, Haonan Qiu, Yanfang Le, Derui Liu, Qiao Xiang, Fei Feng, Peng Zhang, Bo Li, et\u00a0al. 2023. Flor: An open high performance { RDMA} framework over heterogeneous { RNICs}. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 931\u2013948."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672264"},{"key":"e_1_3_3_2_18_2","first-page":"15","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Liu Kefei","year":"2023","unstructured":"Kefei Liu, Zhuo Jiang, Jiao Zhang, Haoran Wei, Xiaolong Zhong, Lizhuang Tan, Tian Pan, and Tao Huang. 2023. Hostping: Diagnosing intra-host network bottlenecks in { RDMA} servers. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 15\u201329."},{"key":"e_1_3_3_2_19_2","first-page":"379","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Liu Kexin","year":"2025","unstructured":"Kexin Liu, Zhaochen Zhang, Chang Liu, Yizhi Wang, Vamsi Addanki, Stefan Schmid, Qingyue Wang, Wei Chen, Xiaoliang Wang, Jiaqi Zheng, et\u00a0al. 2025. Pyrrha:{ Congestion-Root-Based} Flow Control to Eliminate { Head-of-Line} Blocking in Datacenter. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). 379\u2013405."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230557"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_3_2_22_2","unstructured":"ns-3 Consortium. 2025. ns-3 Network Simulator. https:\/\/www.nsnam.org\/. Accessed: 2026-03-04."},{"key":"e_1_3_3_2_23_2","unstructured":"Paris Traceroute Team. n. d.. Paris Traceroute. https:\/\/paris-traceroute.net\/. Accessed: 2026-03-04."},{"key":"e_1_3_3_2_24_2","first-page":"55","volume-title":"2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Peng Yanghua","year":"2017","unstructured":"Yanghua Peng, Ji Yang, Chuan Wu, Chuanxiong Guo, Chengchen Hu, and Zongpeng Li. 2017. { deTector} : a topology-aware monitoring system for data center networks. In 2017 USENIX Annual Technical Conference (USENIX ATC 17). 55\u201368."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_3_2_26_2","first-page":"599","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","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 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). 599\u2013614."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750490"},{"key":"e_1_3_3_2_28_2","first-page":"267","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Wang Weitao","year":"2022","unstructured":"Weitao Wang, Xinyu\u00a0Crystal Wu, Praveen Tammana, Ang Chen, and TS\u00a0Eugene Ng. 2022. Closed-loop network performance monitoring and diagnosis with { SpiderMon}. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 267\u2013285."},{"key":"e_1_3_3_2_29_2","first-page":"855","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Zhang Zhehui","year":"2021","unstructured":"Zhehui Zhang, Haiyang Zheng, Jiayao Hu, Xiangning Yu, Chenchen Qi, Xuemei Shi, and Guohui Wang. 2021. Hashing linearity enables relative path control in data centers. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). 855\u2013862."},{"key":"e_1_3_3_2_30_2","first-page":"559","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric\u00a0P Xing, et\u00a0al. 2022. Alpa: Automating inter-and { Intra-Operator} parallelism for distributed deep learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 559\u2013578."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3406214"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Yibo Zhu Haggai Eran Daniel Firestone Chuanxiong Guo Marina Lipshteyn Yehonatan Liron Jitendra Padhye Shachar Raindel Mohamad\u00a0Haj Yahia and Ming Zhang. 2015. Congestion control for large-scale RDMA deployments. ACM SIGCOMM Computer Communication Review 45 4 (2015) 523\u2013536.","DOI":"10.1145\/2829988.2787484"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787483"}],"event":{"name":"APNet 2026: The 10th Asia-Pacific Workshop on Networking","location":"Singapore Singapore","acronym":"APNet '26"},"container-title":["Proceedings of the 10th Asia-Pacific Workshop on Networking"],"original-title":[],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T08:17:19Z","timestamp":1784621839000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3820441.3820449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":32,"alternative-id":["10.1145\/3820441.3820449","10.1145\/3820441"],"URL":"https:\/\/doi.org\/10.1145\/3820441.3820449","relation":{},"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"2026-08-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}