{"id":"https://openalex.org/W4413908774","doi":"https://doi.org/10.1145/3736229.3736261","title":"Using LLMs to infer provenance information","display_name":"Using LLMs to infer provenance information","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4413908774","doi":"https://doi.org/10.1145/3736229.3736261"},"language":"en","primary_location":{"id":"doi:10.1145/3736229.3736261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736229.3736261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736229.3736261","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 ProvenanceWeek 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3736229.3736261","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007728085","display_name":"Abdullah Hamed Almuntashiri","orcid":"https://orcid.org/0000-0002-7343-6468"},"institutions":[{"id":"https://openalex.org/I47164929","display_name":"Najran University","ror":"https://ror.org/05edw4a90","country_code":"SA","type":"education","lineage":["https://openalex.org/I47164929"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Abdullah Hamed Almuntashiri","raw_affiliation_strings":["University of Southampton, Southampton, United Kingdom and Najran University, Najran, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, United Kingdom and Najran University, Najran, Saudi Arabia","institution_ids":["https://openalex.org/I47164929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039087877","display_name":"Luis Ib\u00e1\u00f1ez","orcid":"https://orcid.org/0000-0001-6993-0001"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luis-Daniel Ib\u00e1\u00f1ez","raw_affiliation_strings":["University of Southampton, Southampton, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013015057","display_name":"Adriane Chapman","orcid":"https://orcid.org/0000-0002-3814-2587"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adriane Chapman","raw_affiliation_strings":["University of Southampton, Southampton, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007728085"],"corresponding_institution_ids":["https://openalex.org/I47164929"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22721015,"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":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9865999817848206,"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":0.9455000162124634,"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":0.8602495193481445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5649441480636597},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3248671889305115},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.20571336150169373},{"id":"https://openalex.org/keywords/paleontology","display_name":"Paleontology","score":0.12169012427330017}],"concepts":[{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.8602495193481445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5649441480636597},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3248671889305115},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.20571336150169373},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.12169012427330017}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3736229.3736261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736229.3736261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736229.3736261","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 ProvenanceWeek 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3736229.3736261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736229.3736261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736229.3736261","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 ProvenanceWeek 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7787407046","display_name":null,"funder_award_id":"EP/SO28366/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320319990","display_name":"National Institute for Health and Care Research","ror":"https://ror.org/0187kwz08"},{"id":"https://openalex.org/F4320320277","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543"},{"id":"https://openalex.org/F4320323502","display_name":"Najran University","ror":"https://ror.org/05edw4a90"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413908774.pdf","grobid_xml":"https://content.openalex.org/works/W4413908774.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W168132470","https://openalex.org/W269919247","https://openalex.org/W1768532251","https://openalex.org/W1967711467","https://openalex.org/W1980115980","https://openalex.org/W2008307986","https://openalex.org/W2043349404","https://openalex.org/W2069028640","https://openalex.org/W2156287317","https://openalex.org/W2222040190","https://openalex.org/W2341844252","https://openalex.org/W2539086290","https://openalex.org/W2609517807","https://openalex.org/W2625373267","https://openalex.org/W2746973212","https://openalex.org/W2747669027","https://openalex.org/W2751442097","https://openalex.org/W2885025596","https://openalex.org/W2885157095","https://openalex.org/W2890128765","https://openalex.org/W2899478536","https://openalex.org/W2912325461","https://openalex.org/W2913304067","https://openalex.org/W3133702157","https://openalex.org/W3197767598","https://openalex.org/W3200572611","https://openalex.org/W4288057803","https://openalex.org/W4312302709","https://openalex.org/W4323655724","https://openalex.org/W4365786623","https://openalex.org/W4366393490","https://openalex.org/W4366598336","https://openalex.org/W4367311294","https://openalex.org/W4385198575","https://openalex.org/W4385365852","https://openalex.org/W4385573954","https://openalex.org/W4386530347","https://openalex.org/W4388605937","https://openalex.org/W4389111287","https://openalex.org/W4391836235","https://openalex.org/W4396843633","https://openalex.org/W4399149917","https://openalex.org/W4399418643","https://openalex.org/W4400016224","https://openalex.org/W4400181815","https://openalex.org/W4402158641","https://openalex.org/W4402288718","https://openalex.org/W4403577400","https://openalex.org/W4404586876","https://openalex.org/W4406500113","https://openalex.org/W4406596702"],"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":{"Having":[0],"a":[1,90,140],"provenance":[2,10,46,55,91,108,120,137],"record":[3,92],"facilitates":[4],"data":[5],"reuse":[6],"and":[7,118],"experimental":[8],"reuse.However,":[9],"capture":[11],"requires":[12],"either:":[13],"specific":[14],"provenance-enabled":[15,29],"systems":[16,30],"to":[17,88],"be":[18],"used":[19],"or":[20],"human":[21],"documentation.While":[22],"there":[23],"have":[24,69],"been":[25],"many":[26],"examples":[27],"of":[28,48,86,114,130,142],"for":[31,45,63,93,107,133],"scientific":[32,49,53,94,97],"usage,":[33],"they":[34],"are":[35],"still":[36],"the":[37,40,52,84,103,112,128,131],"exception,":[38],"not":[39,60],"norm.The":[41],"one,":[42],"standard":[43],"place":[44],"information":[47,78,121,138],"experiments":[50,95],"remains":[51],"publication.Unfortunately,":[54],"buried":[56],"in":[57,77,116,135],"text":[58],"is":[59],"immediately":[61],"useful":[62],"computational":[64],"purposes.Large":[65],"Language":[66],"Models":[67],"(LLMs)":[68],"demonstrated":[70],"exceptional":[71],"capability":[72,113],"across":[73,139],"various":[74],"tasks,":[75],"particularly":[76],"extraction.In":[79],"this":[80],"paper,":[81],"we":[82,126],"explore":[83],"potential":[85],"LLMs":[87],"infer":[89],"from":[96,122],"papers.We":[98],"develop":[99],"an":[100],"extractor,":[101],"identify":[102],"most":[104],"effective":[105],"prompt":[106],"extraction.Our":[109],"results":[110],"emphasise":[111],"ChatGPT-4o":[115],"accessing":[117],"extracting":[119,136],"biomedical":[123,143],"research":[124,144],"papers.Additionally,":[125],"assess":[127],"scalability":[129],"extractor":[132],"use":[134],"set":[141],"papers.":[145]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}