{"id":"https://openalex.org/W4413212461","doi":"https://doi.org/10.1109/ms.2025.3597574","title":"When AI-Generated Unit Tests Validate Bugs: The Risk of Faulty Assertions","display_name":"When AI-Generated Unit Tests Validate Bugs: The Risk of Faulty Assertions","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4413212461","doi":"https://doi.org/10.1109/ms.2025.3597574"},"language":"en","primary_location":{"id":"doi:10.1109/ms.2025.3597574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ms.2025.3597574","pdf_url":null,"source":{"id":"https://openalex.org/S6725529","display_name":"IEEE Software","issn_l":"0740-7459","issn":["0740-7459","1937-4194"],"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 Software","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/A5054968221","display_name":"Noble Saji Mathews","orcid":"https://orcid.org/0000-0003-2266-8848"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Noble Saji Mathews","raw_affiliation_strings":["David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada","University of Waterloo, Waterloo, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029916309","display_name":"Meiyappan Nagappan","orcid":"https://orcid.org/0000-0003-4533-4728"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Meiyappan Nagappan","raw_affiliation_strings":["David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada","University of Waterloo, Waterloo, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054968221"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2526341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":"1","first_page":"98","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9968000054359436,"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/T10260","display_name":"Software Engineering Research","score":0.9921000003814697,"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":0.9879000186920166,"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":0.6711260676383972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6452611684799194},{"id":"https://openalex.org/keywords/unit-testing","display_name":"Unit testing","score":0.5551968812942505},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4459399878978729},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4227454960346222},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4154427647590637},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.40601783990859985},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2613469660282135}],"concepts":[{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.6711260676383972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6452611684799194},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.5551968812942505},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4459399878978729},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4227454960346222},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4154427647590637},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.40601783990859985},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2613469660282135}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ms.2025.3597574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ms.2025.3597574","pdf_url":null,"source":{"id":"https://openalex.org/S6725529","display_name":"IEEE Software","issn_l":"0740-7459","issn":["0740-7459","1937-4194"],"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 Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2041713059","https://openalex.org/W2122205205","https://openalex.org/W2998870469","https://openalex.org/W4220699888","https://openalex.org/W4384304865","https://openalex.org/W4394015350","https://openalex.org/W4399491517","https://openalex.org/W4400484392","https://openalex.org/W4400484796","https://openalex.org/W4403536220","https://openalex.org/W4406800520"],"related_works":["https://openalex.org/W2615173508","https://openalex.org/W2593332592","https://openalex.org/W4380354325","https://openalex.org/W2205285032","https://openalex.org/W2886461259","https://openalex.org/W2501857584","https://openalex.org/W56260862","https://openalex.org/W4390788373","https://openalex.org/W2621101275","https://openalex.org/W2054637161"],"abstract_inverted_index":{"There":[0],"is":[1],"increasing":[2],"research":[3],"and":[4,37,115,121],"commercial":[5],"exploration":[6],"into":[7],"tools":[8,28,58,113],"for":[9,30],"automated":[10],"unit":[11,31,65,110],"test":[12,26,50,98,111,122],"generation":[13,27,112],"using":[14],"Large":[15],"Language":[16],"Models":[17],"(LLMs).":[18],"This":[19],"paper":[20],"critically":[21],"examines":[22],"how":[23,82],"recent":[24],"LLM-based":[25,109],"pitched":[29],"testing":[32,66],"such":[33],"as":[34,75],"Qodo":[35],"Cover":[36],"GitHub":[38],"Copilot":[39],"handle":[40],"buggy":[41,73],"code.":[42],"Considering":[43],"bugs":[44,89,94],"are":[45],"only":[46],"exposed":[47],"by":[48],"failing":[49],"cases,":[51],"we":[52,77],"explore":[53],"the":[54,61,96,106],"question:":[55],"can":[56,85],"these":[57,79],"truly":[59],"achieve":[60],"intended":[62],"objectives":[63],"of":[64,108],"-":[67],"find":[68],"bugs?":[69],"Using":[70],"real":[71],"human-written":[72],"code":[74],"input,":[76],"evaluate":[78],"tools,":[80],"showing":[81],"LLM-generated":[83],"tests":[84],"fail":[86],"to":[87],"detect":[88],"and,":[90],"more":[91],"alarmingly,":[92],"validate":[93],"in":[95],"generated":[97],"suite.":[99],"These":[100],"findings":[101],"raise":[102],"important":[103],"questions":[104],"about":[105],"usefulness":[107],"today":[114],"their":[116],"impact":[117],"on":[118],"software":[119],"quality":[120],"suite":[123],"reliability.":[124]},"counts_by_year":[],"updated_date":"2025-12-30T23:08:21.542490","created_date":"2025-10-10T00:00:00"}