{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T21:10:01Z","timestamp":1748725801502,"version":"3.41.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319273075"},{"type":"electronic","value":"9783319273082"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-27308-2_54","type":"book-chapter","created":{"date-parts":[[2015,12,17]],"date-time":"2015-12-17T13:29:53Z","timestamp":1450358993000},"page":"669-681","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Canaries in a Coal Mine: Using Application-Level Checkpoints to Detect Memory Failures"],"prefix":"10.1007","author":[{"given":"Patrick M.","family":"Widener","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurt B.","family":"Ferreira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathan","family":"Fabian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,12,18]]},"reference":[{"issue":"13","key":"54_CR1","doi-asserted-by":"publisher","first-page":"136403","DOI":"10.1103\/PhysRevLett.104.136403","volume":"104","author":"A Bart\u00f3k","year":"2010","unstructured":"Bart\u00f3k, A., Payne, M., Kondor, R., Cs\u00e1nyi, G.: Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. Phys. Rev. Lett. 104(13), 136403 (2010)","journal-title":"Phys. Rev. Lett."},{"key":"54_CR2","first-page":"993","volume":"3","author":"D Blei","year":"2003","unstructured":"Blei, D., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. JMLR 3, 993\u20131022 (2003)","journal-title":"JMLR"},{"key":"54_CR3","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Cappello, F., Djilali, S., Fedak, G., Germain, C., Herault, T., Lemarinier, P., Lodygensky, O., Magniette, F., Neri, V., Selikhov, A.: MPICH-V: Toward a scalable fault tolerant MPI for volatile nodes. In: Conference on High Performance Networking and Computing (SC2002), pp. 1\u201318. Baltimore, MD, November 2002","DOI":"10.1109\/SC.2002.10048"},{"key":"54_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/978-3-642-29740-3_28","volume-title":"Euro-Par 2011: Parallel Processing Workshops","author":"PG Bridges","year":"2012","unstructured":"Bridges, P.G., Hoemmen, M., Ferreira, K.B., Heroux, M.A., Soltero, P., Brightwell, R.: Cooperative application\/OS DRAM fault recovery. In: Alexander, M., D\u2019Ambra, P., Belloum, A., Bosilca, G., Cannataro, M., Danelutto, M., Traff, J.L., Vall\u00e9e, G., Weidendorfer, J., Martino, B., Gerndt, M., Jeannot, E., Namyst, R., Roman, J., Scott, S.L. (eds.) Euro-Par 2011, Part II. LNCS, vol. 7156, pp. 241\u2013250. Springer, Heidelberg (2012)"},{"key":"#cr-split#-54_CR5.1","unstructured":"Cappello, F., Geist, A., Gropp, W., Kale, S., Kramer, B., Snir, M.: Toward exascale resilience: 2014 update. Supercomput.Front. Innovations 1"},{"key":"#cr-split#-54_CR5.2","unstructured":"(1) (2014). http:\/\/superfri.org\/superfri\/article\/view\/14"},{"issue":"1","key":"54_CR6","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/214451.214456","volume":"3","author":"KM Chandy","year":"1985","unstructured":"Chandy, K.M., Lamport, L.: Distributed snapshots: determining global states of distributed systems. ACM Trans. Comput. Syst. 3(1), 63\u201375 (1985)","journal-title":"ACM Trans. Comput. Syst."},{"key":"54_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z.: Extending algorithm-based fault tolerance to tolerate fail-stop failures in high performance distributed environments. In: IPDPS, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/IPDPS.2008.4536158"},{"key":"54_CR8","unstructured":"Chen, Z., Dongarra, J.: Algorithm-based checkpoint-free fault tolerance for parallel matrix computations on volatile resources. In: 20th International Parallel and Distributed Processing Symposium, 2006. IPDPS 2006, April 2006"},{"key":"54_CR9","doi-asserted-by":"crossref","unstructured":"Hertel, E.S.J., Bell, R.L., Elrick, M.G., Farnsworth, A.V., Kerley, G.I., McGlaun, J.M., Petney, S.V., Silling, S.A., Taylor, P.A., Yarrington, L.: CTH: A software family for multi-dimensional shock physics analysis. In: Proceedings of the 19th International Symposium on Shock Waves, pp. 377\u2013382, July 1993","DOI":"10.1007\/978-3-642-78829-1_61"},{"issue":"3","key":"54_CR10","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1145\/568522.568525","volume":"34","author":"ENM Elnozahy","year":"2002","unstructured":"Elnozahy, E.N.M., Alvisi, L., Wang, Y.M., Johnson, D.B.: A survey of rollback-recovery protocols in message-passing systems. ACM Comput. Surv. 34(3), 375\u2013408 (2002)","journal-title":"ACM Comput. Surv."},{"key":"54_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/11428831_39","volume-title":"Computational Science \u2013 ICCS 2005","author":"C Engelmann","year":"2005","unstructured":"Engelmann, C., Geist, G.A.: Super-scalable algorithms for computing on 100,000 processors. In: Sunderam, V.S., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) ICCS 2005. LNCS, vol. 3514, pp. 313\u2013321. Springer, Heidelberg (2005)"},{"issue":"1","key":"54_CR12","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119\u2013139 (1997)","journal-title":"J. Comput. Syst. Sci."},{"key":"54_CR13","first-page":"625","volume":"7","author":"B Fritzke","year":"1995","unstructured":"Fritzke, B., et al.: A growing neural gas network learns topologies. Adv. Neural Inf. Process. Syst. 7, 625\u2013632 (1995)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"54_CR14","unstructured":"Hall, M., et al.: The WEKA data mining software: an update. SIGKDD Explorations 11(1) (2009). http:\/\/www.cs.waikato.ac.nz\/ml\/weka\/"},{"key":"54_CR15","doi-asserted-by":"crossref","unstructured":"Kuang-Hua, H., Abraham, J.A.: Algorithm-based fault tolerance for matrix operations. IEEE Trans. Comput. 33, 518\u2013528 (1984). http:\/\/dx.doi.org\/10.1109\/TC.1984.1676475","DOI":"10.1109\/TC.1984.1676475"},{"key":"54_CR16","doi-asserted-by":"crossref","unstructured":"Lemarinier, P., Bouteiller, A., Herault, T., Krawezik, G., Cappello, F.: Improved message logging versus improved coordinated checkpointing for fault tolerant MPI. In: IEEE International Conference on Cluster Computing, pp. 115\u2013124 (2004)","DOI":"10.1109\/CLUSTR.2003.1253321"},{"key":"54_CR17","unstructured":"Li, W.J., Wang, K., Stolfo, S.J., Herzog, B.: Fileprints: Identifying file types by n-gram analysis. In: Information Assurance Workshop, 2005, IAW 2005. In: Proceedings from the Sixth Annual IEEE SMC, pp. 64\u201371. IEEE (2005)"},{"issue":"2","key":"54_CR18","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theor. 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theor."},{"issue":"4","key":"54_CR19","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/SURV.2008.080406","volume":"10","author":"TT Nguyen","year":"2008","unstructured":"Nguyen, T.T., Armitage, G.: A survey of techniques for internet traffic classification using machine learning. IEEE Commun. Surv. Tutorials 10(4), 56\u201376 (2008)","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"54_CR20","unstructured":"Pedregosa, F., et al.: Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011). http:\/\/scikit-learn.org\/"},{"key":"54_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/jcph.1995.1039","volume":"117","author":"SJ Plimpton","year":"1995","unstructured":"Plimpton, S.J.: Fast parallel algorithms for short-range molecular dynamics. J. Comput. Phys. 117, 1\u201319 (1995)","journal-title":"J. Comput. Phys."},{"key":"54_CR22","unstructured":"Rennie, J.D., Shih, L., Teevan, J., Karger, D.R., et al.: Tackling the poor assumptions of naive bayes text classifiers. In: ICML, vol. 3, pp. 616\u2013623. Washington DC (2003)"},{"issue":"4","key":"54_CR23","doi-asserted-by":"crossref","first-page":"639","DOI":"10.3233\/JCS-2010-0410","volume":"19","author":"K Rieck","year":"2011","unstructured":"Rieck, K., Trinius, P., Willems, C., Holz, T.: Automatic analysis of malware behavior using machine learning. J. Comput. Secur. 19(4), 639\u2013668 (2011)","journal-title":"J. Comput. Secur."},{"issue":"1","key":"54_CR24","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1145\/1057977.1057980","volume":"37","author":"Y Saito","year":"2005","unstructured":"Saito, Y., Shapiro, M.: Optimistic replication. ACM Comput. Surv. 37(1), 42\u201381 (2005)","journal-title":"ACM Comput. Surv."},{"key":"54_CR25","doi-asserted-by":"crossref","unstructured":"Sommer, R., Paxson, V.: Outside the closed world: on using machine learning for network intrusion detection. In: 2010 IEEE Symposium on Security and Privacy (SP), pp. 305\u2013316. IEEE (2010)","DOI":"10.1109\/SP.2010.25"},{"key":"54_CR26","unstructured":"Sridharan, V., DeBardeleben, N., Blanchard, S., Ferreira, K., Stearley, J., Shalf, J., Gurumurthi, S.: Memory errors in modern systems: the good, the bad, and the ugly. In: Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2015, pp. 297\u2013310. ACM, New York (2015). http:\/\/doi.acm.org\/10.1145\/2694344.2694348"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2015: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-27308-2_54","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T20:48:33Z","timestamp":1748724513000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-27308-2_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319273075","9783319273082"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-27308-2_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"18 December 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}