{"id":"https://openalex.org/W4387007461","doi":"https://doi.org/10.1109/e-science58273.2023.10254822","title":"Towards Lightweight Data Integration Using Multi-Workflow Provenance and Data Observability","display_name":"Towards Lightweight Data Integration Using Multi-Workflow Provenance and Data Observability","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4387007461","doi":"https://doi.org/10.1109/e-science58273.2023.10254822"},"language":"en","primary_location":{"id":"doi:10.1109/e-science58273.2023.10254822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science58273.2023.10254822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on e-Science (e-Science)","raw_type":"proceedings-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/A5042209170","display_name":"Renan P. Souza","orcid":"https://orcid.org/0000-0002-9479-4432"},"institutions":[{"id":"https://openalex.org/I4388482696","display_name":"Naval Research Laboratory Information Technology Division","ror":"https://ror.org/04xfp8b22","country_code":null,"type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028","https://openalex.org/I4388482696"]},{"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":true,"raw_author_name":"Renan Souza","raw_affiliation_strings":["National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4388482696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079278437","display_name":"Tyler J. Skluzacek","orcid":"https://orcid.org/0000-0003-2242-4931"},"institutions":[{"id":"https://openalex.org/I4388482696","display_name":"Naval Research Laboratory Information Technology Division","ror":"https://ror.org/04xfp8b22","country_code":null,"type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028","https://openalex.org/I4388482696"]},{"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":"Tyler J. Skluzacek","raw_affiliation_strings":["National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4388482696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034261249","display_name":"Sean R. Wilkinson","orcid":"https://orcid.org/0000-0002-1443-7479"},"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"]},{"id":"https://openalex.org/I4388482696","display_name":"Naval Research Laboratory Information Technology Division","ror":"https://ror.org/04xfp8b22","country_code":null,"type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028","https://openalex.org/I4388482696"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean R. Wilkinson","raw_affiliation_strings":["National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4388482696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013879711","display_name":"Maxim Ziatdinov","orcid":"https://orcid.org/0000-0003-2570-4592"},"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"]},{"id":"https://openalex.org/I4388482696","display_name":"Naval Research Laboratory Information Technology Division","ror":"https://ror.org/04xfp8b22","country_code":null,"type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028","https://openalex.org/I4388482696"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxim Ziatdinov","raw_affiliation_strings":["National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4388482696"]}]},{"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"]},{"id":"https://openalex.org/I4388482696","display_name":"Naval Research Laboratory Information Technology Division","ror":"https://ror.org/04xfp8b22","country_code":null,"type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028","https://openalex.org/I4388482696"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael Ferreira da Silva","raw_affiliation_strings":["National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4388482696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042209170"],"corresponding_institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4388482696"],"apc_list":null,"apc_paid":null,"fwci":9.051,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9746868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9914000034332275,"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":0.9868000149726868,"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":0.7838001251220703},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7771729230880737},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.7623556852340698},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5694088935852051},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5555786490440369},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5252924561500549},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4260067343711853},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3812670409679413},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.36836177110671997},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21814095973968506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838001251220703},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7771729230880737},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7623556852340698},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5694088935852051},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5555786490440369},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5252924561500549},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4260067343711853},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3812670409679413},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36836177110671997},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21814095973968506},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/e-science58273.2023.10254822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science58273.2023.10254822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3894026082","display_name":null,"funder_award_id":"DE-AC05-00OR22725,DE-AC05-00OR22725,DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1569403765","https://openalex.org/W1798528872","https://openalex.org/W1906647448","https://openalex.org/W1967093902","https://openalex.org/W2016488143","https://openalex.org/W2021171338","https://openalex.org/W2064862566","https://openalex.org/W2079429717","https://openalex.org/W2752857821","https://openalex.org/W2906035385","https://openalex.org/W2943761765","https://openalex.org/W2946003964","https://openalex.org/W3011096584","https://openalex.org/W3012014012","https://openalex.org/W3027848381","https://openalex.org/W3032545863","https://openalex.org/W3080278526","https://openalex.org/W3080577970","https://openalex.org/W3088331312","https://openalex.org/W3090519803","https://openalex.org/W3104388511","https://openalex.org/W3137837084","https://openalex.org/W3193404501","https://openalex.org/W3203236248","https://openalex.org/W3209936002","https://openalex.org/W4206264294","https://openalex.org/W4226038906","https://openalex.org/W4226278328","https://openalex.org/W4239417161","https://openalex.org/W4311434070","https://openalex.org/W4312081285","https://openalex.org/W4387236975","https://openalex.org/W4388855598","https://openalex.org/W4392297945","https://openalex.org/W4392825400","https://openalex.org/W6925554194"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W2104042711","https://openalex.org/W4206221578"],"abstract_inverted_index":{"Modern":[0],"large-scale":[1],"scientific":[2,29],"discovery":[3],"requires":[4],"multidisciplinary":[5],"collaboration":[6],"across":[7],"diverse":[8],"computing":[9],"facilities,":[10],"including":[11],"High":[12],"Performance":[13],"Computing":[14],"(HPC)":[15],"machines":[16],"and":[17,44,64,75,94,101,121,146],"the":[18,33,48,109,112,185],"Edge-to-Cloud":[19],"continuum.":[20],"Integrated":[21,86],"data":[22,70,91,123,143],"analysis":[23,141],"plays":[24],"a":[25,127,149],"crucial":[26],"role":[27],"in":[28,32,111,148,169],"discovery,":[30],"especially":[31],"current":[34],"AI":[35,40],"era,":[36],"by":[37],"enabling":[38],"Responsible":[39],"development,":[41],"FAIR,":[42],"Reproducibility,":[43],"User":[45],"Steering.":[46],"However,":[47],"heterogeneous":[49],"nature":[50],"of":[51],"science":[52,158],"poses":[53],"challenges":[54],"such":[55],"as":[56],"dealing":[57],"with":[58,164],"multiple":[59,162],"supporting":[60],"tools,":[61],"cross-facility":[62],"environments,":[63],"efficient":[65],"HPC":[66],"execution.":[67],"Building":[68],"on":[69,161,180,184],"observability,":[71,106],"adapter":[72],"system":[73],"design,":[74],"provenance,":[76,120],"we":[77],"propose":[78],"MIDA:":[79],"an":[80],"approach":[81],"for":[82,97,131,156],"lightweight":[83],"runtime":[84,125],"Multi-workflow":[85],"Data":[87],"Analysis.":[88],"MIDA":[89],"defines":[90],"observability":[92],"strategies":[93],"adaptability":[95],"methods":[96],"various":[98],"parallel":[99],"systems":[100],"machine":[102],"learning":[103,153],"tools.":[104],"With":[105],"it":[107],"intercepts":[108],"dataflows":[110],"background":[113],"without":[114],"requiring":[115],"instrumentation":[116],"while":[117],"integrating":[118,142],"domain,":[119],"telemetry":[122],"at":[124],"into":[126],"unified":[128],"database":[129],"ready":[130],"user":[132],"steering":[133],"queries.":[134],"We":[135,171],"conduct":[136],"experiments":[137],"showing":[138],"end-to-end":[139],"multi-workflow":[140],"from":[144],"Dask":[145],"MLFlow":[147],"real":[150],"distributed":[151],"deep":[152],"use":[154],"case":[155],"materials":[157],"that":[159],"runs":[160],"environments":[163],"up":[165,176],"to":[166,177],"276":[167],"GPUs":[168],"parallel.":[170],"show":[172],"near-zero":[173],"overhead":[174],"running":[175],"100,000":[178],"tasks":[179],"1,680":[181],"CPU":[182],"cores":[183],"Summit":[186],"supercomputer.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}