{"id":"https://openalex.org/W7128627777","doi":"https://doi.org/10.1145/3797033","title":"From Bugs to Benchmarks: A Comprehensive Survey of Software Defect Datasets","display_name":"From Bugs to Benchmarks: A Comprehensive Survey of Software Defect Datasets","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128627777","doi":"https://doi.org/10.1145/3797033"},"language":"en","primary_location":{"id":"doi:10.1145/3797033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3797033","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","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/A5101653886","display_name":"Haonan Zhu","orcid":"https://orcid.org/0009-0006-1492-2446"},"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":"Hao-Nan Zhu","raw_affiliation_strings":["University of California, Davis"],"raw_orcid":"https://orcid.org/0009-0006-1492-2446","affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077696028","display_name":"Robert M. Furth","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":"Robert Furth","raw_affiliation_strings":["University of California, Davis"],"raw_orcid":"https://orcid.org/0009-0009-5373-5901","affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013438083","display_name":"Michael Pradel","orcid":"https://orcid.org/0000-0003-1623-498X"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Pradel","raw_affiliation_strings":["University of Stuttgart"],"raw_orcid":"https://orcid.org/0000-0003-1623-498X","affiliations":[{"raw_affiliation_string":"University of Stuttgart","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010991469","display_name":"Cindy Rubio-Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-0861-3763"},"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":"Cindy Rubio-Gonz\u00e1lez","raw_affiliation_strings":["University of California, Davis"],"raw_orcid":"https://orcid.org/0000-0002-0861-3763","affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.7794,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98452167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"58","issue":"10","first_page":"1","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9120000004768372,"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":0.9120000004768372,"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":0.031700000166893005,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.01759999990463257,"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/software-bug","display_name":"Software bug","score":0.7383000254631042},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7106999754905701},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5485000014305115},{"id":"https://openalex.org/keywords/software-peer-review","display_name":"Software peer review","score":0.47049999237060547},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.46399998664855957},{"id":"https://openalex.org/keywords/software-analytics","display_name":"Software analytics","score":0.4277999997138977},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.41690000891685486},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.38999998569488525},{"id":"https://openalex.org/keywords/social-software-engineering","display_name":"Social software engineering","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014000058174133},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.7383000254631042},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7106999754905701},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5644000172615051},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5388000011444092},{"id":"https://openalex.org/C74579156","wikidata":"https://www.wikidata.org/wiki/Q7554342","display_name":"Software peer review","level":5,"score":0.47049999237060547},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.46399998664855957},{"id":"https://openalex.org/C171981572","wikidata":"https://www.wikidata.org/wiki/Q7554239","display_name":"Software analytics","level":5,"score":0.4277999997138977},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.41690000891685486},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.38999998569488525},{"id":"https://openalex.org/C182500959","wikidata":"https://www.wikidata.org/wiki/Q7551380","display_name":"Social software engineering","level":5,"score":0.38909998536109924},{"id":"https://openalex.org/C10272871","wikidata":"https://www.wikidata.org/wiki/Q929972","display_name":"Software inspection","level":5,"score":0.3799999952316284},{"id":"https://openalex.org/C48002344","wikidata":"https://www.wikidata.org/wiki/Q2919644","display_name":"Verification and validation","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3447999954223633},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.3328000009059906},{"id":"https://openalex.org/C202105479","wikidata":"https://www.wikidata.org/wiki/Q265013","display_name":"Software evolution","level":5,"score":0.32440000772476196},{"id":"https://openalex.org/C123551368","wikidata":"https://www.wikidata.org/wiki/Q7122888","display_name":"Package development process","level":5,"score":0.3068000078201294},{"id":"https://openalex.org/C46110900","wikidata":"https://www.wikidata.org/wiki/Q11702993","display_name":"Software walkthrough","level":5,"score":0.30469998717308044},{"id":"https://openalex.org/C2984328558","wikidata":"https://www.wikidata.org/wiki/Q188522","display_name":"Software testing","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C39890963","wikidata":"https://www.wikidata.org/wiki/Q1702721","display_name":"Personal software process","level":5,"score":0.2924000024795532},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.2856000065803528},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.28139999508857727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3797033","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.49016278982162476,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1987289444","https://openalex.org/W1989657183","https://openalex.org/W2095709152","https://openalex.org/W2109540106","https://openalex.org/W2141051748","https://openalex.org/W2145458045","https://openalex.org/W2146878883","https://openalex.org/W2156633971","https://openalex.org/W2156723666","https://openalex.org/W2157353183","https://openalex.org/W2160517961","https://openalex.org/W2166766372","https://openalex.org/W2170771779","https://openalex.org/W2343875716","https://openalex.org/W2405678927","https://openalex.org/W2537787699","https://openalex.org/W2762550985","https://openalex.org/W2794494879","https://openalex.org/W2850992922","https://openalex.org/W2883977877","https://openalex.org/W2884326032","https://openalex.org/W2884642766","https://openalex.org/W2888223970","https://openalex.org/W2897316866","https://openalex.org/W2897961188","https://openalex.org/W2899510293","https://openalex.org/W2913711852","https://openalex.org/W2945432765","https://openalex.org/W2967457710","https://openalex.org/W2967591898","https://openalex.org/W2972077015","https://openalex.org/W2980518752","https://openalex.org/W2981475630","https://openalex.org/W2984385475","https://openalex.org/W2998011150","https://openalex.org/W3007045600","https://openalex.org/W3033777149","https://openalex.org/W3034114804","https://openalex.org/W3035061803","https://openalex.org/W3081159607","https://openalex.org/W3085711994","https://openalex.org/W3090561201","https://openalex.org/W3090643686","https://openalex.org/W3090797304","https://openalex.org/W3091588759","https://openalex.org/W3105943882","https://openalex.org/W3173591235","https://openalex.org/W3181990673","https://openalex.org/W3195703954","https://openalex.org/W3195794356","https://openalex.org/W3196239222","https://openalex.org/W3201041782","https://openalex.org/W4200634422","https://openalex.org/W4220749113","https://openalex.org/W4226363281","https://openalex.org/W4284702776","https://openalex.org/W4285144131","https://openalex.org/W4285490453","https://openalex.org/W4285586669","https://openalex.org/W4288080276","https://openalex.org/W4309077889","https://openalex.org/W4312300075","https://openalex.org/W4312307983","https://openalex.org/W4312519911","https://openalex.org/W4323308631","https://openalex.org/W4378942602","https://openalex.org/W4380758748","https://openalex.org/W4383221530","https://openalex.org/W4384030667","https://openalex.org/W4384155409","https://openalex.org/W4384345745","https://openalex.org/W4384938773","https://openalex.org/W4387298393","https://openalex.org/W4389737048","https://openalex.org/W4390956105","https://openalex.org/W4398239044","https://openalex.org/W4398239188","https://openalex.org/W4399668136","https://openalex.org/W4399837262","https://openalex.org/W4400242059","https://openalex.org/W4400242157","https://openalex.org/W4400242207","https://openalex.org/W4400242435","https://openalex.org/W4400484321","https://openalex.org/W4401352313","https://openalex.org/W4402442668","https://openalex.org/W4402442868","https://openalex.org/W4402457214","https://openalex.org/W4402457504","https://openalex.org/W4402457546","https://openalex.org/W4403537118","https://openalex.org/W4411993048"],"related_works":[],"abstract_inverted_index":{"Software":[0],"defect":[1,41,70,107],"datasets,":[2,71],"which":[3],"are":[4,9],"collections":[5],"of":[6,24,67,98,103],"software":[7,25,34,40,69,106],"bugs,":[8],"essential":[10],"resources":[11,48],"to":[12,57],"facilitate":[13],"empirical":[14],"research":[15,88],"and":[16,78],"enable":[17],"standardized":[18],"benchmarking":[19],"for":[20,49,86],"a":[21,64],"wide":[22],"range":[23],"engineering":[26],"techniques,":[27],"including":[28],"emerging":[29],"areas":[30],"like":[31],"agentic":[32],"AI-based":[33],"development.":[35],"Over":[36],"the":[37,50,59],"years,":[38],"numerous":[39],"datasets":[42,108],"have":[43],"been":[44],"developed,":[45],"providing":[46],"rich":[47],"community,":[51],"yet":[52],"making":[53],"it":[54],"increasingly":[55],"difficult":[56],"navigate":[58],"landscape.":[60],"This":[61],"article":[62],"provides":[63],"comprehensive":[65],"survey":[66],"151":[68],"covering":[72],"their":[73],"scope,":[74],"construction,":[75],"availability,":[76],"usability,":[77],"practical":[79],"uses.":[80],"We":[81],"also":[82],"suggest":[83],"potential":[84],"opportunities":[85],"future":[87],"based":[89],"on":[90],"our":[91],"findings,":[92],"such":[93],"as":[94],"addressing":[95],"underrepresented":[96],"kinds":[97],"defects.":[99],"A":[100],"complete":[101],"catalog":[102],"all":[104],"surveyed":[105],"is":[109],"available":[110],"at":[111],"https://defect-datasets.github.io/":[112],".":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-12T00:00:00"}