{"id":"https://openalex.org/W2200241032","doi":"https://doi.org/10.1109/bigdata.2015.7364047","title":"Big data provenance: Challenges, state of the art and opportunities","display_name":"Big data provenance: Challenges, state of the art and opportunities","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2200241032","doi":"https://doi.org/10.1109/bigdata.2015.7364047","mag":"2200241032","pmid":"https://pubmed.ncbi.nlm.nih.gov/29399671"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7364047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mdsoar.org/bitstreams/bcb94da4-da60-44de-8c38-7c2ca8ea834f/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101750217","display_name":"Jianwu Wang","orcid":"https://orcid.org/0000-0002-9933-1170"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianwu Wang","raw_affiliation_strings":["Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD, U.S.A","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002534857","display_name":"Daniel Crawl","orcid":"https://orcid.org/0000-0003-1013-8241"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Crawl","raw_affiliation_strings":["San Diego Supercomputer Center, University of California, San Diego, La Jolla, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center, University of California, San Diego, La Jolla, CA, U.S.A","institution_ids":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010043183","display_name":"Shweta Purawat","orcid":"https://orcid.org/0000-0002-5183-2750"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shweta Purawat","raw_affiliation_strings":["San Diego Supercomputer Center, University of California, San Diego, La Jolla, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center, University of California, San Diego, La Jolla, CA, U.S.A","institution_ids":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101845660","display_name":"Mai Thanh Thi Nguyen","orcid":"https://orcid.org/0000-0001-8006-4028"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mai Nguyen","raw_affiliation_strings":["San Diego Supercomputer Center, University of California, San Diego, La Jolla, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center, University of California, San Diego, La Jolla, CA, U.S.A","institution_ids":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028701796","display_name":"\u0130lkay Alt\u0131nta\u015f","orcid":"https://orcid.org/0000-0002-2196-0305"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilkay Altintas","raw_affiliation_strings":["San Diego Supercomputer Center, University of California, San Diego, La Jolla, CA, U.S.A"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center, University of California, San Diego, La Jolla, CA, U.S.A","institution_ids":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101750217"],"corresponding_institution_ids":["https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":22.6628,"has_fulltext":true,"cited_by_count":95,"citation_normalized_percentile":{"value":0.99162827,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2015","issue":null,"first_page":"2509","last_page":"2516"},"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/T11937","display_name":"Research Data Management Practices","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9599000215530396,"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/provenance","display_name":"Provenance","score":0.8652889132499695},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8612953424453735},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8335504531860352},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.727683961391449},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.7234611511230469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6757875680923462},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.41886916756629944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27074018120765686},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25305530428886414}],"concepts":[{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.8652889132499695},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8612953424453735},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8335504531860352},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.727683961391449},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7234611511230469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757875680923462},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.41886916756629944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27074018120765686},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25305530428886414},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/bigdata.2015.7364047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmid:29399671","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29399671","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings : ... IEEE International Conference on Big Data. IEEE International Conference on Big Data","raw_type":null},{"id":"pmh:oai:mdsoar.org:11603/31616","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/31616","pdf_url":"https://mdsoar.org/bitstreams/bcb94da4-da60-44de-8c38-7c2ca8ea834f/download","source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:pubmedcentral.nih.gov:5796788","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5796788","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Big Data","raw_type":"Text"},{"id":"doi:10.13016/m2q4w9-011v","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2q4w9-011v","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:mdsoar.org:11603/31616","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/31616","pdf_url":"https://mdsoar.org/bitstreams/bcb94da4-da60-44de-8c38-7c2ca8ea834f/download","source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3261282454","display_name":"ABI Development: bioKepler: A Comprehensive Bioinformatics Scientific Workflow Module for Distributed Analysis of Large-Scale Biological Data","funder_award_id":"1062565","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713346733","display_name":null,"funder_award_id":"P41 GM103426","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6345853531","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7199578972","display_name":null,"funder_award_id":"GM103426","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7264659024","display_name":null,"funder_award_id":"1331615","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7786736537","display_name":null,"funder_award_id":"62565","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8710349911","display_name":null,"funder_award_id":"DE-SC0012630","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309204","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2200241032.pdf","grobid_xml":"https://content.openalex.org/works/W2200241032.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W22495568","https://openalex.org/W89955767","https://openalex.org/W135267584","https://openalex.org/W161296890","https://openalex.org/W180519810","https://openalex.org/W1501507312","https://openalex.org/W1543225912","https://openalex.org/W1582664144","https://openalex.org/W1659560869","https://openalex.org/W1794174336","https://openalex.org/W1798525880","https://openalex.org/W1813492422","https://openalex.org/W1935979693","https://openalex.org/W1940361326","https://openalex.org/W1966952999","https://openalex.org/W1971433346","https://openalex.org/W1981868776","https://openalex.org/W1994326726","https://openalex.org/W2003017496","https://openalex.org/W2022280610","https://openalex.org/W2023116290","https://openalex.org/W2063652569","https://openalex.org/W2071598946","https://openalex.org/W2080731889","https://openalex.org/W2085496318","https://openalex.org/W2098028511","https://openalex.org/W2098935637","https://openalex.org/W2133986470","https://openalex.org/W2136895839","https://openalex.org/W2155909634","https://openalex.org/W4230704764","https://openalex.org/W4297814130","https://openalex.org/W4299639459"],"related_works":["https://openalex.org/W2354627941","https://openalex.org/W2347483153","https://openalex.org/W2353379336","https://openalex.org/W2379683085","https://openalex.org/W2363868702","https://openalex.org/W2374448931","https://openalex.org/W2376723740","https://openalex.org/W2370535391","https://openalex.org/W2370679613","https://openalex.org/W2380057024"],"abstract_inverted_index":{"Ability":[0],"to":[1,11,84,121],"track":[2],"provenance":[3,36,54,64,82,93,114],"is":[4],"a":[5,118],"key":[6],"feature":[7],"of":[8,28,39,50,79,87,94],"scientific":[9],"workflows":[10,116],"support":[12],"data":[13],"lineage":[14],"and":[15,26,37,48,60,70,77,91,110],"reproducibility.":[16],"The":[17,45],"challenges":[18,34,59,76],"that":[19,98],"are":[20],"introduced":[21],"by":[22],"the":[23,63,75,85,88,92,95],"volume,":[24],"variety":[25,49],"velocity":[27],"Big":[29,40,52,80,112,123],"Data,":[30,41],"also":[31,103],"pose":[32],"related":[33,83],"for":[35],"quality":[38],"defined":[42],"as":[43,117],"veracity.":[44],"increasing":[46],"size":[47],"distributed":[51],"Data":[53,81,113],"information":[55],"bring":[56],"new":[57],"technical":[58],"opportunities":[61,78],"throughout":[62],"lifecycle":[65],"including":[66],"recording,":[67],"querying,":[68],"sharing":[69],"utilization.":[71],"This":[72],"paper":[73],"discusses":[74],"veracity":[86],"datasets":[89],"themselves":[90],"analytical":[96],"processes":[97],"analyze":[99,122],"these":[100],"datasets.":[101],"It":[102],"explains":[104],"our":[105],"current":[106],"efforts":[107],"towards":[108],"tracking":[109],"utilizing":[111],"using":[115],"programming":[119],"model":[120],"Data.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}