{"id":"https://openalex.org/W4416033693","doi":"https://doi.org/10.18653/v1/2025.newsum-main.13","title":"NSF-SciFy: Mining the NSF Awards Database for Scientific Claims","display_name":"NSF-SciFy: Mining the NSF Awards Database for Scientific Claims","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033693","doi":"https://doi.org/10.18653/v1/2025.newsum-main.13"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.newsum-main.13","doi":"https://doi.org/10.18653/v1/2025.newsum-main.13","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.newsum-main.13","pdf_url":null,"source":{"id":"https://openalex.org/S7407113620","display_name":"Workshop on New Frontiers in Summarization (NewSum)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The 5th New Frontiers in Summarization Workshop","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.2118.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113813635","display_name":"Delip Rao","orcid":"https://orcid.org/0000-0002-4534-9906","observed_orcids":["https://orcid.org/0000-0002-4534-9906"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Delip Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057842780","display_name":"Weiqiu You","orcid":"https://orcid.org/0009-0009-9326-1077","observed_orcids":["https://orcid.org/0009-0009-9326-1077"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiqiu You","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Eric Wong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Wong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068508539","display_name":"Chris Callison-Burch","orcid":"https://orcid.org/0000-0001-8196-1943","observed_orcids":["https://orcid.org/0000-0001-8196-1943"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Callison-Burch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.30364722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5679000020027161,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5679000020027161,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.31859999895095825,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.012000000104308128,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/zero-shot-prompting","display_name":"zero-shot prompting","score":0.746999979019165},{"id":"https://openalex.org/keywords/materials-research","display_name":"materials research","score":0.593999981880188},{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4424000084400177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39730000495910645},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.32679998874664307},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2928999960422516},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.25589999556541443},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.24950000643730164},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2362000048160553}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.newsum-main.13","doi":"https://doi.org/10.18653/v1/2025.newsum-main.13","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.newsum-main.13","pdf_url":null,"source":{"id":"https://openalex.org/S7407113620","display_name":"Workshop on New Frontiers in Summarization (NewSum)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The 5th New Frontiers in Summarization Workshop","raw_type":"proceedings-article"},{"id":"doi:10.18653/v1/2026.acl-long.2118","doi":"https://doi.org/10.18653/v1/2026.acl-long.2118","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2118","pdf_url":"https://aclanthology.org/2026.acl-long.2118.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2118","doi":"https://doi.org/10.18653/v1/2026.acl-long.2118","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2118","pdf_url":"https://aclanthology.org/2026.acl-long.2118.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6430229357","display_name":null,"funder_award_id":"HR00112520300","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6813546606","display_name":"CAREER: Certified Explanations for Trustworthy Artificial Intelligence","funder_award_id":"2442421","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033693.pdf","grobid_xml":"https://content.openalex.org/works/W4416033693.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416034443","https://openalex.org/W4385574202","https://openalex.org/W7128514732","https://openalex.org/W4221160682","https://openalex.org/W3183518142","https://openalex.org/W7090894040","https://openalex.org/W4386931060","https://openalex.org/W4416252333","https://openalex.org/W4416037912","https://openalex.org/W3171702324"],"abstract_inverted_index":{"We":[0],"introduce":[1],"NSF-SCIFY,":[2],"a":[3,33,74],"comprehensive":[4],"dataset":[5,107],"of":[6,80],"scientific":[7,20,81,150],"claims":[8,39,56,65,82,129],"and":[9,29,46,61,83,99,120,153],"investigation":[10,84,100],"proposals":[11],"extracted":[12,128],"from":[13,40,57],"National":[14],"Science":[15],"Foundation":[16],"award":[17],"abstracts.While":[18],"previous":[19],"claim":[21,97,119,148],"verification":[22],"datasets":[23],"have":[24],"been":[25],"limited":[26],"in":[27,146],"size":[28],"scope,":[30],"NSF-SCIFY":[31],"represents":[32],"significant":[34],"advance":[35],"with":[36,54,63,111],"2.8":[37],"million":[38],"400,000":[41],"abstracts":[42],"spanning":[43],"all":[44],"science":[45,59],"mathematics":[47],"disciplines.We":[48],"present":[49],"two":[50],"focused":[51],"subsets:":[52],"NSF-SCIFY-MATSCI":[53],"114,000":[55],"materials":[58],"awards,":[60],"NSF-SCIFY-20K":[62],"135,000":[64],"across":[66],"five":[67],"NSF":[68],"directorates.Using":[69],"zero-shot":[70],"prompting,":[71],"we":[72],"develop":[73],"scalable":[75],"approach":[76],"for":[77,118,138],"joint":[78],"extraction":[79,122],"proposals.We":[85],"demonstrate":[86],"the":[87],"dataset's":[88],"utility":[89],"through":[90],"three":[91],"downstream":[92],"tasks:":[93],"non-technical":[94],"abstract":[95],"generation,":[96],"extraction,":[98],"proposal":[101,121],"extraction.Fine-tuning":[102],"language":[103],"models":[104],"on":[105],"our":[106],"yields":[108],"substantial":[109],"improvements,":[110],"relative":[112],"gains":[113],"often":[114],"exceeding":[115],"100%,":[116],"particularly":[117],"tasks.Our":[123],"error":[124],"analysis":[125,155],"reveals":[126],"that":[127],"exhibit":[130],"high":[131],"precision":[132],"but":[133],"lower":[134],"recall,":[135],"suggesting":[136],"opportunities":[137],"further":[139],"methodological":[140],"refinement.NSF-SCIFY":[141],"enables":[142],"new":[143],"research":[144],"directions":[145],"large-scale":[147],"verification,":[149],"discovery":[151],"tracking,":[152],"meta-scientific":[154],"1":[156],".":[157]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-11-08T00:00:00"}