{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:53:51Z","timestamp":1768031631948,"version":"3.49.0"},"reference-count":88,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T00:00:00Z","timestamp":1726444800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T00:00:00Z","timestamp":1726444800000},"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","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,16]]},"DOI":"10.1109\/e-science62913.2024.10678669","type":"proceedings-article","created":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T17:23:25Z","timestamp":1726853005000},"page":"1-9","source":"Crossref","is-referenced-by-count":2,"title":["Diaspora: Resilience-Enabling Services for Real-Time Distributed Workflows"],"prefix":"10.1109","author":[{"given":"Bogdan","family":"Nicolae","sequence":"first","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Justin M.","family":"Wozniak","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Tekin","family":"Bicer","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Hai","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Parth","family":"Patel","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Haochen","family":"Pan","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Amal","family":"Gueroudji","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Maxime","family":"Gonthier","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Valerie","family":"Hayot-Sasson","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Eliu","family":"Huerta","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Kyle","family":"Chard","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Ryan","family":"Chard","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Matthieu","family":"Dorier","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Nageswara S. V.","family":"Rao","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory"}]},{"given":"Anees","family":"Al-Najjar","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory"}]},{"given":"Alessandra","family":"Corsi","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}]},{"given":"Ian","family":"Foster","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]}],"member":"263","reference":[{"key":"ref1","article-title":"High-Luminosity Large Hadron Collider (HL-LHC): Technical design report","volume-title":"CERN, Tech. Rep. CERN-2020-010","author":"Aberle","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-4655(01)00254-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW59300.2023.00143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.1158573"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature09419"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.375595"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624613"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/smll.201802291"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-nucl-102010-130059"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41550-021-01405-0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01712-9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aav2211"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2442-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsc.2020.100370"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemmater.2c03593"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1063\/5.0059767"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms10882"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100606"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/718\/2\/022004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-019-0097-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-019-0101-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/568522.568525"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88871-0_61"},{"key":"ref24","first-page":"911","article-title":"VeloC: Towards high performance adaptive asynchronous checkpointing at large scale","volume-title":"IPDPS19: The 2019 IEEE International Parallel and Distributed Processing Symposium","author":"Nicolae"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470462"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2012.6232369"},{"key":"ref27","first-page":"93","article-title":"Scalable multi-versioning ordered key-value stores with persistent memory support","volume-title":"IPDPS 2022: The 36th IEEE International Parallel and Distributed Processing Symposium","author":"Nicolae"},{"key":"ref28","first-page":"73","article-title":"GPU-enabled asynchronous multi-level checkpoint caching and prefetching","volume-title":"HPDC23: The 32nd International Symposium on High-Performance Parallel and Distributed Computing","author":"Maurya"},{"key":"ref29","article-title":"VELOC: VEry Low Overhead Checkpointing in the age of exascale","volume-title":"SuperCheck21: The First International Symposium on Checkpointing for Supercomputing, Virtual Event","author":"Nicolae"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.06.003"},{"key":"ref31","first-page":"336","article-title":"Towards low-overhead resilience for data parallel deep learning","volume-title":"CCGrid22: The 22th IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing","author":"Nicolae"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015617019423"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.938"},{"key":"ref34","first-page":"2","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","volume-title":"9th USENIX Conference on Networked Systems Design and Implementation","author":"Zaharia"},{"key":"ref35","first-page":"135","article-title":"Virtual log-structured storage for high-performance streaming","volume-title":"CLUSTER21: The 2021 IEEE International Conference on Cluster Computing","author":"Marcu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.01.010"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.968"},{"key":"ref38","first-page":"1","article-title":"Capturing and enhancing in situ system observability for failure detection","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Huang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3456859.3456863"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-10063-9"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3508297.3508302"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3518781.3519179"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3500917"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1145\/3386723.3387865","article-title":"LSTM-based models for earthquake prediction","volume-title":"3rd International Conference on Networking, Information Systems and Security","author":"Berhich"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3568429"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3409963.3410492"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM55787.2022.9964533"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.37"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2011.389"},{"issue":"2011","key":"ref50","first-page":"1","article-title":"Kafka: A distributed messaging system for log processing","volume-title":"Proceedings of the NetDB","volume":"11","author":"Kreps et al"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00071"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286239"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1996109.1996119"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1996109.1996114"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1029\/2020AV000354"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807646"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47954-6_11"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2017.09.002"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2004.06.008"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2010.98"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/BROADNETS.2006.4374316"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-09430-3"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00041"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3526058.3535453"},{"key":"ref65","article-title":"TomoGAN: Low-dose x-ray tomography with generative adversarial networks","author":"Liu","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41496-z"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.07.016"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1080\/08940886.2022.2112500"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96498-6_10"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356220"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460380"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.2352\/EI.2024.36.12.HPCI-188"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1186\/s40679-017-0040-7"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1063\/5.0013065"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-34525-1"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.2352\/EI.2023.35.11.HPCI-232"},{"key":"ref77","article-title":"Real-time edge inference for ptychographic nanoscale xray imaging","author":"Babu","year":"2021","journal-title":"Argonne National Lab.(ANL), Argonne, IL (United States), Tech. Rep."},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-020-9802-0"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2016.7870901"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3307681.3325400"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392683"},{"key":"ref82","article-title":"Octopus: Experiences with a hybrid event-driven architecture for distributed scientific computing","author":"Pan","year":"2024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88808-6_2"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/2187671.2187677"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3246954"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23606-8_10"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.04.024"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23606-8_6"}],"event":{"name":"2024 IEEE 20th International Conference on e-Science (e-Science)","location":"Osaka, Japan","start":{"date-parts":[[2024,9,16]]},"end":{"date-parts":[[2024,9,20]]}},"container-title":["2024 IEEE 20th International Conference on e-Science (e-Science)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10677510\/10678656\/10678669.pdf?arnumber=10678669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T04:02:39Z","timestamp":1726977759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10678669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,16]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/e-science62913.2024.10678669","relation":{},"subject":[],"published":{"date-parts":[[2024,9,16]]}}}