{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:08:27Z","timestamp":1777486107038,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,5]]},"DOI":"10.1145\/3680256.3721320","type":"proceedings-article","created":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T01:00:58Z","timestamp":1746234058000},"page":"187-194","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["FAILS: A Framework for Automated Collection and Analysis of LLM Service Incidents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7285-1574","authenticated-orcid":false,"given":"S\u00e1ndor","family":"Battaglini-Fischer","sequence":"first","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8076-5755","authenticated-orcid":false,"given":"Nishanthi","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7696-2525","authenticated-orcid":false,"given":"B\u00e1lint L\u00e1szl\u00f3","family":"Szarvas","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0353-7968","authenticated-orcid":false,"given":"Xiaoyu","family":"Chu","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8030-9398","authenticated-orcid":false,"given":"Alexandru","family":"Iosup","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"AlertSite Software as a Service - Everbridge at SmartBear Connect. https:\/\/smartbear.com\/product\/alertsite (Accessed 14","year":"2025","unstructured":"2018. AlertSite Software as a Service - Everbridge at SmartBear Connect. https:\/\/smartbear.com\/product\/alertsite (Accessed 14. Jan. 2025)."},{"key":"e_1_3_2_1_2_1","volume-title":"https:\/\/www.pingdom.com (Accessed 14","year":"2025","unstructured":"2024. Pingdom. https:\/\/www.pingdom.com (Accessed 14. Jan. 2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"UptimeRobot: Free Website Monitoring Service. https:\/\/uptimerobot.com (Accessed 14","year":"2025","unstructured":"2024. UptimeRobot: Free Website Monitoring Service. https:\/\/uptimerobot.com (Accessed 14. Jan. 2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"https:\/\/www.selenium.dev\/about (Accessed 14","author":"Selenium About","year":"2025","unstructured":"2025. About Selenium. https:\/\/www.selenium.dev\/about (Accessed 14. Jan. 2025)."},{"key":"e_1_3_2_1_5_1","volume-title":"https:\/\/status.anthropic.com (Accessed 13","author":"Status Anthropic","year":"2025","unstructured":"2025. Anthropic Status. https:\/\/status.anthropic.com (Accessed 13. Jan. 2025)."},{"key":"e_1_3_2_1_6_1","volume-title":"Character AI Status Status. https:\/\/status.character.ai (Accessed 13","year":"2025","unstructured":"2025. Character AI Status Status. https:\/\/status.character.ai (Accessed 13. Jan. 2025)."},{"key":"e_1_3_2_1_7_1","volume-title":"https:\/\/downdetector.com (Accessed 14","year":"2025","unstructured":"2025. Downdetector. https:\/\/downdetector.com (Accessed 14. Jan. 2025)."},{"key":"e_1_3_2_1_8_1","volume-title":"https:\/\/status.openai.com (Accessed 13","author":"Status AI","year":"2025","unstructured":"2025. OpenAI Status. https:\/\/status.openai.com (Accessed 13. Jan. 2025)."},{"key":"e_1_3_2_1_9_1","volume-title":"React Data Grid component - MUI X. https:\/\/mui.com\/x\/react-data-grid\/'srsltid=AfmBOoozaD7Vh9WjEftiJHA_6H7zcC6IxiDtbtqjVAlI_JDkBaDBdTsi (Accessed 13","year":"2025","unstructured":"2025. React Data Grid component - MUI X. https:\/\/mui.com\/x\/react-data-grid\/'srsltid=AfmBOoozaD7Vh9WjEftiJHA_6H7zcC6IxiDtbtqjVAlI_JDkBaDBdTsi (Accessed 13. Jan. 2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"Stability AI Platform - Status. https:\/\/stabilityai.instatus.com (Accessed 13","year":"2025","unstructured":"2025. Stability AI Platform - Status. https:\/\/stabilityai.instatus.com (Accessed 13. Jan. 2025)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.31098\/ijmadic.v1i2.1872"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2004.2"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.12237"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/HONET63146.2024.10822885"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS63350.2024.00097"},{"key":"e_1_3_2_1_16_1","unstructured":"Xiaoyu Chu Sacheendra Talluri Qingxian Lu and Alexandru Iosup. 2025. An Empirical Characterization of Outages and Incidents in Public Services for Large Language Models. arXiv:2501.12469 [cs.PF] https:\/\/arxiv.org\/abs\/2501.12469"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578245.3584726"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2019.00055"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.78"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126937"},{"key":"e_1_3_2_1_21_1","volume-title":"Characterization of Large Language Model Development in the Datacenter. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Hu Qinghao","year":"2024","unstructured":"Qinghao Hu, Zhisheng Ye, Zerui Wang, Guoteng Wang, Meng Zhang, Qiaoling Chen, Peng Sun, Dahua Lin, Xiaolin Wang, Yingwei Luo, Yonggang Wen, and Tianwei Zhang. 2024. Characterization of Large Language Model Development in the Datacenter. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 709--729. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/hu"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100660"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.02425"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.32628\/CSEIT241051057"},{"key":"e_1_3_2_1_25_1","unstructured":"@OpenAI. 2024. OpenAI's post on X apologizing for downtime. https:\/\/x.com\/OpenAI\/status\/1867000372826607627. Accessed: 2025-01--15."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05482-y"},{"key":"e_1_3_2_1_27_1","unstructured":"New Relic. 2023. Observability Report. https:\/\/newrelic.com\/resources\/report\/observability-forecast\/2023\/about-this-report. Accessed: 2025-01--15."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSOS52086.2021.00039"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.17644"},{"key":"e_1_3_2_1_30_1","volume-title":"A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382","author":"White Jules","year":"2023","unstructured":"Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C Schmidt. 2023. A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.06684"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Nezih Yigitbasi Matthieu Gallet Derrick Kondo Alexandru Iosup and D. Epema. 2010. Analysis and Modeling of Time-Correlated Failures in Large-Scale Distributed Systems. Telecommunications Policy - TELECOMMUN POLICY (Oct. 2010) 65--72. doi:10.1109\/GRID.2010.5697961","DOI":"10.1109\/GRID.2010.5697961"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.00125"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.16038"}],"event":{"name":"ICPE '25: 16th ACM\/SPEC International Conference on Performance Engineering","location":"Toronto ON Canada","acronym":"ICPE '25","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Companion of the 16th ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680256.3721320","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680256.3721320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T23:49:11Z","timestamp":1755906551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680256.3721320"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,5]]},"references-count":34,"alternative-id":["10.1145\/3680256.3721320","10.1145\/3680256"],"URL":"https:\/\/doi.org\/10.1145\/3680256.3721320","relation":{},"subject":[],"published":{"date-parts":[[2025,5,5]]},"assertion":[{"value":"2025-05-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}