{"id":"https://openalex.org/W3045754299","doi":"https://doi.org/10.1145/3394486.3403205","title":"Vamsa: Automated Provenance Tracking in Data Science Scripts","display_name":"Vamsa: Automated Provenance Tracking in Data Science Scripts","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3045754299","doi":"https://doi.org/10.1145/3394486.3403205","mag":"3045754299"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403205","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403205","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mohammad Hossein Namaki","orcid":null},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Hossein Namaki","raw_affiliation_strings":["Washington State University, Pullman, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, WA, USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Avrilia Floratou","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avrilia Floratou","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fotis Psallidas","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fotis Psallidas","raw_affiliation_strings":["Microsoft, Redmond, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Subru Krishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subru Krishnan","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ashvin Agrawal","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashvin Agrawal","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yinghui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinghui Wu","raw_affiliation_strings":["Case Western Reserve University, Cleveland, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Western Reserve University, Cleveland, OH, USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiwen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiwen Zhu","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":null,"display_name":"Markus Weimer","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Markus Weimer","raw_affiliation_strings":["Microsoft, Sunnyvale, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1542","last_page":"1551"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9868999719619751,"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/scripting-language","display_name":"Scripting language","score":0.7620999813079834},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.657800018787384},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6046000123023987},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.37610000371932983},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.35109999775886536},{"id":"https://openalex.org/keywords/tracking-system","display_name":"Tracking system","score":0.2971000075340271}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7620999813079834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454000115394592},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.657800018787384},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44620001316070557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4169999957084656},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C2983325608","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Data association","level":3,"score":0.251800000667572},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394486.3403205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403205","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403205","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.01861","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.01861","pdf_url":"https://arxiv.org/pdf/2001.01861","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"}],"best_oa_location":{"id":"doi:10.1145/3394486.3403205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403205","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403205","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3045754299.pdf","grobid_xml":"https://content.openalex.org/works/W3045754299.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W22495568","https://openalex.org/W1545590260","https://openalex.org/W1906647448","https://openalex.org/W1959365993","https://openalex.org/W1983178058","https://openalex.org/W2047182010","https://openalex.org/W2072269087","https://openalex.org/W2583856578","https://openalex.org/W2614986686","https://openalex.org/W2616121800","https://openalex.org/W2784241156","https://openalex.org/W2784722566","https://openalex.org/W2798535736","https://openalex.org/W2801126065","https://openalex.org/W2808972066","https://openalex.org/W2929793114","https://openalex.org/W2949053898","https://openalex.org/W2969671095","https://openalex.org/W6608436939","https://openalex.org/W6639080219"],"related_works":[],"abstract_inverted_index":{"There":[0],"has":[1],"recently":[2],"been":[3,82],"a":[4,43,79],"lot":[5],"of":[6,12,17,29,39,46,88,103],"ongoing":[7],"research":[8],"in":[9,78,96,100],"the":[10,24,35,47,53,64,69,86,94,101,105],"areas":[11],"fairness,":[13],"bias":[14],"and":[15,52],"explainability":[16],"machine":[18],"learning":[19],"(ML)":[20],"models":[21,51],"due":[22],"to":[23,56,73,84],"self-evident":[25],"or":[26],"regulatory":[27],"requirements":[28],"various":[30],"ML":[31,50,65,90],"applications.":[32],"We":[33,92],"make":[34],"following":[36],"observation:":[37],"All":[38],"these":[40],"approaches":[41],"require":[42],"robust":[44],"understanding":[45],"relationship":[48],"between":[49],"data":[54,111],"used":[55,83,109],"train":[57],"them.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"introduce":[63],"provenance":[66],"tracking":[67],"problem:":[68],"fundamental":[70],"idea":[71],"is":[72],"automatically":[74],"track":[75],"which":[76],"columns":[77],"dataset":[80],"have":[81],"derive":[85],"features/labels":[87],"an":[89],"model.":[91],"discuss":[93],"challenges":[95],"capturing":[97],"such":[98],"information":[99],"context":[102],"Python,":[104],"most":[106],"common":[107],"language":[108],"by":[110],"scientists.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2020-08-03T00:00:00"}