{"id":"https://openalex.org/W7162415480","doi":"https://doi.org/10.1145/3788853.3801877","title":"An (Updated) Overview of Data Provenance: Concepts, Challenges and Opportunities","display_name":"An (Updated) Overview of Data Provenance: Concepts, Challenges and Opportunities","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162415480","doi":"https://doi.org/10.1145/3788853.3801877"},"language":null,"primary_location":{"id":"doi:10.1145/3788853.3801877","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801877","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":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788853.3801877","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080325696","display_name":"Chrysanthi Kosyfaki","orcid":"https://orcid.org/0000-0002-0920-1437"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chrysanthi Kosyfaki","raw_affiliation_strings":["Hong Kong University of Science and Technology, Clear Water Bay, New Territories, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-0920-1437","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Clear Water Bay, New Territories, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129762005","display_name":"Paul Groth","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paul Groth","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0183-6910","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"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":0.84500433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"563","last_page":"570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.953000009059906,"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":0.953000009059906,"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":0.014000000432133675,"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/T14427","display_name":"Environmental Monitoring and Data Management","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2815999984741211},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.26589998602867126},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.26589998602867126},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.259799987077713},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.25099998712539673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41920000314712524},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.28380000591278076},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.24330000579357147},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.23960000276565552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788853.3801877","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801877","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":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788853.3801877","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801877","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":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W274239259","https://openalex.org/W1552694902","https://openalex.org/W1582521812","https://openalex.org/W1988545508","https://openalex.org/W1999563429","https://openalex.org/W2023230299","https://openalex.org/W2063871082","https://openalex.org/W2099360200","https://openalex.org/W2114998795","https://openalex.org/W2125399128","https://openalex.org/W2127279146","https://openalex.org/W2131760692","https://openalex.org/W2152577585","https://openalex.org/W2165766811","https://openalex.org/W2293299776","https://openalex.org/W2583856578","https://openalex.org/W2613457660","https://openalex.org/W2743230100","https://openalex.org/W2888214251","https://openalex.org/W2889523940","https://openalex.org/W2893640193","https://openalex.org/W2919933843","https://openalex.org/W2948985893","https://openalex.org/W2955344300","https://openalex.org/W3021830120","https://openalex.org/W3049189941","https://openalex.org/W3112547247","https://openalex.org/W3169050797","https://openalex.org/W3173090758","https://openalex.org/W3177222803","https://openalex.org/W4220709071","https://openalex.org/W4221090794","https://openalex.org/W4230159918","https://openalex.org/W4231337418","https://openalex.org/W4232632123","https://openalex.org/W4285606919","https://openalex.org/W4289534019","https://openalex.org/W4311703141","https://openalex.org/W4313502410","https://openalex.org/W4365786623","https://openalex.org/W4380928210","https://openalex.org/W4386768917","https://openalex.org/W4396892533","https://openalex.org/W4405377093","https://openalex.org/W4414244639","https://openalex.org/W4414427896"],"related_works":[],"abstract_inverted_index":{"Data":[0],"provenance,":[1],"also":[2],"known":[3],"as":[4],"data":[5,14,23,42,49,60,105,136],"lineage,":[6],"tracks":[7],"the":[8,26,36,102,109],"origins,":[9],"transformations,":[10],"and":[11,32,40,56,64,69,87,98,140],"movements":[12],"of":[13,78],"throughout":[15],"its":[16],"lifecycle.":[17],"This":[18,93],"concept":[19],"was":[20],"popularized":[21],"within":[22],"management":[24],"in":[25,44,58,101,131],"early":[27],"2000s":[28],"by":[29],"Buneman,":[30],"Khanna,":[31],"Tan":[33],"to":[34,38],"address":[35],"need":[37],"understand":[39],"verify":[41],"modifications":[43],"complex":[45],"systems.":[46],"Since":[47],"then,":[48],"provenance":[50,106],"has":[51,124],"seen":[52],"significant":[53],"development,":[54],"research,":[55],"application":[57],"various":[59],"systems,":[61,68,81,142],"including":[62],"relational":[63,110,146],"NoSQL":[65],"databases,":[66],"workflow":[67],"scientific":[70],"computing":[71],"platforms.":[72],"Moreover,":[73],"there":[74,123],"is":[75],"a":[76,126],"rise":[77],"explainable":[79],"AI":[80],"regulatory":[82],"frameworks":[83],"demanding":[84],"transparency":[85],"(GDPR),":[86],"cloud":[88],"architectures":[89],"requiring":[90],"lineage":[91],"tracking.":[92],"growth":[94],"reflects":[95],"both":[96],"industrial":[97],"academic":[99],"interest":[100],"field.":[103],"Initially,":[104],"focused":[107],"on":[108],"model,":[111],"with":[112],"semantics":[113],"expressed":[114],"through":[115],"why-provenance,":[116],"where-provenance":[117],"and,":[118],"how-provenance.":[119],"However,":[120],"more":[121],"recently,":[122],"been":[125],"shift":[127],"towards":[128],"broader":[129],"applications":[130],"machine":[132],"learning":[133],"pipelines,":[134],"big":[135],"frameworks,":[137],"knowledge":[138],"graphs,":[139],"streaming":[141],"expanding":[143],"beyond":[144],"traditional":[145],"databases.":[147]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-27T00:00:00"}
