{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:38:47Z","timestamp":1783784327780,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T00:00:00Z","timestamp":1681516800000},"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":[[2023,4,15]]},"DOI":"10.1145\/3578245.3584726","type":"proceedings-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T22:14:44Z","timestamp":1680560084000},"page":"263-268","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["How Do ML Jobs Fail in Datacenters? Analysis of a Long-Term Dataset from an HPC Cluster"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0353-7968","authenticated-orcid":false,"given":"Xiaoyu","family":"Chu","sequence":"first","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3461-4919","authenticated-orcid":false,"given":"Sacheendra","family":"Talluri","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6999-7297","authenticated-orcid":false,"given":"Laurens","family":"Versluis","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2014.34"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.317"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2019.00081"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2018.00021"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126937"},{"key":"e_1_3_2_1_6_1","unstructured":"LLC LANS. [n. d.]. Operational data to support and enable computer science research."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"e_1_3_2_1_8_1","volume-title":"Google cluster-usage traces: format schema","author":"Reiss Charles","year":"2011","unstructured":"Charles Reiss, John Wilkes, and Joseph L Hellerstein. 2011. Google cluster-usage traces: format schema. Google Inc., White Paper, Vol. 1 (2011)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2015.139"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.37"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2016.2543718"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2009.4"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/GRID.2010.5697961"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2011.07.040"}],"event":{"name":"ICPE '23: ACM\/SPEC International Conference on Performance Engineering","location":"Coimbra Portugal","acronym":"ICPE '23","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Companion of the 2023 ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578245.3584726","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578245.3584726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:20Z","timestamp":1750182560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578245.3584726"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,15]]},"references-count":14,"alternative-id":["10.1145\/3578245.3584726","10.1145\/3578245"],"URL":"https:\/\/doi.org\/10.1145\/3578245.3584726","relation":{},"subject":[],"published":{"date-parts":[[2023,4,15]]},"assertion":[{"value":"2023-04-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}