{"id":"https://openalex.org/W4281808401","doi":"https://doi.org/10.1145/3520312.3534867","title":"ExeBench: an ML-scale dataset of executable C functions","display_name":"ExeBench: an ML-scale dataset of executable C functions","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281808401","doi":"https://doi.org/10.1145/3520312.3534867"},"language":"en","primary_location":{"id":"doi:10.1145/3520312.3534867","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3520312.3534867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming","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/A5020795476","display_name":"Jordi Armengol-Estap\u00e9","orcid":"https://orcid.org/0000-0001-8893-6185"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jordi Armengol-Estap\u00e9","raw_affiliation_strings":["University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072181658","display_name":"Jackson Woodruff","orcid":"https://orcid.org/0000-0003-2650-9596"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jackson Woodruff","raw_affiliation_strings":["University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091099679","display_name":"Alexander Brauckmann","orcid":"https://orcid.org/0000-0001-5774-3970"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexander Brauckmann","raw_affiliation_strings":["University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072335056","display_name":"Jos\u00e9 Wesley de Souza Magalh\u00e3es","orcid":"https://orcid.org/0000-0003-2767-1130"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Wesley de Souza Magalh\u00e3es","raw_affiliation_strings":["University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027001025","display_name":"Michael O\u2019Boyle","orcid":"https://orcid.org/0000-0003-1619-5052"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael F. P. O'Boyle","raw_affiliation_strings":["University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020795476"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":5.1535,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95719182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9926999807357788,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9884999990463257,"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/executable","display_name":"Executable","score":0.9084128141403198},{"id":"https://openalex.org/keywords/toolchain","display_name":"Toolchain","score":0.8977016806602478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8805038928985596},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6099060773849487},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.598889172077179},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5968159437179565},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5801388025283813},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5545293688774109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45031264424324036},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4392277002334595},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4323987662792206},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42907798290252686},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.4259640872478485},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.4176710844039917},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41612130403518677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3831561505794525},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25085848569869995},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.11230471730232239}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.9084128141403198},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.8977016806602478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805038928985596},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6099060773849487},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.598889172077179},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5968159437179565},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5801388025283813},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5545293688774109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45031264424324036},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4392277002334595},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4323987662792206},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42907798290252686},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.4259640872478485},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.4176710844039917},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41612130403518677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3831561505794525},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25085848569869995},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.11230471730232239},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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:10.1145/3520312.3534867","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3520312.3534867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2003199018","https://openalex.org/W2073429012","https://openalex.org/W2095938258","https://openalex.org/W2108598243","https://openalex.org/W2148190602","https://openalex.org/W2171683519","https://openalex.org/W2282866165","https://openalex.org/W2342190614","https://openalex.org/W2463123136","https://openalex.org/W2762387874","https://openalex.org/W2773253898","https://openalex.org/W2786672974","https://openalex.org/W2883889688","https://openalex.org/W2899519917","https://openalex.org/W2924497240","https://openalex.org/W2954451301","https://openalex.org/W2963935794","https://openalex.org/W2964002372","https://openalex.org/W2979792666","https://openalex.org/W2980002700","https://openalex.org/W2980791959","https://openalex.org/W3010630042","https://openalex.org/W3038600945","https://openalex.org/W3092371116","https://openalex.org/W3099223177","https://openalex.org/W3109092993","https://openalex.org/W3112486745","https://openalex.org/W3114760331","https://openalex.org/W3162962341","https://openalex.org/W3165784750","https://openalex.org/W3167560564","https://openalex.org/W3177765786","https://openalex.org/W3197876970","https://openalex.org/W4214583996","https://openalex.org/W4226277721","https://openalex.org/W4248950571","https://openalex.org/W4281862314","https://openalex.org/W4283799640","https://openalex.org/W4288577412","https://openalex.org/W4289255588","https://openalex.org/W4298144617","https://openalex.org/W4300007223","https://openalex.org/W6729410713","https://openalex.org/W6759311563","https://openalex.org/W6761126846","https://openalex.org/W6762083219","https://openalex.org/W6785361340","https://openalex.org/W6788175385","https://openalex.org/W6804406612","https://openalex.org/W6893983461"],"related_works":["https://openalex.org/W2256611834","https://openalex.org/W2598672065","https://openalex.org/W1993817217","https://openalex.org/W3120610872","https://openalex.org/W1638297612","https://openalex.org/W2523911541","https://openalex.org/W3162089186","https://openalex.org/W2033235985","https://openalex.org/W2763289028","https://openalex.org/W2031796104"],"abstract_inverted_index":{"Machine-learning":[0],"promises":[1],"to":[2,39,52,64,97],"transform":[3],"compilation":[4],"and":[5,67,69,110,124,136],"software":[6],"engineering,":[7],"yet":[8],"is":[9,21,76,127],"frequently":[10],"limited":[11],"by":[12],"the":[13,77,108,149],"scope":[14],"of":[15,24,32,72,114,129,143,152],"available":[16,80],"datasets.":[17],"In":[18],"particular,":[19],"there":[20],"a":[22,30,46,102],"lack":[23],"runnable,":[25],"real-world":[26,61,84,130],"datasets":[27],"required":[28],"for":[29],"range":[31],"tasks":[33],"ranging":[34],"from":[35,88],"neural":[36],"program":[37,42],"synthesis":[38],"machine":[40,153],"learning-guided":[41],"optimization.":[43],"We":[44,100,116],"introduce":[45],"new":[47],"dataset,":[48],"ExeBench,":[49],"which":[50],"attempts":[51],"address":[53],"this.":[54],"It":[55],"tackles":[56],"two":[57],"key":[58],"issues":[59],"with":[60,90],"code:":[62],"references":[63],"external":[65],"types":[66],"functions":[68,146],"scalable":[70],"generation":[71,151],"IO":[73,91],"examples.":[74],"ExeBench":[75,132],"first":[78],"publicly":[79],"dataset":[81],"that":[82,93,104],"pairs":[83],"C":[85,139],"code":[86],"taken":[87],"GitHub":[89],"examples":[92],"allow":[94],"these":[95],"programs":[96],"be":[98],"run.":[99],"develop":[101],"toolchain":[103],"scrapes":[105],"GitHub,":[106],"analyzes":[107],"code,":[109],"generates":[111],"runnable":[112],"snippets":[113],"code.":[115,131],"analyze":[117],"our":[118],"benchmark":[119],"suite":[120],"using":[121],"several":[122],"metrics,":[123],"show":[125],"it":[126],"representative":[128],"contains":[133],"4.5M":[134],"compilable":[135],"700k":[137],"executable":[138],"functions.":[140],"This":[141],"scale":[142],"executable,":[144],"real":[145],"will":[147],"enable":[148],"next":[150],"learning-based":[154],"programming":[155],"tasks.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}