{"id":"https://openalex.org/W6907179428","doi":"https://doi.org/10.21227/vp9n-wv96","title":"he FormAI Dataset : 112,000 AI generated C Programs Classified by Vulnerabilities","display_name":"he FormAI Dataset : 112,000 AI generated C Programs Classified by Vulnerabilities","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W6907179428","doi":"https://doi.org/10.21227/vp9n-wv96"},"language":"en","primary_location":{"id":"doi:10.21227/vp9n-wv96","is_oa":true,"landing_page_url":"https://doi.org/10.21227/vp9n-wv96","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/vp9n-wv96","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tihanyi, Norbert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Tihanyi, Norbert","raw_affiliation_strings":["Technology Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bisztray, Tamas","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Bisztray, Tamas","raw_affiliation_strings":["University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hain, Ridhi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hain, Ridhi","raw_affiliation_strings":["Technology Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Amine Ferrag, Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Amine Ferrag, Mohamed","raw_affiliation_strings":["Technology Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":null,"display_name":"C. Cordeiro, Lucas","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C. Cordeiro, Lucas","raw_affiliation_strings":["University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mavroeidis, Vasileios","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Mavroeidis, Vasileios","raw_affiliation_strings":["University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5309000015258789},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.522599995136261},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5224000215530396},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.41179999709129333},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131999969482422},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5309000015258789},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C22680326","wikidata":"https://www.wikidata.org/wiki/Q7444867","display_name":"Secure coding","level":5,"score":0.3853999972343445},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.375},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2802000045776367}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/vp9n-wv96","is_oa":true,"landing_page_url":"https://doi.org/10.21227/vp9n-wv96","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/vp9n-wv96","is_oa":true,"landing_page_url":"https://doi.org/10.21227/vp9n-wv96","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},"sustainable_development_goals":[{"score":0.6596775650978088,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,13],"FormAI":[1],"dataset":[2,83,107],"is":[3,48],"the":[4,55,64,103,106,128,133],"first":[5],"AI-generated":[6],"repository":[7],"comprising":[8],"112,000":[9],"compilable":[10],"C":[11],"programs.":[12],"length":[14],"of":[15,29,99,132],"each":[16],"generated":[17,109],"program":[18,47,130],"varies":[19],"between":[20],"6":[21],"and":[22,90],"616":[23],"lines,":[24],"covering":[25],"a":[26,58,85,92,96],"diverse":[27,93],"set":[28],"tasks":[30],"ranging":[31],"from":[32],"simple":[33],"to":[34,119],"complex":[35],"ones,":[36],"such":[37],"as":[38],"network":[39],"management,":[40],"table":[41],"games,":[42],"or":[43],"string":[44],"manipulation.":[45],"Each":[46],"labelled":[49],"based":[50,62],"on":[51,63],"vulnerabilities":[52,75],"present":[53],"in":[54,105],"code":[56],"using":[57],"formal":[59],"verification":[60],"method":[61],"Efficient":[65],"SMT-based":[66],"Bounded":[67],"Model":[68],"Checker":[69],"(ESBMC).":[70],"This":[71],"strategy":[72],"conclusively":[73],"identifies":[74],"without":[76],"reporting":[77],"false":[78],"positives.":[79],"We":[80],"built":[81],"this":[82],"with":[84],"methodology":[86],"utilizing":[87],"zero-shot":[88],"prompts,":[89],"created":[91],"datasets":[94],"facilitating":[95],"wide":[97],"range":[98],"coding":[100],"errors.":[101],"All":[102],"programs":[104],"were":[108],"by":[110],"GPT-3.5-turbo.":[111],"Additionally,":[112],"these":[113],"labeled":[114],"samples":[115],"can":[116],"be":[117],"utilized":[118],"train":[120],"Large":[121],"Language":[122],"Models":[123],"(LLMs)":[124],"since":[125],"they":[126],"contain":[127],"exact":[129],"location":[131],"software":[134],"vulnerability.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
