{"id":"https://openalex.org/W4400484606","doi":"https://doi.org/10.1145/3663533.3664036","title":"MoreFixes: A Large-Scale Dataset of CVE Fix Commits Mined through Enhanced Repository Discovery","display_name":"MoreFixes: A Large-Scale Dataset of CVE Fix Commits Mined through Enhanced Repository Discovery","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400484606","doi":"https://doi.org/10.1145/3663533.3664036"},"language":"en","primary_location":{"id":"doi:10.1145/3663533.3664036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3663533.3664036","pdf_url":null,"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 20th International Conference on Predictive Models and Data Analytics in Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3663533.3664036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100494909","display_name":"Jafar Akhoundali","orcid":"https://orcid.org/0009-0002-8260-9508"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jafar Akhoundali","raw_affiliation_strings":["Leiden University, Leiden, Netherlands"],"raw_orcid":"https://orcid.org/0009-0002-8260-9508","affiliations":[{"raw_affiliation_string":"Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100494910","display_name":"Sajad Rahim Nouri","orcid":null},"institutions":[{"id":"https://openalex.org/I110525433","display_name":"Islamic Azad University, Tehran","ror":"https://ror.org/01kzn7k21","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Sajad Rahim Nouri","raw_affiliation_strings":["Islamic Azad University of Ramsar, Ramsar, Iran"],"raw_orcid":"https://orcid.org/0009-0003-4076-3037","affiliations":[{"raw_affiliation_string":"Islamic Azad University of Ramsar, Ramsar, Iran","institution_ids":["https://openalex.org/I110525433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074964009","display_name":"Kristian F. D. Rietveld","orcid":"https://orcid.org/0000-0003-0455-3430"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kristian Rietveld","raw_affiliation_strings":["Leiden University, Leiden, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0455-3430","affiliations":[{"raw_affiliation_string":"Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068415784","display_name":"Olga Gadyatskaya","orcid":"https://orcid.org/0000-0002-3760-9165"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Olga Gadyatskaya","raw_affiliation_strings":["Leiden University, Leiden, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-3760-9165","affiliations":[{"raw_affiliation_string":"Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4384,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.96542509,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9966999888420105,"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":0.9966999888420105,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.595417857170105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5930602550506592},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38573184609413147},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1159336268901825}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.595417857170105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5930602550506592},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38573184609413147},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1159336268901825},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3663533.3664036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3663533.3664036","pdf_url":null,"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 20th International Conference on Predictive Models and Data Analytics in Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_4213015","is_oa":true,"landing_page_url":"https://zenodo.org/records/13983082","pdf_url":"https://scholarlypublications.universiteitleiden.nl/access/item%3A4213016/view","source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PROMISE 2024","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3663533.3664036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3663533.3664036","pdf_url":null,"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 20th International Conference on Predictive Models and Data Analytics in Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2025411198","https://openalex.org/W2477342951","https://openalex.org/W2766411424","https://openalex.org/W2963926786","https://openalex.org/W2969343988","https://openalex.org/W3156480510","https://openalex.org/W3183469243","https://openalex.org/W3195703954","https://openalex.org/W4281398044","https://openalex.org/W4286331368","https://openalex.org/W4286331440","https://openalex.org/W4292258179","https://openalex.org/W4308641648","https://openalex.org/W4308643023","https://openalex.org/W4312856222","https://openalex.org/W4318305465","https://openalex.org/W4384345694","https://openalex.org/W4384345705","https://openalex.org/W4385412165","https://openalex.org/W4387298393","https://openalex.org/W4388212383","https://openalex.org/W4388483128","https://openalex.org/W4388826738","https://openalex.org/W4389215044","https://openalex.org/W4389544221","https://openalex.org/W4398161280","https://openalex.org/W4400121141","https://openalex.org/W6892510730","https://openalex.org/W6892610320"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Vulnerability":[0],"datasets":[1,28,187],"have":[2,59,87],"become":[3],"an":[4],"important":[5],"instrument":[6],"in":[7,160,165,173,192],"software":[8,198],"security":[9],"research,":[10],"being":[11],"used":[12],"to":[13,70,75,90,119,150,202,215,237,256],"develop":[14],"automated,":[15],"machine":[16],"learning-based":[17],"vulnerability":[18,45,130,186,195],"detection":[19,196],"and":[20,61,169,188,197,224,230],"patching":[21],"approaches.":[22],"Yet,":[23],"any":[24],"limitations":[25],"of":[26,34,43,51,83,98,122,220],"these":[27],"may":[29,47],"translate":[30],"into":[31],"inadequate":[32],"performance":[33],"the":[35,40,49,92,102,120,127,183,203,238,257],"developed":[36],"solutions.":[37],"For":[38],"example,":[39],"limited":[41],"size":[42],"a":[44,63,81,157,162,170,205,244],"dataset":[46,97,107,131,154,178,251],"restrict":[48],"applicability":[50],"deep":[52],"learning":[53],"techniques.":[54],"In":[55],"our":[56,84,123,153,250],"work,":[57,152],"we":[58,86,248],"designed":[60],"implemented":[62],"novel":[64],"workflow":[65],"with":[66,101,132,141],"several":[67],"heuristic":[68],"methods":[69,73,225],"combine":[71],"state-of-the-art":[72],"related":[74,236],"CVE":[76,99,129],"fix":[77,104,133,239],"commits":[78,134,144,240],"gathering.":[79],"As":[80],"consequence":[82],"improvements,":[85],"been":[88],"able":[89],"gather":[91],"largest":[93],"programming":[94],"language-independent":[95],"real-world":[96,185],"vulnerabilities":[100],"associated":[103,140],"commits.":[105],"Our":[106,176],"containing":[108],"26,617":[109],"unique":[110,115,143],"CVEs":[111,138,213],"coming":[112],"from":[113],"6,945":[114],"GitHub":[116],"projects":[117],"is,":[118],"best":[121],"knowledge,":[124],"by":[125,227],"far":[126],"biggest":[128],"available":[135,242,255],"today.":[136],"These":[137],"are":[139,241],"31,883":[142],"that":[145,209],"fixed":[146],"those":[147],"vulnerabilities.":[148],"Compared":[149],"prior":[151],"brings":[155],"about":[156],"397%":[158],"increase":[159,164,172],"CVEs,":[161],"295%":[163],"covered":[166],"open-source":[167],"projects,":[168],"480%":[171],"commit":[174],"fixes.":[175],"larger":[177],"thus":[179],"substantially":[180],"improves":[181],"over":[182],"current":[184],"enables":[189],"further":[190],"progress":[191],"research":[193],"on":[194,212],"security.":[199],"We":[200],"release":[201],"community":[204],"14GB":[206],"PostgreSQL":[207],"database":[208],"contains":[210],"information":[211],"up":[214],"January":[216],"24,":[217],"2024,":[218],"CWEs":[219],"each":[221,228],"CVE,":[222],"files":[223,235],"changed":[226],"commit,":[229],"repository":[231],"metadata.":[232],"Additionally,":[233],"patch":[234],"as":[243],"separate":[245],"package.":[246],"Furthermore,":[247],"make":[249],"collection":[252],"tool":[253],"also":[254],"community.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}