{"id":"https://openalex.org/W7160898571","doi":"https://doi.org/10.1145/3807899.3808688","title":"End-to-End Auditing of ML Pipelines through Data Provenance and Model Explainability","display_name":"End-to-End Auditing of ML Pipelines through Data Provenance and Model Explainability","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7160898571","doi":"https://doi.org/10.1145/3807899.3808688"},"language":null,"primary_location":{"id":"doi:10.1145/3807899.3808688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807899.3808688","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 Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807899.3808688","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114738677","display_name":"Pasquale Leonardo Lazzaro","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pasquale Leonardo Lazzaro","raw_affiliation_strings":["Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy"],"raw_orcid":"https://orcid.org/0009-0008-4634-6564","affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135948179","display_name":"Elia Guglielmi","orcid":"https://orcid.org/0009-0001-7772-2680"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elia Guglielmi","raw_affiliation_strings":["Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy"],"raw_orcid":"https://orcid.org/0009-0001-7772-2680","affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018918066","display_name":"Paolo Missier","orcid":"https://orcid.org/0000-0002-0978-2446"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paolo Missier","raw_affiliation_strings":["School of Computer Science, University of Birmingham, Birmingham, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-0978-2446","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005845219","display_name":"Riccardo Torlone","orcid":"https://orcid.org/0000-0003-1484-3693"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Torlone","raw_affiliation_strings":["Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1484-3693","affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria Sezione di Informatica e Automazione, Universit\u00e0 degli Studi Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60566882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.6421999931335449,"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":0.6421999931335449,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.03200000151991844,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10142","display_name":"Formal Methods in Verification","score":0.031300000846385956,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/pipeline-transport","display_name":"Pipeline transport","score":0.6462000012397766},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.5056999921798706},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.43149998784065247}],"concepts":[{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6462000012397766},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.397599995136261},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.34529998898506165},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.34529998898506165},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3260999917984009},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C77595967","wikidata":"https://www.wikidata.org/wiki/Q3151013","display_name":"Forensic engineering","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2590000033378601}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3807899.3808688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807899.3808688","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 Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/550156","is_oa":false,"landing_page_url":"https://hdl.handle.net/11590/550156","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3807899.3808688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807899.3808688","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 Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1552694902","https://openalex.org/W2167541073","https://openalex.org/W2432911982","https://openalex.org/W2962756421","https://openalex.org/W4412663328"],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"reliable":[1],"machine":[2],"learning":[3],"solutions":[4],"requires":[5],"rigorous":[6],"end-to-end":[7,60],"auditing":[8],"of":[9,45,166],"the":[10,43,140,172],"entire":[11,141],"data":[12,20,39,61,72,83,125,168],"lifecycle.":[13],"However,":[14],"in":[15,89,186,193],"complex":[16,167],"data-centric":[17],"ML":[18],"pipelines,":[19],"preparation":[21],"and":[22,103,123,129,182,188],"model":[23,76,87,136],"training":[24,124],"are":[25],"often":[26],"treated":[27],"as":[28,120],"isolated":[29],"silos,":[30],"making":[31],"it":[32],"fundamentally":[33],"difficult":[34],"to":[35,65,98,134],"trace":[36],"how":[37],"specific":[38],"manipulation":[40],"steps":[41],"affect":[42],"behavior":[44],"a":[46,94,105,145],"deployed":[47],"model.":[48],"In":[49],"this":[50,67,112],"paper,":[51],"we":[52],"present":[53],"PROXAI":[54,131],"(PROvenance":[55],"for":[56,179],"eXplainable":[57],"AI),":[58],"an":[59],"management":[62],"architecture":[63],"designed":[64],"bridge":[66],"gap":[68],"by":[69],"integrating":[70],"multi-granular":[71],"provenance":[73,108,113],"with":[74,115,157],"influence-based":[75],"interpretability.":[77],"Unlike":[78],"tools":[79],"that":[80,152],"only":[81],"track":[82],"lineage":[84],"or":[85],"analyze":[86],"weights":[88],"isolation,":[90],"our":[91],"framework":[92],"utilizes":[93],"Large":[95],"Language":[96],"Model":[97],"orchestrate":[99],"semantic":[100,154],"pipeline":[101,191],"segmentation":[102],"populate":[104],"comprehensive":[106],"graph-based":[107],"repository.":[109],"By":[110],"coupling":[111],"metadata":[114],"Explainable":[116],"AI":[117],"metrics,":[118],"such":[119],"SHAP":[121],"values":[122],"influence":[126],"functions":[127],"(First-Order":[128],"TracIn),":[130],"allows":[132],"practitioners":[133],"debug":[135],"failures":[137],"systematically":[138],"across":[139],"pipeline.":[142],"It":[143],"introduces":[144],"novel":[146],"hybrid":[147],"Retrieval-Augmented":[148],"Generation":[149],"(RAG)":[150],"interface":[151],"combines":[153],"vector":[155],"search":[156],"topological":[158],"graph":[159],"embeddings":[160],"(Node2Vec),":[161],"enabling":[162],"natural":[163],"language":[164],"traversal":[165],"pipelines.":[169],"We":[170],"describe":[171],"system":[173],"architecture,":[174],"its":[175,184],"decoupled":[176],"execution":[177],"strategies":[178],"dependency":[180],"management,":[181],"demonstrate":[183],"effectiveness":[185],"identifying":[187],"resolving":[189],"critical":[190],"errors":[192],"real-world":[194],"scenarios.":[195]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-13T00:00:00"}