{"id":"https://openalex.org/W2150874999","doi":"https://doi.org/10.1109/tse.2007.70773","title":"Classifying Software Changes: Clean or Buggy?","display_name":"Classifying Software Changes: Clean or Buggy?","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2150874999","doi":"https://doi.org/10.1109/tse.2007.70773","mag":"2150874999"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2007.70773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2007.70773","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-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/A5100695700","display_name":"Sunghun Kim","orcid":"https://orcid.org/0000-0002-3813-4229"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunghun Kim","raw_affiliation_strings":["Massachusetts Inst. of Technol., Cambridge","Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Inst. of Technol., Cambridge","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089970457","display_name":"E. James Whitehead","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E. James Whitehead,","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100388333","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0003-4299-1511"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["University of California, Santa Cruz, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":74.2856,"has_fulltext":false,"cited_by_count":676,"citation_normalized_percentile":{"value":0.99889656,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"34","issue":"2","first_page":"181","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980000257492065,"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":0.996399998664856,"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":0.8741406202316284},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7137197256088257},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6067267060279846},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6030838489532471},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5734164714813232},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5118588805198669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5100801587104797},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.4713434875011444},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.45406290888786316},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.43192368745803833},{"id":"https://openalex.org/keywords/open-source-software","display_name":"Open source software","score":0.41802114248275757},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40255314111709595},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2411365509033203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8741406202316284},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7137197256088257},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6067267060279846},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6030838489532471},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5734164714813232},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5118588805198669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5100801587104797},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.4713434875011444},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.45406290888786316},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.43192368745803833},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.41802114248275757},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40255314111709595},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2411365509033203}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/tse.2007.70773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2007.70773","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.160.503","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.soe.ucsc.edu/~ejw/papers/kim-tse-2008.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.5587","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.5587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.ucsc.edu/%7Eyiz/papers/J2-SoftwareEngineer.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.219.2942","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.219.2942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucsc.edu/~ejw/papers/cc.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-41943","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-41943","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:repository.ust.hk:1783.1-41943","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-41943","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W98709482","https://openalex.org/W1522930027","https://openalex.org/W1540371141","https://openalex.org/W1542632805","https://openalex.org/W1564131673","https://openalex.org/W1570448133","https://openalex.org/W1584735725","https://openalex.org/W1968150772","https://openalex.org/W1993836075","https://openalex.org/W2007705030","https://openalex.org/W2023450550","https://openalex.org/W2025674334","https://openalex.org/W2027483357","https://openalex.org/W2029853454","https://openalex.org/W2046671629","https://openalex.org/W2049828091","https://openalex.org/W2054520963","https://openalex.org/W2064319223","https://openalex.org/W2067048176","https://openalex.org/W2079317829","https://openalex.org/W2084812512","https://openalex.org/W2097403040","https://openalex.org/W2098629748","https://openalex.org/W2100945416","https://openalex.org/W2101154344","https://openalex.org/W2101620885","https://openalex.org/W2110385988","https://openalex.org/W2115224143","https://openalex.org/W2118020653","https://openalex.org/W2119777739","https://openalex.org/W2124666592","https://openalex.org/W2128666163","https://openalex.org/W2141558501","https://openalex.org/W2145073242","https://openalex.org/W2145103646","https://openalex.org/W2146682513","https://openalex.org/W2147105902","https://openalex.org/W2149684865","https://openalex.org/W2149899391","https://openalex.org/W2150102617","https://openalex.org/W2150786161","https://openalex.org/W2151553346","https://openalex.org/W2154816175","https://openalex.org/W2156909104","https://openalex.org/W2157353183","https://openalex.org/W2158997610","https://openalex.org/W2159610968","https://openalex.org/W2160958420","https://openalex.org/W2163960678","https://openalex.org/W2164519300","https://openalex.org/W2166490929","https://openalex.org/W2171733741","https://openalex.org/W2282011913","https://openalex.org/W2539187648","https://openalex.org/W2751318774","https://openalex.org/W2966207845","https://openalex.org/W3009784374","https://openalex.org/W3017367945","https://openalex.org/W3022512959","https://openalex.org/W3112020351","https://openalex.org/W3141989311","https://openalex.org/W3145932680","https://openalex.org/W4235354960","https://openalex.org/W4236531428","https://openalex.org/W4241947741","https://openalex.org/W4243052451","https://openalex.org/W4244437277","https://openalex.org/W4251218026","https://openalex.org/W4254306780","https://openalex.org/W4256147943","https://openalex.org/W4296394699","https://openalex.org/W6631307659","https://openalex.org/W6681651645","https://openalex.org/W6681875376","https://openalex.org/W6829896844"],"related_works":["https://openalex.org/W2113128227","https://openalex.org/W632256878","https://openalex.org/W2491403535","https://openalex.org/W3123068371","https://openalex.org/W4211197663","https://openalex.org/W2104915799","https://openalex.org/W1518632238","https://openalex.org/W1839869193","https://openalex.org/W4311938462","https://openalex.org/W2083085980"],"abstract_inverted_index":{"This":[0],"paper":[1,157],"introduces":[2],"a":[3,17,24,68,114,133,152,159,176],"new":[4,25],"technique":[5,130],"for":[6,132,167],"finding":[7],"latent":[8],"software":[9,26,49,69,75],"bugs":[10,47],"called":[11],"change":[12,27,41,95,112,163,174,182],"classification.":[13],"Change":[14,99],"classification":[15,42,100,164,183],"uses":[16],"machine":[18,59],"learning":[19,60],"classifier":[20,52,81],"to":[21,31,113],"determine":[22],"whether":[23],"is":[28,53,109],"more":[29],"similar":[30],"prior":[32],"buggy":[33,86,94],"changes,":[34],"or":[35,87],"clean":[36,88],"changes.":[37,50],"In":[38],"this":[39],"manner,":[40],"predicts":[43],"the":[44,58,64,106,125,129,156,162,179,192],"existence":[45],"of":[46,67,136,151,155,161,178,181,191,195,198],"in":[48,73],"The":[51,79],"trained":[54,80],"using":[55],"features":[56,169],"(in":[57],"sense)":[61],"extracted":[62],"from":[63,170],"revision":[65],"history":[66],"project,":[70],"as":[71,85],"stored":[72],"its":[74],"configuration":[76],"management":[77],"repository.":[78],"can":[82,145],"classify":[83],"changes":[84],"with":[89],"78%":[90],"accuracy":[91],"and":[92,139,142,173,189],"65%":[93],"recall":[96],"(on":[97],"average).":[98],"has":[101],"several":[102],"desirable":[103],"qualities:":[104],"(1)":[105],"prediction":[107],"granularity":[108],"small":[110],"(a":[111],"single":[115],"file),":[116],"(2)":[117],"predictions":[118,144],"do":[119],"not":[120],"require":[121],"semantic":[122],"information":[123],"about":[124],"source":[126,171,187],"code,":[127],"(3)":[128],"works":[131],"broad":[134],"array":[135],"project":[137],"types":[138],"programming":[140],"languages,":[141],"(4)":[143],"be":[146],"made":[147],"immediately":[148],"upon":[149],"completion":[150],"change.":[153],"Contributions":[154],"include":[158],"description":[160],"approach,":[165],"techniques":[166],"extracting":[168],"code":[172],"histories,":[175],"characterization":[177],"performance":[180],"across":[184],"12":[185],"open":[186],"projects,":[188],"evaluation":[190],"predictive":[193],"power":[194],"different":[196],"groups":[197],"features.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":45},{"year":2021,"cited_by_count":62},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":55},{"year":2018,"cited_by_count":58},{"year":2017,"cited_by_count":49},{"year":2016,"cited_by_count":46},{"year":2015,"cited_by_count":46},{"year":2014,"cited_by_count":31},{"year":2013,"cited_by_count":30},{"year":2012,"cited_by_count":40}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}