{"id":"https://openalex.org/W4411450188","doi":"https://doi.org/10.1145/3715778","title":"Less Is More: On the Importance of Data Quality for Unit Test Generation","display_name":"Less Is More: On the Importance of Data Quality for Unit Test Generation","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411450188","doi":"https://doi.org/10.1145/3715778"},"language":"en","primary_location":{"id":"doi:10.1145/3715778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3715778","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3715778","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002275934","display_name":"Junwei Zhang","orcid":"https://orcid.org/0000-0003-4323-8951"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4323-8951","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047688641","display_name":"Xing Hu","orcid":"https://orcid.org/0000-0003-0093-3292"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Hu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0093-3292","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082429541","display_name":"Shan Gao","orcid":"https://orcid.org/0009-0006-2695-2968"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Gao","raw_affiliation_strings":["Huawei, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-2695-2968","affiliations":[{"raw_affiliation_string":"Huawei, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006669765","display_name":"Xin Xia","orcid":"https://orcid.org/0000-0002-6302-3256"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xia","raw_affiliation_strings":["Huawei, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6302-3256","affiliations":[{"raw_affiliation_string":"Huawei, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081036622","display_name":"David Lo","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Lo","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4367-7201","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114429788","display_name":"Shanping Li","orcid":"https://orcid.org/0000-0003-2615-9792"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanping Li","raw_affiliation_strings":["Zhejiang University, 0000-0003-2615-9792, China"],"raw_orcid":"https://orcid.org/0000-0003-2615-9792","affiliations":[{"raw_affiliation_string":"Zhejiang University, 0000-0003-2615-9792, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2308,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95096947,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2","issue":"FSE","first_page":"1293","last_page":"1316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9962000250816345,"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":0.7337138652801514},{"id":"https://openalex.org/keywords/unit-testing","display_name":"Unit testing","score":0.732136070728302},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5701146721839905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4996969699859619},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4989774227142334},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.474107563495636},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4364585280418396},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43637949228286743},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43427711725234985},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.41562044620513916},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.38284018635749817},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.13672968745231628},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13437160849571228},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1117120087146759},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.10795965790748596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337138652801514},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.732136070728302},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5701146721839905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4996969699859619},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4989774227142334},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.474107563495636},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4364585280418396},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43637949228286743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43427711725234985},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.41562044620513916},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.38284018635749817},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.13672968745231628},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13437160849571228},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1117120087146759},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.10795965790748596},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3715778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3715778","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3715778","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3715778","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1965194038","https://openalex.org/W1971650562","https://openalex.org/W2017319780","https://openalex.org/W2027422213","https://openalex.org/W2041713059","https://openalex.org/W2101105183","https://openalex.org/W2107709519","https://openalex.org/W2109596254","https://openalex.org/W2110908283","https://openalex.org/W2139935350","https://openalex.org/W2146178292","https://openalex.org/W2156723666","https://openalex.org/W2464784130","https://openalex.org/W2472622445","https://openalex.org/W2508179673","https://openalex.org/W2682664750","https://openalex.org/W2884276923","https://openalex.org/W2888078871","https://openalex.org/W2912218663","https://openalex.org/W2966980041","https://openalex.org/W2980708516","https://openalex.org/W3005628256","https://openalex.org/W3086938529","https://openalex.org/W3091284975","https://openalex.org/W3100191342","https://openalex.org/W3105903381","https://openalex.org/W3134770171","https://openalex.org/W3139053720","https://openalex.org/W4210327135","https://openalex.org/W4220852596","https://openalex.org/W4221157342","https://openalex.org/W4236586490","https://openalex.org/W4246945666","https://openalex.org/W4281763794","https://openalex.org/W4284681867","https://openalex.org/W4284690374","https://openalex.org/W4285605356","https://openalex.org/W4308641647","https://openalex.org/W4313059319","https://openalex.org/W4313547555","https://openalex.org/W4318902699","https://openalex.org/W4320854935","https://openalex.org/W4376122390","https://openalex.org/W4376167329","https://openalex.org/W4384155677","https://openalex.org/W4384304865","https://openalex.org/W4384345694","https://openalex.org/W4384345708","https://openalex.org/W4385473722","https://openalex.org/W4385965483","https://openalex.org/W4386185625","https://openalex.org/W4387711873","https://openalex.org/W4388483238","https://openalex.org/W4389104713","https://openalex.org/W4391558635","https://openalex.org/W4400104564","https://openalex.org/W4402042086","https://openalex.org/W4405627388","https://openalex.org/W6603313918","https://openalex.org/W6603944243","https://openalex.org/W6949155868"],"related_works":["https://openalex.org/W3008339103","https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W1508895727","https://openalex.org/W4312188863","https://openalex.org/W2041589963"],"abstract_inverted_index":{"Unit":[0],"testing":[1,11],"is":[2,21],"crucial":[3],"for":[4,73],"software":[5,15],"development":[6],"and":[7,13,23,108,132,137,172,192,199,220],"maintenance.":[8],"Effective":[9],"unit":[10,19,40],"ensures":[12],"improves":[14,258,285],"quality,":[16,61],"but":[17],"writing":[18],"tests":[20],"time-consuming":[22],"labor-intensive.":[24],"Recent":[25],"studies":[26],"have":[27],"proposed":[28],"deep":[29],"learning":[30],"(DL)":[31],"techniques":[32],"or":[33,48],"large":[34],"language":[35],"models":[36,44],"(LLMs)":[37],"to":[38,103,114,130,152,222],"automate":[39],"test":[41,74,92,110,157,187,229,241],"generation.":[42,75],"These":[43],"are":[45],"usually":[46],"trained":[47],"fine-tuned":[49],"on":[50,67,87,184,228,256],"large-scale":[51],"datasets.":[52,159],"Despite":[53],"growing":[54],"awareness":[55],"of":[56,59,70,85,90,119,139,156,201,226,244],"the":[57,68,83,88,98,105,134,140,154,224,240,245,248,252,267,271,274,298],"importance":[58],"data":[60],"there":[62],"has":[63],"been":[64],"limited":[65],"research":[66],"quality":[69,155],"datasets":[71,202],"used":[72],"To":[76,177],"bridge":[77],"this":[78],"gap,":[79],"we":[80,122,144,181,209],"systematically":[81],"examine":[82],"impact":[84,225],"noise":[86,141,227,237,284],"performance":[89,260],"learning-based":[91],"generation":[93,111,158,188,230,242],"models.":[94,246],"We":[95],"first":[96],"apply":[97,182],"open":[99],"card":[100],"sorting":[101],"method":[102],"analyze":[104],"most":[106],"popular":[107],"largest":[109],"dataset,":[112,255,273],"Methods2Test,":[113],"categorize":[115],"eight":[116],"distinct":[117],"types":[118],"noise.":[120],"Further,":[121],"conduct":[123,210],"detailed":[124],"interviews":[125],"with":[126,251],"17":[127],"domain":[128],"experts":[129],"validate":[131],"assess":[133,223],"importance,":[135],"reasonableness,":[136],"correctness":[138],"taxonomy.":[142],"Then,":[143],"propose":[145],"CleanTest,":[146],"an":[147],"automated":[148],"noise-cleaning":[149],"framework":[150],"designed":[151],"improve":[153,277],"CleanTest":[160,183],"comprises":[161],"three":[162],"filters:":[163],"a":[164,168,173,291],"rule-based":[165,169],"syntax":[166],"filter,":[167,171],"relevance":[170],"model-based":[174],"coverage":[175,279],"filter.":[176],"evaluate":[178],"its":[179,206,259],"effectiveness,":[180],"two":[185],"widely-used":[186],"datasets,":[189],"i.e.,":[190],"Methods2Test":[191,254],"Atlas.":[193],"Our":[194],"findings":[195],"indicate":[196],"that":[197,235],"43.52%":[198],"29.65%":[200],"contain":[203],"noise,":[204],"highlighting":[205],"prevalence.":[207],"Finally,":[208],"comparative":[211],"experiments":[212],"using":[213,266],"four":[214,249,275],"LLMs":[215,250,276],"(i.e.,":[216],"CodeBERT,":[217],"AthenaTest,":[218],"StarCoder,":[219],"CodeLlama7B)":[221],"performance.":[231],"The":[232],"results":[233],"show":[234],"filtering":[236,283],"positively":[238],"influences":[239],"ability":[243],"Fine-tuning":[247],"filtered":[253],"average,":[257],"by":[261,280,297],"67%":[262],"in":[263,290,294],"branch":[264,278],"coverage,":[265],"Defects4J":[268],"benchmark.":[269],"For":[270],"Atlas":[272],"39%.":[281],"Additionally,":[282],"bug":[286],"detection":[287],"performance,":[288],"resulting":[289],"21.42%":[292],"increase":[293],"bugs":[295],"detected":[296],"generated":[299],"tests.":[300]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}