{"id":"https://openalex.org/W1771830246","doi":"https://doi.org/10.1145/2884781.2884848","title":"On the \"naturalness\" of buggy code","display_name":"On the \"naturalness\" of buggy code","publication_year":2016,"publication_date":"2016-05-13","ids":{"openalex":"https://openalex.org/W1771830246","doi":"https://doi.org/10.1145/2884781.2884848","mag":"1771830246"},"language":"en","primary_location":{"id":"doi:10.1145/2884781.2884848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884781.2884848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.zora.uzh.ch/id/eprint/197772/1/icse2016a.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064541855","display_name":"Baishakhi Ray","orcid":"https://orcid.org/0000-0003-3406-5235"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baishakhi Ray","raw_affiliation_strings":["University of Virginia","University of Virginia'"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"University of Virginia'","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009679905","display_name":"Vincent J. Hellendoorn","orcid":"https://orcid.org/0000-0001-7516-0525"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Hellendoorn","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018471345","display_name":"Saheel Godhane","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saheel Godhane","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110579339","display_name":"Zhaopeng Tu","orcid":"https://orcid.org/0000-0002-7900-6055"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhaopeng Tu","raw_affiliation_strings":["Huawei Technologies Co. Ltd","Huawei Technologies, Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd","institution_ids":["https://openalex.org/I4210160618"]},{"raw_affiliation_string":"Huawei Technologies, Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082720005","display_name":"Alberto Bacchelli","orcid":"https://orcid.org/0000-0003-0193-6823"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alberto Bacchelli","raw_affiliation_strings":["Delft University of Technology","Delft University of Technology,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology,,,,,","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036744986","display_name":"Pr\u00e9mkumar D\u00e9vanbu","orcid":"https://orcid.org/0000-0002-4346-5276"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Premkumar Devanbu","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":254,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"428","last_page":"439"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9983999729156494,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/naturalness","display_name":"Naturalness","score":0.8959896564483643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8057088255882263},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.5746294856071472},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5337783694267273},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5311241149902344},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.53061443567276},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.524109959602356},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.47556987404823303},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.4479559659957886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44387584924697876},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4415874183177948},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42427289485931396},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4181615114212036},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4155849814414978},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3945428729057312},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.342396080493927},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.26676374673843384}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8959896564483643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057088255882263},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.5746294856071472},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5337783694267273},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5311241149902344},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.53061443567276},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.524109959602356},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.47556987404823303},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.4479559659957886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44387584924697876},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4415874183177948},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42427289485931396},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4181615114212036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4155849814414978},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3945428729057312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.342396080493927},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.26676374673843384},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2884781.2884848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884781.2884848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:www.zora.uzh.ch:197772","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.zora.uzh.ch/id/eprint/197772/1/icse2016a.pdf","source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Ray, Baishakhi; Hellendoorn, Vincent; Godhane, Saheel; Tu, Zhaopeng; Bacchelli, Alberto; Devanbu, Premkumar (2016). On the \"naturalness\" of buggy code. In: the 38th International Conference, Austin, Texas, 14 June 2016 - 22 June 2016. ACM Press, 428-439.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:tud:oai:tudelft.nl:uuid:06b98630-5baa-41d7-b98f-26e7d26f7d4a","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:06b98630-5baa-41d7-b98f-26e7d26f7d4a","pdf_url":"http://resolver.tudelft.nl/uuid:06b98630-5baa-41d7-b98f-26e7d26f7d4a","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings - 2016 IEEE/ACM 38th IEEE International Conference on Software Engineering Companion, ICSE 2016, 1","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"doi:10.5167/uzh-197772","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-197772","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:www.zora.uzh.ch:197772","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.zora.uzh.ch/id/eprint/197772/1/icse2016a.pdf","source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Ray, Baishakhi; Hellendoorn, Vincent; Godhane, Saheel; Tu, Zhaopeng; Bacchelli, Alberto; Devanbu, Premkumar (2016). On the \"naturalness\" of buggy code. In: the 38th International Conference, Austin, Texas, 14 June 2016 - 22 June 2016. ACM Press, 428-439.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7432288113","display_name":"SHF: Large: Collaborative Research: Exploiting the Naturalness of Software","funder_award_id":"1414172","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1771830246.pdf","grobid_xml":"https://content.openalex.org/works/W1771830246.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1570448133","https://openalex.org/W1912598576","https://openalex.org/W1968027261","https://openalex.org/W1972141422","https://openalex.org/W1974020522","https://openalex.org/W1975040830","https://openalex.org/W1989657183","https://openalex.org/W1998259093","https://openalex.org/W2017439596","https://openalex.org/W2018866163","https://openalex.org/W2019230987","https://openalex.org/W2025677988","https://openalex.org/W2030857403","https://openalex.org/W2033418259","https://openalex.org/W2043811931","https://openalex.org/W2054520963","https://openalex.org/W2060384944","https://openalex.org/W2067436653","https://openalex.org/W2074032109","https://openalex.org/W2074218040","https://openalex.org/W2078393527","https://openalex.org/W2080529963","https://openalex.org/W2090878800","https://openalex.org/W2097227214","https://openalex.org/W2100310618","https://openalex.org/W2100945416","https://openalex.org/W2105300539","https://openalex.org/W2111421634","https://openalex.org/W2111949697","https://openalex.org/W2116272605","https://openalex.org/W2119682413","https://openalex.org/W2121866145","https://openalex.org/W2123227336","https://openalex.org/W2130243914","https://openalex.org/W2132887549","https://openalex.org/W2134237567","https://openalex.org/W2136279823","https://openalex.org/W2137813581","https://openalex.org/W2139885493","https://openalex.org/W2140609933","https://openalex.org/W2142403498","https://openalex.org/W2142481192","https://openalex.org/W2142958724","https://openalex.org/W2143861926","https://openalex.org/W2149598089","https://openalex.org/W2151553346","https://openalex.org/W2156981320","https://openalex.org/W2157353183","https://openalex.org/W2158744032","https://openalex.org/W2163732854","https://openalex.org/W2165747537","https://openalex.org/W2168411647","https://openalex.org/W2914040074","https://openalex.org/W2918145851","https://openalex.org/W2966207845","https://openalex.org/W2999074369","https://openalex.org/W3145932680","https://openalex.org/W4235354960"],"related_works":["https://openalex.org/W2078744341","https://openalex.org/W2029555411","https://openalex.org/W1992074508","https://openalex.org/W2774439323","https://openalex.org/W3151530686","https://openalex.org/W1509265476","https://openalex.org/W2981446648","https://openalex.org/W2183678285","https://openalex.org/W4383568364","https://openalex.org/W2975512365"],"abstract_inverted_index":{"Real":[0],"software,":[1],"the":[2,8,112,118,191,211],"kind":[3],"working":[4],"programmers":[5],"produce":[6],"by":[7,145],"kLOC":[9],"to":[10,15,25,44,67,128,153,171,209],"solve":[11],"real-world":[12],"problems,":[13],"tends":[14,24,127],"be":[16,26,129,204],"\"natural\",":[17],"like":[18],"speech":[19],"or":[20,65,215],"natural":[21],"language;":[22],"it":[23],"highly":[27,164],"repetitive":[28],"and":[29,41,55,78,105,117,179,217,230],"predictable.":[30],"Researchers":[31],"have":[32],"captured":[33],"this":[34,83,87],"naturalness":[35,113],"of":[36,94,114,193,213],"software":[37],"through":[38],"statistical":[39,70],"models":[40],"used":[42],"them":[43],"good":[45,69],"effect":[46],"in":[47,75,169,197],"suggestion":[48],"engines,":[49],"porting":[50],"tools,":[51],"coding":[52],"standards":[53],"checkers,":[54],"idiom":[56],"miners.":[57],"This":[58,199],"suggests":[59,200],"that":[60,62,123,201,218],"code":[61,116,124,195],"appears":[63],"improbable,":[64],"surprising,":[66],"a":[68,91,159,205],"language":[71,109],"model":[72],"is":[73,167],"\"unnatural\"":[74],"some":[76,172],"sense,":[77],"thus":[79],"possibly":[80],"suspicious.":[81],"In":[82],"paper,":[84],"we":[85],"investigate":[86],"hypothesis.":[88],"We":[89,121],"consider":[90],"large":[92],"corpus":[93],"bug":[95,175,184],"fix":[96],"commits":[97],"(ca.":[98],"7,139),":[99],"from":[100,182,224],"10":[101],"different":[102],"Java":[103],"projects,":[104],"focus":[106],"on":[107,163],"its":[108],"statistics,":[110],"evaluating":[111],"buggy":[115],"corresponding":[119],"fixes.":[120,233],"find":[122],"with":[125],"bugs":[126,138],"more":[130],"entropic":[131,165],"(i.e.":[132],"unnatural),":[133],"becoming":[134],"less":[135],"so":[136],"as":[137],"are":[139],"fixed.":[140],"Ordering":[141],"files":[142],"for":[143,228,232],"inspection":[144],"their":[146],"average":[147],"entropy":[148,188,202,226],"yields":[149],"cost-effectiveness":[150,170,192],"scores":[151],"comparable":[152],"popular":[154],"defect":[155],"prediction":[156],"methods.":[157],"At":[158],"finer":[160],"granularity,":[161],"focusing":[162],"lines":[166],"similar":[168],"well-known":[173],"static":[174],"finders":[176,185],"(PMD,":[177],"FindBugs)":[178],"ordering":[180],"warnings":[181],"these":[183],"using":[186,225],"an":[187],"measure":[189],"improves":[190],"inspecting":[194],"implicated":[196],"warnings.":[198],"may":[203,222],"valid,":[206],"simple":[207],"way":[208],"complement":[210],"effectiveness":[212],"PMD":[214],"FindBugs,":[216],"search-based":[219],"bug-fixing":[220],"methods":[221],"benefit":[223],"both":[227],"fault-localization":[229],"searching":[231]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":38},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}