{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:04:01Z","timestamp":1785603841416,"version":"3.56.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T00:00:00Z","timestamp":1687564800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T00:00:00Z","timestamp":1687564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11227-023-05482-y","type":"journal-article","created":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T11:31:12Z","timestamp":1687606272000},"page":"435-462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Analyzing and predicting job failures from HPC system log"],"prefix":"10.1007","volume":"80","author":[{"given":"Ju-Won","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chul-Ho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,24]]},"reference":[{"issue":"2\u20133","key":"5482_CR1","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1002\/isaf.325","volume":"18","author":"HA Abdou","year":"2011","unstructured":"Abdou HA, Pointon J (2011) Credit scoring, statistical techniques and evaluation criteria: a review of the literature. Intell Syst Accounting Financ Manag 18(2\u20133):59\u201388","journal-title":"Intell Syst Accounting Financ Manag"},{"key":"5482_CR2","doi-asserted-by":"crossref","unstructured":"Abeyratne N, Chen HM, Oh B, et\u00a0al (2016) Checkpointing exascale memory systems with existing memory technologies. In: International Symposium on Memory Systems (MEMSYS\u201916), ACM, pp 18\u201329","DOI":"10.1145\/2989081.2989121"},{"key":"5482_CR3","doi-asserted-by":"crossref","unstructured":"Alharthi KA, Jhumka A, Di S, et\u00a0al (2022) Clairvoyant: a log-based transformer-decoder for failure prediction in large-scale systems. In: Proceedings of the 36th ACM International Conference on Supercomputing, pp 1\u201314","DOI":"10.1145\/3524059.3532374"},{"key":"5482_CR4","volume-title":"Credit scoring: the principles and practicalities","author":"M Bailey","year":"2001","unstructured":"Bailey M (2001) Credit scoring: the principles and practicalities. White Box Publishing, Bristol"},{"key":"5482_CR5","doi-asserted-by":"crossref","unstructured":"Benoit A, Le\u00a0F\u00e8vre V, Raghavan P, et\u00a0al (2020) Design and comparison of resilient scheduling heuristics for parallel jobs. In: 2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), IEEE, pp 567\u2013576","DOI":"10.1109\/IPDPSW50202.2020.00099"},{"key":"5482_CR6","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural networks for pattern recognition","author":"CM Bishop","year":"1995","unstructured":"Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford"},{"key":"5482_CR7","volume-title":"Pattern recognition and machine learning","author":"CM Bishop","year":"2006","unstructured":"Bishop CM, Nasrabadi NM (2006) Pattern recognition and machine learning. Springer, Berlin"},{"key":"5482_CR8","unstructured":"Borges G, David M, Gomes J, et\u00a0al (2007) Sun Grid Engine, a new scheduler for EGEE middleware. In: IBERGRID\u2013Iberian Grid Infrastructure Conference"},{"issue":"1","key":"5482_CR9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"key":"5482_CR10","volume-title":"The hundred-page machine learning book","author":"A Burkov","year":"2019","unstructured":"Burkov A (2019) The hundred-page machine learning book. Andriy Burkov, Quebec City"},{"key":"5482_CR11","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"key":"5482_CR12","doi-asserted-by":"crossref","unstructured":"Cirne W, Berman F (2001) A comprehensive model of the supercomputer workload. In: IEEE International Workshop on Workload Characterization, pp 140\u2013148","DOI":"10.1109\/WWC.2001.990753"},{"key":"5482_CR13","doi-asserted-by":"crossref","unstructured":"Das A, Mueller F, Rountree B (2020) Aarohi: making real-time node failure prediction feasible. In: 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, pp 1092\u20131101","DOI":"10.1109\/IPDPS47924.2020.00115"},{"key":"5482_CR14","doi-asserted-by":"crossref","unstructured":"Di S, Gupta R, Snir M, et\u00a0al (2017) Logaider: a tool for mining potential correlations of HPC log events. In: IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid\u201917), IEEE, pp 442\u2013451","DOI":"10.1109\/CCGRID.2017.18"},{"key":"5482_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-20943-2_1","volume-title":"Fault tolerance techniques for high-performance computing","author":"J Dongarra","year":"2015","unstructured":"Dongarra J, Herault T, Robert Y (2015) Fault tolerance techniques for high-performance computing. Springer, Cham, pp 3\u201385"},{"issue":"3","key":"5482_CR16","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1007\/s11227-013-0884-0","volume":"65","author":"IP Egwutuoha","year":"2013","unstructured":"Egwutuoha IP, Levy D, Selic B et al (2013) A survey of fault tolerance mechanisms and checkpoint\/restart implementations for high performance computing systems. J Supercomput 65(3):1302\u20131326","journal-title":"J Supercomput"},{"key":"5482_CR17","unstructured":"Feitelson D (2022) Parallel workloads archive and standard workload format. http:\/\/www.cs.huji.ac.il\/labs\/parallel\/workload, Accessed Nov. 25, 2022"},{"issue":"10","key":"5482_CR18","doi-asserted-by":"publisher","first-page":"2967","DOI":"10.1016\/j.jpdc.2014.06.013","volume":"74","author":"DG Feitelson","year":"2014","unstructured":"Feitelson DG, Tsafrir D, Krakov D (2014) Experience with using the parallel workloads archive. J Parallel Distrib Comput 74(10):2967\u20132982","journal-title":"J Parallel Distrib Comput"},{"key":"5482_CR19","volume-title":"An introduction to heavy-tailed and subexponential distributions. Springer series in operations research and financial engineering","author":"S Foss","year":"2013","unstructured":"Foss S, Korshunov D, Zachary S (2013) An introduction to heavy-tailed and subexponential distributions. Springer series in operations research and financial engineering, 2nd edn. Springer, New York","edition":"2"},{"key":"5482_CR20","doi-asserted-by":"crossref","unstructured":"Gainaru A, Cappello F, Snir M, et\u00a0al (2012) Fault prediction under the microscope: a closer look into HPC systems. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC\u201912), IEEE, pp 1\u201311","DOI":"10.1109\/SC.2012.57"},{"key":"5482_CR21","doi-asserted-by":"crossref","unstructured":"Gotoda S, Ito M, Shibata N (2012) Task scheduling algorithm for multicore processor system for minimizing recovery time in case of single node fault. In: IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid\u201912), IEEE, pp 260\u2013267","DOI":"10.1109\/CCGrid.2012.23"},{"key":"5482_CR22","doi-asserted-by":"crossref","unstructured":"Gupta S, Tiwari D, Jantzi C, et\u00a0al (2015) Understanding and exploiting spatial properties of system failures on extreme-scale HPC systems. In: IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN\u201915), IEEE, pp 37\u201344","DOI":"10.1109\/DSN.2015.52"},{"issue":"9","key":"5482_CR23","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263\u20131284","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"5482_CR24","doi-asserted-by":"crossref","unstructured":"Heien E, LaPine D, Kondo D, et\u00a0al (2011) Modeling and tolerating heterogeneous failures in large parallel systems. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC\u201911)","DOI":"10.1145\/2063384.2063444"},{"issue":"1","key":"5482_CR25","first-page":"3905","volume":"16","author":"T Hothorn","year":"2015","unstructured":"Hothorn T, Zeileis A (2015) partykit: a modular toolkit for recursive partytioning in R. J Mach Learn Res 16(1):3905\u20133909","journal-title":"J Mach Learn Res"},{"issue":"4","key":"5482_CR26","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1109\/TNSM.2020.3034647","volume":"17","author":"S Huang","year":"2020","unstructured":"Huang S, Liu Y, Fung C et al (2020) Hitanomaly: hierarchical transformers for anomaly detection in system log. IEEE Trans Netw Serv Manage 17(4):2064\u20132076","journal-title":"IEEE Trans Netw Serv Manage"},{"key":"5482_CR27","doi-asserted-by":"crossref","unstructured":"Jin H, Ke T, Chen Y, et\u00a0al (2012) Checkpointing orchestration: toward a scalable HPC fault-tolerant environment. In: IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid\u201912), IEEE, pp 276\u2013283","DOI":"10.1109\/CCGrid.2012.61"},{"key":"5482_CR28","volume-title":"Stochastic ageing and dependence for reliability","author":"CD Lai","year":"2006","unstructured":"Lai CD, Xie M, Barlow RE (2006) Stochastic ageing and dependence for reliability. Springer-Verlag, New York"},{"issue":"5","key":"5482_CR29","doi-asserted-by":"publisher","first-page":"4582","DOI":"10.1007\/s11227-020-03445-1","volume":"77","author":"B Le\u00f3n","year":"2021","unstructured":"Le\u00f3n B, Franco D, Rexachs D et al (2021) Analysis of parallel application checkpoint storage for system configuration. J Supercomput 77(5):4582\u20134617","journal-title":"J Supercomput"},{"issue":"13","key":"5482_CR30","doi-asserted-by":"publisher","first-page":"15404","DOI":"10.1007\/s11227-022-04482-8","volume":"78","author":"B Le\u00f3n","year":"2022","unstructured":"Le\u00f3n B, M\u00e9ndez S, Franco D et al (2022) A model of checkpoint behavior for applications that have i\/o. J Supercomput 78(13):15404\u201315436","journal-title":"J Supercomput"},{"key":"5482_CR31","doi-asserted-by":"crossref","unstructured":"Li H, Groep D, Wolters L (2004) Workload characteristics of a multi-cluster supercomputer. In: Workshop on Job Scheduling Strategies for Parallel Processing, pp 176\u2013193","DOI":"10.1007\/11407522_10"},{"key":"5482_CR32","doi-asserted-by":"crossref","unstructured":"Li H, Groep D, Wolters L, et\u00a0al (2006) Job failure analysis and its implications in a large-scale production grid. In: IEEE International Conference on E-Science and Grid Computing (E-Science\u201906), IEEE, pp 27\u201327","DOI":"10.1109\/E-SCIENCE.2006.261111"},{"issue":"1","key":"5482_CR33","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1002\/widm.8","volume":"1","author":"WY Loh","year":"2011","unstructured":"Loh WY (2011) Classification and regression trees. Wiley Interdiscip Rev Data Min Knowl Discov 1(1):14\u201323","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"issue":"2","key":"5482_CR34","doi-asserted-by":"publisher","first-page":"1870","DOI":"10.1109\/TNSM.2021.3055425","volume":"18","author":"W Meng","year":"2021","unstructured":"Meng W, Liu Y, Zhang S et al (2021) Logclass: anomalous log identification and classification with partial labels. IEEE Trans Netw Serv Manage 18(2):1870\u20131884","journal-title":"IEEE Trans Netw Serv Manage"},{"issue":"4","key":"5482_CR35","doi-asserted-by":"publisher","first-page":"1762","DOI":"10.1016\/j.eswa.2007.08.070","volume":"35","author":"JH Min","year":"2008","unstructured":"Min JH, Lee YC (2008) A practical approach to credit scoring. Expert Syst Appl 35(4):1762\u20131770","journal-title":"Expert Syst Appl"},{"key":"5482_CR36","doi-asserted-by":"crossref","unstructured":"Naksinehaboon N, Liu Y, Leangsuksun C, et\u00a0al (2008) Reliability-aware approach: An incremental checkpoint\/restart model in HPC environments. In: IEEE\/ACM International Symposium on Cluster Computing and the Grid (CCGrid\u201908), IEEE, pp 783\u2013788","DOI":"10.1109\/CCGRID.2008.109"},{"issue":"2","key":"5482_CR37","doi-asserted-by":"publisher","first-page":"3028","DOI":"10.1016\/j.eswa.2008.01.018","volume":"36","author":"L Nanni","year":"2009","unstructured":"Nanni L, Lumini A (2009) An experimental comparison of ensemble of classifiers for bankruptcy prediction and credit scoring. Expert Syst Appl 36(2):3028\u20133033","journal-title":"Expert Syst Appl"},{"key":"5482_CR38","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1016\/j.apenergy.2013.08.061","volume":"113","author":"AT Nguyen","year":"2014","unstructured":"Nguyen AT, Reiter S, Rigo P (2014) A review on simulation-based optimization methods applied to building performance analysis. Appl Energy 113:1043\u20131058","journal-title":"Appl Energy"},{"key":"5482_CR39","doi-asserted-by":"crossref","unstructured":"Oliner A, Stearley J (2007) What supercomputers say: a study of five system logs. In: IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN\u201907), pp 575\u2013584","DOI":"10.1109\/DSN.2007.103"},{"key":"5482_CR40","doi-asserted-by":"crossref","unstructured":"Parasyris K, Keller K, Bautista-Gomez L, et\u00a0al (2020) Checkpoint restart support for heterogeneous hpc applications. In: 20th IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID), pp 242\u2013251","DOI":"10.1109\/CCGrid49817.2020.00-69"},{"key":"5482_CR41","doi-asserted-by":"crossref","unstructured":"Park JW (2019) Queue waiting time prediction for large-scale high-performance computing system. In: 2019 International Conference on High Performance Computing & Simulation (HPCS), IEEE, pp 850\u2013855","DOI":"10.1109\/HPCS48598.2019.9188119"},{"issue":"11","key":"5482_CR42","doi-asserted-by":"publisher","first-page":"4635","DOI":"10.1007\/s11227-017-2038-2","volume":"73","author":"JW Park","year":"2017","unstructured":"Park JW, Kim E (2017) Runtime prediction of parallel applications with workload-aware clustering. J Supercomput 73(11):4635\u20134651","journal-title":"J Supercomput"},{"key":"5482_CR43","doi-asserted-by":"crossref","unstructured":"Park JW, Kim E (2018) Exploiting the behavior of the failed job in high performance computing system. In: 2018 18th International Conference on Computational Science and Applications (ICCSA), IEEE, pp 1\u20133","DOI":"10.1109\/ICCSA.2018.8439570"},{"key":"5482_CR44","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"5482_CR45","doi-asserted-by":"crossref","unstructured":"Rodrigo\u00a0\u00c1lvarez GP, \u00d6stberg PO, Elmroth E, et\u00a0al (2015) HPC system lifetime story: Workload characterization and evolutionary analyses on NERSC systems. In: ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC\u201915), pp 57\u201360","DOI":"10.1145\/2749246.2749270"},{"key":"5482_CR46","unstructured":"Roux NL, Schmidt M, Bach F (2012) A stochastic gradient method with an exponential convergence rate for finite training sets. In: NIPS\u201912 - 26th Annual Conference on Neural Information Processing Systems"},{"issue":"1","key":"5482_CR47","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MSPEC.2022.9676353","volume":"59","author":"D Schneider","year":"2022","unstructured":"Schneider D (2022) The exascale era is upon us: the frontier supercomputer may be the first to reach 1,000,000,000,000,000,000 operations per second. IEEE Spectr 59(1):34\u201335","journal-title":"IEEE Spectr"},{"issue":"4","key":"5482_CR48","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/TDSC.2009.4","volume":"7","author":"B Schroeder","year":"2010","unstructured":"Schroeder B, Gibson G (2010) A large-scale study of failures in high-performance computing systems. IEEE Trans Depend Secur Comput 7(4):337\u2013350","journal-title":"IEEE Trans Depend Secur Comput"},{"key":"5482_CR49","doi-asserted-by":"crossref","unstructured":"Tiwari D, Gupta S, Vazhkudai SS (2014) Lazy checkpointing: Exploiting temporal locality in failures to mitigate checkpointing overheads on extreme-scale systems. In: Proceedings of IEEE\/IFIP DSN, pp 25\u201336","DOI":"10.1109\/DSN.2014.101"},{"key":"5482_CR50","doi-asserted-by":"crossref","unstructured":"Wu M, Sun XH, Jin H (2007) Performance under failures of high-end computing. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC\u201907), ACM, p\u00a048","DOI":"10.1145\/1362622.1362687"},{"key":"5482_CR51","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1007\/978-3-662-45402-2_144","volume-title":"Computer science and its applications","author":"J Yoon","year":"2015","unstructured":"Yoon J, Hong T, Park C et al (2015) Stable HPC cluster management scheme through performance evaluation. In: Park JJJH, Stojmenovic I, Jeong HY et al (eds) Computer science and its applications. Springer, Berlin, pp 1017\u20131023"},{"key":"5482_CR52","doi-asserted-by":"crossref","unstructured":"You H, Zhang H (2012) Comprehensive workload analysis and modeling of a petascale supercomputer. In: Workshop on Job Scheduling Strategies for Parallel Processing, pp 253\u2013271","DOI":"10.1007\/978-3-642-35867-8_14"},{"issue":"2","key":"5482_CR53","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.camwa.2011.07.040","volume":"63","author":"Y Yuan","year":"2012","unstructured":"Yuan Y, Wu Y, Wang Q et al (2012) Job failures in high performance computing systems: a large-scale empirical study. Comput Math Appl 63(2):365\u2013377","journal-title":"Comput Math Appl"},{"key":"5482_CR54","doi-asserted-by":"crossref","unstructured":"Zheng Z, Yu L, Tang W, et\u00a0al (2011) Co-analysis of RAS log and job log on Blue Gene\/P. In: IEEE International Parallel & Distributed Processing Symposium (IPDPS\u201911), pp 840\u2013851","DOI":"10.1109\/IPDPS.2011.83"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05482-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05482-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05482-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T11:22:47Z","timestamp":1704712967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05482-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,24]]},"references-count":54,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["5482"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05482-y","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,24]]},"assertion":[{"value":"6 June 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}