{"id":"https://openalex.org/W2061557777","doi":"https://doi.org/10.1145/2597073.2597128","title":"Generating duplicate bug datasets","display_name":"Generating duplicate bug datasets","publication_year":2014,"publication_date":"2014-05-20","ids":{"openalex":"https://openalex.org/W2061557777","doi":"https://doi.org/10.1145/2597073.2597128","mag":"2061557777"},"language":"en","primary_location":{"id":"doi:10.1145/2597073.2597128","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597073.2597128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Working Conference on Mining Software Repositories","raw_type":"proceedings-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/A5056799505","display_name":"Alina Lazar","orcid":"https://orcid.org/0000-0002-2096-1541"},"institutions":[{"id":"https://openalex.org/I161203489","display_name":"Youngstown State University","ror":"https://ror.org/038zf2n28","country_code":"US","type":"education","lineage":["https://openalex.org/I161203489"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alina Lazar","raw_affiliation_strings":["Youngstown State University, USA","Youngstown State University , USA"],"affiliations":[{"raw_affiliation_string":"Youngstown State University, USA","institution_ids":["https://openalex.org/I161203489"]},{"raw_affiliation_string":"Youngstown State University , USA","institution_ids":["https://openalex.org/I161203489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110118783","display_name":"Sarah Ritchey","orcid":null},"institutions":[{"id":"https://openalex.org/I161203489","display_name":"Youngstown State University","ror":"https://ror.org/038zf2n28","country_code":"US","type":"education","lineage":["https://openalex.org/I161203489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Ritchey","raw_affiliation_strings":["Youngstown State University, USA","Youngstown State University , USA"],"affiliations":[{"raw_affiliation_string":"Youngstown State University, USA","institution_ids":["https://openalex.org/I161203489"]},{"raw_affiliation_string":"Youngstown State University , USA","institution_ids":["https://openalex.org/I161203489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045476556","display_name":"Bonita Sharif","orcid":"https://orcid.org/0000-0002-5178-7160"},"institutions":[{"id":"https://openalex.org/I161203489","display_name":"Youngstown State University","ror":"https://ror.org/038zf2n28","country_code":"US","type":"education","lineage":["https://openalex.org/I161203489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bonita Sharif","raw_affiliation_strings":["Youngstown State University, USA","Youngstown State University , USA"],"affiliations":[{"raw_affiliation_string":"Youngstown State University, USA","institution_ids":["https://openalex.org/I161203489"]},{"raw_affiliation_string":"Youngstown State University , USA","institution_ids":["https://openalex.org/I161203489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056799505"],"corresponding_institution_ids":["https://openalex.org/I161203489"],"apc_list":null,"apc_paid":null,"fwci":9.467,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.97609728,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"395"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9957000017166138,"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":0.9894999861717224,"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":0.7921721935272217},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5965685844421387},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.5740198493003845},{"id":"https://openalex.org/keywords/eclipse","display_name":"Eclipse","score":0.5515793561935425},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5196229815483093},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.49537527561187744},{"id":"https://openalex.org/keywords/software-regression","display_name":"Software regression","score":0.4806903004646301},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4785614311695099},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4688343405723572},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.45301300287246704},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3823740780353546},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37491583824157715},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.19609495997428894},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10394138097763062},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.09125697612762451}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921721935272217},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5965685844421387},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.5740198493003845},{"id":"https://openalex.org/C2778505590","wikidata":"https://www.wikidata.org/wiki/Q141022","display_name":"Eclipse","level":2,"score":0.5515793561935425},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5196229815483093},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.49537527561187744},{"id":"https://openalex.org/C191727507","wikidata":"https://www.wikidata.org/wiki/Q24346","display_name":"Software regression","level":5,"score":0.4806903004646301},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4785614311695099},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4688343405723572},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.45301300287246704},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3823740780353546},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37491583824157715},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.19609495997428894},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10394138097763062},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.09125697612762451},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2597073.2597128","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597073.2597128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Working Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1968610848","https://openalex.org/W1981109290","https://openalex.org/W1999910737","https://openalex.org/W2018582844","https://openalex.org/W2053158571","https://openalex.org/W2130146200","https://openalex.org/W2158133897","https://openalex.org/W2158760041","https://openalex.org/W2165022036","https://openalex.org/W2167630669"],"related_works":["https://openalex.org/W3009111612","https://openalex.org/W2044225531","https://openalex.org/W2597543511","https://openalex.org/W2901462014","https://openalex.org/W3045036521","https://openalex.org/W3004570974","https://openalex.org/W2135303064","https://openalex.org/W3185667871","https://openalex.org/W2603381882","https://openalex.org/W2529044956"],"abstract_inverted_index":{"Automatic":[0],"identification":[1,34],"of":[2,22,108,111,119,149],"duplicate":[3,31,112,154],"bug":[4,23,32,48,96,101,155,168],"reports":[5,156],"is":[6,125],"an":[7],"important":[8],"research":[9],"problem":[10],"in":[11,81,84,92],"the":[12,30,54,74,78,95,103,158],"mining":[13],"software":[14],"repositories":[15],"field.":[16],"This":[17],"paper":[18],"presents":[19],"a":[20,85,106,123,134,147],"collection":[21],"datasets":[24,37],"collected,":[25],"cleaned":[26,79],"and":[27,51,66,77,132,140,170],"preprocessed":[28],"for":[29,129],"report":[33],"problem.":[35],"The":[36,58],"were":[38],"extracted":[39],"from":[40,100],"open-source":[41],"systems":[42,59],"that":[43],"use":[44],"Bugzilla":[45],"as":[46,127],"their":[47],"tracking":[49],"component":[50],"contain":[52],"all":[53,109],"bugs":[55,113],"ever":[56],"submitted.":[57],"used":[60,146,165],"are":[61],"Eclipse,":[62],"Open":[63],"Office,":[64],"NetBeans":[65],"Mozilla.":[67],"For":[68,89],"each":[69,90],"dataset,":[70,91],"we":[71],"store":[72],"both":[73],"initial":[75],"data":[76,80,97,151,160],"separate":[82],"collections":[83,98],"mongoDB":[86],"document-oriented":[87],"database.":[88],"addition":[93],"to":[94,137,152,166],"downloaded":[99],"repositories,":[102],"database":[104],"includes":[105],"set":[107,161],"pairs":[110,118],"together":[114],"with":[115],"randomly":[116],"selected":[117],"non-duplicate":[120],"bugs.":[121],"Such":[122],"dataset":[124],"useful":[126],"input":[128],"classification":[130],"models":[131],"forms":[133],"good":[135],"base":[136],"support":[138],"replications":[139],"comparisons":[141],"by":[142],"other":[143],"researchers.":[144],"We":[145],"subset":[148],"this":[150],"predict":[153,167],"but":[157],"same":[159],"may":[162],"also":[163],"be":[164],"priorities":[169],"severity.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
