{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T11:18:54Z","timestamp":1758280734874,"version":"3.37.3"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["CNS-1855565","CCF-1853714","CCF-1910747","CNS-1943204"],"award-info":[{"award-number":["CNS-1855565","CCF-1853714","CCF-1910747","CNS-1943204"]}]},{"name":"DOE","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpds.2024.3374555","type":"journal-article","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T18:17:55Z","timestamp":1710440275000},"page":"844-861","source":"Crossref","is-referenced-by-count":7,"title":["PROV-IO: A Cross-Platform Provenance Framework for Scientific Data on HPC Systems"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1440-7568","authenticated-orcid":false,"given":"Runzhou","family":"Han","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0741-3436","authenticated-orcid":false,"given":"Mai","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3048-3448","authenticated-orcid":false,"given":"Suren","family":"Byna","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7038-8360","authenticated-orcid":false,"given":"Houjun","family":"Tang","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0725-0833","authenticated-orcid":false,"given":"Bin","family":"Dong","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4078-8149","authenticated-orcid":false,"given":"Dong","family":"Dai","sequence":"additional","affiliation":[{"name":"University of North Carolina, Charlotte, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6525-6299","authenticated-orcid":false,"given":"Yong","family":"Chen","sequence":"additional","affiliation":[{"name":"Samsung Research Labs, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongkyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research Labs, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Hassoun","sequence":"additional","affiliation":[{"name":"Samsung Research Labs, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8625-5095","authenticated-orcid":false,"given":"David","family":"Thorsley","sequence":"additional","affiliation":[{"name":"Samsung Research Labs, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2011.2155130"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41567-019-0780-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00035"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44503-X_20"},{"key":"ref7","first-page":"6","article-title":"Interoperability for provenance-aware databases using PROV and JSON","volume-title":"Proc. 7th USENIX Workshop Theory Pract. Provenance","author":"Niu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3186549.3186551"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300066"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICISCE.2015.23"},{"key":"ref11","first-page":"43","article-title":"Provenance-aware storage systems","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Muniswamy-Reddy"},{"key":"ref12","first-page":"10","article-title":"Layering in provenance systems","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Muniswamy-Reddy"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3442322.3442329"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1084805.1084812"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376772"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2018.00039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2019.00047"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WORKS49585.2019.00006"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6544"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2006.5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2008.67"},{"article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","year":"2019","author":"Shoeybi","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2452376.2452478"},{"key":"ref36","article-title":"H5Prov: I\/O performance analysis of science applications using HDF5 file-level provenance","author":"Li","year":"2019","journal-title":"Cray User Group (CUG19) Conf."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1966895.1966900"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW54622.2021.00012"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","first-page":"1","article-title":"Efficient large-scale language model training on GPU clusters using Megatron-LM","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Narayanan"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref42"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref43"},{"article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","year":"2019","author":"Raffel","key":"ref44"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35170-9_6"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531477"},{"article-title":"Pointer sentinel mixture models","year":"2016","author":"Merity","key":"ref64"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5334\/jors.bq"},{"key":"ref68","first-page":"319","article-title":"Trustworthy whole-system provenance for the Linux kernel","volume-title":"Proc. 24th USENIX Conf. Secur. Symp.","author":"Bates"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/357775.357777"},{"key":"ref70","first-page":"262","article-title":"Trio: A system for integrated management of data, accuracy, and lineage","volume-title":"Proc. 2nd Biennial Conf. Innov. Data Syst. Res.","author":"Widom"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2596628"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300084"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3220539"},{"article-title":"Building containerized environments for reproducibility and traceability of scientific workflows","year":"2020","author":"Olaya","key":"ref74"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2014.49"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00179"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2723711"},{"key":"ref82","first-page":"449","article-title":"Torturing databases for fun and profit","volume-title":"Proc. 11th USENIX Symp. Operating Syst. Des. Implementation","author":"Zheng"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205302"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3483447"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3281031"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW51947.2020.00013"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3465332.3470873"},{"key":"ref88","first-page":"961","article-title":"Lessons and actions: What we learned from 10k SSD-related storage system failures","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Xu"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2013.19"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2021.100006"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00028"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW-DISCS.2018.00010"},{"key":"ref93","first-page":"7","article-title":"Understanding the fault resilience of file system checkers","volume-title":"Proc. 9th USENIX Workshop Hot Top. Storage File Syst.","author":"Gatla"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCNC.2017.7876233"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW-DISCS.2016.013"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2016.7549401"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941574"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.44"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2019.00-20"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/2992782"},{"key":"ref101","first-page":"271","article-title":"Understanding the robustness of SSDs under power fault","volume-title":"Proc. 11th USENIX Conf. File Storage Technol.","author":"Zheng"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00029"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2012.6507475"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/10474166\/10472875-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10474166\/10472875.pdf?arnumber=10472875","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T04:47:11Z","timestamp":1712983631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10472875\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":66,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3374555","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}