{"id":"https://openalex.org/W2979566992","doi":"https://doi.org/10.1145/3360588","title":"Improving bug detection via context-based code representation learning and attention-based neural networks","display_name":"Improving bug detection via context-based code representation learning and attention-based neural networks","publication_year":2019,"publication_date":"2019-10-10","ids":{"openalex":"https://openalex.org/W2979566992","doi":"https://doi.org/10.1145/3360588","mag":"2979566992"},"language":"en","primary_location":{"id":"doi:10.1145/3360588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3360588","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3360588","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3360588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107249192","display_name":"Yi Li","orcid":"https://orcid.org/0009-0007-0143-0677"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Li","raw_affiliation_strings":["New Jersey Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070990953","display_name":"Shaohua Wang","orcid":"https://orcid.org/0000-0001-5777-7759"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaohua Wang","raw_affiliation_strings":["New Jersey Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089000736","display_name":"Tien N. Nguyen","orcid":"https://orcid.org/0009-0006-7962-6090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien N. Nguyen","raw_affiliation_strings":["University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042201485","display_name":"Son Nguyen","orcid":"https://orcid.org/0000-0002-8970-9870"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Son Van Nguyen","raw_affiliation_strings":["University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":25.3409,"has_fulltext":true,"cited_by_count":162,"citation_normalized_percentile":{"value":0.99457243,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"3","issue":"OOPSLA","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.827507495880127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6367864012718201},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.6304020881652832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6198524832725525},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5520161986351013},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5043255090713501},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48619669675827026},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47761672735214233},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4442930519580841},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4136212468147278},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.412426620721817},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16083088517189026},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14782503247261047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827507495880127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6367864012718201},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.6304020881652832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6198524832725525},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5520161986351013},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5043255090713501},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48619669675827026},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47761672735214233},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4442930519580841},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4136212468147278},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.412426620721817},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16083088517189026},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14782503247261047},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3360588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3360588","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3360588","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},{"id":"pmh:oai:zenodo.org:3719219","is_oa":true,"landing_page_url":"https://zenodo.org/record/3719219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.1145/3360588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3360588","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3360588","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1311026310","display_name":"CI-EN: Boa: Enhancing Infrastructure for Studying Software and its Evolution at a Large Scale","funder_award_id":"1513263","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6913106001","display_name":"SHF: Large: Collaborative Research: Exploiting the Naturalness of Software","funder_award_id":"1723215","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7387244200","display_name":"SHF:Small: Build Code Maintenance and Detecting, Testing, Locating Configuration and Build Errors","funder_award_id":"1723432","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8064159086","display_name":"TWC: Small: Detection and Prevention of Prior Known Software Security Vulnerabilities","funder_award_id":"1723198","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8311159335","display_name":"SHF: Large:Collaborative Research: Inferring Software Specifications from Open Source Repositories by Leveraging Data and Collective Community Expertise","funder_award_id":"1518897","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/W2979566992.pdf","grobid_xml":"https://content.openalex.org/works/W2979566992.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1771830246","https://openalex.org/W1968784174","https://openalex.org/W2025677988","https://openalex.org/W2041496338","https://openalex.org/W2054520963","https://openalex.org/W2059215200","https://openalex.org/W2077241052","https://openalex.org/W2093094052","https://openalex.org/W2124153277","https://openalex.org/W2125343911","https://openalex.org/W2142403498","https://openalex.org/W2142958724","https://openalex.org/W2144344516","https://openalex.org/W2148702066","https://openalex.org/W2163605009","https://openalex.org/W2164519300","https://openalex.org/W2360967250","https://openalex.org/W2375939852","https://openalex.org/W2511803001","https://openalex.org/W2514538448","https://openalex.org/W2619311298","https://openalex.org/W2621225554","https://openalex.org/W2767717989","https://openalex.org/W2811484325","https://openalex.org/W2883359218","https://openalex.org/W2886081690","https://openalex.org/W2899171197","https://openalex.org/W2899516694","https://openalex.org/W2962756421","https://openalex.org/W3003877692","https://openalex.org/W3004040842","https://openalex.org/W3005620216","https://openalex.org/W3104712907","https://openalex.org/W3145932680","https://openalex.org/W4239312229","https://openalex.org/W4254645357"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W2183246718","https://openalex.org/W2099261052","https://openalex.org/W3209204065","https://openalex.org/W2105707930","https://openalex.org/W1755711892","https://openalex.org/W2160907113","https://openalex.org/W4308823623","https://openalex.org/W2019168903","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Bug":[0],"detection":[1,31,258,298],"has":[2],"been":[3],"shown":[4],"to":[5,10,86,92,108,122,156,163,180,199,219,248,307],"be":[6,204],"an":[7],"effective":[8],"way":[9],"help":[11],"developers":[12],"in":[13,23,55,169,188,231,267,309],"detecting":[14,56],"bugs":[15,57,266,280],"early,":[16],"thus,":[17,207],"saving":[18],"much":[19],"effort":[20],"and":[21,47,62,82,103,151,299],"time":[22],"software":[24],"development":[25],"process.":[26],"Recently,":[27],"deep":[28],"learning-based":[29,40],"bug":[30,257,297],"approaches":[32],"have":[33,215,243],"gained":[34],"successes":[35],"over":[36,302],"the":[37,42,78,95,98,110,115,123,132,137,140,144,158,166,175,185,189,194,200,209,255,268,284,303],"traditional":[38],"machine":[39],"approaches,":[41,46],"rule-based":[43],"program":[44],"analysis":[45],"mining-based":[48],"approaches.":[49,259,286],"However,":[50],"they":[51],"are":[52,197],"still":[53],"limited":[54],"that":[58,119,196,239,290],"involve":[59],"multiple":[60],"methods":[61,118,230],"suffer":[63],"high":[64],"rate":[65],"of":[66,80,149,174,211,270],"false":[67,159],"positives.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,171],"propose":[73,91],"a":[74,224,244],"combination":[75],"approach":[76,222],"with":[77,114,228,254,283],"use":[79,93,148,173],"contexts":[81],"attention":[83,176],"neural":[84,177],"network":[85,178],"overcome":[87],"those":[88],"limitations.":[89],"We":[90,214,287],"as":[94],"global":[96,127],"context":[97,128,134],"Program":[99],"Dependence":[100],"Graph":[101,106],"(PDG)":[102],"Data":[104],"Flow":[105],"(DFG)":[107],"connect":[109],"method":[111],"under":[112],"investigation":[113],"other":[116,304],"relevant":[117],"might":[120],"contribute":[121],"buggy":[124,186,201],"code.":[125,191],"The":[126,147,236],"is":[129,276,293],"complemented":[130],"by":[131],"local":[133],"extracted":[135],"from":[136,143],"path":[138],"on":[139,184,223,250],"AST":[141],"built":[142],"method\u2019s":[145],"body.":[146],"PDG":[150],"DFG":[152],"enables":[153],"our":[154,212,221,240,291],"model":[155],"reduce":[157],"positive":[160],"rate,":[161],"while":[162],"complement":[164],"for":[165,296],"potential":[167],"reduction":[168],"recall,":[170],"make":[172],"mechanism":[179],"put":[181],"more":[182,278],"weights":[183],"paths":[187,195,202],"source":[190],"That":[192],"is,":[193],"similar":[198],"will":[203],"ranked":[205],"higher,":[206],"improving":[208],"recall":[210],"model.":[213],"conducted":[216],"several":[217],"experiments":[218],"evaluate":[220],"very":[225],"large":[226],"dataset":[227],"+4.973M":[229],"92":[232],"different":[233],"project":[234],"versions.":[235],"results":[237],"show":[238],"tool":[241,261],"can":[242,262],"relative":[245],"improvement":[246],"up":[247,306],"160%":[249],"F-score":[251],"when":[252,281],"comparing":[253,282],"state-of-the-art":[256],"Our":[260],"detect":[263],"48":[264],"true":[265,279],"list":[269],"top":[271],"100":[272],"reported":[273,289],"bugs,":[274],"which":[275],"24":[277],"baseline":[285],"also":[288],"representation":[292],"better":[294],"suitable":[295],"relatively":[300],"improves":[301],"representations":[305],"206%":[308],"accuracy.":[310]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":12}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}