{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:38Z","timestamp":1786120838156,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818373","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"7773-7784","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Don't Predict, Prioritize: Rethinking GPU Reliability Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0364-1681","authenticated-orcid":false,"given":"Difeng","family":"Ma","sequence":"first","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9288-4787","authenticated-orcid":false,"given":"Changhua","family":"Pei","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2554-6490","authenticated-orcid":false,"given":"Yuanwei","family":"Lu","sequence":"additional","affiliation":[{"name":"Stepfun, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3961-8877","authenticated-orcid":false,"given":"Quan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8534-4909","authenticated-orcid":false,"given":"Zexin","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9113-2660","authenticated-orcid":false,"given":"Yibo","family":"Zhu","sequence":"additional","affiliation":[{"name":"StepFun, Shaihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-5806","authenticated-orcid":false,"given":"Daxin","family":"Jiang","sequence":"additional","affiliation":[{"name":"StepFun, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5113-838X","authenticated-orcid":false,"given":"Dan","family":"Pei","sequence":"additional","affiliation":[{"name":"Computer Science Department, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0146-7257","authenticated-orcid":false,"given":"Jingjing","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4964-1135","authenticated-orcid":false,"given":"Gaogang","family":"Xie","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The Kendall rank correlation coefficient. Encyclopedia of measurement and statistics 2","author":"Abdi Herv\u00e9","year":"2007","unstructured":"Herv\u00e9 Abdi. 2007. The Kendall rank correlation coefficient. Encyclopedia of measurement and statistics 2 (2007), 508-510."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118445112.stat01100"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102363"},{"key":"e_1_3_2_1_4_1","first-page":"23","article-title":"From ranknet to lambdarank to lambdamart: An overview","volume":"11","author":"Burges Christopher JC","year":"2010","unstructured":"Christopher JC Burges. 2010. From ranknet to lambdarank to lambdamart: An overview. Learning 11, 23-581 (2010), 81.","journal-title":"Learning"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Y Chiang and Y Ouyang. 2014. Profit Optimization in SLA-Aware Cloud Services with a Finite Capacity Queuing Model Mathematical Problems in Engineering. (2014).","DOI":"10.1155\/2014\/534510"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00089"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1972.tb00899.x"},{"key":"e_1_3_2_1_9_1","unstructured":"Shengkun Cui Archit Patke Ziheng Chen Aditya Ranjan Hung Nguyen Phuong Cao Saurabh Jha Brett Bode Gregory Bauer Chandra Narayanaswami et al. 2025. Characterizing GPU Resilience and Impact on AI\/HPC Systems. arXiv preprint arXiv:2503.11901 (2025)."},{"key":"e_1_3_2_1_10_1","first-page":"505","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Deng Yangtao","year":"2025","unstructured":"Yangtao Deng, Xiang Shi, Zhuo Jiang, Xingjian Zhang, Lei Zhang, Zhang Zhang, Bo Li, Zuquan Song, Hang Zhu, Gaohong Liu, et al. 2025. Minder: Faulty machine detection for large-scale distributed model training. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). 505-521."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2022.3141341"},{"key":"e_1_3_2_1_12_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_13_1","first-page":"298","article-title":"GPU Reliability in AI Clusters: A Study of Failure Modes and Effects","volume":"4","author":"Gupta Sameeksha","year":"2025","unstructured":"Sameeksha Gupta. 2025. GPU Reliability in AI Clusters: A Study of Failure Modes and Effects. Journal Of Engineering And Computer Sciences 4, 6 (2025), 298-306.","journal-title":"Journal Of Engineering And Computer Sciences"},{"key":"e_1_3_2_1_14_1","first-page":"202","volume-title":"ICML","volume":"1","author":"Hamerly Greg","year":"2001","unstructured":"Greg Hamerly, Charles Elkan, et al. 2001. Bayesian approaches to failure prediction for disk drives. In ICML, Vol. 1. Citeseer, 202-209."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Hemant Ishwaran Udaya B Kogalur Eugene H Blackstone and Michael S Lauer. 2008. Random survival forests. (2008).","DOI":"10.1214\/08-AOAS169"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00096"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2016.019"},{"key":"e_1_3_2_1_18_1","unstructured":"G Ke LightGBM. 2017. A Highly Efficient Gradient Boosting Decision Tree. Garnett IGaUVLaSBaHWaRFaSVaR editor (2017)."},{"key":"e_1_3_2_1_19_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579370.3594777"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2013.01.012"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Tie-Yan Liu et al. 2009. Learning to rank for information retrieval. Foundations and Trends\u00ae in Information Retrieval 3 3 (2009) 225-331.","DOI":"10.1561\/1500000016"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2996747"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-S58398.2023.00020"},{"key":"e_1_3_2_1_25_1","volume-title":"Adaptive On-Line Discrete Degradation State Distribution Prediction Methodology for Cloud Computing Optical Fiber Ports","author":"Mou Yujie","year":"2025","unstructured":"Yujie Mou, Dong Wang, Jie Liu, Wang Shi, Shiyu Hu, and Ming Lu. 2025. Adaptive On-Line Discrete Degradation State Distribution Prediction Methodology for Cloud Computing Optical Fiber Ports. IEEE Transactions on Instrumentation and Measurement (2025)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2018.00022"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539196"},{"key":"e_1_3_2_1_28_1","unstructured":"NVIDIA. [n.d.]. NVIDIA Certified PCIe Configuration Guide. https:\/\/docs.nvidia.com\/certification-programs\/pdf\/nvidia-certified-configuration-guide.pdf Accessed: 2025-07-18."},{"key":"e_1_3_2_1_29_1","unstructured":"NVIDIA. [n.d.]. NVIDIA NVLink and NVSwitch Overview. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/ Accessed: 2025-07-18."},{"key":"e_1_3_2_1_30_1","unstructured":"NVIDIA. 2023. Understanding Xid Errors. https:\/\/docs.nvidia.com\/deploy\/xid-errors\/. Accessed: 2025-07-18."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656615"},{"key":"e_1_3_2_1_32_1","first-page":"17","article-title":"Failure Trends in a Large Disk Drive Population","volume":"7","author":"Pinheiro Eduardo","year":"2007","unstructured":"Eduardo Pinheiro, Wolf-Dietrich Weber, and Luiz Andr\u00e9 Barroso. 2007. Failure Trends in a Large Disk Drive Population. In Fast, Vol. 7. 17-23.","journal-title":"Fast"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786763.2694348"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676151.3719353"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317918"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2021.03.229"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-W.2017.20"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225106"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:12:26Z","timestamp":1786065146000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818373"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":38,"alternative-id":["10.1145\/3770855.3818373","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818373","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}