{"id":"https://openalex.org/W4417174940","doi":"https://doi.org/10.1145/3750720.3757295","title":"Provenance Tracking in Large-Scale Machine Learning Systems","display_name":"Provenance Tracking in Large-Scale Machine Learning Systems","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4417174940","doi":"https://doi.org/10.1145/3750720.3757295"},"language":"en","primary_location":{"id":"doi:10.1145/3750720.3757295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750720.3757295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3750720.3757295?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3750720.3757295?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094119452","display_name":"Gabriele Padovani","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gabriele Padovani","raw_affiliation_strings":["DISI, University of Trento, Trento, Trentino, Italy"],"raw_orcid":"https://orcid.org/0009-0002-3711-7643","affiliations":[{"raw_affiliation_string":"DISI, University of Trento, Trento, Trentino, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026632303","display_name":"Valentine Anantharaj","orcid":"https://orcid.org/0000-0002-9356-1311"},"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":"Valentine Anantharaj","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-9356-1311","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037047082","display_name":"Sandro Fiore","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sandro Fiore","raw_affiliation_strings":["DISI, University of Trento, Trento, Trentino, Italy"],"raw_orcid":"https://orcid.org/0000-0002-8430-6087","affiliations":[{"raw_affiliation_string":"DISI, University of Trento, Trento, Trentino, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59265392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9664000272750854,"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":0.9664000272750854,"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":0.015399999916553497,"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/T12127","display_name":"Software System Performance and Reliability","score":0.0017999999690800905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7289999723434448},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.6567000150680542},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5569999814033508},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5094000101089478},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4431000053882599},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.39629998803138733},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.3930000066757202},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.37139999866485596},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3301999866962433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840999960899353},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7289999723434448},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.6567000150680542},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5569999814033508},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43309998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40709999203681946},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40059998631477356},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3833000063896179},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C118530786","wikidata":"https://www.wikidata.org/wiki/Q1134732","display_name":"Instrumentation (computer programming)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C198140048","wikidata":"https://www.wikidata.org/wiki/Q10859422","display_name":"Software versioning","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3750720.3757295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750720.3757295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3750720.3757295?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.01075","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.01075","pdf_url":"https://arxiv.org/pdf/2507.01075","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"pmh:oai:iris.unitn.it:11572/473810","is_oa":true,"landing_page_url":"https://dl.acm.org/doi/10.1145/3750720.3757295","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2507.01075","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01075","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3750720.3757295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3750720.3757295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3750720.3757295?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G375662711","display_name":null,"funder_award_id":"17/06/2022","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5356239126","display_name":null,"funder_award_id":"CN00000013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842645033","display_name":"An interdisciplinary Digital Twin Engine for science","funder_award_id":"101058386","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417174940.pdf","grobid_xml":"https://content.openalex.org/works/W4417174940.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2100197079","https://openalex.org/W4391093525","https://openalex.org/W4313156423","https://openalex.org/W3125458322","https://openalex.org/W3007609272","https://openalex.org/W4402404317","https://openalex.org/W4292121845","https://openalex.org/W4312349930","https://openalex.org/W2069028640","https://openalex.org/W4406157184","https://openalex.org/W3176771520","https://openalex.org/W2540743583","https://openalex.org/W4210916416","https://openalex.org/W4406459055","https://openalex.org/W4380928210","https://openalex.org/W4205738517","https://openalex.org/W3000668449","https://openalex.org/W3011096584","https://openalex.org/W3090519803","https://openalex.org/W4402674052","https://openalex.org/W4387007461","https://openalex.org/W2019371364","https://openalex.org/W4380885974"],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,10,51,63,106,135,150,179],"demand":[2],"for":[3,46,183],"large-scale":[4],"AI":[5,100,119],"models":[6,120],"continues":[7],"to":[8,15,116,141,165],"grow,":[9],"optimization":[11],"of":[12,68,108],"their":[13],"training":[14,57],"balance":[16,32],"computational":[17],"efficiency,":[18],"execution":[19],"time,":[20],"accuracy":[21],"and":[22,39,49,58,66,70,83,94,97,153,160,162],"energy":[23],"consumption":[24],"represents":[25],"a":[26,73,126,138],"critical":[27],"multidimensional":[28],"challenge.":[29],"Achieving":[30],"this":[31,77,104,131],"requires":[33],"not":[34],"only":[35],"innovative":[36],"algorithmic":[37],"techniques":[38],"hardware":[40],"architectures":[41],"but":[42],"also":[43,190],"comprehensive":[44],"tools":[45,170],"monitoring,":[47],"analyzing,":[48],"understanding":[50],"underlying":[52],"processes":[53],"involved":[54],"in":[55,76,99,121,145,187],"model":[56],"deployment.":[59],"Provenance":[60],"data\u2014information":[61],"about":[62],"origins,":[64],"context,":[65],"transformations":[67],"data":[69,144,168],"processes\u2014has":[71],"become":[72],"key":[74],"component":[75],"pursuit.":[78],"By":[79],"leveraging":[80],"provenance,":[81],"researchers":[82],"engineers":[84],"can":[85,112],"gain":[86],"insights":[87],"into":[88],"resource":[89],"usage":[90],"patterns,":[91],"identify":[92],"inefficiencies,":[93],"ensure":[95],"reproducibility":[96],"accountability":[98],"development":[101],"workflows.":[102],"For":[103],"reason,":[105],"question":[107],"how":[109],"distributed":[110],"resources":[111],"be":[113],"optimally":[114],"utilized":[115],"scale":[117],"large":[118],"an":[122],"energy-efficient":[123],"manner":[124],"is":[125,175],"fundamental":[127],"one.":[128],"To":[129],"support":[130],"effort,":[132],"we":[133],"introduce":[134],"yProv4ML":[136,156],"library,":[137],"tool":[139],"designed":[140],"collect":[142],"provenance":[143],"JSON":[146],"format,":[147],"compliant":[148],"with":[149,178],"W3C":[151],"PROV":[152],"ProvML":[154],"standards.":[155],"focuses":[157],"on":[158],"flexibility":[159],"extensibility,":[161],"enables":[163],"users":[164],"integrate":[166],"additional":[167],"collection":[169],"via":[171],"plugins.":[172],"The":[173],"library":[174],"fully":[176],"integrated":[177],"yProv":[180],"framework,":[181],"allowing":[182],"higher":[184],"level":[185],"pairing":[186],"tasks":[188],"run":[189],"through":[191],"workflow":[192],"management":[193],"systems.":[194]},"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}