{"id":"https://openalex.org/W4411091462","doi":"https://doi.org/10.1145/3713082.3730382","title":"Can Large Language Models Verify System Software? A Case Study Using FSCQ as a Benchmark","display_name":"Can Large Language Models Verify System Software? A Case Study Using FSCQ as a Benchmark","publication_year":2025,"publication_date":"2025-05-14","ids":{"openalex":"https://openalex.org/W4411091462","doi":"https://doi.org/10.1145/3713082.3730382"},"language":"en","primary_location":{"id":"doi:10.1145/3713082.3730382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3713082.3730382","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3713082.3730382","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 Workshop on Hot Topics in Operating Systems","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/10.1145/3713082.3730382","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014455770","display_name":"Jianxing Qin","orcid":"https://orcid.org/0009-0004-1581-9577"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianxing Qin","raw_affiliation_strings":["Duke University"],"raw_orcid":"https://orcid.org/0009-0004-1581-9577","affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109725601","display_name":"Alexander Du","orcid":"https://orcid.org/0009-0003-5268-4934"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Du","raw_affiliation_strings":["Duke University"],"raw_orcid":"https://orcid.org/0009-0003-5268-4934","affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722775","display_name":"Danfeng Zhang","orcid":"https://orcid.org/0000-0003-1942-6872"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danfeng Zhang","raw_affiliation_strings":["Duke University"],"raw_orcid":"https://orcid.org/0000-0003-1942-6872","affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000778364","display_name":"Matthew Lentz","orcid":"https://orcid.org/0000-0003-1034-2736"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Lentz","raw_affiliation_strings":["Duke University"],"raw_orcid":"https://orcid.org/0000-0003-1034-2736","affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007943946","display_name":"Danyang Zhuo","orcid":"https://orcid.org/0000-0002-0611-3941"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danyang Zhuo","raw_affiliation_strings":["Duke University"],"raw_orcid":"https://orcid.org/0000-0002-0611-3941","affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014455770"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":1.3517,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82285214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11424","display_name":"Security and Verification in Computing","score":0.9986000061035156,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.8079113960266113},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7745157480239868},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46951931715011597},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4505579173564911},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3745478391647339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079113960266113},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7745157480239868},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46951931715011597},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4505579173564911},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3745478391647339},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3713082.3730382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3713082.3730382","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3713082.3730382","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 Workshop on Hot Topics in Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3713082.3730382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3713082.3730382","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3713082.3730382","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 Workshop on Hot Topics in Operating Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3747759880","display_name":"CAREER: OS-Managed Remote Procedure Call for Datacenter Applications","funder_award_id":"2238665","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6314641595","display_name":null,"funder_award_id":"2238665, 2402696","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G641696011","display_name":"Collaborative Research: NeTS: Medium: Application Defined Networking","funder_award_id":"2402696","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/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411091462.pdf","grobid_xml":"https://content.openalex.org/works/W4411091462.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1972014769","https://openalex.org/W2091776255","https://openalex.org/W2136310957","https://openalex.org/W2761236351","https://openalex.org/W2761718075","https://openalex.org/W2963412521","https://openalex.org/W3080426653","https://openalex.org/W3197040007","https://openalex.org/W3205972330","https://openalex.org/W4389520453","https://openalex.org/W4403536499"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4,19,27],"demonstrated":[5],"remarkable":[6],"coding":[7,23],"capabilities.":[8],"They":[9],"excel":[10],"in":[11,22,31],"code":[12],"synthesis":[13],"benchmarks":[14],"across":[15],"diverse":[16],"domains":[17],"and":[18,35,75,113,157],"become":[20],"ubiquitous":[21],"tools.":[24],"Recently,":[25],"they":[26],"also":[28],"shown":[29],"promise":[30,105],"generating":[32],"mathematical":[33],"proofs":[34,48,78,136],"small":[36],"software":[37,52,81,89],"programs.":[38],"In":[39],"this":[40,67,107],"paper,":[41],"we":[42,91,158],"explore":[43],"their":[44],"potential":[45],"to":[46],"produce":[47],"for":[49,79,87,125,131],"complex":[50],"system":[51,80,88],"(e.g.,":[53],"file":[54,96],"systems),":[55],"where":[56],"verification":[57,73],"typically":[58],"requires":[59],"substantial":[60],"manual":[61],"effort.":[62],"By":[63],"automating":[64],"parts":[65],"of":[66,106,145],"process,":[68],"LLMs":[69,86,120],"could":[70],"reduce":[71],"the":[72,104],"burden":[74],"make":[76,141],"rigorous":[77],"more":[82],"accessible.":[83],"To":[84],"evaluate":[85],"verification,":[90],"use":[92],"FSCQ,":[93],"a":[94,114],"verified":[95],"system,":[97],"as":[98],"our":[99],"benchmark.":[100],"Our":[101],"results":[102],"confirm":[103],"approach:":[108],"with":[109,134],"appropriate":[110],"proof":[111,123,166],"context":[112],"straightforward":[115],"best-first":[116],"tree":[117],"search,":[118],"off-the-shelf":[119],"achieve":[121,149],"38%":[122],"coverage":[124],"theorems":[126],"sampled":[127],"from":[128],"FSCQ.":[129],"Moreover,":[130],"simpler":[132],"theorems---those":[133],"human":[135],"under":[137],"64":[138],"tokens,":[139],"which":[140],"up":[142],"about":[143],"60%":[144],"all":[146],"FSCQ":[147],"theorems---LLMs":[148],"over":[150],"57%":[151],"coverage.":[152,167],"These":[153],"findings":[154],"are":[155],"preliminary,":[156],"anticipate":[159],"that":[160],"various":[161],"techniques":[162],"can":[163],"further":[164],"improve":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
