{"id":"https://openalex.org/W4412663328","doi":"https://doi.org/10.1186/s40537-025-01209-3","title":"An LLM-guided platform for multi-granular collection and management of data provenance","display_name":"An LLM-guided platform for multi-granular collection and management of data provenance","publication_year":2025,"publication_date":"2025-07-26","ids":{"openalex":"https://openalex.org/W4412663328","doi":"https://doi.org/10.1186/s40537-025-01209-3"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-025-01209-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01209-3","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01209-3","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01209-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099161613","display_name":"Luca Gregori","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":"Luca Gregori","raw_affiliation_strings":["DICITA, Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"DICITA, Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","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":["DICITA, Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"DICITA, Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070576777","display_name":"Michele Di Lazzaro","orcid":"https://orcid.org/0000-0002-5001-4537"},"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":"Marialaura Lazzaro","raw_affiliation_strings":["DICITA, Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"DICITA, Universit\u00e0 Roma Tre, Roma, 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":true,"raw_author_name":"Paolo Missier","raw_affiliation_strings":["School of Computer Science, University of Birmingham, Birmingham, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, Birmingham, UK","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":["DICITA, Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"DICITA, Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018918066"],"corresponding_institution_ids":["https://openalex.org/I79619799"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":4.4311,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94898922,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"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/T11937","display_name":"Research Data Management Practices","score":0.9966999888420105,"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":0.9927999973297119,"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/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.7585328221321106},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405688762664795},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.5259854197502136},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37435394525527954},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.21046331524848938},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.12093490362167358}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.7585328221321106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405688762664795},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.5259854197502136},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37435394525527954},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.21046331524848938},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.12093490362167358},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s40537-025-01209-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01209-3","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01209-3","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2558adb29a5d470bb1a0cbfa436842fb","is_oa":true,"landing_page_url":"https://doaj.org/article/2558adb29a5d470bb1a0cbfa436842fb","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 12, Iss 1, Pp 1-28 (2025)","raw_type":"article"},{"id":"pmh:oai:iris.uniroma3.it:11590/520376","is_oa":false,"landing_page_url":"https://hdl.handle.net/11590/520376","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/article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/6ae0f859-8cf4-4cc9-8fd2-11a33a2c0ef2","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/6ae0f859-8cf4-4cc9-8fd2-11a33a2c0ef2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gregori, L, Lazzaro, P L, Lazzaro, M, Missier, P & Torlone, R 2025, 'An LLM-guided platform for multi-granular collection and management of data provenance', Journal of Big Data, vol. 12, no. 1, 187. https://doi.org/10.1186/s40537-025-01209-3","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-025-01209-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01209-3","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01209-3","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412663328.pdf","grobid_xml":"https://content.openalex.org/works/W4412663328.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1906647448","https://openalex.org/W2116984840","https://openalex.org/W2119325664","https://openalex.org/W2466173809","https://openalex.org/W2600741786","https://openalex.org/W2606811865","https://openalex.org/W2752857821","https://openalex.org/W2885025596","https://openalex.org/W2891503716","https://openalex.org/W2945172243","https://openalex.org/W2951565607","https://openalex.org/W3045754299","https://openalex.org/W3082494217","https://openalex.org/W3086791196","https://openalex.org/W3105684693","https://openalex.org/W3105704032","https://openalex.org/W3125323336","https://openalex.org/W3134111219","https://openalex.org/W4210354100","https://openalex.org/W4230159918","https://openalex.org/W4312302709","https://openalex.org/W4399728785"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"As":[0],"machine":[1,84],"learning":[2,85],"and":[3,60,68,143,169],"AI":[4],"systems":[5],"become":[6],"more":[7],"prevalent,":[8],"understanding":[9],"how":[10,39],"their":[11,19],"decisions":[12],"are":[13,41],"made":[14],"is":[15,26,87],"key":[16],"to":[17,50,89,99],"maintaining":[18],"trust.":[20],"To":[21],"solve":[22],"this":[23,112,141],"problem,":[24],"it":[25],"widely":[27],"accepted":[28],"that":[29],"fundamental":[30],"support":[31],"can":[32],"be":[33],"provided":[34],"by":[35],"the":[36,44,58,91,97,125,151,155,160,176],"knowledge":[37],"of":[38,62,72,81,106,127,149,162,164],"data":[40,48,70,73,77,108,121,180,189],"altered":[42],"in":[43,76,136,154,184],"pre-processing":[45,107],"phase,":[46],"using":[47],"provenance":[49,71,122,177],"track":[51],"such":[52],"changes.":[53],"This":[54],"paper":[55],"focuses":[56],"on":[57,102,111,124],"design":[59],"development":[61],"a":[63,103,137,185],"system":[64],"for":[65,96,118,140,158,179,188],"collecting,":[66],"managing,":[67],"querying":[69],"preparation":[74,181],"pipelines":[75,86,135,157,182],"science.":[78],"An":[79],"investigation":[80],"publicly":[82],"available":[83],"conducted":[88],"identify":[90],"most":[92],"important":[93],"features":[94],"required":[95],"tool":[98],"achieve":[100],"impact":[101],"broad":[104],"selection":[105],"manipulation.":[109],"Building":[110],"study,":[113],"we":[114],"present":[115],"an":[116,128,146],"approach":[117],"transparently":[119],"collecting":[120],"based":[123],"use":[126],"LLM":[129],"to:":[130],"(i)":[131],"automatically":[132],"rewrite":[133],"user-defined":[134],"format":[138],"suitable":[139],"activity":[142],"(ii)":[144],"store":[145],"accurate":[147],"description":[148],"all":[150],"activities":[152],"involved":[153],"input":[156],"supporting":[159,175],"explanation":[161],"each":[163],"them.":[165],"We":[166],"then":[167],"illustrate":[168],"test":[170],"implementation":[171],"choices":[172],"aimed":[173],"at":[174],"capture":[178],"efficiently":[183],"transparent":[186],"way":[187],"scientists.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
