{"id":"https://openalex.org/W4416004498","doi":"https://doi.org/10.1145/3731599.3767582","title":"LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology","display_name":"LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004498","doi":"https://doi.org/10.1145/3731599.3767582"},"language":"en","primary_location":{"id":"doi:10.1145/3731599.3767582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767582","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767582","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101762558","display_name":"Renan Souza","orcid":"https://orcid.org/0000-0002-1794-808X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renan Souza","raw_affiliation_strings":["Oak Ridge National Lab., Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-1794-808X","affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab., Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120297698","display_name":"Timothy Poteet","orcid":"https://orcid.org/0009-0003-6105-3050"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy Poteet","raw_affiliation_strings":["Oak Ridge National Lab., Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0009-0003-6105-3050","affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab., Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005043233","display_name":"Brian D. Etz","orcid":"https://orcid.org/0000-0002-0855-4863"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Etz","raw_affiliation_strings":["Oak Ridge National Lab., Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-0855-4863","affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab., Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103164271","display_name":"Daniel Rosendo","orcid":"https://orcid.org/0000-0003-1175-8426"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Rosendo","raw_affiliation_strings":["Oak Ridge National Lab., Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0003-1175-8426","affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab., Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102942440","display_name":"Amal Gueroudji","orcid":"https://orcid.org/0009-0004-4830-3139"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amal Gueroudji","raw_affiliation_strings":["Argonne National Lab., Lemont, USA"],"raw_orcid":"https://orcid.org/0009-0004-4830-3139","affiliations":[{"raw_affiliation_string":"Argonne National Lab., Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082901516","display_name":"Woong Shin","orcid":"https://orcid.org/0000-0001-7207-7814"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Woong Shin","raw_affiliation_strings":["Oak Ridge National Lab., Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0001-7207-7814","affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab., Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068721920","display_name":"Prasanna Balaprakash","orcid":"https://orcid.org/0000-0002-0292-5715"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasanna Balaprakash","raw_affiliation_strings":["Oak Ridge National Lab., Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-0292-5715","affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab., Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072339196","display_name":"Rafael Ferreira da Silva","orcid":"https://orcid.org/0000-0002-1720-0928"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael Ferreira da Silva","raw_affiliation_strings":["Oak Ridge National Lab., Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-1720-0928","affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab., Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2257","last_page":"2268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8720999956130981,"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":0.8720999956130981,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.10649999976158142,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.002300000051036477,"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/workflow","display_name":"Workflow","score":0.83160001039505},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6323000192642212},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48750001192092896},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4325000047683716},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.33629998564720154},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.3343999981880188},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.33399999141693115},{"id":"https://openalex.org/keywords/workflow-engine","display_name":"Workflow engine","score":0.33169999718666077}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.83160001039505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095999956130981},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.33169999718666077},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731599.3767582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767582","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.13978","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.13978","pdf_url":"https://arxiv.org/pdf/2509.13978","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767582","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1988545508","https://openalex.org/W2079429717","https://openalex.org/W3082494217","https://openalex.org/W3090519803","https://openalex.org/W3217337599","https://openalex.org/W4206264294","https://openalex.org/W4392358084","https://openalex.org/W4396827151","https://openalex.org/W4398174193","https://openalex.org/W4403537101","https://openalex.org/W4410454004","https://openalex.org/W4412663328","https://openalex.org/W4414299303","https://openalex.org/W6968612307"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"scientific":[1],"discovery":[2],"increasingly":[3],"relies":[4],"on":[5,60],"workflows":[6],"that":[7,84,103,128],"process":[8],"data":[9,26,50,69,94],"across":[10,112],"the":[11,48],"Edge,":[12],"Cloud,":[13],"and":[14,21,35,53,81,116,122,133,139],"High":[15],"Performance":[16],"Computing":[17],"(HPC)":[18],"continuum.":[19],"Comprehensive":[20],"in-depth":[22],"analyses":[23],"of":[24],"these":[25],"are":[27],"critical":[28],"for":[29,92],"hypothesis":[30],"validation,":[31],"anomaly":[32],"detection,":[33],"reproducibility,":[34],"impactful":[36],"findings.":[37],"Although":[38],"workflow":[39],"provenance":[40,49,109],"techniques":[41],"support":[42],"such":[43],"analyses,":[44],"at":[45],"large":[46],"scale,":[47],"become":[51],"complex":[52],"difficult":[54],"to":[55],"analyze.":[56],"Existing":[57],"systems":[58],"depend":[59],"custom":[61],"scripts,":[62],"structured":[63,108],"queries,":[64],"or":[65],"static":[66],"dashboards,":[67],"limiting":[68],"interaction.":[70],"In":[71],"this":[72],"work,":[73],"we":[74],"introduce":[75],"an":[76],"evaluation":[77],"methodology,":[78],"reference":[79],"architecture,":[80],"open-source":[82],"implementation":[83],"leverages":[85],"interactive":[86],"Large":[87],"Language":[88],"Model":[89],"(LLM)":[90],"agents":[91],"runtime":[93],"analysis.":[95],"Our":[96],"approach":[97],"uses":[98],"a":[99,123],"lightweight,":[100],"metadata-driven":[101],"design":[102],"translates":[104],"natural":[105],"language":[106],"into":[107],"queries.":[110],"Evaluations":[111],"LLaMA,":[113],"GPT,":[114],"Gemini,":[115],"Claude,":[117],"covering":[118],"diverse":[119],"query":[120],"classes":[121],"real-world":[124],"chemistry":[125],"workflow,":[126],"show":[127],"modular":[129],"design,":[130],"prompt":[131],"tuning,":[132],"Retrieval-Augmented":[134],"Generation":[135],"(RAG)":[136],"enable":[137],"accurate":[138],"insightful":[140],"LLM":[141],"agent":[142],"responses":[143],"beyond":[144],"recorded":[145],"provenance.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
