{"id":"https://openalex.org/W3213259750","doi":"https://doi.org/10.1007/s10664-021-10092-4","title":"Problems with SZZ and features: An empirical study of the state of practice of defect prediction data collection","display_name":"Problems with SZZ and features: An empirical study of the state of practice of defect prediction data collection","publication_year":2022,"publication_date":"2022-01-18","ids":{"openalex":"https://openalex.org/W3213259750","doi":"https://doi.org/10.1007/s10664-021-10092-4","mag":"3213259750"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-021-10092-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-021-10092-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-021-10092-4.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10664-021-10092-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027032646","display_name":"Steffen Herbold","orcid":"https://orcid.org/0000-0001-9765-2803"},"institutions":[{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Steffen Herbold","raw_affiliation_strings":["Institute of Software and Systems Engineering, TU Clausthal, Clausthal-Zellerfeld, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9765-2803","affiliations":[{"raw_affiliation_string":"Institute of Software and Systems Engineering, TU Clausthal, Clausthal-Zellerfeld, Germany","institution_ids":["https://openalex.org/I43980791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089799382","display_name":"Alexander Trautsch","orcid":"https://orcid.org/0000-0001-5236-7953"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Trautsch","raw_affiliation_strings":["Institute of Computer Science, University of Goettingen, Goettingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Goettingen, Goettingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068855431","display_name":"Fabian Trautsch","orcid":"https://orcid.org/0000-0002-8374-9142"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian Trautsch","raw_affiliation_strings":["Institute of Computer Science, University of Goettingen, Goettingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Goettingen, Goettingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081738655","display_name":"Benjamin Ledel","orcid":null},"institutions":[{"id":"https://openalex.org/I43980791","display_name":"Clausthal University of Technology","ror":"https://ror.org/04qb8nc58","country_code":"DE","type":"education","lineage":["https://openalex.org/I43980791"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Ledel","raw_affiliation_strings":["Institute of Software and Systems Engineering, TU Clausthal, Clausthal-Zellerfeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software and Systems Engineering, TU Clausthal, Clausthal-Zellerfeld, Germany","institution_ids":["https://openalex.org/I43980791"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027032646"],"corresponding_institution_ids":["https://openalex.org/I43980791"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":15.3136,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.99027315,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"27","issue":"2","first_page":null,"last_page":null},"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":0.9948999881744385,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9865999817848206,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6974543333053589},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6789130568504333},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.6334686875343323},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6100066304206848},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.567730188369751},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5119389295578003},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5055122375488281},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46204468607902527},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.43446409702301025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37748801708221436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3688858151435852},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1454784870147705},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13406696915626526},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.12933841347694397},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1172204315662384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974543333053589},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6789130568504333},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.6334686875343323},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6100066304206848},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.567730188369751},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5119389295578003},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5055122375488281},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46204468607902527},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.43446409702301025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37748801708221436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3688858151435852},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1454784870147705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13406696915626526},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.12933841347694397},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1172204315662384},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10664-021-10092-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-021-10092-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-021-10092-4.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1911.08938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.08938","pdf_url":"https://arxiv.org/pdf/1911.08938","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/98985","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/98985","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"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":"journal_article"}],"best_oa_location":{"id":"doi:10.1007/s10664-021-10092-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-021-10092-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-021-10092-4.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7548216887","display_name":null,"funder_award_id":"402774445","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320330127","display_name":"Technische Universit\u00e4t Clausthal","ror":"https://ror.org/04qb8nc58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3213259750.pdf","grobid_xml":"https://content.openalex.org/works/W3213259750.grobid-xml"},"referenced_works_count":88,"referenced_works":["https://openalex.org/W168970045","https://openalex.org/W349770100","https://openalex.org/W1565746575","https://openalex.org/W1969082431","https://openalex.org/W1978813754","https://openalex.org/W1987855178","https://openalex.org/W1998167229","https://openalex.org/W2016944307","https://openalex.org/W2025700486","https://openalex.org/W2033079433","https://openalex.org/W2045116160","https://openalex.org/W2053154970","https://openalex.org/W2061019658","https://openalex.org/W2068430427","https://openalex.org/W2083221797","https://openalex.org/W2083641167","https://openalex.org/W2099677903","https://openalex.org/W2101227285","https://openalex.org/W2107277166","https://openalex.org/W2107692981","https://openalex.org/W2110385988","https://openalex.org/W2111421634","https://openalex.org/W2113533445","https://openalex.org/W2115105080","https://openalex.org/W2126160338","https://openalex.org/W2126166995","https://openalex.org/W2132887549","https://openalex.org/W2142481192","https://openalex.org/W2145574830","https://openalex.org/W2146335723","https://openalex.org/W2146338950","https://openalex.org/W2147386665","https://openalex.org/W2149783794","https://openalex.org/W2151666086","https://openalex.org/W2153054327","https://openalex.org/W2153150125","https://openalex.org/W2157353183","https://openalex.org/W2158744032","https://openalex.org/W2158864412","https://openalex.org/W2159610968","https://openalex.org/W2161762274","https://openalex.org/W2162739315","https://openalex.org/W2164777277","https://openalex.org/W2374812233","https://openalex.org/W2408181256","https://openalex.org/W2471516951","https://openalex.org/W2476682851","https://openalex.org/W2510885373","https://openalex.org/W2523229043","https://openalex.org/W2530824252","https://openalex.org/W2549738163","https://openalex.org/W2561301563","https://openalex.org/W2589275250","https://openalex.org/W2593156329","https://openalex.org/W2605547445","https://openalex.org/W2606150376","https://openalex.org/W2735995639","https://openalex.org/W2744565623","https://openalex.org/W2766521509","https://openalex.org/W2792987835","https://openalex.org/W2796283679","https://openalex.org/W2802138742","https://openalex.org/W2888756142","https://openalex.org/W2895149850","https://openalex.org/W2897961188","https://openalex.org/W2900961173","https://openalex.org/W2901159202","https://openalex.org/W2903359694","https://openalex.org/W2954276596","https://openalex.org/W2963548617","https://openalex.org/W2964279097","https://openalex.org/W2980706498","https://openalex.org/W2984452309","https://openalex.org/W3004570974","https://openalex.org/W3009290003","https://openalex.org/W3034060521","https://openalex.org/W3034114804","https://openalex.org/W3091744225","https://openalex.org/W3095160805","https://openalex.org/W3102725096","https://openalex.org/W3102742699","https://openalex.org/W3144106047","https://openalex.org/W3162494388","https://openalex.org/W4229530126","https://openalex.org/W4243379839","https://openalex.org/W4243910833","https://openalex.org/W4247834613","https://openalex.org/W6906368339"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775","https://openalex.org/W2952904874"],"abstract_inverted_index":{"Abstract":[0],"Context":[1],"The":[2],"SZZ":[3,33,69,124,139],"algorithm":[4,70],"is":[5,134,149,158,217],"the":[6,32,63,68,72,94,118,173,176,211,231,234,237],"de":[7],"facto":[8],"standard":[9],"for":[10,19,93,154,205],"labeling":[11],"bug":[12,119,127],"fixing":[13,120],"commits":[14,121],"and":[15,71,88],"finding":[16],"inducing":[17],"changes":[18],"defect":[20,36,64,97,187,206,224,240],"prediction":[21,37,188],"data.":[22,98],"Recent":[23],"research":[24,48],"uncovered":[25],"potential":[26],"problems":[27],"in":[28,136,185],"different":[29],"parts":[30],"of":[31,62,74,85,96,107,117,175,180,213,233,236,239],"algorithm.":[34],"Most":[35],"data":[38,189],"sets":[39,244],"provide":[40,58],"only":[41,115],"static":[42],"code":[43],"metrics":[44],"as":[45,152,161,191],"features,":[46],"while":[47],"indicates":[49],"that":[50,114,157,182,196,210],"other":[51],"features":[52,77,181,202,216],"are":[53,125,168,183,193,203,226],"also":[54,171],"important.":[55],"Objective":[56],"We":[57,81,99,112,170,208],"an":[59,101],"empirical":[60,102],"analysis":[61],"labels":[65,225],"created":[66],"with":[67,138,222],"impact":[73,174],"commonly":[75],"used":[76,82,135],"on":[78,104],"results.":[79],"Method":[80],"a":[83,130,145,227,248],"combination":[84,137],"manual":[86],"validation":[87],"adopted":[89],"or":[90],"improved":[91],"heuristics":[92],"collection":[95],"conducted":[100],"study":[103],"398":[105],"releases":[106],"38":[108],"Apache":[109],"projects.":[110],"Results":[111],"found":[113,209],"half":[116],"determined":[122],"by":[123],"actually":[126],"fixing.":[128],"If":[129],"six-month":[131],"time":[132],"frame":[133],"to":[140,230,246],"determine":[141],"which":[142],"bugs":[143],"affect":[144],"release,":[146],"one":[147],"file":[148,156],"incorrectly":[150],"labeled":[151,160],"defective":[153,166],"every":[155],"correctly":[159],"defective.":[162],"In":[163],"addition,":[164],"two":[165],"files":[167],"missed.":[169],"explored":[172],"relatively":[177],"small":[178],"set":[179],"available":[184],"most":[186],"sets,":[190],"there":[192],"multiple":[194],"publications":[195],"indicate":[197],"that,":[198],"e.g.,":[199],"churn":[200],"related":[201],"important":[204],"prediction.":[207,241],"difference":[212],"using":[214],"more":[215],"not":[218],"significant.":[219],"Conclusion":[220],"Problems":[221],"inaccurate":[223],"severe":[228,250],"threat":[229],"validity":[232],"state":[235],"art":[238],"Small":[242],"feature":[243],"seem":[245],"be":[247],"less":[249],"threat.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":9}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2021-11-22T00:00:00"}