{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:35:24Z","timestamp":1755999324253,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T00:00:00Z","timestamp":1656288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Department of Energy","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1855565,1853714,1910747,1943204"],"award-info":[{"award-number":["1855565,1853714,1910747,1943204"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,27]]},"DOI":"10.1145\/3502181.3531477","type":"proceedings-article","created":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T22:14:30Z","timestamp":1656022470000},"page":"213-226","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["PROV-IO"],"prefix":"10.1145","author":[{"given":"Runzhou","family":"Han","sequence":"first","affiliation":[{"name":"Iowa State University, Ames, IA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suren","family":"Byna","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Houjun","family":"Tang","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Dong","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mai","family":"Zheng","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, IA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2011.2155130"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18"},{"key":"e_1_3_2_1_3_1","unstructured":"Fair principles. [Online]. Available: https:\/\/www.go-fair.org\/fair-principles\/ (visited on 10\/04\/2021).  Fair principles. [Online]. Available: https:\/\/www.go-fair.org\/fair-principles\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41567-019-0780-5"},{"key":"e_1_3_2_1_5_1","volume-title":"DASSA: Parallel DAS Data Storage and Analysis for Subsurface Event Detection,\" in 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS'20)","author":"Dong B.","year":"2020","unstructured":"B. Dong , \" DASSA: Parallel DAS Data Storage and Analysis for Subsurface Event Detection,\" in 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS'20) , 2020 . B. Dong et al., \"DASSA: Parallel DAS Data Storage and Analysis for Subsurface Event Detection,\" in 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS'20), 2020."},{"key":"e_1_3_2_1_6_1","volume-title":"Why and where: A characterization of data provenance,\" in Proceedings of the 8th International Conference on Database Theory (ICDT'01)","author":"Buneman P.","year":"2001","unstructured":"P. Buneman , \" Why and where: A characterization of data provenance,\" in Proceedings of the 8th International Conference on Database Theory (ICDT'01) , 2001 . P. Buneman et al., \"Why and where: A characterization of data provenance,\" in Proceedings of the 8th International Conference on Database Theory (ICDT'01), 2001."},{"key":"e_1_3_2_1_7_1","volume-title":"Interoperability for provenance-aware databases using PROV and JSON,\" in 7th USENIX Workshop on the Theory and Practice of Provenance (TaPP'15)","author":"Niu X.","year":"2015","unstructured":"X. Niu , \" Interoperability for provenance-aware databases using PROV and JSON,\" in 7th USENIX Workshop on the Theory and Practice of Provenance (TaPP'15) , 2015 . X. Niu et al., \"Interoperability for provenance-aware databases using PROV and JSON,\" in 7th USENIX Workshop on the Theory and Practice of Provenance (TaPP'15), 2015."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3186549"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300066"},{"key":"e_1_3_2_1_10_1","volume-title":"A provenance storage method based on parallel database,\" in 2015 2nd International Conference on Information Science and Control Engineering (ICISCE'15)","author":"Wang Z.","year":"2015","unstructured":"Z. Wang , \" A provenance storage method based on parallel database,\" in 2015 2nd International Conference on Information Science and Control Engineering (ICISCE'15) , 2015 . Z. Wang et al., \"A provenance storage method based on parallel database,\" in 2015 2nd International Conference on Information Science and Control Engineering (ICISCE'15), 2015."},{"key":"e_1_3_2_1_11_1","volume-title":"Muniswamy-Reddy et al., \"Provenance-aware storage systems,\" in Proceedings of the Annual Conference on USENIX '06 Annual Technical Conference (ATC'06)","author":"K.","year":"2006","unstructured":"K.- K. Muniswamy-Reddy et al., \"Provenance-aware storage systems,\" in Proceedings of the Annual Conference on USENIX '06 Annual Technical Conference (ATC'06) , 2006 . K.-K. Muniswamy-Reddy et al., \"Provenance-aware storage systems,\" in Proceedings of the Annual Conference on USENIX '06 Annual Technical Conference (ATC'06), 2006."},{"key":"e_1_3_2_1_12_1","volume-title":"Muniswamy-Reddy et al., \"Layering in provenance systems,\" in Proceed- ings of the 2009 Conference on USENIX Annual Technical Conference (ATC'09)","author":"K.","year":"2009","unstructured":"K.- K. Muniswamy-Reddy et al., \"Layering in provenance systems,\" in Proceed- ings of the 2009 Conference on USENIX Annual Technical Conference (ATC'09) , 2009 . K.-K. Muniswamy-Reddy et al., \"Layering in provenance systems,\" in Proceed- ings of the 2009 Conference on USENIX Annual Technical Conference (ATC'09), 2009."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442322.3442329"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1084805"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376772"},{"key":"e_1_3_2_1_16_1","volume-title":"Big provenance stream processing for data intensive com- putations,\" in 2018 IEEE 14th International Conference on eScience (eScience'18)","author":"Suriarachchi I.","year":"2018","unstructured":"I. Suriarachchi , \" Big provenance stream processing for data intensive com- putations,\" in 2018 IEEE 14th International Conference on eScience (eScience'18) , 2018 . I. Suriarachchi et al., \"Big provenance stream processing for data intensive com- putations,\" in 2018 IEEE 14th International Conference on eScience (eScience'18), 2018."},{"key":"e_1_3_2_1_17_1","volume-title":"Efficient runtime capture of multiworkflow data using prove- nance,\" in 2019 15th International Conference on eScience (eScience'19)","author":"Souza R.","year":"2019","unstructured":"R. Souza , \" Efficient runtime capture of multiworkflow data using prove- nance,\" in 2019 15th International Conference on eScience (eScience'19) , 2019 . R. Souza et al., \"Efficient runtime capture of multiworkflow data using prove- nance,\" in 2019 15th International Conference on eScience (eScience'19), 2019."},{"key":"e_1_3_2_1_18_1","volume-title":"Provenance data in the machine learning lifecycle in computational science and engineering,\" in 2019 IEEE\/ACM Workflows in Support of Large-Scale Science (WORKS'19)","author":"Souza R.","year":"2019","unstructured":"R. Souza , \" Provenance data in the machine learning lifecycle in computational science and engineering,\" in 2019 IEEE\/ACM Workflows in Support of Large-Scale Science (WORKS'19) , 2019 . R. Souza et al., \"Provenance data in the machine learning lifecycle in computational science and engineering,\" in 2019 IEEE\/ACM Workflows in Support of Large-Scale Science (WORKS'19), 2019."},{"key":"e_1_3_2_1_19_1","unstructured":"The prov data model - w3c. [Online]. Available: https:\/\/www.w3.org\/TR\/prov- overview\/ (visited on 10\/04\/2021).  The prov data model - w3c. [Online]. Available: https:\/\/www.w3.org\/TR\/prov- overview\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"Experiencing provlake to manage the data lineage of ai workflows,\" in Meeting in Innovation in Information Systems (EISI) in Brazilian Symposium in Information Systems (SBSI'20)","author":"Azevedo L.","year":"2020","unstructured":"L. Azevedo , \" Experiencing provlake to manage the data lineage of ai workflows,\" in Meeting in Innovation in Information Systems (EISI) in Brazilian Symposium in Information Systems (SBSI'20) , 2020 . L. Azevedo et al., \"Experiencing provlake to manage the data lineage of ai workflows,\" in Meeting in Innovation in Information Systems (EISI) in Brazilian Symposium in Information Systems (SBSI'20), 2020."},{"key":"e_1_3_2_1_21_1","volume-title":"A framework for collecting provenance in data-centric scientific workflows,\" in 2006 IEEE International Conference on Web Services (ICWS'06)","author":"Simmhan Y. L.","year":"2006","unstructured":"Y. L. Simmhan , \" A framework for collecting provenance in data-centric scientific workflows,\" in 2006 IEEE International Conference on Web Services (ICWS'06) , 2006 . Y. L. Simmhan et al., \"A framework for collecting provenance in data-centric scientific workflows,\" in 2006 IEEE International Conference on Web Services (ICWS'06), 2006."},{"key":"e_1_3_2_1_22_1","volume-title":"End-to-end escience: Integrating workflow, query, visualization, and provenance at an ocean observatory,\" in 2008 IEEE Fourth International Conference on eScience (eScience'08)","author":"Howe B.","year":"2008","unstructured":"B. Howe , \" End-to-end escience: Integrating workflow, query, visualization, and provenance at an ocean observatory,\" in 2008 IEEE Fourth International Conference on eScience (eScience'08) , 2008 . B. Howe et al., \"End-to-end escience: Integrating workflow, query, visualization, and provenance at an ocean observatory,\" in 2008 IEEE Fourth International Conference on eScience (eScience'08), 2008."},{"key":"e_1_3_2_1_23_1","unstructured":"Resource description framework. [Online]. Available: https:\/\/www.w3.org\/RDF\/ (visited on 10\/04\/2021).  Resource description framework. [Online]. Available: https:\/\/www.w3.org\/RDF\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_24_1","unstructured":"X. Allison etal A graph neural network-based top quark reconstruction package.. Available: https:\/\/indico.cern.ch\/event\/932415\/contributions\/3918265\/attachments\/2086561\/3505362\/GNN_Top_Reco_-_Allison_Xu.pdf (visited on 10\/04\/2021).  X. Allison et al. A graph neural network-based top quark reconstruction package.. Available: https:\/\/indico.cern.ch\/event\/932415\/contributions\/3918265\/attachments\/2086561\/3505362\/GNN_Top_Reco_-_Allison_Xu.pdf (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_25_1","unstructured":"H5bench. [Online]. Available: https:\/\/www.hdfgroup.org\/solutions\/hdf5\/ (visited on 10\/04\/2021).  H5bench. [Online]. Available: https:\/\/www.hdfgroup.org\/solutions\/hdf5\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_26_1","unstructured":"Adios. [Online]. Available: https:\/\/www.olcf.ornl.gov\/center-projects\/adios\/.  Adios. [Online]. Available: https:\/\/www.olcf.ornl.gov\/center-projects\/adios\/."},{"key":"e_1_3_2_1_27_1","volume-title":"Trustworthy whole-system provenance for the linux kernel,\" in Proceedings of the 24th USENIX Conference on Security Symposium (Security'15)","author":"Bates A.","year":"2015","unstructured":"A. Bates , \" Trustworthy whole-system provenance for the linux kernel,\" in Proceedings of the 24th USENIX Conference on Security Symposium (Security'15) , 2015 . A. Bates et al., \"Trustworthy whole-system provenance for the linux kernel,\" in Proceedings of the 24th USENIX Conference on Security Symposium (Security'15), 2015."},{"key":"e_1_3_2_1_28_1","volume-title":"The w3c prov family of specifications for modelling prove- nance metadata,\" in Proceedings of the 16th International Conference on Extending Database Technology (EDBT'13)","author":"Missier P.","year":"2013","unstructured":"P. Missier , \" The w3c prov family of specifications for modelling prove- nance metadata,\" in Proceedings of the 16th International Conference on Extending Database Technology (EDBT'13) , 2013 . P. Missier et al., \"The w3c prov family of specifications for modelling prove- nance metadata,\" in Proceedings of the 16th International Conference on Extending Database Technology (EDBT'13), 2013."},{"key":"e_1_3_2_1_29_1","unstructured":"Hdf5. [Online]. Available: https:\/\/https:\/\/www.hdfgroup.org\/solutions\/hdf5\/ (visited on 10\/04\/2021).  Hdf5. [Online]. Available: https:\/\/https:\/\/www.hdfgroup.org\/solutions\/hdf5\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_30_1","unstructured":"Netcdf. [Online]. Available: https:\/\/www.unidata.ucar.edu\/software\/netcdf\/ (visited on 10\/04\/2021).  Netcdf. [Online]. Available: https:\/\/www.unidata.ucar.edu\/software\/netcdf\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_31_1","unstructured":"Automatic library tracking database at nersc. [Online]. Available: https:\/\/www. nersc.gov\/assets\/altdatNERSC.pdf (visited on 10\/04\/2021).  Automatic library tracking database at nersc. [Online]. Available: https:\/\/www. nersc.gov\/assets\/altdatNERSC.pdf (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_32_1","volume-title":"H5prov: I\/o performance analysis of science applications using hdf5 file-level provenance,\" in Cray User Group (CUG'19)","author":"Li T.","year":"2019","unstructured":"T. Li , \" H5prov: I\/o performance analysis of science applications using hdf5 file-level provenance,\" in Cray User Group (CUG'19) , 2019 . T. Li et al., \"H5prov: I\/o performance analysis of science applications using hdf5 file-level provenance,\" in Cray User Group (CUG'19), 2019."},{"key":"e_1_3_2_1_33_1","volume-title":"An overview of the hdf5 technology suite and its applications,\" in Proceedings of the EDBT\/ICDT 2011 Workshop on Array Databases (AD'11)","author":"Folk M.","year":"2011","unstructured":"M. Folk , \" An overview of the hdf5 technology suite and its applications,\" in Proceedings of the EDBT\/ICDT 2011 Workshop on Array Databases (AD'11) , 2011 . M. Folk et al., \"An overview of the hdf5 technology suite and its applications,\" in Proceedings of the EDBT\/ICDT 2011 Workshop on Array Databases (AD'11), 2011."},{"key":"e_1_3_2_1_34_1","unstructured":"Darshan hpc i\/o characterization tool. [Online]. Available: https:\/\/www.mcs. anl.gov\/research\/projects\/darshan\/ (visited on 10\/04\/2021).  Darshan hpc i\/o characterization tool. [Online]. Available: https:\/\/www.mcs. anl.gov\/research\/projects\/darshan\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_35_1","volume-title":"Verifying io synchronization from mpi traces,\" in 2021 IEEE\/ACM Sixth International Parallel Data Systems Workshop (PDSW'21)","author":"Yellapragada S.","year":"2021","unstructured":"S. Yellapragada , \" Verifying io synchronization from mpi traces,\" in 2021 IEEE\/ACM Sixth International Parallel Data Systems Workshop (PDSW'21) , 2021 . S. Yellapragada et al., \"Verifying io synchronization from mpi traces,\" in 2021 IEEE\/ACM Sixth International Parallel Data Systems Workshop (PDSW'21), 2021."},{"key":"e_1_3_2_1_36_1","unstructured":"Ext4. [Online]. Available: https:\/\/ext4.wiki.kernel.org\/index.php\/Main_Page (visited on 10\/04\/2021).  Ext4. [Online]. Available: https:\/\/ext4.wiki.kernel.org\/index.php\/Main_Page (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_37_1","volume-title":"Spade: Support for provenance auditing in distributed en- vironments,\" in Proceedings of the 13th International Middleware Conference (Middleware'12)","author":"Gehani A.","year":"2012","unstructured":"A. Gehani , \" Spade: Support for provenance auditing in distributed en- vironments,\" in Proceedings of the 13th International Middleware Conference (Middleware'12) , 2012 . A. Gehani et al., \"Spade: Support for provenance auditing in distributed en- vironments,\" in Proceedings of the 13th International Middleware Conference (Middleware'12), 2012."},{"key":"e_1_3_2_1_38_1","unstructured":"Gotcha v1.0.2. [Online]. Available: https:\/\/github.com\/LLNL\/GOTCHA (visited on 10\/04\/2021).  Gotcha v1.0.2. [Online]. Available: https:\/\/github.com\/LLNL\/GOTCHA (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_39_1","unstructured":"Redland rdf. [Online]. Available: https:\/\/librdf.org (visited on 10\/04\/2021).  Redland rdf. [Online]. Available: https:\/\/librdf.org (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_40_1","unstructured":"Apache jena. [Online]. Available: https:\/\/jena.apache.org (visited on 10\/04\/2021).  Apache jena. [Online]. Available: https:\/\/jena.apache.org (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_41_1","unstructured":"Neo4j. [Online]. Available: https:\/\/neo4j.com (visited on 10\/04\/2021).  Neo4j. [Online]. Available: https:\/\/neo4j.com (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_42_1","unstructured":"Blazegraph. [Online]. Available: https:\/\/blazegraph.com (visited on 10\/04\/2021).  Blazegraph. [Online]. Available: https:\/\/blazegraph.com (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_43_1","unstructured":"Apache rya. [Online]. Available: https:\/\/rya.apache.org (visited on 10\/04\/2021).  Apache rya. [Online]. Available: https:\/\/rya.apache.org (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_44_1","unstructured":"Anzographdb. [Online]. Available: https:\/\/cambridgesemantics.com\/anzograph\/ (visited on 10\/04\/2021).  Anzographdb. [Online]. Available: https:\/\/cambridgesemantics.com\/anzograph\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_45_1","unstructured":"Terse rdf triple language. [Online]. Available: https:\/\/www.w3.org\/TR\/turtle\/ (visited on 10\/04\/2021).  Terse rdf triple language. [Online]. Available: https:\/\/www.w3.org\/TR\/turtle\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_46_1","unstructured":"N-triples. [Online]. Available: https:\/\/www.w3.org\/TR\/n-triples\/ (visited on 10\/04\/2021).  N-triples. [Online]. Available: https:\/\/www.w3.org\/TR\/n-triples\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_47_1","unstructured":"Sparql query language for rdf. [Online]. Available: https:\/\/www.w3.org\/TR\/rdf- sparql-query\/ (visited on 10\/04\/2021).  Sparql query language for rdf. [Online]. Available: https:\/\/www.w3.org\/TR\/rdf- sparql-query\/ (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_48_1","unstructured":"Graphviz. [Online]. Available: https:\/\/graphviz.org (visited on 10\/04\/2021).  Graphviz. [Online]. Available: https:\/\/graphviz.org (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5334\/jors.bq"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/357775.357777"},{"key":"e_1_3_2_1_51_1","volume-title":"A system for integrated management of data, accuracy, and lin- eage,\" in 2nd Biennial Conference on Innovative Data Systems Research (CIDR'05)","author":"Widom J.","year":"2005","unstructured":"J. Widom , \"Trio : A system for integrated management of data, accuracy, and lin- eage,\" in 2nd Biennial Conference on Innovative Data Systems Research (CIDR'05) , 2005 . J. Widom, \"Trio: A system for integrated management of data, accuracy, and lin- eage,\" in 2nd Biennial Conference on Innovative Data Systems Research (CIDR'05), 2005."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2596628"},{"key":"e_1_3_2_1_53_1","volume-title":"Hypothetical reasoning via provenance abstraction,\" in Pro- ceedings of the 2019 International Conference on Management of Data (SIGMOD'19)","author":"Deutch D.","year":"2019","unstructured":"D. Deutch , \" Hypothetical reasoning via provenance abstraction,\" in Pro- ceedings of the 2019 International Conference on Management of Data (SIGMOD'19) , 2019 . D. Deutch et al., \"Hypothetical reasoning via provenance abstraction,\" in Pro- ceedings of the 2019 International Conference on Management of Data (SIGMOD'19), 2019."},{"key":"e_1_3_2_1_54_1","volume-title":"Study in usefulness of middleware-only provenance,\" in 2014 IEEE 10th International Conference on eScience (eScience'14)","author":"Zhou Q.","year":"2014","unstructured":"Q. Zhou , \" Study in usefulness of middleware-only provenance,\" in 2014 IEEE 10th International Conference on eScience (eScience'14) , 2014 . Q. Zhou et al., \"Study in usefulness of middleware-only provenance,\" in 2014 IEEE 10th International Conference on eScience (eScience'14), 2014."},{"key":"e_1_3_2_1_55_1","unstructured":"Braid-db. [Online]. Available: https:\/\/github.com\/ANL-Braid\/DB\/.  Braid-db. [Online]. Available: https:\/\/github.com\/ANL-Braid\/DB\/."},{"key":"e_1_3_2_1_56_1","unstructured":"Chimbuko. [Online]. Available: https:\/\/github.com\/CODARcode\/Chimbuko (visited on 10\/04\/2021).  Chimbuko. [Online]. Available: https:\/\/github.com\/CODARcode\/Chimbuko (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_57_1","volume-title":"A vision for managing extreme-scale data hoards,\" in IEEE 39th International Conference on Distributed Computing Systems (ICDCS'19)","author":"Logan J.","year":"2019","unstructured":"J. Logan , \" A vision for managing extreme-scale data hoards,\" in IEEE 39th International Conference on Distributed Computing Systems (ICDCS'19) , 2019 . J. Logan et al., \"A vision for managing extreme-scale data hoards,\" in IEEE 39th International Conference on Distributed Computing Systems (ICDCS'19), 2019."},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data (SIGMOD'15)","author":"Alvaro P.","year":"2015","unstructured":"P. Alvaro in Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data (SIGMOD'15) , 2015 . P. Alvaro et al., \"Lineage-driven fault injection,\" in Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data (SIGMOD'15), 2015."},{"key":"e_1_3_2_1_59_1","unstructured":"Apache taverna. [Online]. Available: https:\/\/incubator.apache.org\/projects\/ taverna.html (visited on 10\/04\/2021).  Apache taverna. [Online]. Available: https:\/\/incubator.apache.org\/projects\/ taverna.html (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_60_1","unstructured":"Effis. [Online]. Available: https:\/\/github.com\/wdmapp\/effis (visited on 10\/04\/2021).  Effis. [Online]. Available: https:\/\/github.com\/wdmapp\/effis (visited on 10\/04\/2021)."},{"key":"e_1_3_2_1_61_1","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Zheng M.","year":"2014","unstructured":"M. Zheng in 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI) , 2014 . M. Zheng et al., \"Torturing Databases for Fun and Profit,\" in 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2014."},{"key":"e_1_3_2_1_62_1","volume-title":"A generic framework for testing parallel file systems,\" in 2016 1st Joint International Workshop on Parallel Data Storage and data Intensive Scalable Computing Systems (PDSW-DISCS)","author":"Cao J.","year":"2016","unstructured":"J. Cao , \" A generic framework for testing parallel file systems,\" in 2016 1st Joint International Workshop on Parallel Data Storage and data Intensive Scalable Computing Systems (PDSW-DISCS) , 2016 . J. Cao et al., \"A generic framework for testing parallel file systems,\" in 2016 1st Joint International Workshop on Parallel Data Storage and data Intensive Scalable Computing Systems (PDSW-DISCS), 2016."},{"key":"e_1_3_2_1_63_1","first-page":"1","volume-title":"PFault: A general framework for analyzing the reliability of high-performance parallel file systems,\" in Proceedings of the 2018 International Conference on Supercomputing (ICS)","author":"Cao J.","year":"2018","unstructured":"J. Cao , \" PFault: A general framework for analyzing the reliability of high-performance parallel file systems,\" in Proceedings of the 2018 International Conference on Supercomputing (ICS) , 2018 , pp. 1 -- 11 . doi: 10.1145\/3205289. 3205302. 10.1145\/3205289 J. Cao et al., \"PFault: A general framework for analyzing the reliability of high-performance parallel file systems,\" in Proceedings of the 2018 International Conference on Supercomputing (ICS), 2018, pp. 1--11. doi: 10.1145\/3205289. 3205302."},{"key":"e_1_3_2_1_64_1","article-title":"A study of failure recovery and logging of high-performance parallel file systems","author":"Han R.","year":"2021","unstructured":"R. Han , \" A study of failure recovery and logging of high-performance parallel file systems ,\" ACM Transactions on Storage (TOS) , 2021 . doi: 10.1145\/3483447. 10.1145\/3483447 R. Han et al., \"A study of failure recovery and logging of high-performance parallel file systems,\" ACM Transactions on Storage (TOS), 2021. doi: 10.1145\/3483447.","journal-title":"ACM Transactions on Storage (TOS)"},{"key":"e_1_3_2_1_65_1","volume-title":"Understanding the fault resilience of file system checkers,\" in 9th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage)","author":"Gatla O. R.","year":"2017","unstructured":"O. R. Gatla , \" Understanding the fault resilience of file system checkers,\" in 9th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage) , 2017 . O. R. Gatla et al., \"Understanding the fault resilience of file system checkers,\" in 9th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage), 2017."},{"key":"e_1_3_2_1_66_1","volume-title":"Towards robust file system checkers,\" in 16th USENIX Con- ference on File and Storage Technologies (FAST)","author":"Gatla O. R.","year":"2018","unstructured":"O. R. Gatla , \" Towards robust file system checkers,\" in 16th USENIX Con- ference on File and Storage Technologies (FAST) , 2018 . O. R. Gatla et al., \"Towards robust file system checkers,\" in 16th USENIX Con- ference on File and Storage Technologies (FAST), 2018."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3281031"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3465332.3470873"},{"key":"e_1_3_2_1_69_1","volume-title":"A performance study of lustre file system checker: Bottlenecks and potentials,\" in 2019 35th Symposium on Mass Storage Systems and Technologies (MSST)","author":"Dai D.","year":"2019","unstructured":"D. Dai , \" A performance study of lustre file system checker: Bottlenecks and potentials,\" in 2019 35th Symposium on Mass Storage Systems and Technologies (MSST) , 2019 . D. Dai et al., \"A performance study of lustre file system checker: Bottlenecks and potentials,\" in 2019 35th Symposium on Mass Storage Systems and Technologies (MSST), 2019."},{"key":"e_1_3_2_1_70_1","volume-title":"Understanding ssd reliability in large-scale cloud systems,\" in 2018 IEEE\/ACM 3rd International Workshop on Parallel Data Storage & Data Intensive Scalable Computing Systems (PDSW-DISCS)","author":"Xu E.","year":"2018","unstructured":"E. Xu , \" Understanding ssd reliability in large-scale cloud systems,\" in 2018 IEEE\/ACM 3rd International Workshop on Parallel Data Storage & Data Intensive Scalable Computing Systems (PDSW-DISCS) , 2018 . E. Xu et al., \"Understanding ssd reliability in large-scale cloud systems,\" in 2018 IEEE\/ACM 3rd International Workshop on Parallel Data Storage & Data Intensive Scalable Computing Systems (PDSW-DISCS), 2018."},{"key":"e_1_3_2_1_71_1","volume-title":"Lessons and actions: What we learned from 10k {ssd-related} storage system failures,\" in 2019 USENIX Annual Technical Conference (USENIX ATC)","author":"Xu E.","year":"2019","unstructured":"E. Xu , \" Lessons and actions: What we learned from 10k {ssd-related} storage system failures,\" in 2019 USENIX Annual Technical Conference (USENIX ATC) , 2019 . E. Xu et al., \"Lessons and actions: What we learned from 10k {ssd-related} storage system failures,\" in 2019 USENIX Annual Technical Conference (USENIX ATC), 2019."},{"key":"e_1_3_2_1_72_1","volume-title":"Networking and Communications (ICNC)","author":"Shi Y.","year":"2017","unstructured":"Y. Shi A Command-Level Study of Linux Kernel Bugs,\" in 2017 Inter- national Conference on Computing , Networking and Communications (ICNC) , 2017. Y. Shi et al., \"A Command-Level Study of Linux Kernel Bugs,\" in 2017 Inter- national Conference on Computing, Networking and Communications (ICNC), 2017."},{"key":"e_1_3_2_1_73_1","volume-title":"Gmprof: A low-overhead, fine-grained profiling approach for GPU programs,\" in 19th International Conference on High Performance Comput- ing (HiPC)","author":"Zheng M.","year":"2012","unstructured":"M. Zheng , \" Gmprof: A low-overhead, fine-grained profiling approach for GPU programs,\" in 19th International Conference on High Performance Comput- ing (HiPC) , 2012 . doi: 10.1109\/HiPC.2012.6507475. 10.1109\/HiPC.2012.6507475 M. Zheng et al., \"Gmprof: A low-overhead, fine-grained profiling approach for GPU programs,\" in 19th International Conference on High Performance Comput- ing (HiPC), 2012. doi: 10.1109\/HiPC.2012.6507475."},{"key":"e_1_3_2_1_74_1","volume-title":"Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)","author":"Huang D.","year":"2013","unstructured":"D. Huang : Hiding disk access latency for HPC applications with a new SSD-enabled data layout,\" in 2013 IEEE 21st International Symposium on Modelling , Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS) , 2013 . D. Huang et al., \"LiU: Hiding disk access latency for HPC applications with a new SSD-enabled data layout,\" in 2013 IEEE 21st International Symposium on Modelling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS), 2013."},{"issue":"1","key":"e_1_3_2_1_75_1","article-title":"Benchmarking for Observability: The Case of Diagnosing Storage Failures","volume":"1","author":"Zhang D.","year":"2021","unstructured":"D. Zhang , \" Benchmarking for Observability: The Case of Diagnosing Storage Failures ,\" BenchCouncil Transactions on Benchmarks, Standards and Evaluations (TBench) , vol. 1 , no. 1 , 2021 . doi: 10.1016\/j.tbench.2021.100006. 10.1016\/j.tbench.2021.100006 D. Zhang et al., \"Benchmarking for Observability: The Case of Diagnosing Storage Failures,\" BenchCouncil Transactions on Benchmarks, Standards and Evaluations (TBench), vol. 1, no. 1, 2021. doi: 10.1016\/j.tbench.2021.100006.","journal-title":"BenchCouncil Transactions on Benchmarks, Standards and Evaluations (TBench)"}],"event":{"name":"HPDC '22: The 31st International Symposium on High-Performance Parallel and Distributed Computing","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Minneapolis MN USA","acronym":"HPDC '22"},"container-title":["Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3502181.3531477","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3502181.3531477","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3502181.3531477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:49Z","timestamp":1750183789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3502181.3531477"}},"subtitle":["An I\/O-Centric Provenance Framework for Scientific Data on HPC Systems"],"short-title":[],"issued":{"date-parts":[[2022,6,27]]},"references-count":75,"alternative-id":["10.1145\/3502181.3531477","10.1145\/3502181"],"URL":"https:\/\/doi.org\/10.1145\/3502181.3531477","relation":{},"subject":[],"published":{"date-parts":[[2022,6,27]]},"assertion":[{"value":"2022-06-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}