{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:15:47Z","timestamp":1768029347985,"version":"3.49.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2019,2,1]]},"DOI":"10.1109\/tpds.2018.2864184","type":"journal-article","created":{"date-parts":[[2018,8,14]],"date-time":"2018-08-14T18:30:58Z","timestamp":1534271458000},"page":"361-374","source":"Crossref","is-referenced-by-count":16,"title":["Exploring Properties and Correlations of Fatal Events in a Large-Scale HPC System"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9935-5674","authenticated-orcid":false,"given":"Sheng","family":"Di","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7776-1834","authenticated-orcid":false,"given":"Hanqi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rinku","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric R.","family":"Pershey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3504-2468","authenticated-orcid":false,"given":"Marc","family":"Snir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franck","family":"Cappello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2014.101"},{"key":"ref33","year":"2004"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/584792.584890"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SocialCom.2010.50"},{"key":"ref30","author":"reynolds","year":"1977","journal-title":"The Analysis of Cross-Classifications"},{"key":"ref37","first-page":"1","article-title":"Disk failures in the real world: What Does an MTTF of 1,000,000 hours mean to You?","author":"schroeder","year":"2007","journal-title":"Proc 5th USENIX Conf File Storage Technol"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2002.1172890"},{"key":"ref35","year":"0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2009.4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2150989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DFT.2017.8244428"},{"key":"ref12","first-page":"1","article-title":"Feng Shui of supercomputer memory positional effects in DRAM and SRAM faults","author":"sridharan","year":"2013","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694348"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2011.07.040"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2007.18"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.83"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1016\/j.jpdc.2013.04.002","article-title":"The failure trace archive: Enabling the comparison of failure measurements and models of distributed systems","volume":"73","author":"javadi","year":"2013","journal-title":"J Parallel Distrib Comput"},{"key":"ref18","year":"0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056044"},{"key":"ref28","author":"kingman","year":"1993","journal-title":"Poisson Processes (Oxford Studies in Probability)"},{"key":"ref4","article-title":"IBM system blue gene solution: Blue gene\/Q system administration","author":"lakner","year":"2013"},{"key":"ref27","year":"0"},{"key":"ref3","year":"0"},{"key":"ref6","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370635"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2017.18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807666"},{"key":"ref7","year":"0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014522573"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.36"},{"key":"ref1","article-title":"3,000-processor supercomputer can only match 1percent of your brain","author":"feinberg","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.52"},{"key":"ref22","year":"0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.50"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126937"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2017.12"},{"key":"ref26","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-018-1806-7"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/71\/8613032\/8436427-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8613032\/08436427.pdf?arnumber=8436427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:43:49Z","timestamp":1657745029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8436427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,1]]},"references-count":38,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2018.2864184","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,1]]}}}