{"id":"https://openalex.org/W4389158536","doi":"https://doi.org/10.1145/3611643.3616243","title":"Baldur: Whole-Proof Generation and Repair with Large Language Models","display_name":"Baldur: Whole-Proof Generation and Repair with Large Language Models","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4389158536","doi":"https://doi.org/10.1145/3611643.3616243"},"language":"en","primary_location":{"id":"doi:10.1145/3611643.3616243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611643.3616243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102852428","display_name":"Emily First","orcid":"https://orcid.org/0000-0002-2896-2928"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Emily First","raw_affiliation_strings":["University of Massachusetts, Amherst, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072217103","display_name":"Markus N. Rabe","orcid":"https://orcid.org/0000-0003-4795-7259"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus N. Rabe","raw_affiliation_strings":["Augment Computing, Palo Alto, USA"],"affiliations":[{"raw_affiliation_string":"Augment Computing, Palo Alto, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078343798","display_name":"Talia Ringer","orcid":"https://orcid.org/0000-0003-1854-3321"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Talia Ringer","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028789964","display_name":"Yuriy Brun","orcid":"https://orcid.org/0000-0003-3027-7986"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuriy Brun","raw_affiliation_strings":["University of Massachusetts, Amherst, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102852428"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":31.7103,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.99744682,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1229","last_page":"1241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9986000061035156,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10126","display_name":"Logic, programming, and type systems","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.9403929114341736},{"id":"https://openalex.org/keywords/hol","display_name":"HOL","score":0.8577756881713867},{"id":"https://openalex.org/keywords/proof-assistant","display_name":"Proof assistant","score":0.8185988664627075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7931185960769653},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6203877925872803},{"id":"https://openalex.org/keywords/proof-complexity","display_name":"Proof complexity","score":0.5662534832954407},{"id":"https://openalex.org/keywords/formal-proof","display_name":"Formal proof","score":0.5619595646858215},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5270167589187622},{"id":"https://openalex.org/keywords/automated-theorem-proving","display_name":"Automated theorem proving","score":0.5024638175964355},{"id":"https://openalex.org/keywords/proof-of-concept","display_name":"Proof of concept","score":0.4653604328632355},{"id":"https://openalex.org/keywords/computer-assisted-proof","display_name":"Computer-assisted proof","score":0.41520771384239197},{"id":"https://openalex.org/keywords/automated-proof-checking","display_name":"Automated proof checking","score":0.41474074125289917},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38102027773857117},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11621689796447754}],"concepts":[{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.9403929114341736},{"id":"https://openalex.org/C17435882","wikidata":"https://www.wikidata.org/wiki/Q17030435","display_name":"HOL","level":2,"score":0.8577756881713867},{"id":"https://openalex.org/C203265346","wikidata":"https://www.wikidata.org/wiki/Q11387554","display_name":"Proof assistant","level":3,"score":0.8185988664627075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931185960769653},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6203877925872803},{"id":"https://openalex.org/C105605280","wikidata":"https://www.wikidata.org/wiki/Q7249999","display_name":"Proof complexity","level":3,"score":0.5662534832954407},{"id":"https://openalex.org/C94461902","wikidata":"https://www.wikidata.org/wiki/Q2762418","display_name":"Formal proof","level":3,"score":0.5619595646858215},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5270167589187622},{"id":"https://openalex.org/C206880738","wikidata":"https://www.wikidata.org/wiki/Q431667","display_name":"Automated theorem proving","level":2,"score":0.5024638175964355},{"id":"https://openalex.org/C124978682","wikidata":"https://www.wikidata.org/wiki/Q1201019","display_name":"Proof of concept","level":2,"score":0.4653604328632355},{"id":"https://openalex.org/C173613240","wikidata":"https://www.wikidata.org/wiki/Q1150675","display_name":"Computer-assisted proof","level":3,"score":0.41520771384239197},{"id":"https://openalex.org/C13766981","wikidata":"https://www.wikidata.org/wiki/Q11387554","display_name":"Automated proof checking","level":3,"score":0.41474074125289917},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38102027773857117},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11621689796447754},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3611643.3616243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611643.3616243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G1100630356","display_name":null,"funder_award_id":"CCF-2210243","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4099531400","display_name":null,"funder_award_id":"HR0011-22-9-0063","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5790514751","display_name":"SHF: Small: Toward Fully Automated Formal Software Verification","funder_award_id":"2210243","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6102193936","display_name":null,"funder_award_id":"HR0011-22-9-006","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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/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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1475493299","https://openalex.org/W1977696633","https://openalex.org/W2012547119","https://openalex.org/W2023035194","https://openalex.org/W2061575154","https://openalex.org/W2070544288","https://openalex.org/W2091015169","https://openalex.org/W2096713153","https://openalex.org/W2136310957","https://openalex.org/W2145373440","https://openalex.org/W2146136779","https://openalex.org/W2153881107","https://openalex.org/W2274071363","https://openalex.org/W2295100577","https://openalex.org/W2320110444","https://openalex.org/W2400994325","https://openalex.org/W2519091744","https://openalex.org/W2730550703","https://openalex.org/W2735571786","https://openalex.org/W2741328617","https://openalex.org/W2767431443","https://openalex.org/W2767437656","https://openalex.org/W2777305358","https://openalex.org/W2792493843","https://openalex.org/W2794832431","https://openalex.org/W2795030435","https://openalex.org/W2801865415","https://openalex.org/W2808863792","https://openalex.org/W2809147512","https://openalex.org/W2809551103","https://openalex.org/W2835280932","https://openalex.org/W2867448323","https://openalex.org/W2901111247","https://openalex.org/W2907705732","https://openalex.org/W2954778170","https://openalex.org/W2961757301","https://openalex.org/W2972031508","https://openalex.org/W2972704946","https://openalex.org/W2973153063","https://openalex.org/W2975950293","https://openalex.org/W2981852735","https://openalex.org/W2991598122","https://openalex.org/W2998011150","https://openalex.org/W2998975145","https://openalex.org/W3001272669","https://openalex.org/W3009805852","https://openalex.org/W3032749142","https://openalex.org/W3033256385","https://openalex.org/W3042956498","https://openalex.org/W3043685015","https://openalex.org/W3080426653","https://openalex.org/W3080745458","https://openalex.org/W3088122504","https://openalex.org/W3090441383","https://openalex.org/W3121734253","https://openalex.org/W3122473522","https://openalex.org/W3142990889","https://openalex.org/W3155806510","https://openalex.org/W3162539581","https://openalex.org/W3193682477","https://openalex.org/W3197040007","https://openalex.org/W4221143046","https://openalex.org/W4224308101","https://openalex.org/W4238083723","https://openalex.org/W4255632703","https://openalex.org/W4281489448","https://openalex.org/W4281663895","https://openalex.org/W4282045675","https://openalex.org/W4283768109","https://openalex.org/W4284705527","https://openalex.org/W4285113234","https://openalex.org/W4288028629","https://openalex.org/W4288089799","https://openalex.org/W4293328634","https://openalex.org/W4307308174","https://openalex.org/W4308760184","https://openalex.org/W4313679740","https://openalex.org/W4366825838","https://openalex.org/W6600050674","https://openalex.org/W6746046042","https://openalex.org/W6810338698"],"related_works":["https://openalex.org/W3163122332","https://openalex.org/W1524804222","https://openalex.org/W3080745458","https://openalex.org/W3100311625","https://openalex.org/W49870449","https://openalex.org/W1497292213","https://openalex.org/W2735509904","https://openalex.org/W2795365301","https://openalex.org/W840808322","https://openalex.org/W840295995"],"abstract_inverted_index":{"Formally":[0],"verifying":[1],"software":[2],"is":[3,107,110],"a":[4,30,38,55,87,130,156,172,179],"highly":[5],"desirable":[6],"but":[7,113],"labor-intensive":[8],"task.":[9],"Recent":[10],"work":[11],"has":[12],"developed":[13],"methods":[14],"to":[15,32,44,58,77,90],"automate":[16,59],"formal":[17,60,247],"verification":[18],"using":[19,41,105,241],"proof":[20,35,133,142,148,165],"assistants,":[21],"such":[22,128],"as":[23,111,129],"Coq":[24],"and":[25,40,71,73,109,135,175,185,196,222],"Isabelle/HOL,":[26],"e.g.,":[27],"by":[28,209],"training":[29],"model":[31,43,88,125],"predict":[33],"one":[34],"step":[36],"at":[37,81],"time":[39],"that":[42,86,102,121,144,202],"search":[45],"through":[46],"the":[47,123,136,160,190,205,218,228,235],"space":[48],"of":[49,159,181,192,217,227],"possible":[50,108],"proofs.":[51],"This":[52,98,232],"paper":[53,233],"introduces":[54],"new":[56,157,238],"method":[57,170],"verification:":[61],"We":[62,83,167,199],"use":[63],"large":[64,242],"language":[65,70,243],"models,":[66],"trained":[67],"on":[68,75,178],"natural":[69],"code":[72],"fine-tuned":[74,89],"proofs,":[76,187],"generate":[78],"whole":[79],"proofs":[80,93,212],"once.":[82],"then":[84],"demonstrate":[85],"repair":[91,143],"generated":[92],"further":[94,145],"increasing":[95],"proving":[96],"power.":[97],"paper:":[99],"(1)":[100],"Demonstrates":[101,120],"whole-proof":[103,193],"generation":[104],"transformers":[106],"effective":[112],"more":[114],"efficient":[115],"than":[116],"search-based":[117],"techniques.":[118],"(2)":[119],"giving":[122],"learned":[124],"additional":[126,215],"context,":[127],"prior":[131,154],"failed":[132],"attempt":[134],"ensuing":[137],"error":[138],"message,":[139],"results":[140],"in":[141,171],"improves":[146],"automated":[147,164],"generation.":[149],"(3)":[150],"Establishes,":[151],"together":[152],"with":[153],"work,":[155],"state":[158],"art":[161],"for":[162,213,237,245],"fully":[163,230],"synthesis.":[166],"reify":[168],"our":[169],"prototype,":[173],"Baldur,":[174],"evaluate":[176],"it":[177],"benchmark":[180],"6,336":[182],"Isabelle/HOL":[183],"theorems":[184,229],"their":[186],"empirically":[188],"showing":[189],"effectiveness":[191],"generation,":[194],"repair,":[195],"added":[197],"context.":[198],"also":[200],"show":[201],"Baldur":[203,221],"complements":[204],"state-of-the-art":[206],"tool,":[207],"Thor,":[208],"automatically":[210],"generating":[211],"an":[214],"8.7%":[216],"theorems.":[219],"Together,":[220],"Thor":[223],"can":[224],"prove":[225],"65.7%":[226],"automatically.":[231],"paves":[234],"way":[236],"research":[239],"into":[240],"models":[244],"automating":[246],"verification.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}