{"id":"https://openalex.org/W7223935201","doi":"https://doi.org/10.48550/arxiv.2610.35596","title":"KAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents","display_name":"KAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7223935201","doi":"https://doi.org/10.48550/arxiv.2610.35596"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.35596","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35596","pdf_url":"https://arxiv.org/pdf/2610.35596","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.35596","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136142244","display_name":"Zihua She","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"She, Zihua","raw_affiliation_strings":["Department of Statistics , Purdue University , West Lafayette , IN 47907 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , Purdue University , West Lafayette , IN 47907 , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159850329","display_name":"Xiao Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Xiao","raw_affiliation_strings":["Department of Statistics , Purdue University , West Lafayette , IN 47907 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , Purdue University , West Lafayette , IN 47907 , USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.6064000129699707,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.6064000129699707,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.2660999894142151,"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/T10142","display_name":"Formal Methods in Verification","score":0.017899999395012856,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/proof-verification","display_name":"proof verification","score":0.7540000081062317},{"id":"https://openalex.org/keywords/lean-4","display_name":"Lean 4","score":0.8349999785423279},{"id":"https://openalex.org/keywords/language-model-agents","display_name":"language model agents","score":0.8289999961853027},{"id":"https://openalex.org/keywords/claude-code","display_name":"Claude Code","score":0.7689999938011169},{"id":"https://openalex.org/keywords/mathlib","display_name":"Mathlib","score":0.7580000162124634},{"id":"https://openalex.org/keywords/automated-verification","display_name":"automated verification","score":0.42500001192092896},{"id":"https://openalex.org/keywords/kappa","display_name":"kappa","score":0.6579999923706055}],"concepts":[{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.8743000030517578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132999897003174},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.6313999891281128},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48579999804496765},{"id":"https://openalex.org/C77265313","wikidata":"https://www.wikidata.org/wiki/Q879844","display_name":"Rest (music)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C172347087","wikidata":"https://www.wikidata.org/wiki/Q3217196","display_name":"Language of mathematics","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C203265346","wikidata":"https://www.wikidata.org/wiki/Q11387554","display_name":"Proof assistant","level":3,"score":0.26030001044273376}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.35596","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35596","pdf_url":"https://arxiv.org/pdf/2610.35596","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2610.35596","doi":"https://doi.org/10.48550/arxiv.2610.35596","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.35596","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.35596","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35596","pdf_url":"https://arxiv.org/pdf/2610.35596","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7087609831","display_name":"Neural Inference of Dynamic Systems","funder_award_id":"2316428","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223935201.pdf","grobid_xml":"https://content.openalex.org/works/W7223935201.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7220154050","https://openalex.org/W7223648501","https://openalex.org/W7204138681","https://openalex.org/W7216481623","https://openalex.org/W7166676332","https://openalex.org/W7165838761","https://openalex.org/W4395021983","https://openalex.org/W7214538152","https://openalex.org/W7203488197","https://openalex.org/W7221758399"],"abstract_inverted_index":{"Papers":[0,23],"in":[1,92,207],"statistical":[2,203],"theory":[3],"rest":[4],"on":[5,144,255],"long":[6],"proofs":[7,42],"that":[8,30,146,226,234],"few":[9],"readers":[10],"check":[11,58],"line":[12],"by":[13,36,62,113,174,237],"line.":[14],"We":[15,179],"present":[16],"KAPPA":[17],"(Kit":[18],"of":[19,43,69,271],"Agents":[20],"for":[21,158],"Proof-checking":[22],"with":[24,53,76,89,102,130,196,231,249],"a":[25,44,84,118,151,167,185],"proof":[26,49,111],"Assistant),":[27],"open-source":[28],"software":[29],"organizes":[31],"language":[32,152,246],"model":[33,176,247],"agents,":[34],"run":[35],"Claude":[37],"Code,":[38],"to":[39,192,200],"translate":[40],"the":[41,48,93,96,103,108,131,181,190,217,220,224,227,240,244,256,265,272],"LaTeX":[45],"paper":[46,94,132,258],"into":[47],"assistant":[50],"Lean":[51,250,278],"4":[52],"its":[54,90,172,277],"library":[55],"Mathlib":[56],"and":[57,95,124,137,140,170,177,188,199,259],"them":[59],"there,":[60],"result":[61,66],"result.":[63,178],"Each":[64],"numbered":[65],"receives":[67],"one":[68],"four":[70,193],"verdicts:":[71],"verified":[72,74],"unconditionally;":[73],"conditionally,":[75],"every":[77,141],"cited":[78],"or":[79,100],"unproved":[80],"input":[81],"stated":[82],"as":[83,267],"named":[85],"hypothesis;":[86],"issue":[87],"recorded,":[88],"place":[91],"side":[97],"at":[98,223],"fault;":[99],"unfinished,":[101],"reason.":[104],"The":[105,154],"kit":[106,155,191,218,273],"follows":[107],"paper's":[109,266],"own":[110],"step":[112,225],"step,":[114],"rather":[115],"than":[116,264,276],"finding":[117],"new":[119],"one.":[120],"Separate":[121],"agents":[122],"write":[123],"review,":[125],"each":[126],"statement":[127],"is":[128,135],"compared":[129],"before":[133,211],"it":[134],"proved":[136],"fingerprinted":[138],"afterwards,":[139],"verdict":[142,270],"rests":[143],"evidence":[145,279],"can":[147],"be":[148],"rerun":[149],"without":[150],"model.":[153],"runs":[156],"unattended":[157],"hours,":[159],"waits":[160],"out":[161],"usage":[162],"limits,":[163],"re-checks":[164],"only":[165],"what":[166],"revision":[168],"changed":[169],"reports":[171],"cost":[173],"role,":[175],"describe":[180],"design,":[182],"walk":[183],"through":[184],"complete":[186],"run,":[187],"apply":[189],"example":[194],"papers":[195,242],"answer":[197],"keys":[198],"three":[201],"published":[202,221],"papers,":[204],"checked":[205],"blind":[206],"their":[208],"versions":[209],"from":[210],"public":[212],"corrections.":[213],"In":[214],"all":[215],"three,":[216],"found":[219],"error":[222],"correction":[228],"names,":[229],"together":[230],"further":[232],"problems":[233],"we":[235],"confirmed":[236],"hand.":[238],"Given":[239],"same":[241,245],"directly,":[243],"working":[248],"classified":[251],"fewer":[252],"results":[253],"correctly":[254],"longest":[257],"reported":[260],"some":[261],"statements":[262],"narrower":[263],"proved;":[268],"no":[269],"claimed":[274],"more":[275],"showed.":[280]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-28T00:00:00"}
