{"id":"https://openalex.org/W4392825400","doi":"https://doi.org/10.1109/tpds.2024.3374555","title":"PROV-IO: A Cross-Platform Provenance Framework for Scientific Data on HPC Systems","display_name":"PROV-IO: A Cross-Platform Provenance Framework for Scientific Data on HPC Systems","publication_year":2024,"publication_date":"2024-03-14","ids":{"openalex":"https://openalex.org/W4392825400","doi":"https://doi.org/10.1109/tpds.2024.3374555"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3374555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3374555","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050327643","display_name":"Runzhou Han","orcid":"https://orcid.org/0000-0003-1440-7568"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Runzhou Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004195454","display_name":"Mai Zheng","orcid":"https://orcid.org/0000-0002-0741-3436"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mai Zheng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062233562","display_name":"Suren Byna","orcid":"https://orcid.org/0000-0003-3048-3448"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suren Byna","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039174701","display_name":"Houjun Tang","orcid":"https://orcid.org/0000-0001-7038-8360"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Houjun Tang","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101687868","display_name":"Bin Dong","orcid":"https://orcid.org/0000-0002-0725-0833"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Dong","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012002926","display_name":"Dong Dai","orcid":"https://orcid.org/0000-0003-4078-8149"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Dai","raw_affiliation_strings":["University of North Carolina, Charlotte, NC, USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina, Charlotte, NC, USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454473","display_name":"Yong Chen","orcid":"https://orcid.org/0009-0001-6525-6299"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Samsung Research Labs, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Samsung Research Labs, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655992","display_name":"Dongkyun Kim","orcid":"https://orcid.org/0000-0002-4222-7444"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongkyun Kim","raw_affiliation_strings":["Samsung Research Labs, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Samsung Research Labs, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012298536","display_name":"Joseph Hassoun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Hassoun","raw_affiliation_strings":["Samsung Research Labs, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Samsung Research Labs, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065376296","display_name":"David Thorsley","orcid":"https://orcid.org/0000-0001-8625-5095"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Thorsley","raw_affiliation_strings":["Samsung Research Labs, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Samsung Research Labs, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5050327643"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":6.4418,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.96198491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"35","issue":"5","first_page":"844","last_page":"861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7994846701622009},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5056250095367432},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.4615504741668701},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3832979202270508},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36512500047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994846701622009},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5056250095367432},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.4615504741668701},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3832979202270508},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36512500047683716},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3374555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3374555","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W168132470","https://openalex.org/W1552694902","https://openalex.org/W1765271930","https://openalex.org/W1964889439","https://openalex.org/W1967841763","https://openalex.org/W1973451694","https://openalex.org/W1979114612","https://openalex.org/W1983178058","https://openalex.org/W1988545508","https://openalex.org/W1994326726","https://openalex.org/W2019371364","https://openalex.org/W2023718005","https://openalex.org/W2032756564","https://openalex.org/W2063564815","https://openalex.org/W2064677272","https://openalex.org/W2069028640","https://openalex.org/W2117444998","https://openalex.org/W2168544140","https://openalex.org/W2171989756","https://openalex.org/W2302501749","https://openalex.org/W2515695346","https://openalex.org/W2548592627","https://openalex.org/W2602323293","https://openalex.org/W2768462553","https://openalex.org/W2791059415","https://openalex.org/W2890169599","https://openalex.org/W2896457183","https://openalex.org/W2903092728","https://openalex.org/W2907009609","https://openalex.org/W2914636073","https://openalex.org/W2948985893","https://openalex.org/W2949033485","https://openalex.org/W2973727699","https://openalex.org/W2982400926","https://openalex.org/W2982421692","https://openalex.org/W3000668449","https://openalex.org/W3005153041","https://openalex.org/W3011096584","https://openalex.org/W3042938130","https://openalex.org/W3087735676","https://openalex.org/W3090519803","https://openalex.org/W3111450607","https://openalex.org/W3121569598","https://openalex.org/W3185152627","https://openalex.org/W3193404501","https://openalex.org/W3211732556","https://openalex.org/W4200414623","https://openalex.org/W4220730878","https://openalex.org/W4283370878","https://openalex.org/W4288089799","https://openalex.org/W4298422451","https://openalex.org/W4313305673","https://openalex.org/W4384705386","https://openalex.org/W4384705434","https://openalex.org/W4385245566","https://openalex.org/W6628249541","https://openalex.org/W6628432071","https://openalex.org/W6628457668","https://openalex.org/W6629041467","https://openalex.org/W6633462303","https://openalex.org/W6639074551","https://openalex.org/W6679932842","https://openalex.org/W6727099177","https://openalex.org/W6741958422","https://openalex.org/W6755207826","https://openalex.org/W6763729197","https://openalex.org/W6767997687","https://openalex.org/W6769627184","https://openalex.org/W6783544800","https://openalex.org/W6799372109"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2354627941","https://openalex.org/W2347483153","https://openalex.org/W2384867379","https://openalex.org/W2353379336","https://openalex.org/W2379683085","https://openalex.org/W2363868702","https://openalex.org/W2374448931","https://openalex.org/W2376723740"],"abstract_inverted_index":{"Data":[0],"provenance,":[1],"or":[2],"data":[3,25,92],"lineage,":[4],"describes":[5],"the":[6,37,60,70,94,159,163],"life":[7],"cycle":[8],"of":[9,24,29,106,145,162],"data.":[10],"In":[11,48],"scientific":[12,55,91],"workflows":[13,56,134,151],"on":[14,69,115,135],"HPC":[15,117,137],"systems,":[16],"scientists":[17,62,165],"often":[18],"seek":[19],"diverse":[20],"provenance":[21,33,43,66,76,87,113,160],"(e.g.,":[22,170],"origins":[23],"products,":[26],"usage":[27],"patterns":[28],"datasets).":[30],"Unfortunately,":[31],"existing":[32],"solutions":[34],"cannot":[35],"address":[36,158],"challenges":[38],"due":[39],"to":[40,63,110],"their":[41],"incompatible":[42],"models":[44],"and/or":[45],"system":[46,186],"implementations.":[47],"this":[49],"paper,":[50],"we":[51,73,102],"analyze":[52],"four":[53],"representative":[54],"in":[57,141,189],"collaboration":[58],"with":[59,119,139,149,167],"domain":[61,164],"identify":[64],"concrete":[65],"needs.":[67],"Based":[68],"first-hand":[71],"analysis,":[72],"propose":[74],"a":[75,104,184],"framework":[77,127],"called":[78],"PROV-IO":[79,107,124,154,180],"<inline-formula><tex-math":[80,108,125,155,181],"notation=\"LaTeX\">$^+$</tex-math></inline-formula>":[81,109,126,156,182],",":[82],"which":[83],"includes":[84],"an":[85],"I/O-centric":[86],"model":[88],"for":[89,176],"describing":[90],"and":[93,98,132],"associated":[95],"I/O":[96],"operations":[97],"environments":[99],"precisely.":[100],"Moreover,":[101,179],"build":[103],"prototype":[105],"enable":[111],"end-to-end":[112],"support":[114,129],"real":[116],"systems":[118],"little":[120],"manual":[121],"effort.":[122],"The":[123],"can":[128,157],"both":[130],"containerized":[131],"non-containerized":[133],"different":[136],"platforms":[138],"flexibility":[140],"selecting":[142],"various":[143],"classes":[144],"provenance.":[146],"Our":[147],"experiments":[148],"realistic":[150],"show":[152],"that":[153],"needs":[161],"effectively":[166],"reasonable":[168],"performance":[169],"less":[171],"than":[172],"3.5%":[173],"tracking":[174],"overhead":[175],"most":[177],"experiments).":[178],"outperforms":[183],"state-of-the-art":[185],"(i.e.,":[187],"ProvLake)":[188],"our":[190],"experiments.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}